@article{10.1145/3570604,
author = {S.K, Prashanthi and Kesanapalli, Sai Anuroop and Simmhan, Yogesh},
title = {Characterizing the Performance of Accelerated Jetson Edge Devices for Training Deep Learning Models},
year = {2022},
issue_date = {December 2022},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {6},
number = {3},
url = {https://doi.org/10.1145/3570604},
doi = {10.1145/3570604},
journal = {Proc. ACM Meas. Anal. Comput. Syst.},
month = {dec},
keywords = {edge accelerators, dnn training, performance characterization}
}

@inproceedings{10.1145/3492321.3519588,
author = {Baranawal, Animesh and Simmhan, Yogesh},
title = {Optimizing the Interval-Centric Distributed Computing Model for Temporal Graph Algorithms},
year = {2022},
url = {https://doi.org/10.1145/3492321.3519588},
doi = {10.1145/3492321.3519588},
booktitle = {Proceedings of the Seventeenth European Conference on Computer Systems},
pages = {541–558},
numpages = {18},
keywords = {distributed graph processing, temporal graphs},
series = {EuroSys '22}
}

@INPROCEEDINGS{9825950,
author={Varshney, Prateeksha and Ramesh, Shriram and Chhabra, Shayal and Khochare, Aakash and Simmhan, Yogesh},
booktitle={2022 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid)},
title={Resilient Execution of Data-triggered Applications on Edge, Fog and Cloud Resources},
year={2022},
volume={},
number={},
pages={473-483},
doi={10.1109/CCGrid54584.2022.00057}}

@INPROCEEDINGS{9973585,
author={Khochare, Aakash and Simmhan, Yogesh and Mehta, Sameep and Agarwal, Arvind},
booktitle={2022 IEEE 18th International Conference on e-Science (e-Science)},
title={Toward Scientific Workflows in a Serverless World},
year={2022},
volume={},
number={},
pages={399-400},
doi={10.1109/eScience55777.2022.00057}
}

@INPROCEEDINGS{9668501,
author={Acharya, Srikrishna and Amrutur, Bharadwaj and Bharathesa, Mukunda and Simmhan, Yogesh},
booktitle={2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS)},
title={CORNET 2.0: A Co-Simulation Middleware for Robot Networks},
year={2022},
volume={},
number={},
pages={684-690},
doi={10.1109/COMSNETS53615.2022.9668501}}

@INPROCEEDINGS{9835369,
author={K, Prashanthi S. and Khochare, Aakash and Kesanapalli, Sai Anuroop and Bhope, Rahul and Simmhan, Yogesh},
booktitle={2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)},
title={Don't Miss the Train: A Case for Systems Research into Training on the Edge},
year={2022},
volume={},
number={},
pages={985-986},
doi={10.1109/IPDPSW55747.2022.00157}}

@article{RAMESH202194,
title = {Granite: A distributed engine for scalable path queries over temporal property graphs},
journal = {Journal of Parallel and Distributed Computing},
volume = {151},
pages = {94-111},
year = {2021},
issn = {0743-7315},
doi = {https://doi.org/10.1016/j.jpdc.2021.02.004},
url = {https://www.sciencedirect.com/science/article/pii/S0743731521000253},
author = {Shriram Ramesh and Animesh Baranawal and Yogesh Simmhan},
keywords = {Graph processing, Temporal graphs, Distributed scheduling, Big data platforms, Query planning},
}

@ARTICLE {9314091,
author = {A. Khochare and A. Krishnan and Y. Simmhan},
journal = {IEEE Transactions on Parallel & Distributed Systems},
title = {A Scalable Platform for Distributed Object Tracking Across a Many-Camera Network},
year = {2021},
volume = {32},
number = {06},
issn = {1558-2183},
pages = {1479-1493},
keywords = {cameras;streaming media;urban areas;tracking;cloud computing;target tracking;scalability},
doi = {10.1109/TPDS.2021.3049450},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
month = {jun}
}

@INPROCEEDINGS{9488740,
author={Khochare, Aakash and Simmhan, Yogesh and Sorbelli, Francesco Betti and Das, Sajal K.},
booktitle={IEEE INFOCOM 2021 - IEEE Conference on Computer Communications},
title={Heuristic Algorithms for Co-scheduling of Edge Analytics and Routes for UAV Fleet Missions},
year={2021},
volume={},
number={},
pages={1-10},
doi={10.1109/INFOCOM42981.2021.9488740}
}

@article{https://doi.org/10.1002/cpe.6804,
author = {Baheti, Shrey and Anjana, Parwat Singh and Peri, Sathya and Simmhan, Yogesh},
title = {DiPETrans: A framework for distributed parallel execution of transactions of blocks in blockchains},
journal = {Concurrency and Computation: Practice and Experience},
volume = {34},
number = {10},
pages = {e6804},
keywords = {blockchain, mining pools, parallel execution, smart contracts, static analysis},
doi = {https://doi.org/10.1002/cpe.6804},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.6804},
year = {2022}
}

@article{10.1145/3446346,
author = {Baheti, Shrey and Badiger, Shreyas and Simmhan, Yogesh},
title = {VIoLET: An Emulation Environment for Validating IoT Deployments at Large Scales},
year = {2021},
issue_date = {July 2021},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {5},
number = {3},
url = {https://doi.org/10.1145/3446346},
doi = {10.1145/3446346},
journal = {ACM Trans. Cyber-Phys. Syst.},
month = {jul},
keywords = {fog computing, distributed systems, virtual environment, cloud computing, scalability, emulation, Internet of Things, edge computing}
}

@article{namtirtha2021best,
title={Best influential spreaders identification using network global structural properties},
author={Namtirtha, Amrita and Dutta, Animesh and Dutta, Biswanath and Sundararajan, Amritha and Simmhan, Yogesh},
journal={Scientific reports},
volume={11},
number={1},
pages={1--15},
year={2021},
publisher={Springer}
}

@InProceedings{10.1007/978-3-030-86475-0_31,
author="Agarwal, Manoj K.
and Baranawal, Animesh
and Simmhan, Yogesh
and Gupta, Manish",
title="Event Related Data Collection from Microblog Streams",
booktitle="Database and Expert Systems Applications",
year="2021",
publisher="Springer International Publishing",
address="Cham",
pages="319--331",
abstract="Many studies have established that microblog streams, e.g., Twitter and Weibo, are leading indicators of emerging events. However, to statistically analyze and discover the emerging trends around these events in microblog message streams, e.g., popularity, sentiments, or aspects, one must identify messages related to an event with high precision and recall. In this paper, we propose a novel problem of automatically discovering meaningful keyword rules, which help identify the most relevant messages in the context of a given event from fast moving and high-volume social media streams. For the specified event, such as {\{}{\#}trump{\}} or {\{}{\#}coronavirus{\}}, our technique automatically extracts the most relevant keyword rules to collect related messages with high precision and recall. The rule set is dynamic, and we continuously identify new rules that capture the event evolution. Experiments with millions of tweets show that the proposed rule extraction method is highly effective for event-related data collection and has precision up to 99{\%} and up to 4.5X recall over the baseline system.",
isbn="978-3-030-86475-0"
}

@Article{amt-14-37-2021,
AUTHOR = {Sahu, R. and Nagal, A. and Dixit, K. K. and Unnibhavi, H. and Mantravadi, S. and Nair, S. and Simmhan, Y. and Mishra, B. and Zele, R. and Sutaria, R. and Motghare, V. M. and Kar, P. and Tripathi, S. N.},
TITLE = {Robust statistical calibration and characterization of portable low-cost air quality monitoring sensors to quantify real-time \chem{O_3} and \chem{NO_2} concentrations in diverse environments},
JOURNAL = {Atmospheric Measurement Techniques},
VOLUME = {14},
YEAR = {2021},
NUMBER = {1},
PAGES = {37--52},
URL = {https://amt.copernicus.org/articles/14/37/2021/},
DOI = {10.5194/amt-14-37-2021}
}

@INPROCEEDINGS{9352914,
author={Acharya, Srikrishna and Sadgun S Devanahalli, S and Rawat, Alok and Kuruvilla, Varghese P and Sharma, Pratik and Amrutur, Bharadwaj and Joglekar, Ashish and Krishnapuram, Raghu and Simmhan, Yogesh and Tyagi, Himanshu},
booktitle={2021 International Conference on COMmunication Systems & NETworkS (COMSNETS)},
title={Network Emulation For Tele-driving Application Development},
year={2021},
volume={},
number={},
pages={109-110},
doi={10.1109/COMSNETS51098.2021.9352914}}

@Article{varshney:spe:2020,
author = {Prateeksha Varshney and Yogesh Simmhan},
journal = {Software: Practice and Experience},
title = {Characterizing Application Scheduling on Edge, Fog and Cloud Computing Resources},
year = {2020},
number = {5},
pages = {558--595},
volume = {50},
doi = {10.1002/spe.2699},
keywords = {iisc, cloud, edge, fog, survey},
}

@Article{simmhan:jiisc:2020,
author = {Yogesh Simmhan and Tarun Rambha and Aakash Khochare and Shriram Ramesh and Animesh Baranawal and John Varghese George and Rahul Atul Bhope and Amrita Namtirtha and Amritha Sundararajan and Sharath Suresh Bhargav and Nihar Thakkar and Raj Kiran},
journal = {Journal of the Indian Institute of Science},
title = {c: Privacy Respecting Contact Tracing for {COVID-19} Management},
year = {2020},
note = {To Appear},
url = {https://arxiv.org/abs/2009.04916},
}

@Article{varshney:tpds:2019,
author = {Prateeksha Varshney and Yogesh Simmhan},
journal = {IEEE Transactions on Parallel and Distributed Systems (TPDS)},
title = {{AutoBoT}: Resilient and Cost-effective Scheduling of a Bag of Tasks on Spot VMs},
year = {2019},
number = {7},
pages = {1512--1527},
volume = {30},
doi = {10.1109/TPDS.2018.2889851},
keywords = {iisc, cloud, scheduling, spot VM},
}

@Article{buyya:csur:2019,
author = {Rajkumar Buyya and Satish Narayana Srirama and Giuliano Casale and Rodrigo N. Calheiros and Yogesh Simmhan and Blesson Varghese and Erol Gelenbe and Bahman Javadi and Luis Miguel Vaquero and Marco A. S. Netto and Adel Nadjaran Toosi and Maria Alejandra Rodriguez and Ignacio Mart{\'{\i}}n Llorente and Sabrina De Capitani di Vimercati and Pierangela Samarati and Dejan S. Milojicic and Carlos A. Varela and Rami Bahsoon and Marcos Dias de Assun{\c{c}}{\~{a}}o and Omer Rana and Wanlei Zhou and Hai Jin and Wolfgang Gentzsch and Albert Y. Zomaya and Haiying Shen},
journal = {ACM Computing Surveys (CSUR)},
title = {A Manifesto for Future Generation Cloud Computing: Research Directions for the Next Decade},
year = {2019},
number = {5},
pages = {105:1--105:38},
volume = {51},
doi = {10.1145/3241737},
keywords = {iisc, cloud},
url = {https://arxiv.org/abs/1711.09123},
}

@Article{ghosh:tcps:2018,
author = {Rajrup Ghosh and Yogesh Simmhan},
journal = {ACM Transactions on Cyber-Physical Systems (TCPS)},
title = {Distributed Scheduling of Event Analytics across Edge and Cloud},
year = {2018},
number = {4},
pages = {24:1--24:28},
volume = {2},
doi = {10.1145/3140256},
keywords = {iisc, peer reviewed, stream processing, edge computing, iot},
owner = {simmhan},
timestamp = {2018.03.12},
url = {https://arxiv.org/abs/1608.01537},
}

@Article{heidari:csur:2018,
author = {Safiollah Heidari and Yogesh Simmhan and Rodrigo N. Calheiros and Rajkumar Buyya},
title = {Scalable Graph Processing Frameworks: A Taxonomy and Open Challenges},
journal = {ACM Computing Surveys (CSUR)},
year = {2018},
volume = {51},
number = {3},
pages = {1--53},
month = jun,
doi = {10.1145/3199523},
keywords = {peer reviewed, iisc, graph processing},
owner = {simmhan},
timestamp = {2018.04.11},
url = {https://dl.acm.org/citation.cfm?id=3199523},
}

@Article{shukla:jpdc:2018,
author = {Anshu Shukla and Yogesh Simmhan},
title = {Model-driven Scheduling for Distributed Stream Processing Systems},
journal = {Journal of Parallel and Distributed Computing (JPDC)},
year = {2018},
volume = {117},
pages = {98--114},
month = jul,
doi = {10.1016/j.jpdc.2018.02.003},
keywords = {peer reviewed, iisc, stream processing},
owner = {simmhan},
timestamp = {2018.04.11},
url = {https://arxiv.org/abs/1702.01785},
}

@Article{simmhan:spe:2018,
author = {Yogesh Simmhan and Pushkara Ravindra and Shilpa Chaturvedi and Malati Hegde and Rashmi Ballamajalu},
title = {Towards a Data-driven IoT Software Architecture for Smart City Utilities},
journal = {Software: Practice and Experience},
year = {2018},
volume = {48},
number = {7},
pages = {1390--1416},
month = jul,
doi = {10.1002/spe.2580},
keywords = {peer reviewed, iisc, smart city, iot},
owner = {simmhan},
timestamp = {2018.05.02},
url = {http://arxiv.org/abs/1803.02500},
}

@Article{jha:ccpe:2017,
author = {Shantenu Jha and Daniel S. Katz Andre Luckow and Omer Rana and Yogesh Simmhan amd Neil Chue Hong},
journal = {Concurrency and Computation: Practice and Experience},
title = {Introducing Distributed Dynamic Data-intensive (D3) Science: Understanding Applications and Infrastructure},
year = {2017},
number = {8},
volume = {29},
doi = {10.1002/cpe.4032},
keywords = {peer reviewed, iisc, escience, big data},
owner = {simmhan},
timestamp = {2018.04.11},
url = {https://github.com/radical-project/3DPAS},
}

