{"id":"https://openalex.org/W2085980508","doi":"https://doi.org/10.1109/bigdata.2013.6691724","title":"Rethinking data management for big data scientific workflows","display_name":"Rethinking data management for big data scientific workflows","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2085980508","doi":"https://doi.org/10.1109/bigdata.2013.6691724","mag":"2085980508"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055471608","display_name":"Karan Vahi","orcid":"https://orcid.org/0000-0001-8622-2082"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karan Vahi","raw_affiliation_strings":["Information Sciences Institute-University of Southern California, USA","[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute-University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079942660","display_name":"Mats Rynge","orcid":"https://orcid.org/0000-0002-1779-7189"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mats Rynge","raw_affiliation_strings":["Information Sciences Institute-University of Southern California, USA","[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute-University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005056823","display_name":"Gideon Juve","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gideon Juve","raw_affiliation_strings":["Information Sciences Institute-University of Southern California, USA","[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute-University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058874412","display_name":"Rajiv Mayani","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajiv Mayani","raw_affiliation_strings":["Information Sciences Institute-University of Southern California, USA","[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute-University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031941569","display_name":"Ewa Deelman","orcid":"https://orcid.org/0000-0001-5106-503X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ewa Deelman","raw_affiliation_strings":["Information Sciences Institute-University of Southern California, USA","[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute-University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Inf. Sci. Inst., Univ. of Southern California, Marina del Rey, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8996362686157227},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.896854043006897},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.742826521396637},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.6380185484886169},{"id":"https://openalex.org/keywords/workflow-engine","display_name":"Workflow engine","score":0.6215574741363525},{"id":"https://openalex.org/keywords/workflow-technology","display_name":"Workflow technology","score":0.5816982984542847},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5239467620849609},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.507942259311676},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.49509397149086},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.44634175300598145},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4370558559894562},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41524776816368103},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2433590590953827},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14766567945480347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8996362686157227},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.896854043006897},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.742826521396637},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.6380185484886169},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.6215574741363525},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.5816982984542847},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5239467620849609},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.507942259311676},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.49509397149086},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.44634175300598145},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4370558559894562},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41524776816368103},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2433590590953827},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14766567945480347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2013.6691724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.2389","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.2389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isi.edu/%7Egideon/publications/VahiK-Rethinking.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":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1604669054","https://openalex.org/W1976457299","https://openalex.org/W1980558577","https://openalex.org/W1996533619","https://openalex.org/W2001372508","https://openalex.org/W2004716951","https://openalex.org/W2006382393","https://openalex.org/W2033650210","https://openalex.org/W2043079212","https://openalex.org/W2069010865","https://openalex.org/W2077215938","https://openalex.org/W2096812688","https://openalex.org/W2102516719","https://openalex.org/W2104704206","https://openalex.org/W2106494836","https://openalex.org/W2108370395","https://openalex.org/W2114516927","https://openalex.org/W2117963990","https://openalex.org/W2123130398","https://openalex.org/W2123663722","https://openalex.org/W2125587567","https://openalex.org/W2129666400","https://openalex.org/W2130651654","https://openalex.org/W2135204661","https://openalex.org/W2146176543","https://openalex.org/W2146917903","https://openalex.org/W2148317584","https://openalex.org/W2153829863","https://openalex.org/W2154010459","https://openalex.org/W2170807833","https://openalex.org/W2170901349","https://openalex.org/W2173213060","https://openalex.org/W2176777808","https://openalex.org/W2913513779","https://openalex.org/W2949835970","https://openalex.org/W2952847206","https://openalex.org/W4236623206","https://openalex.org/W4252427272","https://openalex.org/W4298068285","https://openalex.org/W6651881141","https://openalex.org/W6674159191","https://openalex.org/W6679121665","https://openalex.org/W6682896412","https://openalex.org/W6758897570"],"related_works":["https://openalex.org/W2372773112","https://openalex.org/W2166433032","https://openalex.org/W2377329191","https://openalex.org/W1887920917","https://openalex.org/W1533256563","https://openalex.org/W2356938388","https://openalex.org/W2148259456","https://openalex.org/W2349553854","https://openalex.org/W1969197689","https://openalex.org/W2127060079"],"abstract_inverted_index":{"Scientific":[0],"workflows":[1,139,214],"consist":[2],"of":[3,115,128,143,146,199,217],"tasks":[4],"that":[5,15,121,166,225,241],"operate":[6],"on":[7,186],"input":[8,69],"data":[9,13,26,38,193],"to":[10,27,65,98,103,152,171,212,230,262],"generate":[11],"new":[12],"products":[14],"are":[16,46],"used":[17,210],"by":[18,84,179],"subsequent":[19],"tasks.":[20,131],"Workflow":[21,205],"management":[22],"systems":[23],"typically":[24],"stage":[25],"computational":[28,57],"sites":[29],"before":[30],"invoking":[31],"the":[32,53,67,126,129,144,174,183,187,203,237],"necessary":[33,68],"computations.":[34],"In":[35,90,132],"some":[36],"cases":[37],"may":[39,59],"be":[40,60],"accessed":[41,176],"using":[42,264],"remote":[43,244],"I/O.":[44],"There":[45],"limitations":[47],"with":[48,87],"these":[49,200],"approaches,":[50,164],"however.":[51],"First,":[52],"storage":[54],"at":[55],"a":[56,85,100,112,180,227,248,258],"site":[58],"limited":[61,88,113],"and":[62,70,105,119,177,208,236],"not":[63,123],"able":[64],"accommodate":[66],"intermediate":[71,192],"data.":[72],"Second,":[73],"even":[74],"if":[75],"there":[76],"is":[77,81],"enough":[78],"storage,":[79],"it":[80],"sometimes":[82],"managed":[83],"filesystem":[86,189,229,260],"scalability.":[89],"recent":[91],"years,":[92],"object":[93,147,169,245,265],"stores":[94,148,170,266],"have":[95,196,209,226],"been":[96],"shown":[97],"provide":[99,111],"scalable":[101],"way":[102],"store":[104,118,172],"access":[106],"large":[107],"datasets,":[108],"however,":[109],"they":[110],"set":[114],"operations":[116],"(retrieve,":[117],"delete)":[120],"do":[122],"always":[124],"match":[125],"requirements":[127],"workflow":[130],"this":[133],"paper,":[134],"we":[135],"show":[136],"how":[137],"scientific":[138,158],"can":[140,252],"take":[141],"advantage":[142],"capabilities":[145],"without":[149,267],"requiring":[150],"users":[151,251],"modify":[153],"their":[154,255,269],"workflow-based":[155],"applications":[156,256],"or":[157],"codes.":[159,271],"We":[160,195],"present":[161],"two":[162],"general":[163],"one":[165,263],"exclusively":[167],"uses":[168],"all":[173],"files":[175],"generated":[178],"workflow,":[181],"while":[182],"other":[184],"relies":[185],"shared":[188,228,259],"for":[190],"caching":[191],"sets.":[194],"implemented":[197],"both":[198],"approaches":[201],"in":[202,215],"Pegasus":[204,250],"Management":[206],"System":[207],"them":[211],"execute":[213],"variety":[216],"execution":[218],"environments":[219,224,232],"ranging":[220],"from":[221,257],"traditional":[222],"supercomputing":[223],"dynamic":[231],"like":[233],"Amazon":[234],"AWS":[235],"Open":[238],"Science":[239],"Grid":[240],"only":[242],"offer":[243],"stores.":[246],"As":[247],"result,":[249],"easily":[253],"migrate":[254],"deployment":[261],"changing":[268],"application":[270]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}