A Framework for Collecting Provenance in Data-Centric Scientific Workflows Export

@inproceedings{citeulike:1378614, 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/or 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)}, address = {Washington, DC, USA}, author = {Simmhan, Y. L. and Plale, B. and Gannon, D.}, booktitle = {Web Services, 2006. ICWS '06. International Conference on}, citeulike-article-id = {1378614}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1173078}, citeulike-linkout-1 = {http://dx.doi.org/10.1109/ICWS.2006.5}, citeulike-linkout-2 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4032054}, doi = {10.1109/ICWS.2006.5}, isbn = {0769526691}, journal = {Web Services, 2006. ICWS '06. International Conference on}, keywords = {framework, karma, provenance, scientific, workflows}, pages = {427--436}, posted-at = {2007-06-11 13:55:26}, priority = {4}, publisher = {IEEE Computer Society}, title = {A Framework for Collecting Provenance in Data-Centric Scientific Workflows}, url = {http://dx.doi.org/10.1109/ICWS.2006.5}, year = {2006} }

TY - CONF ID - citeulike:1378614 L3 - citeulike-article-id:1378614 N2 - 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/or 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) JF - Web Services, 2006. ICWS '06. International Conference on SN - 0769526691 AD - Washington, DC, USA EP - 436 TI - A Framework for Collecting Provenance in Data-Centric Scientific Workflows PB - IEEE Computer Society T2 - Web Services, 2006. ICWS '06. International Conference on SP - 427 KW - framework KW - karma KW - provenance KW - scientific KW - workflows AU - Simmhan, YL AU - Plale, B AU - Gannon, D PY - 2006/// UR - http://dx.doi.org/10.1109/ICWS.2006.5 ER -