@Article{zhou:fgcs:2017,
author = {Qunzhi Zhou and Yogesh Simmhan and Viktor Prasanna},
journal = {Future Generation Computer Systems},
title = {Knowledge-infused and Consistent Complex Event Processing over Real-time and Persistent Streams},
year = {2017},
pages = {391--406},
volume = {76},
doi = {10.1016/j.future.2016.10.030},
keywords = {peer reviewed, cep, stream processing, semantics, iisc},
owner = {simmhan},
timestamp = {2018.04.11},
}

@Article{shukla:ccpe:2017,
author = {Anshu Shukla and Shilpa Chaturvedi and Yogesh Simmhan},
title = {RIoTBench: An IoT Benchmark for Distributed Stream Processing Systems},
journal = {Concurrency and Computation: Practice and Experience},
year = {2017},
volume = {29},
number = {21},
pages = {1--22},
doi = {10.1002/cpe.4257},
keywords = {iisc, iot, stream processing, benchmark, peer reviewed},
owner = {simmhan},
timestamp = {2018.04.11},
url = {https://arxiv.org/abs/1701.08530},
}

@Article{kumbhare:tcc:2015,
author = {Alok Gautam Kumbhare and Yogesh Simmhan and Marc Frincu and Viktor K. Prasanna},
title = {Reactive Resource Provisioning Heuristics for Dynamic Dataflows on Cloud Infrastructure},
journal = {IEEE Transactions on Cloud Computing (TCC)},
year = {2015},
volume = {3},
number = {2},
pages = {105--118},
doi = {10.1109/TCC.2015.2394316},
keywords = {peer reviewed, iisc, stream processing, cloud},
timestamp = {2017.03.31},
}

@Article{Aman:tkde:2015,
author = {Saima Aman and Yogesh Simmhan and Viktor Prasanna},
title = {Holistic Measures for Evaluating Prediction Models in Smart Grids},
journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},
year = {2015},
volume = {27},
number = {2},
pages = {475--488},
month = feb,
note = {[IF 2.476, CORE A]},
doi = {10.1109/TKDE.2014.2327022},
keywords = {usc, machine learning, smart grid, peer reviewed, iisc},
owner = {Simmhan},
timestamp = {2016.07.20},
}

@Article{Aman:comm:2013,
author = {Saima Aman and Yogesh Simmhan and Viktor K. Prasanna},
title = {Energy Management Systems: State of the Art and Emerging Trends},
journal = {IEEE Communications Magazine},
year = {2013},
volume = {51},
number = {1},
pages = {114 -119},
month = {January},
note = {[IF 3.785]},
doi = {10.1109/MCOM.2013.6400447},
keywords = {smart grid, peer reviewed, usc},
owner = {Simmhan},
publisher = {IEEE},
timestamp = {2012.09.11},
}

@Article{simmhan:cise:2013,
author = {Yogesh Simmhan and Saima Aman and Alok Kumbhare and Rongyang Liu and Sam Stevens and Qunzhi Zhou and Viktor Prasanna},
title = {Cloud-Based Software Platform for Big Data Analytics in Smart Grids},
journal = {Computing in Science and Engineering},
year = {2013},
volume = {15},
number = {4},
pages = {38 - 47},
note = {[IF 1.422, CORE C]},
doi = {10.1109/MCSE.2013.39},
keywords = {usc, smart grid, cloud, peer reviewed},
owner = {Simmhan},
publisher = {IEEE and AIP},
timestamp = {2018.04.11},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-cise-2013.pdf},
}

@Article{Simmhan:ijca:2011,
title = {Using Provenance for Personalized Quality Ranking of Scientific Datasets},
author = {Yogesh Simmhan and Beth Plale},
journal = {International Journal of Computers and Their Applications (IJCA)},
year = {2011},
month = {September},
number = {3},
pages = {180--195},
volume = {18},
abstract = {The rapid growth of eScience has led to an explosion in the creation and availability of scientific datasets that includes raw instrument data and derived datasets from model simulations. A large number of these datasets are surfacing online in public and private catalogs, often annotated with XML metadata, as part of community efforts to foster open research. With this rapid expansion comes the challenge of filtering and selecting datasets that best match the needs of scientists. We address a key aspect of the scientific data discovery process by ranking search results according to a personalized data quality score based on a declarative quality profile to help scientists select the most suitable data for their applications. Our quality model is resilient to missing metadata using a novel strategy that uses provenance in its absence. Intuitively, our premise is that the quality score for a dataset depends on its provenance – the scientific task and its inputs that created the dataset – and it is possible to define a quality function based on provenance metadata that predicts the same quality score as one evaluated using the user’s quality profile over the complete metadata. Here, we present a model and architecture for data quality scoring, apply machine learning techniques to construct a quality function that uses provenance as proxy for missing metadata, and empirically test the prediction power of our quality function. Our results show that for some scientific tasks, quality scores based on provenance closely track the quality scores based on complete metadata properties, with error margins between 1 – 29%.},
entrytype = {journal},
issn = {1076-5204},
keywords = {usc, provenance, iu, peer reviewed, karma, special issue},
owner = {Simmhan},
publisher = {ISCA},
timestamp = {2011.07.31},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-ijca-2011.pdf}
}

@Article{Zhao:ijca:2011,
title = {Querying Provenance Information in Distributed Environments},
author = {Jing Zhao and Yogesh Simmhan and Karthik Gomadam and Viktor K. Prasanna},
journal = {International Journal of Computers and Their Applications (IJCA)},
year = {2011},
month = {September},
number = {3},
pages = {196--215},
volume = {18},
abstract = {The growing recognition of the importance of provenance for data intensive and multidisciplinary domains is leading to careful collection of provenance. One consequence of this is the proliferation of provenance repositories hosted for individual organization or communities, with limited ability to reconstruct and query for and on provenance across them. Community standards like the Open Provenance Model (OPM) allow uniform interpretation and exchange of provenance metadata but do not prescribe query or service specifications to access provenance. If data reuse and sharing across institutions is not accompanied by passing provenance at the time of data exchange, we need to track the provenance and query for them or over them across distributed provenance repositories. In this article, we present approaches for querying over distributed provenance information, and address two common provenance query models that we formalize: provenance retrieval query and provenance filter query. Our problem is motivated by Smart Oilfield applications in the energy informatics domain, and we evaluate the performance of our algorithms using synthetic workflows based on the domain.},
issn = {1076-5204},
keywords = {usc, smart oilfield, provenance, peer reviewed, special issue},
owner = {Simmhan},
publisher = {ISCA},
timestamp = {2011.07.31},
url = {http://ceng.usc.edu/~simmhan/pubs/zhao-ijca-2011.pdf}
}

@Article{Moreau:fgcs:2011,
author = {Luc Moreau and Ben Clifford and Juliana Freire and Joe Futrelle and Yolanda Gil and Paul Groth and Natalia Kwasnikowska and Simon Miles and Paolo Missier and Jim Myers and Beth Plale and Yogesh Simmhan and Eric Stephan and Jan Van den Bussche},
title = {The Open Provenance Model core specification (v1.1)},
journal = {Future Generation Computer Systems (FGCS)},
year = {2011},
volume = {27},
pages = {743--756},
note = {[IF 2.43, CORE A]},
abstract = {The Open Provenance Model is a model of provenance that is designed to meet the following requirements: (1) Allow provenance information to be exchanged between systems, by means of a compatibility layer based on a shared provenance model. (2) Allow developers to build and share tools that operate on such a provenance model. (3) Define provenance in a precise, technology-agnostic manner. (4) Support a digital representation of provenance for any “thing”, whether produced by computer systems or not. (5) Allow multiple levels of description to coexist. (6) Define a core set of rules that identify the valid inferences that can be made on provenance representation. This document contains the specification of the Open Provenance Model (v1.1) resulting from a community effort to achieve inter-operability in the Provenance Challenge series.},
doi = {doi:10.1016/j.future.2010.07.005},
editor = {Yogesh Simmhan and Paul Groth and Luc Moreau},
issn = {0167-739X},
issue = {6},
keywords = {msr, provenance, opm, representation, inter-operability, peer reviewed},
owner = {Simmhan},
publisher = {Elsevier},
timestamp = {2016.07.20},
url = {http://ceng.usc.edu/~simmhan/pubs/moreau-fgcs-2011.pdf},
}

@Article{Simmhan:fgcs:2011,
author = {Yogesh Simmhan and Roger Barga},
title = {Analysis of approaches for supporting the Open Provenance Model: A case study of the Trident workflow workbench},
journal = {Future Generation Computer Systems (FGCS)},
year = {2011},
volume = {27},
pages = {790--796},
note = {[IF 2.43, CORE A]},
abstract = {The Trident workbench is a platform for composing, executing and managing scientific workflows. While Trident collects provenance in its native provenance model, the third provenance challenge was an opportunity to build support for the Open Provenance Model into Trident. There are several possible approaches to harmonize our native model with OPM, and such choices are also available to other existing provenance and workflow systems working towards OPM compatibility. We identify and analyze the relative merits of these approaches in an effort to inform practitioners planning to support OPM in their existing provenance/workflow systems. Further, we describe our experience with using the integration approach we choose to interoperate with other teams as part of the challenge.},
doi = {doi:10.1016/j.future.2010.10.005},
editor = {Yogesh Simmhan and Paul Groth and Luc Moreau},
issn = {0167-739X},
issue = {6},
keywords = {msr, provenance, opm, trident, workflow, inter-operability, provenance challenge, peer reviewed},
owner = {Simmhan},
publisher = {Elsevier},
timestamp = {2016.07.20},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-fgcs-2011.pdf},
}

@Article{Barga:deb:2010,
title = {Provenance for Scientific Workflows: Towards Reproducible Research},
author = {Roger Barga and Yogesh Simmhan and Eran Chinthaka Withana and Satya Sahoo and Jared Jackson and Nelson Araujo},
journal = {Data Engineering Bulletin (DEB)},
year = {2010},
month = {September},
number = {3},
pages = {50--59},
volume = {33},
editor = {Wang-Chiew Tan},
keywords = {msr, provenance, trident, workflow, peer reviewed},
owner = {Simmhan},
publisher = {IEEE},
timestamp = {2011.01.07},
url = {http://sites.computer.org/debull/A10sept/barga.pdf}
}

@Article{Simmhan:cpe:2008,
title = {Query capabilities of the Karma provenance framework},
author = {Yogesh L. Simmhan and Beth Plale and Dennis Gannon},
journal = {Concurrency and Computation: Practice \& Experience, Special Issue on The First Provenance Challenge},
year = {2008},
month = {April},
note = {[IF 0.636, CORE A]},
pages = {441--451},
volume = {20},
abstract = {Provenance metadata in e-Science captures the derivation history of data products generated from scientific workflows. Provenance forms a glue linking workflow execution with associated data products, and finds use in determining the quality of derived data, tracking resource usage, and for verifying and validating scientific experiments. In this article, we discuss the scope of provenance collected in the Karma provenance framework used in the LEAD Cyberinfrastructure project, distinguishing provenance metadata from generic annotations. We further describe our approaches to querying for different forms of provenance in Karma in the context of queries in the first provenance challenge. We use an incremental, building-block method to construct provenance queries based on the fundamental querying capabilities provided by the Karma service centered on the provenance data model. This has the advantage of keeping the Karma service generic and simple, and yet supports a wide range of queries. Karma successfully answers all but one challenge query. Copyright © 2007 John Wiley & Sons, Ltd.},
acmid = {1350749},
address = {Chichester, UK},
doi = {10.1002/cpe.v20:5},
issn = {1532-0626},
issue = {5},
keywords = {iu, provenance, data provenance, process provenance, provenance queries, workflows, karma, escience, provenance challenge, peer reviewed},
numpages = {11},
owner = {Simmhan},
publisher = {John Wiley and Sons Ltd.},
timestamp = {2012.09.11}
}

@Article{Simmhan:ijwsr:2008,
title = {Karma2: Provenance Management for Data-Driven Workflows},
author = {Yogesh L. Simmhan and Beth Plale and Dennis Gannon},
journal = {International Journal of Web Services Research (IJWSR)},
year = {2008},
note = {[IF 0.371, CORE C]},
number = {2},
pages = {1--22},
volume = {5},
abstract = {The increasing ability for the sciences to sense the world around us is resulting in a growing need for datadriven e-Science applications that are under the control of workflows composed of services on the Grid. The focus of our work is on provenance collection for these workflows that are necessary to validate the work-flow and to determine quality of generated data products. The challenge we address is to record uniform and usable provenance metadata that meets the domain needs while minimizing the modification burden on the service authors and the performance overhead on the workflow engine and the services. The framework is based on generating discrete provenance activities during the lifecycle of a workflow execution that can be aggregated to form complex data and process provenance graphs that can span across workflows. The implementation uses a loosely coupled publish-subscribe architecture for propagating these activities, and the capabilities of the system satisfy the needs of detailed provenance collection. A performance evaluation of a prototype finds a minimal performance overhead (in the range of 1% for an eight-service workflow using 271 data products).},
doi = {10.4018/jwsr.2008040101},
issn = {1545-7362},
keywords = {msr, provenance, karma, workflow, escience, peer reviewed},
owner = {Simmhan},
publisher = {IGI Publishing},
timestamp = {2011.01.07}
}

