{"id":"https://openalex.org/W2152956081","doi":"https://doi.org/10.1145/1341811.1341822","title":"Workflow task clustering for best effort systems with Pegasus","display_name":"Workflow task clustering for best effort systems with Pegasus","publication_year":2008,"publication_date":"2008-01-29","ids":{"openalex":"https://openalex.org/W2152956081","doi":"https://doi.org/10.1145/1341811.1341822","mag":"2152956081"},"language":"en","primary_location":{"id":"doi:10.1145/1341811.1341822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1341811.1341822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM Mardi Gras conference: From lightweight mash-ups to lambda grids: Understanding the spectrum of distributed computing requirements, applications, tools, infrastructures, interoperability, and the incremental adoption of key capabilities","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100738660","display_name":"Gurmeet Singh","orcid":"https://orcid.org/0000-0003-0230-0990"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gurmeet Singh","raw_affiliation_strings":["USC Information Sciences Institute, Marina Del Rey, CA"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina Del Rey, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112510497","display_name":"Mei-Hui Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei-Hui Su","raw_affiliation_strings":["USC Information Sciences Institute, Marina Del Rey, CA"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina Del Rey, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055471608","display_name":"Karan Vahi","orcid":"https://orcid.org/0000-0001-8622-2082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karan Vahi","raw_affiliation_strings":["USC Information Sciences Institute, Marina Del Rey, CA"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina Del Rey, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031941569","display_name":"Ewa Deelman","orcid":"https://orcid.org/0000-0001-5106-503X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ewa Deelman","raw_affiliation_strings":["USC Information Sciences Institute, Marina Del Rey, CA"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina Del Rey, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031340202","display_name":"G. Bruce Berriman","orcid":"https://orcid.org/0000-0001-8388-534X"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bruce Berriman","raw_affiliation_strings":["California Institute of Technology, Pasadena, CA"],"affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, CA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050303012","display_name":"John Good","orcid":"https://orcid.org/0009-0003-3906-719X"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Good","raw_affiliation_strings":["California Institute of Technology, Pasadena, CA"],"affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, CA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061630529","display_name":"Daniel S. Katz","orcid":"https://orcid.org/0000-0001-5934-7525"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Katz","raw_affiliation_strings":["Louisiana State University, Baton Rouge, LA"],"affiliations":[{"raw_affiliation_string":"Louisiana State University, Baton Rouge, LA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034246908","display_name":"Gaurang Mehta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaurang Mehta","raw_affiliation_strings":["USC Information Sciences Institute, Marina Del Rey, CA"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina Del Rey, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100738660"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2422,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.9724852,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8812724351882935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8444851040840149},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.7866732478141785},{"id":"https://openalex.org/keywords/workflow-technology","display_name":"Workflow technology","score":0.7432388067245483},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.730249285697937},{"id":"https://openalex.org/keywords/workflow-engine","display_name":"Workflow engine","score":0.695855975151062},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6022722125053406},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5817874073982239},{"id":"https://openalex.org/keywords/message-queue","display_name":"Message queue","score":0.4930867850780487},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45056360960006714},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.4240080714225769},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.394784152507782},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3866320550441742},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1946844458580017},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1306186020374298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10562065243721008},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08544895052909851},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07089555263519287}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8812724351882935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8444851040840149},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.7866732478141785},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.7432388067245483},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.730249285697937},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.695855975151062},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6022722125053406},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5817874073982239},{"id":"https://openalex.org/C26324664","wikidata":"https://www.wikidata.org/wiki/Q1065525","display_name":"Message queue","level":2,"score":0.4930867850780487},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45056360960006714},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.4240080714225769},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.394784152507782},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3866320550441742},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1946844458580017},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1306186020374298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10562065243721008},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08544895052909851},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07089555263519287}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1341811.1341822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1341811.1341822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM Mardi Gras conference: From lightweight mash-ups to lambda grids: Understanding the spectrum of distributed computing requirements, applications, tools, infrastructures, interoperability, and the incremental adoption of key capabilities","raw_type":"proceedings-article"},{"id":"pmh:oai:authors.library.caltech.edu:72948","is_oa":false,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20161219-162847685","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.5652","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.5652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/~gurmeet/papers/MardiGras_v3.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G8192970235","display_name":null,"funder_award_id":"OCI-0722019","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W110825830","https://openalex.org/W170219002","https://openalex.org/W259012431","https://openalex.org/W1500581971","https://openalex.org/W1599248213","https://openalex.org/W1603527427","https://openalex.org/W1605746882","https://openalex.org/W1768975796","https://openalex.org/W2000300079","https://openalex.org/W2006382393","https://openalex.org/W2040466547","https://openalex.org/W2046255109","https://openalex.org/W2048779915","https://openalex.org/W2058791854","https://openalex.org/W2104449761","https://openalex.org/W2108599535","https://openalex.org/W2120764569","https://openalex.org/W2124043382","https://openalex.org/W2129666400","https://openalex.org/W2138985109","https://openalex.org/W2140332639","https://openalex.org/W2148317584","https://openalex.org/W2149294210","https://openalex.org/W2152526229","https://openalex.org/W2155670739","https://openalex.org/W2254543411","https://openalex.org/W2535439249","https://openalex.org/W2571928150","https://openalex.org/W4255673994","https://openalex.org/W4285719527","https://openalex.org/W6635848423","https://openalex.org/W6678010750","https://openalex.org/W6680753075"],"related_works":["https://openalex.org/W2379425324","https://openalex.org/W2373541195","https://openalex.org/W2376410910","https://openalex.org/W2091596831","https://openalex.org/W2365658322","https://openalex.org/W2352344200","https://openalex.org/W329008868","https://openalex.org/W2906819665","https://openalex.org/W2375552622","https://openalex.org/W2367975678"],"abstract_inverted_index":{"Many":[0],"scientific":[1],"workflows":[2],"are":[3,12,19],"composed":[4,13],"of":[5,14,16,40,54,65,72,84],"fine":[6],"computational":[7,52],"granularity":[8,53],"tasks,":[9],"yet":[10],"they":[11],"thousands":[15],"them":[17],"and":[18],"data":[20],"intensive":[21],"in":[22,113],"nature,":[23],"thus":[24],"requiring":[25],"resources":[26],"such":[27,41],"as":[28],"the":[29,38,51,62,66,70,81,85,89,101,114],"TeraGrid":[30,103],"to":[31,36,49,60,119],"execute":[32],"efficiently.":[33],"In":[34,76],"order":[35],"improve":[37],"performance":[39,82],"applications,":[42],"we":[43,79],"often":[44],"employ":[45],"task":[46],"clustering":[47,86,107],"techniques":[48,87],"increase":[50],"workflow":[55,67,91,99,115],"tasks.":[56],"The":[57],"goal":[58],"is":[59],"minimize":[61],"completion":[63,116],"time":[64,117],"by":[68],"reducing":[69],"impact":[71,83],"queue":[73],"wait":[74],"times.":[75],"this":[77],"paper,":[78],"examine":[80],"using":[88,96],"Pegasus":[90],"management":[92],"system.":[93],"Experiments":[94],"performed":[95],"an":[97],"astronomy":[98],"on":[100],"NCSA":[102],"cluster":[104],"show":[105],"that":[106],"can":[108],"achieve":[109],"a":[110],"significant":[111],"reduction":[112],"(up":[118],"97%).":[120]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
