{"id":"https://openalex.org/W4406460777","doi":"https://doi.org/10.1109/bigdata62323.2024.10825855","title":"Improving I/O-aware Workflow Scheduling via Data Flow Characterization and trade-off Analysis","display_name":"Improving I/O-aware Workflow Scheduling via Data Flow Characterization and trade-off Analysis","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406460777","doi":"https://doi.org/10.1109/bigdata62323.2024.10825855"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5026765811","display_name":"Luanzheng Guo","orcid":"https://orcid.org/0000-0001-8266-0923"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luanzheng Guo","raw_affiliation_strings":["Pacific Northwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102821589","display_name":"Meng Tang","orcid":"https://orcid.org/0009-0003-5995-6947"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Tang","raw_affiliation_strings":["Illinois Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010460625","display_name":"Hyungro Lee","orcid":"https://orcid.org/0000-0002-4221-7094"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyungro Lee","raw_affiliation_strings":["Pacific Northwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063476184","display_name":"Jesun Firoz","orcid":"https://orcid.org/0000-0002-8174-2545"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesun Firoz","raw_affiliation_strings":["Pacific Northwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047746050","display_name":"Nathan R. Tallent","orcid":"https://orcid.org/0000-0003-4297-3057"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan R. Tallent","raw_affiliation_strings":["Pacific Northwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026765811"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":0.7326,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75332339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3674","last_page":"3681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9952999949455261,"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":0.9952999949455261,"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":0.9926999807357788,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9764999747276306,"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":0.7335506677627563},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6800389885902405},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.455070436000824},{"id":"https://openalex.org/keywords/data-flow-analysis","display_name":"Data-flow analysis","score":0.43656691908836365},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4245809018611908},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.3285486102104187},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2204948365688324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08740314841270447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335506677627563},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6800389885902405},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.455070436000824},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.43656691908836365},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4245809018611908},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.3285486102104187},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2204948365688324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08740314841270447},{"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:10.1109/bigdata62323.2024.10825855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1967239133","https://openalex.org/W1997882450","https://openalex.org/W2011039300","https://openalex.org/W2070232376","https://openalex.org/W2078962046","https://openalex.org/W2079031056","https://openalex.org/W2086539288","https://openalex.org/W2105517570","https://openalex.org/W2118953734","https://openalex.org/W2122747952","https://openalex.org/W2127556182","https://openalex.org/W2149294210","https://openalex.org/W2153752762","https://openalex.org/W2161455936","https://openalex.org/W2401246392","https://openalex.org/W2408470734","https://openalex.org/W2412848782","https://openalex.org/W2525254816","https://openalex.org/W2747878524","https://openalex.org/W2767236912","https://openalex.org/W2778417717","https://openalex.org/W2886514749","https://openalex.org/W2953385701","https://openalex.org/W2954427512","https://openalex.org/W2985168981","https://openalex.org/W3003319291","https://openalex.org/W3011895995","https://openalex.org/W3099464315","https://openalex.org/W3138006684","https://openalex.org/W3156353042","https://openalex.org/W3156503983","https://openalex.org/W3177106889","https://openalex.org/W3194513155","https://openalex.org/W3203002808","https://openalex.org/W4200555459","https://openalex.org/W4200570984","https://openalex.org/W4224330085","https://openalex.org/W4241856644","https://openalex.org/W4285504037","https://openalex.org/W4285609472","https://openalex.org/W4307080517","https://openalex.org/W4311797354","https://openalex.org/W4312743628","https://openalex.org/W4321636569","https://openalex.org/W4364322167","https://openalex.org/W4365461160","https://openalex.org/W4385575005","https://openalex.org/W4387006313","https://openalex.org/W4388102940","https://openalex.org/W4388561279","https://openalex.org/W4391623927"],"related_works":["https://openalex.org/W59945861","https://openalex.org/W1551967076","https://openalex.org/W2151163382","https://openalex.org/W4256382613","https://openalex.org/W316163056","https://openalex.org/W2092972345","https://openalex.org/W2138414258","https://openalex.org/W2527311635","https://openalex.org/W1549956274","https://openalex.org/W1484884871"],"abstract_inverted_index":{"The":[0,122,146,174],"scientific":[1],"computing":[2],"paradigm":[3],"has":[4,20],"transitioned":[5],"from":[6],"compute-intensive":[7],"to":[8,76,109,138,181,184],"I/O-intensive":[9,171],"and":[10,36,53,61,79,88,99,119,136,144],"memory-intensive":[11],"in":[12],"the":[13,66,111,158,185],"past":[14],"decade,":[15],"especially":[16],"when":[17],"data-driven":[18],"science":[19],"become":[21],"common":[22],"practice.":[23],"Numerous":[24],"empirical":[25],"I/O-aware":[26,165],"scheduling":[27,137,151,166],"optimizations":[28],"have":[29],"been":[30],"developed":[31],"by":[32,95,141],"incorporating":[33],"I/O":[34,62,81,86,96,104,123,130],"capacity":[35],"bandwidth":[37],"as":[38],"constraints":[39],"into":[40,128],"scheduling.":[41],"Unfortunately,":[42],"there":[43],"is":[44],"a":[45,72,169],"lack":[46],"of":[47,56,74,179],"data":[48,93],"flow":[49,84,115,120,160],"(I/O)":[50],"characterization":[51],"tools":[52],"an":[54,103],"understanding":[55],"trade-offs":[57],"between":[58,114],"concurrency,":[59,118,134],"locality,":[60],"bandwidth.":[63],"To":[64],"bridge":[65],"gap,":[67],"this":[68],"work":[69],"1)":[70],"presents":[71],"set":[73],"descriptors":[75,124],"characterize,":[77],"organize,":[78],"visualize":[80],"profiles,":[82],"including":[83],"size,":[85],"bandwidth,":[87],"operation":[89],"count,":[90],"which":[91],"group":[92],"flows":[94],"types,":[97,142],"tasks,":[98,143],"files;":[100],"2)":[101],"proposes":[102],"Roofline":[105],"model-based":[106],"trade-off":[107,113,148],"analysis":[108,149],"find":[110],"optimal":[112],"operational":[116],"intensity,":[117],"performance.":[121],"generate":[125,154],"useful":[126],"insights":[127],"complicated":[129],"behaviors,":[131],"suggesting":[132],"distinct":[133],"storage,":[135],"be":[139],"used":[140],"files.":[145],"proposed":[147],"guides":[150],"decisions":[152],"that":[153],"resource":[155],"assignment":[156],"with":[157],"best":[159],"parallelism.":[161],"We":[162],"evaluate":[163],"our":[164],"methodology":[167],"on":[168],"highly":[170],"workflow\u20131000":[172],"Genomes.":[173],"experimental":[175],"results":[176],"demonstrate":[177],"speedups":[178],"up":[180],"2.4\u00d7":[182],"compared":[183],"state-of-the-art":[186],"methods.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}