@Article{Gannon:ieee:2005,
title = {Building Grid Portal Applications from a Web-Service Component Architecture},
author = {Dennis Gannon and Jay Alameda and Octav Chipara and Marcus Christie and Vinayak Dukle and Liang Fang and Matthew Farellee and Geoffrey Fox and Shawn Hampton and Gopi Kandaswamy and Deepti Kodeboyina and Charlie Moad and Marlon Pierce and Beth Plale and Albert Rossi and Yogesh Simmhan and Anuraag Sarangi and Aleksander Slominski and Satoshi Shirasauna and Thomas Thomas},
journal = {Proceedings of the IEEE, Special issue on Grid Computing},
year = {2005},
month = {March},
note = {[IF 6.81]},
number = {3},
pages = {551--563},
volume = {93},
abstract = {This paper describes an approach to building Grid applications based on the premise that users who wish to access and run these applications prefer to do so without becoming experts on Grid technology. We describe an application architecture based on wrapping user applications and application workflows as web services and web service resources.These services are visible to the users and to resource providers through a family of Grid portal components that can be used to configure, launch and monitor complex applications in the scientific language of the end user. The applications in this model are instantiated by an application factory service. The layered design of the architecture makes it possible for an expert to configure an application factory service with a custom user interface client that may be dynamical loaded into the portal.},
doi = {10.1109/JPROC.2004.842756},
issn = {0018-9219},
keywords = {iu,grid, portal,web service, peer reviewed},
owner = {Simmhan},
publisher = {IEEE},
timestamp = {2012.09.11}
}

@Article{Simmhan:record:2005,
title = {A Survey of Data Provenance in e-Science},
author = {Yogesh Simmhan and Beth Plale and Dennis Gannon},
journal = {SIGMOD Record},
year = {2005},
note = {[IF 0.667]},
number = {3},
pages = {31--36},
volume = {34},
abstract = {Data management is growing in complexity as large-scale applications take advantage of the loosely coupled resources brought together by grid middleware and by abundant storage capacity. Metadata describing the data products used in and generated by these applications is essential to disambiguate the data and enable reuse. Data provenance, one kind of metadata, pertains to the derivation history of a data product starting from its original sources. In this paper we create a taxonomy of data provenance characteristics and apply it to current research efforts in e-science, focusing primarily on scientific workflow approaches. The main aspect of our taxonomy categorizes provenance systems based on why they record provenance, what they describe, how they represent and store provenance, and ways to disseminate it. The survey culminates with an identification of open research problems in the field.},
doi = {10.1145/1084805.1084812},
ee = {http://doi.acm.org/10.1145/1084812},
issn = {0163-5808},
keywords = {iu, provenance, escience, peer reviewed},
owner = {Simmhan},
publisher = {ACM},
timestamp = {2012.09.11}
}

@Article{Gannon:cluster:2002,
title = {Programming the Grid: Distributed Software Components, P2P and Grid Web Services for Scientific Applications},
author = {Dennis Gannon and Randall Bramley and Geoffrey Fox and Shava Smallen and Al Rossi and Rachana Ananthakrishnan and Felipe Bertrand and Kenneth Chiu and Matt Farrellee and Madhusudhan Govindaraju and Sriram Krishnan and Lavanya Ramakrishnan and Yogesh Simmhan and Aleksander Slominski and Yu Ma and Caroline Olariu and Nicolas Rey-Cenvaz},
journal = {Cluster Computing},
year = {2002},
note = {[IF 0.519]},
number = {3},
pages = {325--336},
volume = {5},
abstract = {Computational Grids have become an important asset in large-scale scientific and engineering research. By providing a set of services that allow a widely distributed collection of resources to be tied together into a relatively seamless computing framework, teams of researchers can collaborate to solve problems that they could not have attempted before. Unfortunately the task of building Grid applications remains extremely difficult because there are few tools available to support developers. To build reliable and re-usable Grid applications, programmers must be equipped with a programming framework that hides the details of most Grid services and allows the developer a consistent, non-complex model in which applications can be composed from well tested, reliable sub-units. This paper describes experiences with using a software component framework for building Grid applications. The framework, which is based on the DOE Common Component Architecture (CCA), allows individual components to export function/service interfaces that can be remotely invoked by other components. The framework also provides a simple messaging/event system for asynchronous notification between application components. The paper also describes how the emerging Web-Services model fits with a component-oriented application design philosophy. To illustrate the connection between web services and Grid application programming we describe a simple design pattern for application factory services which can be used to simplify the task of building reliable Grid programs. Finally we address several issues of Grid programming that better understood from the perspective of Peer-to-Peer (P2P) systems. In particular we describe how models for collaboration and resource sharing fit well with many grid application scenarios.},
doi = {10.1023/A:1015633507128},
issn = {1386-7857},
keywords = {iu, component, grid, web service, escience, peer reviewed},
owner = {Simmhan},
publisher = {Springer Netherlands},
timestamp = {2012.09.11}
}

@Article{Krishnan:sciprog:2002,
author = {Sriram Krishnan and Randall Bramley and Dennis Gannon and Rachana Ananthakrishnan and Madhusudhan Govindaraju and Aleksander Slominski and Yogesh Simmhan and Jay Alameda and Richard Alkire and Timothy Drews and Eric Webb},
title = {The XCAT Science Portal},
journal = {Scientific Programming},
year = {2002},
volume = {10},
number = {4},
pages = {303---317},
month = {December},
issn = {1058-9244},
note = {[IF 0.967]},
abstract = {This paper describes the design and prototype implementation of the XCAT Grid Science Portal. The portal lets grid application programmers script complex distributed computations and package these applications with simple interfaces for others to use. Each application is packaged as a notebook which consists of webpages and editable parameterized scripts. The portal is a workstation-based specialized personal web server, capable of executing the application scripts and launching remote grid applications for the user. The portal server can receive event streams published by the application and grid resource information published by Network Weather Service(NWS) or Autopilot sensors. Notebooks can be published and stored in web based archives for others to retrieve and modify. The XCAT Grid Science Portal has been tested with various applications, including the distributed simulation of chemical processes in semiconductor manufacturing and collaboratory support for X-ray crystallographers.},
address = {Amsterdam, The Netherlands},
keywords = {iu, component, portal, escience, peer reviewed},
location = {Denver, CO, USA},
opthrefnote = {\href{http://dx.doi.org/}{doi/}},
owner = {Simmhan},
publisher = {IOS Press},
timestamp = {2018.04.11},
url = {https://content.iospress.com/articles/scientific-programming/spr00107},
}

@InProceedings{ramesh:ccgrid:2020,
author = {Shriram Ramesh and Animesh Baranawal and Yogesh Simmhan},
booktitle = {{IEEE/ACM} International Symposium on Cluster, Cloud and Internet Computing (CCGRID)},
title = {A Distributed Path Query Engine for Temporal Property Graphs},
year = {2020},
pages = {499--508},
doi = {10.1109/CCGrid49817.2020.00-43},
}

@InProceedings{acharya:comsnet:2020,
author = {Srikrishna Acharya and Amrutur Bharadwaj and Yogesh Simmhan and Aditya Gopalan and Parimal Parag and Himanshu Tyagi},
booktitle = {{IEEE} International Conference on COMmunication Systems {\&} NETworkS ({COMSNETS})},
title = {{CORNET:} {A} Co-Simulation Middleware for Robot Networks},
year = {2020},
pages = {245--251},
doi = {10.1109/COMSNETS48256.2020.9027459},
}

@InProceedings{garg:europar:2020,
author = {Dhruv Garg and Prathik Shirolkar and Anshu Shukla and Yogesh Simmhan},
booktitle = {International Conference on Parallel and Distributed Computing (Euro-Par)},
title = {TorqueDB: Distributed Querying of Time-Series Data from Edge-local Storage},
year = {2020},
pages = {281--295},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
volume = {12247},
doi = {10.1007/978-3-030-57675-2\_18},
}

@InProceedings{gandhi:icde:2020,
author = {Swapnil Gandhi and Yogesh Simmhan},
booktitle = {{IEEE} International Conference on Data Engineering ({ICDE})},
title = {An Interval-centric Model for Distributed Computing over Temporal Graphs},
year = {2020},
pages = {1129--1140},
doi = {10.1109/ICDE48307.2020.00102},
}

@InProceedings{monga:icws:2019,
author = {Sumit Kumar Monga and Sheshadri K R and Yogesh Simmhan},
booktitle = {IEEE International Conference on Web Services (ICWS)},
title = {ElfStore: A Resilient Data Storage Service for Federated Edge and Fog Resources},
year = {2019},
note = {[CORE A]},
pages = {336--345},
doi = {10.1109/ICWS.2019.00062},
keywords = {iisc, edge, fog, storage, reliability},
}

@InProceedings{jaiswal:ipdpsw:2019,
author = {Siddharth D. Jaiswal and Yogesh Simmhan},
booktitle = {IEEE International Workshop on High-Performance Big Data, Deep Learning, and Cloud Computing (HPBDC), Co-located with IEEE International Parallel and Distributed Processing Symposium (IPDPS)},
title = {A Partition-centric Distributed Algorithm for Identifying Euler Circuits in Large Graphs},
year = {2019},
pages = {452--459},
doi = {10.1109/IPDPSW.2019.00085},
keywords = {iisc, graph, subgraph centric, algorithm},
url = {https://arxiv.org/abs/1903.06950},
}

@InProceedings{dindokar:cloud:2019,
author = {Ravikant Dindokar and Yogesh Simmhan},
booktitle = {IEEE International Conference on Cloud Computing (CLOUD)},
title = {Adaptive Partition Migration for Irregular Graph Algorithms on Elastic Resources},
year = {2019},
note = {[CORE B]},
pages = {281--290},
doi = {10.1109/CLOUD.2019.00-28},
keywords = {iisc, graph, cloud, goffish},
}

@InProceedings{khochare:ccgrid:2019,
author = {Aakash Khochare and Sheshadri Ramachandra and Shriram Ramesh and Yogesh Simmhan},
booktitle = {IEEE International Scalable Computing Challenge (SCALE), Co-located with {IEEE/ACM} International Symposium on Cluster, Cloud and Grid Computing ({CCGRID})},
title = {Dynamic Scaling of Video Analytics for Wide-area Tracking in Urban Spaces},
year = {2019},
note = {SCALE Challenge Winner},
pages = {76--81},
doi = {10.1109/CCGRID.2019.00018},
keywords = {iisc, edge, video analytics},
}

@InProceedings{simmhan:escience:2019,
author = {Yogesh Simmhan and Malati Hegde and Rajesh Zele and Sachchida N. Tripathi and Srijith Nair and Sumit K. Monga and Ravi Sahu and Kuldeep Dixit and Ronak Sutaria and Brijesh Mishra and Anamika Sharma and Anand SVR},
booktitle = {{IEEE} International Conference on eScience ({eScience})},
title = {{SATVAM:} Toward an IoT Cyber-Infrastructure for Low-Cost Urban Air Quality Monitoring},
year = {2019},
pages = {57--66},
doi = {10.1109/eScience.2019.00014},
}

@InProceedings{khochare:icdcn:2019,
author = {Aakash Khochare and Yogesh Simmhan},
booktitle = {{ACM} International Conference on Distributed Computing and Networking ({ICDCN})},
title = {A scalable and composable analytics platform for distributed wide-area tracking},
year = {2019},
note = {Extended Abstract},
pages = {506},
doi = {10.1145/3288599.3299753},
}

@InProceedings{chaturvedi:isorc:2019,
author = {Shilpa Chaturvedi and Yogesh Simmhan},
booktitle = {{IEEE} International Symposium on Real-Time Distributed Computing ({ISORC})},
title = {Toward Resilient Stream Processing on Clouds using Moving Target Defense},
year = {2019},
pages = {134--142},
doi = {10.1109/ISORC.2019.00035},
}

@InProceedings{chaudhary:hipcw:2019,
author = {Diksha Chaudhary and Bratati Kahali and Yogesh Simmhan},
booktitle = {Women in Data Science and Computing Workshop, Co-located with IEEE International Conference on High Performance Computing, Data, and Analytics (HiPC)},
title = {An Empirical Study on Efficient Storage of Human Genome Data},
year = {2019},
pages = {87--92},
doi = {10.1109/HiPCW.2019.00030},
}

@InProceedings{badiger:europar:2018,
author = {Shreyas Badiger and Shrey Baheti and Yogesh Simmhan},
title = {VIoLET: A Large-scale Virtual Environment for Internet of Things},
booktitle = {International European Conference on Parallel and Distributed Computing (EuroPar)},
year = {2018},
pages = {1--16},
note = {[CORE A]},
keywords = {iisc, peer reviewed, iot},
owner = {simmhan},
timestamp = {2018.05.02},
url = {https://github.com/dream-lab/VIoLET},
}

@InProceedings{shukla:icdcs:2018,
author = {Anshu Shukla and Yogesh Simmhan},
title = {Toward Reliable and Rapid Elasticity for Streaming Dataflows on Clouds},
booktitle = {IEEE International Conference on Distributed Computing Systems (ICDCS)},
year = {2018},
pages = {1--11},
note = {[CORE A]},
keywords = {peer reviewed, iisc, stream processing},
owner = {simmhan},
timestamp = {2018.05.02},
url = {https://arxiv.org/abs/1712.00605},
}

@InProceedings{ghosh:ccgrid:2018,
author = {Rajrup Ghosh and Siva Prakash Reddy and Yogesh Simmhan},
title = {Adaptive Energy-aware Scheduling of Dynamic Event Analytics across Edge and Cloud Resources},
booktitle = {IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)},
year = {2018},
pages = {1--11},
note = {[CORE A]},
url = {https://arxiv.org/abs/1801.01087},
}

@InProceedings{varshney:icfec:2017,
author = {Prateeksha Varshney and Yogesh Simmhan},
title = {Demystifying Fog Computing: Characterizing Architectures, Applications and Abstractions},
booktitle = {IEEE International Conference on Fog and Edge Computing (ICFEC)},
year = {2017},
pages = {1--10},
doi = {10.1109/ICFEC.2017.20},
keywords = {peer reviewed, iISc, cloud, IoT, fog, edge},
owner = {simmhan},
timestamp = {2018.03.12},
url = {https://arxiv.org/abs/1702.06331},
}

@InProceedings{khochare:iscocw:2017,
author = {Aakash Khochare and Pushkara Ravindra and Siva Prakash Reddy and Yogesh Simmhan},
title = {Distributed Video Analytics across Edge and Cloud using ECHO},
booktitle = {International Conference on Service-Oriented Computing (ICSOC) Demo},
year = {2017},
pages = {1--6},
keywords = {iisc, peer reviewed, iot, edge computing},
owner = {simmhan},
timestamp = {2018.04.11},
url = {http://www.icsoc.spilab.es/wp-content/uploads/2017/10/Distributed-Video-Analytics-across-Edge-and-Cloud-using-ECHO.pdf},
}

