{"id":"https://openalex.org/W3093580137","doi":"https://doi.org/10.1109/jsyst.2021.3129974","title":"Speculative Container Scheduling for Deep Learning Applications in a Kubernetes Cluster","display_name":"Speculative Container Scheduling for Deep Learning Applications in a Kubernetes Cluster","publication_year":2021,"publication_date":"2021-12-10","ids":{"openalex":"https://openalex.org/W3093580137","doi":"https://doi.org/10.1109/jsyst.2021.3129974","mag":"3093580137"},"language":"en","primary_location":{"id":"doi:10.1109/jsyst.2021.3129974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsyst.2021.3129974","pdf_url":null,"source":{"id":"https://openalex.org/S95999327","display_name":"IEEE Systems Journal","issn_l":"1932-8184","issn":["1932-8184","1937-9234","2373-7816"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Systems Journal","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.11307","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013723403","display_name":"Ying Mao","orcid":"https://orcid.org/0000-0002-4484-4892"},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Mao","raw_affiliation_strings":["Department of Computer and Information Science, Fordham University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4484-4892","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Fordham University, New York, NY, USA","institution_ids":["https://openalex.org/I164389053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057669703","display_name":"Yuqi Fu","orcid":"https://orcid.org/0009-0009-6556-9162"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]},{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqi Fu","raw_affiliation_strings":["Department of Computer and Information Science, Fordham University, New York, NY, USA","Department of Computer Science, George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Fordham University, New York, NY, USA","institution_ids":["https://openalex.org/I164389053"]},{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045059848","display_name":"Wenjia Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenjia Zheng","raw_affiliation_strings":["Department of Computer and Information Science, Fordham University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Fordham University, New York, NY, USA","institution_ids":["https://openalex.org/I164389053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073321754","display_name":"Long Cheng","orcid":"https://orcid.org/0000-0003-1638-059X"},"institutions":[{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Cheng","raw_affiliation_strings":["School of Control and Computer Engineering, North China Electric Power University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1638-059X","affiliations":[{"raw_affiliation_string":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China","institution_ids":["https://openalex.org/I153473198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006107034","display_name":"Qingzhi Liu","orcid":"https://orcid.org/0000-0003-2621-9222"},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Qingzhi Liu","raw_affiliation_strings":["Information Technology Group, Wageningen University and Research, Wageningen, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-2621-9222","affiliations":[{"raw_affiliation_string":"Information Technology Group, Wageningen University and Research, Wageningen, The Netherlands","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063703614","display_name":"Dingwen Tao","orcid":"https://orcid.org/0000-0001-5422-4497"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dingwen Tao","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5422-4497","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA","institution_ids":["https://openalex.org/I72951846"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3969,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.97082459,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"3770","last_page":"3781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9951000213623047,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9951000213623047,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9911999702453613,"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":0.672753632068634},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5740256309509277},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5183601975440979},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.4479936957359314},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44614356756210327},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.30262935161590576},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18190860748291016},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.11598056554794312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.672753632068634},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5740256309509277},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5183601975440979},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.4479936957359314},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44614356756210327},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.30262935161590576},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18190860748291016},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.11598056554794312},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jsyst.2021.3129974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsyst.2021.3129974","pdf_url":null,"source":{"id":"https://openalex.org/S95999327","display_name":"IEEE