{"id":"https://openalex.org/W2766766128","doi":"https://doi.org/10.1145/3150994.3150998","title":"A machine learning approach for modular workflow performance prediction","display_name":"A machine learning approach for modular workflow performance prediction","publication_year":2017,"publication_date":"2017-10-31","ids":{"openalex":"https://openalex.org/W2766766128","doi":"https://doi.org/10.1145/3150994.3150998","mag":"2766766128"},"language":"en","primary_location":{"id":"doi:10.1145/3150994.3150998","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3150994.3150998","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3150998&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Workshop on Workflows in Support of Large-Scale Science","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3150998&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024079779","display_name":"Alok Singh","orcid":"https://orcid.org/0000-0002-2683-0542"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alok Singh","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103572065","display_name":"Arvind Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Rao","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010043183","display_name":"Shweta Purawat","orcid":"https://orcid.org/0000-0002-5183-2750"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shweta Purawat","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028701796","display_name":"\u0130lkay Alt\u0131nta\u015f","orcid":"https://orcid.org/0000-0002-2196-0305"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilkay Altintas","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024079779"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":7.5927,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.97112704,"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":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980000257492065,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.8815054893493652},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8734118938446045},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6331429481506348},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5792802572250366},{"id":"https://openalex.org/keywords/workflow-technology","display_name":"Workflow technology","score":0.5778459906578064},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.5654363036155701},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4721301198005676},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4648728668689728},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44309911131858826},{"id":"https://openalex.org/keywords/workflow-engine","display_name":"Workflow engine","score":0.42566725611686707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35602039098739624},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2049458622932434},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.120404452085495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8815054893493652},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8734118938446045},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6331429481506348},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5792802572250366},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.5778459906578064},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.5654363036155701},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4721301198005676},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4648728668689728},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44309911131858826},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.42566725611686707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35602039098739624},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2049458622932434},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.120404452085495},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3150994.3150998","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3150994.3150998","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3150998&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Workshop on Workflows in Support of Large-Scale Science","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3150994.3150998","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3150994.3150998","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3150998&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Workshop on Workflows in Support of Large-Scale Science","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3261282454","display_name":"ABI Development: bioKepler: A Comprehensive Bioinformatics Scientific Workflow Module for Distributed Analysis of Large-Scale Biological Data","funder_award_id":"1062565","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713346733","display_name":null,"funder_award_id":"P41 GM103426","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7199578972","display_name":null,"funder_award_id":"GM103426","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7264659024","display_name":null,"funder_award_id":"1331615","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7786736537","display_name":null,"funder_award_id":"62565","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8421416343","display_name":null,"funder_award_id":"NIH P41 GM103426","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8710349911","display_name":null,"funder_award_id":"DE-SC0012630","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8877069089","display_name":null,"funder_award_id":"DBI 1062565 and 1331615","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2766766128.pdf","grobid_xml":"https://content.openalex.org/works/W2766766128.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1504930038","https://openalex.org/W1557038314","https://openalex.org/W1678356000","https://openalex.org/W1814568923","https://openalex.org/W1964357740","https://openalex.org/W1966275653","https://openalex.org/W1974985151","https://openalex.org/W1983833794","https://openalex.org/W1989673248","https://openalex.org/W1990257473","https://openalex.org/W2001134579","https://openalex.org/W2016395505","https://openalex.org/W2018225704","https://openalex.org/W2019436626","https://openalex.org/W2047280416","https://openalex.org/W2101234009","https://openalex.org/W2108905989","https://openalex.org/W2113555024","https://openalex.org/W2119821739","https://openalex.org/W2132219981","https://openalex.org/W2143426320","https://openalex.org/W2149122656","https://openalex.org/W2152064897","https://openalex.org/W2154513453","https://openalex.org/W2156560068","https://openalex.org/W2156607194","https://openalex.org/W2157070686","https://openalex.org/W2157777898","https://openalex.org/W2158462536","https://openalex.org/W2165844343","https://openalex.org/W2168934464","https://openalex.org/W2171060037","https://openalex.org/W2182468807","https://openalex.org/W2609265534","https://openalex.org/W2911956241","https://openalex.org/W2911964244","https://openalex.org/W2997591727","https://openalex.org/W4239510810"],"related_works":["https://openalex.org/W2352774566","https://openalex.org/W2049143847","https://openalex.org/W2356466503","https://openalex.org/W2376671203","https://openalex.org/W2391168633","https://openalex.org/W2385499106","https://openalex.org/W1574425962","https://openalex.org/W2354357087","https://openalex.org/W2387628393","https://openalex.org/W2370201914"],"abstract_inverted_index":{"Scientific":[0],"workflows":[1,51,176],"provide":[2,205],"an":[3,11,133],"opportunity":[4],"for":[5,71,87],"declarative":[6],"computational":[7,33],"experiment":[8],"design":[9],"in":[10,48,103,215],"intuitive":[12],"and":[13,27,117,135,152,177,210],"efficient":[14],"way.":[15],"A":[16],"distributed":[17],"workflow":[18,67,102,189,220],"is":[19,98],"typically":[20],"executed":[21,191],"on":[22,52,192],"a":[23,30,43,66,80,93,101,105,120,130,136,141,147,156],"variety":[24,31,44],"of":[25,32,92,111,132,159,164,187,212,218],"resources":[26],"it":[28,169],"uses":[29],"algorithms":[34,214],"or":[35],"tools":[36],"to":[37,99,122,149,170,172,179],"achieve":[38],"the":[39,109,124,165,193,208,216],"desired":[40],"outcomes.":[41],"Such":[42],"imposes":[45],"additional":[46],"complexity":[47],"scheduling":[49],"these":[50],"large":[53],"scale":[54,178],"computers.":[55],"As":[56],"computation":[57],"becomes":[58],"more":[59],"distributed,":[60],"insights":[61,206],"into":[62,207],"expected":[63],"workload":[64,151],"that":[65,83,107],"presents":[68],"become":[69],"critical":[70],"effective":[72],"resource":[73,139],"allocation.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"present":[79,183],"modular":[81,162],"framework":[82,167],"leverages":[84],"Machine":[85,200],"Learning":[86,201],"creating":[88],"precise":[89],"performance":[90,184,221],"predictions":[91,126],"workflow.":[94],"The":[95,161,203],"central":[96],"idea":[97],"partition":[100],"such":[104],"way":[106,121],"makes":[108],"task":[110],"forecasting":[112],"each":[113],"atomic":[114],"unit":[115,158],"manageable":[116],"gives":[118,145],"us":[119,146],"combine":[123],"individual":[125],"efficiently.":[127],"We":[128,182],"recognize":[129],"combination":[131],"executable":[134],"specific":[137],"physical":[138],"as":[140,155],"single":[142,157],"module.":[143],"This":[144],"handle":[148],"characterize":[150],"machine":[153],"power":[154],"prediction.":[160,222],"approach":[163],"presented":[166],"allows":[168],"adapt":[171],"highly":[173],"complex":[174],"nested":[175],"new":[180],"scenarios.":[181],"estimation":[185],"results":[186,204],"independent":[188],"modules":[190],"XSEDE":[194],"SDSC":[195],"Comet":[196],"cluster":[197],"using":[198],"various":[199],"algorithms.":[202],"behavior":[209],"effectiveness":[211],"different":[213],"context":[217],"scientific":[219]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}