@InProceedings{ravindra:iscoc:2017,
author = {Pushkara Ravindra and Aakash Khochare and Siva Prakash Reddy and Sarthak Sharma and Prateeksha Varshney and Yogesh Simmhan},
title = {ECHO: An Adaptive Orchestration Platform for Hybrid Dataflows across Cloud and Edge},
booktitle = {International Conference on Service-Oriented Computing (ICSOC)},
year = {2017},
pages = {1--16},
note = {[CORE A]},
doi = {10.1007/978-3-319-69035-3_28},
keywords = {iisc, peer reviewed, iot, edge computing},
owner = {simmhan},
timestamp = {2018.03.12},
url = {https://arxiv.org/abs/1707.00889},
}

@InProceedings{dindokar:hipcw:2017,
author = {Ravikant Dindokar and Yogesh Simmhan},
title = {Characterization of Vertex-centric Breadth First Search for Lattice Graphs},
booktitle = {IEEE International Workshop on Foundations in Big Data Computing (BigDF), Co-located with HiPC},
year = {2017},
pages = {1--8},
doi = {10.1109/HiPCW.2017.00014},
keywords = {iisc, peer reviewed, graph processing},
owner = {simmhan},
timestamp = {2018.04.11},
}

@InProceedings{kalyanasundaram:hipc:2017,
author = {Jayanth Kalyanasundaram and Yogesh Simmhan},
title = {ARM Wrestling with Big Data: A Study of Commodity ARM64 Server for Big Data Workloads},
booktitle = {IEEE International Conference on High Performance Computing, Data, and Analytics (HiPC)},
year = {2017},
pages = {1--10},
note = {Best paper finalist, [CORE B]},
doi = {10.1109/HiPC.2017.00032},
keywords = {iisc, peer reviewed, big data, low power},
owner = {simmhan},
timestamp = {2018.03.12},
url = {https://arxiv.org/abs/1701.05996},
}

@InProceedings{chaturvedi:escience:2017,
author = {Shilpa Chaturvedi and Sahil Tyagi and Yogesh Simmhan},
booktitle = {IEEE International Conference on eScience ({eScience})},
title = {Collaborative Reuse of Streaming Dataflows in IoT Applications},
year = {2017},
note = {[CORE A]},
pages = {1--10},
doi = {10.1109/eScience.2017.54},
keywords = {iisc, peer reviewed, iot, stream processing},
owner = {simmhan},
timestamp = {2018.04.11},
url = {https://arxiv.org/abs/1709.03332},
}

@InProceedings{jamadagni:ccgrid:2016,
author = {Nitin Jamadagni and Yogesh Simmhan},
title = {GoDB: From Batch Processing to Distributed Querying over Property Graphs},
booktitle = {IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing (CCGrid)},
year = {2016},
pages = {281--290},
note = {[CORE A]},
doi = {10.1109/CCGrid.2016.105},
keywords = {godb, goffish, peer reviewed, IISc, graph},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://ieeexplore.ieee.org/document/7515700/},
}

@InProceedings{dindokar:ccgrid:2016,
author = {Ravikant Dindokar and Yogesh Simmhan},
title = {Elastic Partition Placement for Non-stationary Graph Algorithms},
booktitle = {IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing (CCGrid)},
year = {2016},
pages = {90--93},
note = {Short Paper, [CORE A]},
doi = {10.1109/CCGrid.2016.97},
keywords = {goffish, peer reviewed, IISc, graph, cloud},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://ieeexplore.ieee.org/document/7515673/},
}

@InProceedings{shukla:tpctc:2016,
author = {Anshu Shukla and Yogesh Simmhan},
title = {Benchmarking Distributed Stream Processing Platforms for IoT Applications},
booktitle = {TPC Technology Conference on Performance Evaluation \& Benchmarking (TPCTC)},
year = {2016},
volume = {10080},
series = {LNCS},
pages = {90--106},
doi = {10.1007/978-3-319-54334-5_7},
keywords = {iot, peer reviewed, iisc, stream, benchmark},
owner = {simmhan},
timestamp = {2018.03.14},
url = {https://arxiv.org/abs/1606.07621},
}

@InProceedings{dindokar:bigdata:2016,
author = {Ravikant Dindokar and Neel Choudhury and Yogesh Simmhan},
title = {A Meta-graph Approach to Analyze Subgraph-centric Distributed Programming Models},
booktitle = {IEEE International Conference on Big Data (Big Data)},
year = {2016},
pages = {37--47},
doi = {10.1109/BigData.2016.7840587},
keywords = {graph, goffish, meta-graph, analysis, iisc, peer reviewed},
owner = {simmhan},
timestamp = {2017.09.22},
url = {http://ieeexplore.ieee.org/document/7840587/},
}

@InProceedings{dindokar:parlearning:2015,
author = {Ravikant Dindokar and Neel Choudhury and Yogesh Simmhan},
booktitle = {IEEE International Workshop on Parallel and Distributed Computing for Large Scale Machine Learning and Big Data Analytics (ParLearning), Co-located with IPDPS},
title = {Analysis of Subgraph-centric Distributed Shortest Path Algorithm},
year = {2015},
note = {Short paper},
pages = {1185--1190},
doi = {10.1109/IPDPSW.2015.87},
keywords = {peer reviewed, iisc, graph processing},
timestamp = {2017.07.23},
url = {http://ieeexplore.ieee.org/document/7284445/},
}

@InProceedings{simmhan:ipdps:2015,
author = {Yogesh Simmhan and Neel Choudhury and Charith Wickramaarachchi and Alok Kumbhare and Marc Frincu and Cauligi Raghavendra and Viktor Prasanna},
title = {Distributed Programming over Time-series Graphs},
booktitle = {IEEE International Parallel \& Distributed Processing Symposium (IPDPS)},
year = {2015},
pages = {809--818},
note = {[CORE A]},
doi = {10.1109/IPDPS.2015.66},
keywords = {graph processing, timeseries, goffish, iISc, usc, peer reviewed},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://ieeexplore.ieee.org/document/7161567/},
}

@InProceedings{shukla:hipcw:2015,
author = {Anshu Shukla and Tarun Sharma and Yogesh Simmhan},
title = {Characterizing Distributed Stream Processing Systems for IoT Applications},
booktitle = {Workshop on Architectural Support and Middleware for InfoSymbiotics/ Dynamic Data Driven Applications Systems (DDDAS), co-located with High Performance Computing Conference (HiPC)},
year = {2015},
pages = {61},
note = {Extended abstract},
doi = {10.1109/HiPCW.2015.22},
keywords = {iisc, iot, stream processing, peer reviewed},
owner = {simmhan},
timestamp = {2017.07.23},
}

@InProceedings{aman:sgcomm:2015,
author = {Saima Aman and Marc Frincu and Charalampos Chelmis and Muhammad Noor and Yogesh Simmhan and Viktor K. Prasanna},
title = {Prediction Models for Dynamic Demand Response: Requirements, Challenges, and Insights},
booktitle = {IEEE International Conference on Smart Grid Communications (SmartGridComm)},
year = {2015},
pages = {1--6},
doi = {10.1109/SmartGridComm.2015.7436323},
keywords = {iisc, peer reviewed, smart grid, iot},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://ieeexplore.ieee.org/document/7436323/},
}

@InProceedings{simmhan:wbdb:2015,
author = {Yogesh Simmhan and Anshu Shukla and Arun Verma},
title = {Benchmarking Fast Data Platforms for the Aadhaar Biometric Database},
booktitle = {Workshop on Big Data Benchmarking (WBDB)},
year = {2015},
volume = {10044},
series = {LNCS},
pages = {21--39},
doi = {10.1007/978-3-319-49748-8_2},
keywords = {iisc, stream processing, uidai, benchmark, peer reviewed},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://arxiv.org/abs/1510.04160},
}

@InProceedings{kumbhare:icdcs:2015,
author = {Alok Kumbhare and Marc Frincu and Yogesh Simmhan and Viktor K. Prasanna},
title = {Fault-Tolerant and Elastic Streaming MapReduce with Decentralized Coordination},
booktitle = {IEEE International Conference on Distributed Computing Systems (ICDCS)},
year = {2015},
pages = {328--338},
note = {[Core A]},
doi = {10.1109/ICDCS.2015.41},
keywords = {iisc, peer reviewed, mapreduce, stream processing},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://ieeexplore.ieee.org/document/7164919/},
}

@InProceedings{chu:ipdps:2014,
author = {Hsuan-Yi Chu and Yogesh Simmhan},
title = {Cost-efficient and Resilient Job Life-cycle Management on Hybrid Clouds},
booktitle = {IEEE International Parallel \& Distributed Processing Symposium (IPDPS)},
year = {2014},
pages = {327--336},
note = {[CORE A]},
doi = {10.1109/IPDPS.2014.43},
keywords = {usc, cloud, peer reviewed, iisc},
owner = {Simmhan},
timestamp = {2017.07.23},
url = {http://ieeexplore.ieee.org/document/6877267/},
}

@InProceedings{simmhan:europar:2014,
author = {Yogesh Simmhan and Alok Kumbhare and Charith Wickramaarachchi and Soonil Nagarkar and Santosh Ravi and Cauligi Raghavendra and Viktor Prasanna},
booktitle = {International European Conference on Parallel Processing (Euro-Par)},
title = {GoFFish: A Sub-Graph Centric Framework for Large-Scale Graph Analytics},
year = {2014},
note = {[CORE A]},
pages = {451--462},
series = {LNCS},
volume = {8632},
doi = {10.1007/978-3-319-09873-9_38},
keywords = {graphs, goffish, cluster, usc, peer reviewed, iisc},
owner = {simmhan},
timestamp = {2017.07.23},
}

@InProceedings{kumbhare:ccgrid:2014,
author = {Alok Kumbhare and Yogesh Simmhan and Viktor K. Prasanna},
title = {PLAStiCC: Predictive Look-Ahead Scheduling for Continuous dataflows on Clouds},
booktitle = {IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)},
year = {2014},
pages = {344--353},
note = {[CORE A]},
doi = {10.1109/CCGrid.2014.60},
keywords = {continuous dataflow, workflow, floe, cloud, iisc, usc, peer reviewed, iisc},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://ieeexplore.ieee.org/document/6846470/},
}

@InProceedings{kushwaha:ccem:2014,
author = {Vedsar Kushwaha and Yogesh Simmhan},
title = {An Analysis of Spot-Priced Clouds for Practical Job Scheduling},
booktitle = {IEEE Cloud Computing for Emerging Markets (CCEM)},
year = {2014},
pages = {1--8},
doi = {10.1109/CCEM.2014.7015488},
keywords = {iisc, cloud, spot, peer reviewed},
owner = {simmhan},
timestamp = {2018.04.11},
}

@InProceedings{govindarajan:comad:2014,
author = {Nithyashri Govindarajan and Yogesh Simmhan and Nitin Jamadagni and Prasant Misra},
title = {Event Processing across Edge and the Cloud for Internet of Things Applications},
booktitle = {International Conference on Management of Data (COMAD)},
year = {2014},
pages = {101--104},
note = {Short paper, [CORE B]},
keywords = {iisc, event processing, cep, iot, peer reviewed, poster},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://dl.acm.org/citation.cfm?id=2726970.2726985},
}

@InProceedings{badam:comad:2014,
author = {Nitin Chandra Badam and Yogesh Simmhan},
title = {Subgraph Rank: PageRank for SubgraphCentric Distributed Graph Processing},
booktitle = {International Conference on Management of Data (COMAD)},
year = {2014},
pages = {38--49},
note = {[CORE B]},
keywords = {iisc, graph, goffish, algorithm, peer reviewed},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://dl.acm.org/citation.cfm?id=2726970.2726979},
}

@InProceedings{kumbhare:sc:2013,
author = {Alok Kumbhare and Yogesh Simmhan and Viktor Prasanna},
title = {Exploiting Application Dynamism and Cloud Elasticity for Continuous Dataflows},
booktitle = {IEEE/ACM International Conference for High Performance Computing Networking, Storage, and Analysis (SC)},
year = {2013},
pages = {1--12},
note = {[CORE A]},
doi = {10.1145/2503210.2503240},
keywords = {usc, cloud, workflow, continuous dataflow, peer reviewed},
owner = {Simmhan},
timestamp = {2013.04.18},
}

@InProceedings{redekopp:ipdps:2013,
author = {Mark Redekopp and Yogesh Simmhan and Viktor K. Prasanna},
title = {Optimizations and Analysis of BSP Graph Processing Models on Public Clouds},
booktitle = {IEEE International Parallel \& Distributed Processing Symposium (IPDPS)},
year = {2013},
pages = {203--214},
note = {[CORE A]},
doi = {10.1109/IPDPS.2013.76},
keywords = {usc, cloud, graphs, azure, peer reviewed},
owner = {Simmhan},
timestamp = {2012.07.20},
url = {https://ieeexplore.ieee.org/document/6569812/},
}

@InProceedings{Wickramaarachchi:escience:2013,
author = {Charith Wickramaarachchi and Yogesh Simmhan},
title = {Continuous Dataflow Update Strategies for Mission-Critical Applications},
booktitle = {IEEE Internatrional Conference on eScience (eScience)},
year = {2013},
pages = {155--163},
note = {[CORE A]},
doi = {10.1109/eScience.2013.35},
keywords = {usc, cloud, workflow, continuous dataflow, peer reviewed},
owner = {simmhan},
timestamp = {2016.07.20},
url = {http://ceng.usc.edu/~simmhan/pubs/wickramaarachchi-escience-2013.pdf},
}