Systems Journal","issn_l":"1932-8184","issn":["1932-8184","1937-9234","2373-7816"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Systems Journal","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2010.11307","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11307","pdf_url":"https://arxiv.org/pdf/2010.11307","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:wur:oai:library.wur.nl:wurpubs/591241","is_oa":false,"landing_page_url":"https://research.wur.nl/en/publications/speculative-container-scheduling-for-deep-learning-applications-i","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Systems Journal, 16(3), 3770 - 3781","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.11307","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11307","pdf_url":"https://arxiv.org/pdf/2010.11307","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1969898572","https://openalex.org/W2014721449","https://openalex.org/W2131774270","https://openalex.org/W2155031841","https://openalex.org/W2334544811","https://openalex.org/W2344148224","https://openalex.org/W2472245678","https://openalex.org/W2496393436","https://openalex.org/W2530389446","https://openalex.org/W2574967308","https://openalex.org/W2759085228","https://openalex.org/W2792281126","https://openalex.org/W2793406860","https://openalex.org/W2886118254","https://openalex.org/W2892840087","https://openalex.org/W2892876587","https://openalex.org/W2899071864","https://openalex.org/W2940806880","https://openalex.org/W2962725887","https://openalex.org/W2962747323","https://openalex.org/W2963330479","https://openalex.org/W2963505890","https://openalex.org/W2963818120","https://openalex.org/W2963877979","https://openalex.org/W2971269401","https://openalex.org/W2971424644","https://openalex.org/W2982182655","https://openalex.org/W2990062730","https://openalex.org/W3002068112","https://openalex.org/W3007154432","https://openalex.org/W3022298203","https://openalex.org/W3022548332","https://openalex.org/W3081586874","https://openalex.org/W3093568822","https://openalex.org/W3131369229","https://openalex.org/W3196022191","https://openalex.org/W3209358303","https://openalex.org/W4207041266","https://openalex.org/W4210625278","https://openalex.org/W4239877333","https://openalex.org/W4318977988","https://openalex.org/W4380789340","https://openalex.org/W6756009870","https://openalex.org/W6758283263","https://openalex.org/W6758474236","https://openalex.org/W6759814162"],"related_works":["https://openalex.org/W2367301169","https://openalex.org/W2352134912","https://openalex.org/W2001079144","https://openalex.org/W4393477817","https://openalex.org/W2048054615","https://openalex.org/W2974221847","https://openalex.org/W2480624181","https://openalex.org/W2581710029","https://openalex.org/W2055230095","https://openalex.org/W3146804403"],"abstract_inverted_index":{"In":[0,119],"the":[1,41,56,82,146,160,166,176],"past":[2],"decade,":[3],"we":[4,122],"have":[5,26],"witnessed":[6],"a":[7,45,125,154],"dramatically":[8],"increasing":[9],"volume":[10],"of":[11,58,149,156,198],"data":[12],"collected":[13],"from":[14],"various":[15,20],"sources.":[16],"To":[17],"maximize":[18],"utilization,":[19],"machine":[21],"and":[22,47,79,95,107,142,163,194],"deep":[23,59,116,132],"learning":[24,60,117,133],"models":[25,42,168],"been":[27],"developed":[28],"to":[29,89,158,169,190],"study":[30],"data.":[31],"While":[32],"data-driven":[33],"applications":[34],"improve":[35],"countless":[36],"products,":[37],"hyperparameter":[38],"tuning":[39],"for":[40,55,71,130,172],"is":[43],"still":[44],"time-consuming":[46],"resource-intensive":[48],"process.":[49],"Cloud":[50],"computing":[51],"provides":[52],"infrastructure":[53],"support":[54],"training":[57,150],"applications.":[61,134],"The":[62],"cloud":[63],"service":[64],"providers":[65],"create":[66],"an":[67,183],"isolated":[68],"virtual":[69],"environment":[70],"clients":[72],"who":[73],"share":[74],"physical":[75],"resources,":[76],"e.g.,":[77],"CPU":[78],"memory.":[80],"On":[81],"cloud,":[83],"resource":[84,109],"management":[85],"schemes":[86],"are":[87],"implemented":[88],"enable":[90],"better":[91],"sharing":[92],"among":[93],"users":[94],"boost":[96],"system-wide":[97],"performance.":[98],"However,":[99],"general":[100],"scheduling":[101],"approaches,":[102],"such":[103,139],"as":[104,140],"spread":[105],"priority":[106],"balanced":[108],"schedulers,":[110],"do":[111],"not":[112],"work":[113],"well":[114],"with":[115],"workloads.":[118],"this":[120],"article,":[121],"propose":[123],"SpeCon,":[124],"novel":[126],"container":[127],"scheduler":[128],"optimized":[129],"short-lived":[131],"Based":[135],"on":[136],"virtualized":[137],"containers,":[138],"Kubernetes":[141],"Docker,":[143],"SpeCon":[144,181],"analyzes":[145],"typical":[147],"characteristics":[148],"processes.":[151],"We":[152],"design":[153],"suite":[155],"algorithms":[157],"monitor":[159],"training\u2019s":[161],"progress":[162],"speculatively":[164],"migrate":[165],"slow-growing":[167],"release":[170],"resources":[171],"fast-growing":[173],"ones.":[174],"Specifically,":[175],"extensive":[177],"experiments":[178],"demonstrate":[179],"that":[180],"improves":[182],"individual":[184],"job\u2019s":[185],"completion":[186],"time":[187],"by":[188],"up":[189],"41.5%,":[191],"14.8%":[192],"system-wide,":[193],"24.7%":[195],"in":[196],"terms":[197],"makespan.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}