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.
%0 Conference Paper
%1 Simmhan:escience:2008
%A Simmhan, Yogesh
%A Barga, Roger
%A van Ingen, Catharine
%A Lazowska, Ed
%A Szalay, Alex
%B International Conference on eScience (eScience)
%D 2008
%I IEEE
%K cloud, data escience, hpc, management, msr, panstarrs, peer poster, reviewed trident, workflows,
%P 434-435
%R 10.1109/eScience.2008.150
%T On Building Scientific Workflow Systems for Data Management in the
Cloud
%X 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.
@inproceedings{Simmhan:escience:2008,
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.},
added-at = {2014-08-13T04:08:36.000+0200},
author = {Simmhan, Yogesh and Barga, Roger and van Ingen, Catharine and Lazowska, Ed and Szalay, Alex},
biburl = {https://www.bibsonomy.org/bibtex/2813825119467c81fa8f272b0c68c07a0/simmhan},
booktitle = {International Conference on eScience (eScience)},
doi = {10.1109/eScience.2008.150},
interhash = {fffc5e57be542b85e8b062be2ff430e4},
intrahash = {813825119467c81fa8f272b0c68c07a0},
keywords = {cloud, data escience, hpc, management, msr, panstarrs, peer poster, reviewed trident, workflows,},
month = {December},
note = {Poster [CORE A]},
owner = {Simmhan},
pages = {434-435},
publisher = {IEEE},
timestamp = {2014-08-13T04:08:36.000+0200},
title = {On Building Scientific Workflow Systems for Data Management in the
Cloud},
year = 2008
}