@InProceedings{zhou:bigdata:2013,
author = {Qunzhi Zhou and Yogesh Simmhan and Viktor Prasanna},
title = {Towards Hybrid Online On-Demand Querying of Realtime Data with Stateful Complex Event Processing},
booktitle = {IEEE International Conference on Big Data (BigData)},
year = {2013},
pages = {199--205},
doi = {10.1109/BigData.2013.6691575},
keywords = {smart grid, cep, usc, peer reviewed, short},
owner = {simmhan},
timestamp = {2013.09.21},
}

@InProceedings{simmhan:smartcities:2013,
author = {Yogesh Simmhan and Muhammad Usman Noor},
booktitle = {Workshop on Big Data and Smarter Cities, Co-located with IEEE International Conference on Big Data},
title = {Scalable Prediction of Energy Consumption using Incremental Time Series Clustering},
year = {2013},
pages = {29--36},
doi = {10.1109/BigData.2013.6691774},
keywords = {smart grid, analytics, usc, peer reviewed},
owner = {simmhan},
timestamp = {2013.09.21},
}

@InProceedings{Kumbhare:cloud:2012,
author = {Alok Kumbhare and Yogesh Simmhan and Viktor Prasanna},
title = {Cryptonite: A Secure and Performant Data Repository on Public Clouds},
booktitle = {IEEE International Cloud Computing Conference (CLOUD)},
year = {2012},
pages = {510--517},
note = {[CORE B]},
doi = {10.1109/CLOUD.2012.109},
keywords = {usc, smart grid, security, data privacy, cloud, azure, peer reviewed},
owner = {Simmhan},
timestamp = {2012.03.18},
url = {https://ieeexplore.ieee.org/document/6253545/},
}

@InProceedings{Simmhan:scale:2012,
author = {Yogesh Simmhan and Vaibhav Agarwal and Saima Aman and Alok Kumbhare and Sreedhar Natarajan and Nikhil Rajguru and Ian Robinson and Samuel Stevens and Wei Yin and Qunzhi Zhou and Viktor Prasanna},
title = {Adaptive Energy Forecasting and Information Diffusion for Smart Power Grids},
booktitle = {IEEE International Scalable Computing Challenge (SCALE)},
year = {2012},
pages = {1--4},
note = {SCALE Challenge Winner},
keywords = {hadoop, openplanet, floe, workflow, information integration, smart grid, peer reviewed, USC, short},
owner = {Simmhan},
timestamp = {2012.03.18},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-scale-2012.pdf},
}

@InProceedings{Yin:mapreduce:2012,
author = {Wei Yin and Yogesh Simmhan and Viktor Prasanna},
title = {Scalable Regression Tree Learning on Hadoop using OpenPlanet},
booktitle = {ACM International Workshop on MapReduce and its Applications (MAPREDUCE)},
year = {2012},
pages = {57--64},
abstract = {As scientific and engineering domains attempt to effectively analyze the deluge of data arriving from sensors and instruments, machine learning is becoming a key data mining tool to build prediction models. Regression tree is a popular learning model that combines decision trees and linear regression to forecast numerical target variables based on a set of input features. Map Reduce is well suited for addressing such data intensive learning applications, and a proprietary regression tree algorithm, PLANET, using MapReduce has been proposed earlier. In this paper, we describe an open source implement of this algorithm, OpenPlanet, on the Hadoop framework using a hybrid approach. Further, we evaluate the performance of OpenPlanet using realworld datasets from the Smart Power Grid domain to perform energy use forecasting, and propose tuning strategies of Hadoop parameters to improve the performance of the default configuration by 75% for a training dataset of 17 million tuples on a 64-core Hadoop cluster on FutureGrid.},
doi = {10.1145/2287016.2287027},
keywords = {cloud, machine learning, map reduce, hadoop, smart grid, peer reviewed, usc},
owner = {Simmhan},
timestamp = {2012.03.18},
url = {http://ceng.usc.edu/~simmhan/pubs/yin-mapreduce-2012.pdf},
}

@InProceedings{Zhao:ipaw:2012,
author = {Jing Zhao and Yogesh Simmhan and Viktor Prasanna},
title = {Presenting Apropos Provenance for Situation Awareness and Forensics},
booktitle = {International Proveanance and Annotation Workshop},
year = {2012},
volume = {7525},
series = {LNCS},
pages = {250--253},
publisher = {Springer},
note = {Poster},
doi = {10.1007/978-3-642-34222-6_30},
keywords = {provenance, smart grid, usc, peer reviewed, short},
owner = {Simmhan},
timestamp = {2012.03.24},
url = {http://dx.doi.org/10.1007/978-3-642-34222-6_30},
}

@InProceedings{Zhou:iswc:2012,
author = {Qunzhi Zhao and Yogesh Simmhan and Viktor K. Prasanna},
title = {Incorporating Semantic Knowledge into Stream Processing for Smart Grid Applications},
booktitle = {International Semantic Web Conference (ISWC)},
year = {2012},
volume = {7650},
series = {LNCS},
pages = {257--273},
note = {[CORE A]},
doi = {10.1007/978-3-642-35173-0_17},
keywords = {peer reviewed, smart grid, cep, usc},
owner = {Simmhan},
timestamp = {2012.06.08},
url = {http://iswc2012.semanticweb.org/sites/default/files/76500254.pdf},
}

@InProceedings{Zhou:itng:2012,
author = {Qunzhi Zhou and Sreedhar Natarajan and Yogesh Simmhan and Viktor Prasanna},
title = {Semantic Information Modeling for Emerging Applications in Smart Grid},
booktitle = {IEEE International Conference on Information Technology : New Generations (ITNG)},
year = {2012},
pages = {775--782},
abstract = {Abstract—Smart Grid modernizes power grid by integrating digital and information technologies. Millions of smart meters, intelligent appliances and communication infrastructures are under deployment allowing advanced IT applications to be developed to protect and optimize power grid operations. Demand response (DR) is one such emerging application to optimize electricity demand by curtailing/shifting power load when peak load occurs. Existing DR approaches are mostly based on static plans such as pricing policies and load shedding schedules. However, improvements to power management applications rely on data emanated from existing and new information sources with the grow of Smart Grid information space. In particular, dynamic DR algorithms may depend on information from smart meters that report interval-based power consumption measurement, HVAC systems that monitor buildings heat and humidity, and even weather forecast services. In order for emerging Smart Grid applications to take advantage of the diverse data influx, extensible information integration is required. In this paper, we develop an integrated Smart Grid information model using Semantic Web techniques and present case studies of using semantic information for dynamic DR. We show the semantic model facilitates information integration and knowledge representation for developing the next generation Smart Grid applications.},
doi = {10.1109/ITNG.2012.150},
keywords = {usc, smart grid, semantic, information integration, peer reviewed},
owner = {Simmhan},
timestamp = {2011.12.29},
url = {http://dx.doi.org/10.1109/ITNG.2012.150},
}

@InProceedings{Aman:dddm:2011,
author = {Saima Aman and Yogesh Simmhan and Viktor K. Prasanna},
title = {Improving Energy Use Forecast for Campus Micro-grids using Indirect Indicators},
booktitle = {International Workshop on Domain Driven Data Mining (DDDM)},
year = {2011},
pages = {389--397},
doi = {10.1109/ICDMW.2011.95},
keywords = {usc, smart grid, machine learning, peer reviewed},
owner = {Simmhan},
timestamp = {2011.07.31},
url = {http://ceng.usc.edu/~simmhan/pubs/aman-dddm-2011.pdf},
}

@InProceedings{Kumbhare:datacloud:2011,
author = {Alok Kumbhare and Yogesh Simmhan and Viktor Prasanna},
title = {Designing a Secure Storage Repository for Sharing Scientific Datasets using Public Clouds},
booktitle = {ACM International Workshop on Data Intensive Computing in the Clouds (DataCloud-SC11)},
year = {2011},
pages = {31--40},
doi = {10.1145/2087522.2087530},
keywords = {peer reviewed, cloud, Azure, security, smart grid, USC},
owner = {Simmhan},
timestamp = {2011.10.17},
url = {http://ceng.usc.edu/~simmhan/pubs/kumbhare-datacloud-2011.pdf},
}

@InProceedings{Redekopp:pargraph:2011,
author = {Mark Redekopp and Yogesh Simmhan and Viktor K. Prasanna},
title = {Performance Analysis of Vertex-centric Graph Algorithms on the Azure Cloud Platform},
booktitle = {IEEE Workshop on Parallel Algorithms and Software for Analysis of Massive Graphs (ParGraph)},
year = {2011},
pages = {1--8},
abstract = {Finding key vertices in large graphs is an important problem in many applications such as social networks, bioinformatics, and distribution networks. Betweenness centrality is a popular algorithm for finding such vertices and has been studied extensively, yielding several parallel formulations suitable to supercomputers and clusters. In this paper we implement and study betweenness centrality in the context of cloud-based platforms using Microsoft Windows Azure as our case study. We demonstrate scalable parallel performance and investigate key issues related to a cloud-based implementation including mitigating penalties associated with VM failures as well as the impact of communication overheads in the cloud. We use a combination of empirical and analytical evaluation using both synthetic small-world and real-world social interaction graphs.},
keywords = {graphs, Azure, Cloud, peer reviewed, USC},
owner = {Simmhan},
timestamp = {2011.10.19},
url = {http://halcyon.usc.edu/~pk/prasannawebsite/papers/2011/redekopp-pargraph-2011.pdf},
}

@InProceedings{Simmhan:sciencecloud:2011,
author = {Yogesh Simmhan and Baohua Cao and Michail Giakkoupis and Viktor K. Prasanna},
title = {Adaptive rate stream processing for smart grid applications on clouds},
booktitle = {ACM International Workshop on Scientific Cloud Computing (ScienceCloud)},
year = {2011},
pages = {33--38},
month = {June},
abstract = {Pervasive smart meters that continuously measure power usage by consumers within a smart (power) grid are providing utilities and power systems researchers with unprecedented volumes of information through streams that need to be processed and analyzed in near realtime. We introduce the use of Cloud platforms to perform scalable, latency sensitive stream processing for eEngineering applications in the smart grid domain. One unique aspect of our work is the use of adaptive rate control to throttle the rate of generation of power events by smart meters, which meets accuracy requirements of smart grid applications while consuming 50% lesser bandwidth resources in the Cloud.},
doi = {10.1145/1996109.1996116},
isbn = {978-1-4503-0699-7},
keywords = {usc, smart grid, cloud, streaming, peer reviewed, short paper},
location = {San Jose, California, USA},
owner = {Simmhan},
timestamp = {2013.01.30},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-sciencecloud-2011.pdf},
}

@InProceedings{Simmhan:hpcdb:2011,
author = {Yogesh Simmhan and Catharine van Ingen and Jim Heasley and Alex Szalay},
title = {Stargazing through a Digital Veil: Managing a Large Scale Sky Survey using Distributed Databases on HPC Clusters},
booktitle = {Workshop on High-Performance Computing meets Databases (HPCDB)},
year = {2011},
pages = {33--36},
doi = {10.1145/2125636.2125648},
keywords = {usc, msr, escience, data management, hpc, graywulf, panstarrs, databases, peer reviewed},
owner = {Simmhan},
timestamp = {2011.09.22},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-hpcdb-2011.pdf},
}

@InProceedings{Simmhan:cloud:2011,
author = {Yogesh Simmhan and Alok Kumbhare and Baohua Cao and Viktor K. Prasanna},
title = {An Analysis of Security and Privacy Issues in Smart Grid Software Architectures on Clouds},
booktitle = {IEEE International Cloud Computing Conference (CLOUD)},
year = {2011},
pages = {582--589},
month = {July},
publisher = {IEEE},
note = {[CORE B]},
abstract = {Power utilities globally are increasingly upgrading to Smart Grids that use bi-directional communication with the consumer to enable an information-driven approach to distributed energy management. Clouds offer features well suited for Smart Grid software platforms and applications, such as elastic resources and shared services. However, the security and privacy concerns inherent in an informationrich Smart Grid environment are further exacerbated by their deployment on Clouds. Here, we present an analysis of security and privacy issues in a Smart Grids software architecture operating on different Cloud environments, in the form of a taxonomy. We use the Los Angeles Smart Grid Project that is underway in the largest U.S. municipal utility to drive this analysis that will benefit both Cloud practitioners targeting Smart Grid applications, and Cloud researchers investigating security and privacy.},
doi = {10.1109/CLOUD.2011.107},
keywords = {usc, cloud, security, privacy, smart grid, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-cloud-2011.pdf},
}

@InProceedings{Simmhan:buildsys:2011,
author = {Yogesh Simmhan and Viktor Prasanna and Saima Aman and Sreedhar Natarajan and Wei Yin and Qunzhi Zhou},
title = {Towards Data-driven Demand-Response Optimization in a Campus Microgrid},
booktitle = {Workshop On Embedded Sensing Systems For Energy-Efficiency In Buildings (BuildSys)},
year = {2011},
pages = {41--42},
publisher = {ACM},
note = {Demo},
abstract = {We describe and demonstrate a prototype software architecture to support data-driven demand response optimization (DR) in the USC campus microgrid, as part of the Los Angeles Smart Grid Demonstration Project. The architecture includes a semantic information repository that integrates diverse data sources to support DR, demand forecasting using scalable machine-learned models, and detection of load curtailment opportunities by matching complex event patterns.},
doi = {10.1145/2434020.2434032},
keywords = {usc, smart grid. information integration, cep, machine learning, peer reviewed, demo},
owner = {Simmhan},
timestamp = {2011.09.26},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-buildsys-2011.pdf},
}

@InProceedings{Zhou:debs:2011,
author = {Qunzhi Zhou and Yogesh Simmhan and Viktor K. Prasanna},
title = {Towards an inexact semantic complex event processing framework},
booktitle = {International Conference on Distributed Event-Based System (DEBS)},
year = {2011},
pages = {401--402},
month = {July},
publisher = {ACM},
note = {Poster},
abstract = {Complex event processing (CEP) deals with detecting real-time situations, represented as event patterns, from among an event cloud. The state-of-the-art CEP systems process events as plain data tuples and are limited to detect precisely defined patterns. Emerging application areas like optimization in smart power grids require CEP to incorporate semantic knowledge of the domain for easier pattern specification, and detect inexact patterns in the presence of uncertainties. In this paper, we present motivating use cases, discuss limitations of existing CEP systems and describe our work towards an Inexact Semantic Complex Event Processing (InSCEP) framework.},
doi = {10.1145/2002259.2002331},
keywords = {usc, smart grid. cep, semantic, peer reviewed, poster},
owner = {Simmhan},
timestamp = {2013.01.30},
url = {http://ceng.usc.edu/~simmhan/pubs/zhou-debs-2011.pdf},
}

@InProceedings{Zinn:ccgrid:2011,
author = {Daniel Zinn and Quinn Hart and Timothy M. McPhillips and Bertram Lud{\"a}scher and Yogesh Simmhan and Michail Giakkoupis and Viktor K. Prasanna},
title = {Towards Reliable, Performant Workflows for Streaming-Applications on Cloud Platforms},
booktitle = {IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)},
year = {2011},
pages = {235--244},
month = {May},
publisher = {IEEE},
note = {[CORE A]},
abstract = {Scientific workflows are commonplace in eScience applications. Yet, the lack of integrated support for data models, including streaming data, structured collections and files, is limiting the ability of workflows to support emerging applications in energy informatics that are stream oriented. This is compounded by the absence of Cloud data services that support reliable and performant streams. In this paper, we propose and present a scientific workflow framework that supports streams as first-class data, and is optimized for performant and reliable execution across desktop and Cloud platforms. The workflow framework features and its empirical evaluation on a private Eucalyptus Cloud are presented.},
doi = {10.1109/CCGrid.2011.74},
keywords = {usc, smart grid, cloud, streaming, peer reviewed, escience},
owner = {Simmhan},
timestamp = {2013.01.30},
url = {http://ceng.usc.edu/~simmhan/pubs/zinn-ccgrid-2011.pdf},
}

@InProceedings{Simmhan:cloudcom:2010,
author = {Yogesh Simmhan and Michail Giakkoupis and Baohua Cao and Viktor K. Prasanna},
title = {On Using Cloud Platforms in a Software Architecture for Smart Energy Grids},
booktitle = {International Conference on Cloud Computing Technology and Science (CloudCom)},
year = {2010},
pages = {1--3},
month = {December},
publisher = {IEEE},
note = {Poster [CORE C]},
abstract = {Increasing concern about energy consumption is leading to infrastructure that continuously monitors consumer energy usage and allow power utilities to provide dynamic feedback to curtail peak power load. Smart Grid infrastructure being deployed globally needs scalable software platforms to rapidly integrate and analyze information streaming from millions of smart meters, forecast power usage and respond to operational events. Cloud platforms are well suited to support such data and compute intensive, always-on applications. We examine opportunities and challenges of using cloud platforms for such applications in the emerging domain of energy informatics.},
keywords = {usc, energy informatics, smart grid, cloud, poster, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
url = {http://salsahpc.indiana.edu/CloudCom2010/EPoster/cloudcom2010_submission_269.pdf},
}

@InProceedings{Simmhan:ipaw:2010,
author = {Yogesh Simmhan and Karthik Gomadam},
title = {Social Web-Scale Provenance in the Cloud},
booktitle = {International Provenance and Annotation Workshop (IPAW)},
year = {2010},
editor = {Deborah McGuinness and James Michaelis and Luc Moreau},
volume = {6378},
series = {Lecture Notes in Computer Science (LNCS)},
pages = {298--300},
publisher = {Springer Berlin / Heidelberg},
abstract = {The lower barrier to entry for users to create and share resources through applications like Facebook and Twitter, and the commoditization of social Web data has heightened issues of privacy, attribution, and copyright. These make it important to track the provenance of social Web data. We outline and discuss key engineering, privacy, and monetization challenges in collecting and analyzing provenance of social Web resources.},
doi = {10.1007/978-3-642-17819-1_39},
keywords = {msr, provenance, social network, cloud, poster, peer reviewed, short paper},
owner = {Simmhan},
timestamp = {2011.01.07},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-ipaw-2010.pdf},
}

@InProceedings{Simmhan:cloud:2010,
author = {Yogesh Simmhan and Catharine van Ingen and Girish Subramanian and Jie Li},
title = {Bridging the Gap between Desktop and the Cloud for eScience Applications},
booktitle = {IEEE International Cloud Computing Conference (CLOUD)},
year = {2010},
pages = {474--481},
month = {July},
publisher = {IEEE},
note = {[CORE B]},
abstract = {The widely discussed scientific data deluge creates a need to computationally scale out eScience applications beyond the local desktop and cope with variable loads over time. Cloud computing offers a scalable, economic, on-demand model well matched to these needs. Yet cloud computing creates gaps that must be crossed to move existing science applications to the cloud. In this article, we propose a Generic Worker framework to deploy and invoke science applications in the cloud with minimal user effort and predictable cost-effective performance. Our framework addresses three distinct challenges posed by the cloud: the complexity of application deployment, invocation of cloud applications from desktop clients, and efficient transparent data transfers across desktop and the cloud. We present an implementation of the Generic Worker for the Microsoft Azure Cloud and evaluate its use for a genomics application. Our evaluation shows that the user complexity to port and scale the application is substantially reduced while introducing a negligible performance overhead of of <; 5% for the genomics application when scaling to 20 VM instances.},
doi = {10.1109/CLOUD.2010.72},
keywords = {msr, cloud, workflow, escience, generic worker, genomics, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-cloud-2010.pdf},
}

@InProceedings{Simmhan:sciencecloud:2010,
author = {Yogesh Simmhan and Lavanya Ramakrishnan},
title = {Comparison of resource platform selection approaches for scientific workflows},
booktitle = {International Workshop on Scientific Cloud Computing (ScienceCloud)},
year = {2010},
series = {High Performance Distributed Computing (HPDC)},
pages = {445--450},
month = {June},
publisher = {ACM},
abstract = {Cloud computing is increasingly considered as an additional computational resource platform for scientific workflows. The cloud offers opportunity to scale-out applications from desktops and local cluster resources. Each platform has different properties (e.g., queue wait times in high performance systems, virtual machine startup overhead in clouds) and characteristics (e.g., custom environments in cloud) that makes choosing from these diverse resource platforms for a workflow execution a challenge for scientists. Scientists are often faced with deciding resource platform selection trade-offs with limited information on the actual workflows. While many workflow planning methods have explored resource selection or task scheduling, these methods often require fine-scale characterization of the workflow that is onerous for a scientist. In this paper, we describe our early exploratory work in using blackbox characteristics for a cost-benefit analysis of using different resource platforms. In our blackbox method, we use only limited high-level information on the workflow length, width, and data sizes. The length and width are indicative of the workflow duration and parallelism. We compare the effectiveness of this approach to other resource selection models using two exemplar scientific workflows on desktop, local cluster, HPC center, and cloud platforms. Early results suggest that the blackbox model often makes the same resource selections as a more fine-grained whitebox model. We believe the simplicity of the blackbox model can help inform a scientist on the applicability of a new resource platform, such as cloud resources, even before porting an existing workflow.},
acmid = {1851541},
doi = {10.1145/1851476.1851541},
isbn = {978-1-60558-942-8},
keywords = {msr, cloud, eScience, hpc, resource management, workflows, azure, scheduling, peer reviewed, short paper},
location = {Chicago, Illinois},
numpages = {6},
owner = {Simmhan},
timestamp = {2013.01.30},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-sciencecloud-2010.pdf},
}

@InProceedings{Simmhan:works:2010,
author = {Yogesh Simmhan and Emad Soroush and Catharine van Ingen and Deb Agarwal and Lavanya Ramakrishnan},
title = {BReW: Blackbox resource selection for e-Science workflows},
booktitle = {IEEE Workshop on Workflows in Support of Large-Scale Science (WORKS)},
year = {2010},
pages = {1--10},
month = {November},
abstract = {Workflows are commonly used to model data intensive scientific analysis. As computational resource needs increase for eScience, emerging platforms like clouds present additional resource choices for scientists and policy makers. We introduce BReW, a tool enables users to make rapid, highlevel platform selection for their workflows using limited workflow knowledge. This helps make informed decisions on whether to port a workflow to a new platform. Our analysis of synthetic and real eScience workflows shows that using just total runtime length, maximum task fanout, and total data used and produced by the workflow, BReW can provide platform predictions comparable to whitebox models with detailed workflow knowledge.},
doi = {10.1109/WORKS.2010.5671857},
keywords = {msr, escience, workflow, cloud, scheduling, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-works-2010.pdf},
}

@InProceedings{Zinn:works:2010,
author = {Daniel Zinn and Quinn Hart and Bertram Ludascher and Yogesh Simmhan},
title = {Streaming satellite data to cloud workflows for on-demand computing of environmental data products},
booktitle = {Workshop on Workflows in Support of Large-Scale Science (WORKS)},
year = {2010},
pages = {1--8},
month = {November},
publisher = {IEEE},
abstract = {Environmental data arriving constantly from satellites and weather stations are used to compute weather coefficients that are essential for agriculture and viticulture. For example, the reference evapotranspiration (ET0) coefficient, overlaid on regional maps, is provided each day by the California Department of Water Resources to local farmers and turf managers to plan daily water use. Scaling out single-processor compute/data intensive applications operating on realtime data to support more users and higher-resolution data poses data engineering challenges. Cloud computing helps data providers expand resource capacity to meet growing needs besides supporting scientific needs like reprocessing historic data using new models. In this article, we examine migration of a legacy script used for daily ET0 computation by CIMIS to a workflow model that eases deployment to and scaling on the Windows Azure Cloud. Our architecture incorporates a direct streaming model into Cloud virtual machines (VMs) that improves the performance by 130% to 160% for our workflow over using Cloud storage for data staging, used commonly. The streaming workflows achieve runtimes comparable to desktop execution for single VMs and a linear speed-up when using multiple VMs, thus allowing computation of environmental coefficients at a much larger resolution than done presently.},
doi = {10.1109/WORKS.2010.5671841},
keywords = {usc, streaming, workflow, cloud, escience, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
url = {http://ceng.usc.edu/~simmhan/pubs/zinn-works-2010.pdf},
}

@InProceedings{Cao:swpm:2009,
author = {Bin Cao and Beth Plale and Girish Subramanian and Paolo Missier and Carole Goble and Yogesh Simmhan},
title = {Semantically Annotated Provenance in the Life Science Grid},
booktitle = {International Workshop on the role of Semantic Web in Provenance Management (SWPM)},
year = {2009},
editor = {Juliana Freire and Paolo Missier and Satya Sanket Sahoo},
volume = {526},
series = {CEUR Workshop Proceedings},
pages = {1--6},
month = {October},
publisher = {CEUR-WS.org},
abstract = {Selected semantic annotation on raw provenance data can help bridge the gap between low level provenance events (e.g., service invocations, data creation, message passing) and the high-level view that the user has of his/her investigation (e.g., data retrieval and analysis). In this initial investigation we added semantically annotated provenance to the Life Science Grid, a cyber-infrastructure framework supporting interactive data exploration and automated data analysis tools, through (i) automated data provenance collection and (ii) automated semantic enrichment of the collected provenance metadata. We use a paradigmatic life sciences use case of interactive data exploration to show that semantically annotated provenance can help users recognize the occurrence of specific patterns of investigation from an otherwise low-level sequence of elementary interaction events.},
keywords = {msr, provenance, karma, lsg, semantic web, life sciences, escience, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
url = {http://ceur-ws.org/Vol-526/paper_5.pdf},
}

@InProceedings{Cao:swf:2009,
author = {Bin Cao and Beth Plale and Girish Subramanian and Ed Robertson and Yogesh Simmhan},
title = {Provenance Information Model of Karma Version 3},
booktitle = {International Workshop on Scientific Workflows (SWF)},
year = {2009},
series = {Congress on Services},
pages = {348--351},
month = {July},
publisher = {IEEE},
abstract = {Provenance that captures e-Science activity has long term value only if the right amount and kind of information is collected. In this paper, we propose a two-layer model for representing provenance information capable of representing both execution information and higher level process details. The information model forms the basis for efficient relational database storage and query, and sets the stage for investigation of the necessary and sufficient information for long-term preservation.},
doi = {10.1109/SERVICES-I.2009.54},
keywords = {msr, karma, provenance, workflow, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
}

@InProceedings{Simmhan:advcomp:2009,
author = {Yogesh Simmhan and Roger Barga and Catharine van Ingen and Ed Lazowska and Alex Szalay},
title = {Building the Trident Scientific Workflow Workbench for Data Management in the Cloud},
booktitle = {Conference on Advanced Engineering Computing and Applications in Sciences (ADVCOMP)},
year = {2009},
pages = {41--50},
month = {October},
publisher = {IEEE},
abstract = {Scientific workflows have gained popularity for modeling and executing in silico experiments by scientists for problem-solving. These workflows primarily engage in computation and data transformation tasks to perform scientific analysis in the Science Cloud. Increasingly workflows are gaining use in managing the scientific data when they arrive from external sensors and are prepared for becoming science ready and available for use in the Cloud. While not directly part of the scientific analysis, these workflows operating behind the Cloud on behalf of the -data valetsￃﾂￂ﾿ play an important role in end-to-end management of scientific data products. They share several features with traditional scientific workflows: both are data intensive and use Cloud resources. However, they also differ in significant respects, for example, in the reliability required, scheduling constraints and the use of provenance collected. In this article, we investigate these two classes of workflows - Science Application workflows and Data Preparation workflows - and use these to drive common and distinct requirements from workflow systems for eScience in the Cloud. We use workflow examples from two collaborations, the NEPTUNE oceanography project and the Pan-STARRS astronomy project, to draw out our comparison. Our analysis of these workflows classes can guide the evolution of workflow systems to support emerging applications in the Cloud and the Trident Scientific Workbench is one such workflow system that has directly benefitted from this to meet the needs of these two eScience projects.},
doi = {10.1109/ADVCOMP.2009.14},
keywords = {msr, workflows, escience, data management, cloud, hpc, trident, panstarrs, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
}

@InProceedings{Simmhan:hicss:2009,
author = {Yogesh Simmhan and Roger Barga and Catharine van Ingen and Maria Nieto-Santisteban and Lazslo Dobos and Nolan Li and Michael Shipway and Alexander S. Szalay and Sue Werner and Jim Heasley},
title = {GrayWulf: Scalable Software Architecture for Data Intensive Computing},
booktitle = {Hawaii International Conference on System Sciences (HICSS)},
year = {2009},
pages = {1--10},
publisher = {IEEE},
note = {[CORE A]},
abstract = {Big data presents new challenges to both cluster infrastructure software and parallel application design. We present a set of software services and design principles for data intensive computing with petabyte data sets, named GrayWulf. These services are intended for deployment on a cluster of commodity servers similar to the well-known Beowulf clusters. We use the Pan-STARRS system currently under development as an example of the architecture and principles in action.},
doi = {10.1109/HICSS.2009.235},
keywords = {msr, workflows, escience, data management, cloud, hpc, trident, graywulf, panstarrs, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
}

@InProceedings{Simmhan:escience:2009,
author = {Yogesh Simmhan and Catharine van Ingen and Alex Szalay and Roger Barga and Jim Heasley},
title = {Building Reliable Data Pipelines for Managing Community Data Using Scientific Workflows},
booktitle = {IEEE International Conference on eScience (eScience)},
year = {2009},
pages = {321--328},
month = {December},
publisher = {IEEE},
note = {[CORE A]},
abstract = {The growing amount of scientific data from sensors and field observations is posing a challenge to ￃﾂￂ﾿data valetsￃﾂￂ﾿ responsible for managing them in data repositories. These repositories built on commodity clusters need to reliably ingest data continuously and ensure its availability to a wide user community. Workflows provide several benefits to modeling data-intensive science applications and many of these benefits can help manage the data ingest pipelines too. But using workflows is not panacea in itself and data valets need to consider several issues when designing workflows that behave reliably on fault prone hardware while retaining the consistency of the scientific data. In this paper, we propose workflow designs for reliable data ingest in a distributed environment and identify workflow framework features to support resilience. We illustrate these using the data pipeline for the Pan-STARRS repository, one of the largest digital surveys that accumulates 100TB of data annually to support 300 astronomers.},
doi = {10.1109/e-Science.2009.52},
keywords = {msr, workflows, data management, cloud, panstarrs, escience, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
}

@InProceedings{Barga:escience:2008,
author = {Roger Barga and Jared Jackson and Nelson Araujo and Dean Guo and Nitin Gautam and Yogesh Simmhan},
title = {The Trident Scientific Workflow Workbench},
booktitle = {IEEE International Conference on eScience (eScience)},
year = {2008},
pages = {317--318},
publisher = {IEEE},
note = {Demo [CORE A]},
abstract = {In our demonstration we present Trident, a scientific workflow workbench built on top of a commercial workflow system to leverage existing functionality to the extent possible. Trident is being developed in collaboration with the scientific computing community for use in a number of ongoing eScience projects that make use of scientific workflows, in particular the Pan-STARRS sky survey project and the Ocean Observatory Initiative. In our demonstration of Trident we will illustrate the ability to utilize both local and cloud resources for storage and execution, as well as services such as provenance, monitoring, logging and scheduling workflows over clusters. Our goal is to release Trident in early 2009 as an open source accelerator for others to use for eScience projects and to continue extending with support for new workflow features and services.},
doi = {10.1109/eScience.2008.126},
keywords = {msr, workflows, escience, trident, panstarrs, neptune, demo, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
}

@InProceedings{Barga:clade:2008,
author = {Roger S. Barga and Dan Fay and Dean Guo and Steven Newhouse and Yogesh Simmhan and Alex Szalay},
title = {Efficient scheduling of scientific workflows in a high performance computing cluster},
booktitle = {International Workshop on Challenges of Large Applications in Distributed Environments (CLADE)},
year = {2008},
pages = {63--68},
publisher = {ACM},
note = {[CORE C]},
abstract = {The scientific computing community, especially academia is clearly in need of technology to handle and organize the 1-100+ Terabyte datasets coming from computer simulations and scientific instrumentation. In this paper we briefly describe GrayWulf, an exemplar cluster for data intensive applications using SQL Server and HPC Clusters. One of the key software components of GrayWulf is Trident, a scientific workflow workbench that performs automatic scheduling of workflows across the cluster. We examine the challenges of scheduling workflows on GrayWulf, algorithms to improve performance, and present early results from applying Trident to schedule data loading workflows on GrayWulf for an actual e-Science project},
acmid = {1383545},
doi = {10.1145/1383529.1383545},
isbn = {978-1-60558-156-9},
keywords = {msr, data intensive, eScience, scheduling, workflow, hpc, peer reviewed},
location = {Boston, MA, USA},
numpages = {6},
owner = {Simmhan},
timestamp = {2013.01.30},
}

@InProceedings{Simmhan:escience:2008,
author = {Yogesh Simmhan and Roger Barga and Catharine van Ingen and Ed Lazowska and Alex Szalay},
title = {On Building Scientific Workflow Systems for Data Management in the Cloud},
booktitle = {IEEE International Conference on eScience (eScience)},
year = {2008},
pages = {434--435},
month = {December},
publisher = {IEEE},
note = {Poster [CORE A]},
abstract = {Scientific workflows have become an archetype to model in silico experiments in the Cloud by scientists. There is a class of workflows that are used to by "data valets" to prepare raw data from scientific instruments into a science-ready form for use by scientists. These share data-intensive traits with traditional scientific workflows, yet differ significantly, for example, in the required degree of reliability and the type of provenance collected. We compare and contrast science application and data valet workflows through exemplar eScience projects to drive shared and unique requirements for scientific workflows across diverse users in a Science Cloud.},
doi = {10.1109/eScience.2008.150},
keywords = {msr, workflows, escience, data management, cloud, hpc, trident, panstarrs, poster, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
}

@InProceedings{Ramakrishnan:iccs:2007,
author = {Ramakrishnan, Lavanya and Simmhan, Yogesh and Plale, Beth},
title = {Realization of Dynamically Adaptive Weather Analysis and Forecasting in LEAD: Four Years Down the Road},
booktitle = {International Conference on Computational Science (ICCS)},
year = {2007},
editor = {Yong Shi and Geert van Albada and Jack Dongarra and Peter Sloot},
volume = {4487},
series = {LNCS},
pages = {1122--1129},
publisher = {Springer Berlin / Heidelberg},
note = {[CORE A]},
abstract = {Linked Environments for Atmospheric Discovery (LEAD) is a large-scale cyberinfrastructure effort in support of mesoscale meteorology. One of the primary goals of the infrastructure is support for real-time dynamic, adaptive response to severe weather. In this paper we revisit the conception of dynamic adaptivity as appeared in our 2005 DDDAS workshop paper, and discuss changes since the original conceptualization, and lessons learned in working with a complex service oriented architecture in support of data driven science.},
doi = {10.1007/978-3-540-72584-8_147},
keywords = {iu, LEAD, escience, workflow, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
}

@InProceedings{Simmhan:gbpse:2006,
author = {Yogesh Simmhan and Sangmi Pallickara and Nithya Vijayakumar and Beth Plale},
title = {Data Management in Dynamic Environment-driven Computational Science},
booktitle = {Grid-Based Problem Solving Environments},
year = {2007},
editor = {Patrick Gaffney and James Pool},
volume = {239},
series = {IFIP Advances in Information and Communication Technology},
pages = {317--333},
publisher = {Springer Boston},
abstract = {Advances in numerical modeling, computational hardware and problem solving environments have driven the growth of computational science over the past decades. Science gateways, based on service oriented architectures and scientific workflows, provide yet another step in democratizing access to advanced numerical and scientific tools, computational resource and massive data storage, and fostering collaborations. Dynamic, data-driven applications, such as those found in weather forecasting, present interesting challenges to Science Gateways, which are being addressed as part of the LEAD Cyberinfrastructure project. In this article, we discuss three important data related problems faced by such adaptive data-driven environments: managing a user’s personal workspace and metadata on the Grid, tracking the provenance of scientific workflows and data products, and continuous data mining over observational weather data.},
doi = {10.1007/978-0-387-73659-4_17},
keywords = {iu, data management, LEAD, provenance, portal, mylead, karma, calder, escience, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
}

@InProceedings{Simmhan:ipaw:2006,
author = {Yogesh L. Simmhan and Beth Plale and Dennis Gannon},
title = {Performance Evaluation of the Karma Provenance Framework for Scientific Workflows},
booktitle = {International Provenance and Annotation Workshop (IPAW)},
year = {2006},
editor = {Luc Moreau and Ian Foster},
volume = {4145},
series = {Lecture Notes in Computer Science (LNCS)},
pages = {222--236},
publisher = {Springer Berlin / Heidelberg},
abstract = {Provenance about workflow executions and data derivations in scientific applications help estimate data quality, track resources, and validate in silico experiments. The Karma provenance framework provides a means to collect workflow, process, and data provenance from data-driven scientific workflows and is used in the Linked Environments for Atmospheric Discovery (LEAD) project. This paper presents a performance analysis of the Karma service as compared against the contemporary PReServ provenance service. Our study finds that Karma scales exceedingly well for collecting and querying provenance records, showing linear or sub-linear scaling with increasing number of provenance records and clients when tested against workloads in the order of 10,000 application-service invocations and over 36 concurrent clients.},
doi = {10.1007/11890850_23},
keywords = {iu, provenance, escience, karma, workflows, peer reviewed},
owner = {ysimmhan},
timestamp = {2006.06.30},
}

@InProceedings{Simmhan:icws:2006,
author = {Yogesh L. Simmhan and Beth Plale and Dennis Gannon},
title = {A Framework for Collecting Provenance in Data-Centric Scientific Workflows},
booktitle = {International Conference on Web Services (ICWS)},
year = {2006},
pages = {427--436},
address = {Chicago, IL, USA},
month = {September},
publisher = {IEEE},
note = {[CORE A]},
abstract = {The increasing ability for the earth sciences to sense the world around us is resulting in a growing need for data-driven applications that are under the control of data-centric workflows composed of grid- and web- services. The focus of our work is on provenance collection for these workflows, necessary to validate the workflow and to determine quality of generated data products. The challenge we address is to record uniform and usable provenance metadata that meets the domain needs while minimizing the modification burden on the service authors and the performance overhead on the workflow engine and the services. The framework, based on a loosely-coupled publish-subscribe architecture for propagating provenance activities, satisfies the needs of detailed provenance collection while a performance evaluation of a prototype finds a minimal performance overhead (in the range of 1\% for an eight service workflow using 271 data products).},
doi = {10.1109/ICWS.2006.5},
keywords = {iu, provenance, escience, karma, workflows, peer reviewed},
owner = {Simmhan},
timestamp = {2013.01.30},
}

@InProceedings{Simmhan:sciflow:2006,
title = {Towards a Quality Model for Effective Data Selection in Collaboratories},
author = {Yogesh L. Simmhan and Beth Plale and Dennis Gannon},
booktitle = {Workshop on Workflow and Data Flow for Scientific Applications (SciFlow)},
year = {2006},
month = {April},
pages = {1--4},
publisher = {IEEE},
series = {International Conference on Data Engineering Workshops},
abstract = {Data-driven scientific applications utilize workflow frameworks to execute complex dataflows, resulting in derived data products of unknown quality. We discuss our on-going research on a quality model that provides users with an integrated estimate of the data quality that is tuned to their application needs, and is available as a numerical quality score that enables uniform comparison of datasets, and increases community’s trust in derived data.},
doi = {10.1109/ICDEW.2006.150},
keywords = {iu, provenance, escience, karma, workflows, short paper, peer reviewed},
owner = {Simmhan},
timestamp = {2005.12.21}
}

@InProceedings{Gannon:icsoc:2005,
author = {Dennis Gannon and Beth Plale and Marcus Christie and Liang Fang and Yi Huang and Scott Jensen and Gopi Kandaswamy and Suresh Marru and Sangmi Lee Pallickara and Satoshi Shirasuna and Yogesh Simmhan and Aleksander Slominski and Yiming Sun},
title = {Service Oriented Architectures for Science Gateways on Grid Systems},
booktitle = {International Conference on Service-Oriented Computing (ICSOC)},
year = {2005},
editor = {Boualem Benatallah and Fabio Casati and Paolo Traverso},
volume = {3826},
series = {Lecture Notes in Computer Science (LNCS)},
pages = {21--32},
publisher = {Springer Berlin / Heidelberg},
note = {[CORE A]},
abstract = {Grid computing is about allocating distributed collections of resources including computers, storage systems, networks and instruments to form a coherent system devoted to a “virtual organization” of users who share a common interest in solving a complex problem or building an efficient agile enterprise. Service oriented architectures have emerged as the standard way to build Grids. This paper provides a brief look at the Open Grid Service Architecture, a standard being proposed by the Global Grid Forum, which provides the foundational concepts of most Grid systems. Above this Grid foundation is a layer of application-oriented services that are managed by workflow tools and “science gateway” portals that provide users transparent access to the applications that use the resources of a Grid. In this paper we will also describe these Gateway framework services and discuss how they relate to and use Grid services.},
doi = {10.1007/11596141_3},
keywords = {iu, portal, web service, grid, peer reviewed},
owner = {Simmhan},
timestamp = {2013.01.30},
}

@InProceedings{Gannon:clade:2004,
author = {Dennis Gannon and Sriram Krishnan and Liang Fang and Gopi Kandaswamy and Yogesh Simmhan and Aleksander Slominski},
title = {On Building Parallel and Grid Applications: Component Technology and Distributed Services},
booktitle = {International Workshop on Challenges of Large Applications in Distributed Environments (CLADE)},
year = {2004},
pages = {44--51},
organization = {IEEE},
note = {[CORE C]},
abstract = {Software Component Frameworks are well known in the commercial business application world and now this technology is being explored with great interest as a way to build large-scale scientific application on parallel computers. In the case of Grid systems, the current architectural model is based on the emerging web services framework. In this paper we describe progress that has been made on the Common Component Architecture model (CCA) and discuss its success and limitations when applied to problems in Grid computing. Our primary conclusion is that a component model fits very well with a services-oriented Grid, but the model of composition must allow for a very dynamic (both in space and it time) control of composition. We note that this adds a new dimension to conventional service workflow and it extends the “Inversion of Control” aspects of must component systems.},
doi = {10.1109/CLADE.2004.1309091},
keywords = {iu, grid, web service, escience, component, peer reviewed},
owner = {Simmhan},
timestamp = {2013.01.30},
}

@InProceedings{Gannon:dbgs:2003,
title = {Building Grid Services for User Portals},
author = {Dennis Gannon and Marcus Christie and Octav Chipara and Liang Fang and Matthew Farrellee and Gopi Kandaswamy and Wei Lu and Beth Plale and Aleksander Slominski and Anuraag Sarangi and Yogesh L. Simmhan},
booktitle = {Workshop on Designing and Building Grid Services (DBGS)},
year = {2003},
address = {Chicago, IL, USA},
publisher = {GGF},
keywords = {iu, portal, grid, web service, escience, peer reviewed},
owner = {Simmhan},
timestamp = {2013.01.30},
url = {http://www.mcs.anl.gov/~keahey/DBGS/DBGS_files/dbgs_papers/gannon.pdf}
}

@InBook{simhan:encycl:2019,
author = {Yogesh Simmhan},
chapter = {Big Data and Fog Computing},
editor = {Sherif Sakr and Albert Y. Zomaya},
publisher = {Springer},
title = {Encyclopedia of Big Data Technologies},
year = {2019},
doi = {10.1007/978-3-319-63962-8_41-1},
keywords = {iisc, big data, fog computing, iot, peer reviewed},
owner = {simmhan},
timestamp = {2018.04.11},
url = {http://arxiv.org/abs/1712.09552},
}

@InBook{simmhan:bidatabook:2016,
chapter = {Big Data Analytics Platforms for Real-Time Applications in IoT},
pages = {115--135},
title = {Big Data Analytics: Methods and Applications},
publisher = {Springer India},
year = {2016},
author = {Yogesh Simmhan and Srinath Perera},
editor = {Saumyadipta Pyne and B.L.S. Prakasa Rao and S.B. Rao},
doi = {10.1007/978-81-322-3628-3_7},
keywords = {iisc, big data, peer reviewed},
owner = {simmhan},
timestamp = {2018.04.11},
}

@InBook{Simmhan:greenit:2011,
title = {Green IT: Technologies and Applications},
author = {Yogesh Simmhan and Qunzhi Zhou and Viktor K. Prasanna},
chapter = {Semantic Information Integration for Smart Grid Applications},
editor = {Kim, Jae H. and Myung J. Lee},
pages = {361--380},
publisher = {Springer Berlin Heidelberg},
year = {2011},
abstract = {The Los Angeles Smart Grid Project aims to use informatics techniques to bring about a quantum leap in the way demand response load optimization is performed in utilities. Semantic information integration, from sources as diverse as Internet-connected smart meters and social networks, is a linchpin to support the advanced analytics and mining algorithms required for this. In association with it, semantic complex event processing system will allow consumer and utility managers to easily specify and enact energy policies continuously. We present the information systems architecture for the project that is under development, and discuss research issues that emerge from having to design a system that supports 1.4 million customers and a rich ecosystem of Smart Grid applications from users, third party vendors, the utility and regulators.},
doi = {10.1007/978-3-642-22179-8_19},
isbn = {978-3-642-22179-8},
keywords = {usc, smart grid, semantic, information integration, peer reviewed},
owner = {Simmhan},
timestamp = {2011.07.31},
url = {http://ceng.usc.edu/~simmhan/pubs/simmhan-greenit-2011.pdf}
}

@InBook{Gannon:hpcbook:2008,
title = {High Performance Computing and Grids in Action},
author = {Dennis Gannon and Beth Plale and Marcus Christie and Yi Huang and Scott Jensen and Ning Liu and Suresh Marru and Sangmi Pallickara and Srinath Perera and Satoshi Shirasuna and Yogesh Simmhan and Aleksander Slominski and Yiming Sun and Nithya Vijayakumar},
chapter = {Building Grid Portals for e-Science: A Service Oriented Architecture},
editor = {Lucio Grandinetti},
pages = {149--166},
publisher = {IOS Press},
year = {2008},
series = {Advances in Parallel Computing},
volume = {16},
abstract = {Grids are built by communities who need a shared cyberinfrastructure to make progress on the critical problems they are currently confronting. An e-science portal is a conventional Web portal that sits on top of a rich collection of web services that allow a community of users access to shared data and application resources without exposing them to the details of Grid computing. In this chapter we describe a service-oriented architecture to support this type of portal.},
isbn = {978-1-58603-839-7},
keywords = {iu,escience, portal, web service, LEAD, peer reviewed},
owner = {Simmhan},
timestamp = {2011.01.07},
url = {http://www.booksonline.iospress.nl/Content/View.aspx?piid=8567}
}

@InBook{Gannon:wfbook:2007,
title = {Workflows for eScience: Scientific Workflows for Grids},
author = {Dennis Gannon and Beth Plale and Suresh Marru and Gopi Kandaswamy and Yogesh Simmhan and Satoshi Shirasuna},
chapter = {Dynamic, Adaptive Workflows for Mesoscale Meteorology},
editor = {Dennis Gannon and Ewa Deelman and Matthew Shields and Ian Taylor},
pages = {126--142},
publisher = {Springer London},
year = {2007},
abstract = {The Linked Environments for Atmospheric Discovery (LEAD) [122] is a National Science Foundation funded1 project to change the paradigm for mesoscale weather prediction from one of static, fixed-schedule computational forecasts to one that is adaptive and driven by weather events. It is a collaboration of eight institutions,2 led by Kelvin Droegemeier of the University of Oklahoma, with the goal of enabling far more accurate and timely predictions of tornadoes and hurricanes than previously considered possible. The traditional approach to weather prediction is a four-phase activity. In the first phase, data from sensors are collected. The sensors include ground instruments such as humidity and temperature detectors, and lightning strike detectors and atmospheric measurements taken from balloons, commercial aircraft, radars, and satellites. The second phase is data assimilation, in which the gathered data are merged together into a set of consistent initial and boundary conditions for a large simulation. The third phase is the weather prediction, which applies numerical equations to measured conditions in order to project future weather conditions. The final phase is the generation of visual images of the processed data products that are analyzed to make predictions. Each phase of activity is performed by one or more application components.},
doi = {10.1007/978-1-84628-757-2_9},
isbn = {978-1-84628-757-2},
keywords = {iu, workflows, grid, escience, peer reviewed},
owner = {Simmhan},
timestamp = {2011.12.29}
}

@Proceedings{mueller:isorc:2020,
title = {Proceedings of the IEEE International Symposium on Object-Oriented Real-Time Distributed Computing (ISORC)},
year = {2020},
editor = {Frank Mueller and Tommaso Cucinotta and Yogesh Simmhan},
isbn = {978-1-7281-6958-3},
doi = {10.1109/ISORC49007.2020},
}

@Proceedings{simmhan:icfec:2020,
title = {Proceedings of the IEEE International Conference on Fog and Edge Computing (ICFEC)},
year = {2020},
editor = {Yogesh Simmhan and Blesson Varghese},
isbn = {978-1-7281-7305-4},
doi = {10.1109/ICFEC50348.2020},
}

@Proceedings{shen:icfec:2019,
title = {Proceedings of the {IEEE} International Conference on Fog and Edge Computing ({ICFEC})},
year = {2019},
editor = {Haiying Shen and Yogesh Simmhan},
isbn = {978-1-7281-2365-3},
url = {https://ieeexplore.ieee.org/xpl/conhome/8730889/proceeding},
}

@Article{simmhan:iotn:2017,
author = {Yogesh Simmhan},
title = {IoT Analytics Across Edge and Cloud Platforms},
journal = {IEEE Internet of Things Newsletter},
year = {2017},
month = may,
keywords = {iisc, edge computing, iot},
owner = {simmhan},
timestamp = {2017.09.22},
url = {http://iot.ieee.org/newsletter/may-2017/iot-analytics-across-edge-and-cloud-platforms},
}

@Article{simmhan:ccpe:2016,
author = {Yogesh Simmhan and Lavanya Ramakrishnan and Gabriel Antoniu and Carole Goble},
title = {Editorial: Cloud computing for data-driven science and engineering},
journal = {Concurrency and Computation: Practice and Experience},
year = {2016},
doi = {10.1002/cpe.3668},
keywords = {iisc, editorial},
owner = {simmhan},
timestamp = {2017.07.23},
url = {http://onlinelibrary.wiley.com/doi/10.1002/cpe.3668/full},
}

@Article{aluru:jpdc:2015,
author = {Srinivas Aluru and Yogesh Simmhan},
title = {Editorial: Scalable Systems for Big Data Management and Analytics},
journal = {Journal of Parallel and Distributed Systems (JPDC)},
year = {2015},
note = {To Appear},
keywords = {Editorial, iisc, big data},
owner = {simmhan},
timestamp = {2016.07.19},
}

@Article{mishra:iotn:2015,
author = {Prasant Misra and Yogesh Simmhan and Jay Warrior},
title = {Towards a Practical Architecture for Internet of Things: An India-centric View},
journal = {IEEE Internet of Things Newsletter},
year = {2015},
pages = {1-2},
keywords = {iot, iisc},
owner = {simmhan},
timestamp = {2018.04.11},
url = {http://iot.ieee.org/newsletter/january-2015/towards-a-practical-architecture-for-internet-of-things-an-india-centric-view.html},
}

@Proceedings{Simmhan:sciencecloud:2012,
title = {Proceedings of the 3rd International Workshop on Scientific Cloud Computing (ScienceCloud)},
year = {2012},
editor = {Yogesh Simmhan and Gabriel Antoniu and Carole Goble and Lavanya Ramakrishnan},
publisher = {ACM},
author = {Yogesh Simmhan and Gabriel Antoniu and Carole Goble and Lavanya Ramakrishnan},
keywords = {editorial, USC},
owner = {Simmhan},
timestamp = {2012.06.08}
}

@Proceedings{Raicu:ScienceCloud2011,
title = {Proceedings of the 2nd International Workshop on Scientific Cloud Computing (ScienceCloud)},
year = {2011},
address = {New York, NY, USA},
editor = {Ioan Raicu and Pete Beckman and Ian T. Foster and Yogesh Simmhan},
publisher = {ACM},
author = {Ioan Raicu and Pete Beckman and Ian T. Foster and Yogesh Simmhan},
isbn = {978-1-4503-0699-7},
keywords = {editorial, USC},
location = {San Jose, California, USA},
owner = {Simmhan},
timestamp = {2012.09.11},
url = {http://dx.doi.org/10.1145/1996109}
}

@Proceedings{Simmhan:HiPC:2011,
title = {HiPC 2011 Student Research Symposium: Message from the co-chairs},
year = {2011},
editor = {Yogesh Simmhan and Ashok Srinivasan},
author = {Yogesh Simmhan and Ashok Srinivasan},
booktitle = {High Performance Computing Conference (HiPC)},
keywords = {editorial, USC},
owner = {Simmhan},
timestamp = {2012.03.18}
}

@Article{Moreau:cpe:2008,
title = {Special Issue: The First Provenance Challenge},
author = {Luc Moreau and Bertram Ludäscher and Ilkay Altintas and Roger S. Barga and Shawn Bowers and Steven Callahan and George Chin, Jr. and Ben Clifford and Shirley Cohen and Sarah Cohen-Boulakia and Susan Davidson and Ewa Deelman and Luciano Digiampietri and Ian Foster and Juliana Freire and James Frew and Joe Futrelle and Tara Gibson and Yolanda Gil and Carole Goble and Jennifer Golbeck and Paul Groth and David A. Holland and Sheng Jiang and Jihie Kim and David Koop and Ales Krenek and Timothy McPhillips and Gaurang Mehta and Simon Miles and Dominic Metzger and Steve Munroe and Jim Myers and Beth Plale and Norbert Podhorszki and Varun Ratnakar and Emanuele Santos and Carlos Scheidegger and Karen Schuchardt and Margo Seltzer and Yogesh L. Simmhan and Claudio Silva and Peter Slaughter and Eric Stephan and Robert Stevens and Daniele Turi and Huy Vo and Mike Wilde and Jun Zhao and Yong Zhao},
journal = {Concurrency and Computation: Practice \& Experience, Special Issue on The First Provenance Challenge},
year = {2008},
month = {April},
note = {[CORE A]},
pages = {409-418},
volume = {20},
abstract = {The first Provenance Challenge was set up in order to provide a forum for the community to understand the capabilities of different provenance systems and the expressiveness of their provenance representations. To this end, a functional magnetic resonance imaging workflow was defined, which participants had to either simulate or run in order to produce some provenance representation, from which a set of identified queries had to be implemented and executed. Sixteen teams responded to the challenge, and submitted their inputs. In this paper, we present the challenge workflow and queries, and summarize the participants' contributions. Copyright © 2007 John Wiley & Sons, Ltd.},
acmid = {1350753},
address = {Chichester, UK},
doi = {10.1002/cpe.v20:5},
issn = {1532-0626},
issue = {5},
keywords = {iu, provenance, provenance challenge},
numpages = {10},
owner = {Simmhan},
publisher = {John Wiley and Sons Ltd.},
timestamp = {2012.09.11}
}

@InProceedings{alva:ccwi:2019,
author = {Prithvi Alva and Sheetal Kumar K.R. and Yogesh Simmhan and Mohan Kumar M.S.},
booktitle = {International Conference on Computing and Control for Water Industry (CCWI)},
title = {Enabling Equitable Water Supply in a Mega-city using a Big Data Analytics Platform},
year = {2019},
note = {Extended Abstract},
pages = {1--2},
}