{"id":"https://openalex.org/W3216235925","doi":"https://doi.org/10.1109/tpds.2021.3124670","title":"Performance and Cost-Efficient Spark Job Scheduling Based on Deep Reinforcement Learning in Cloud Computing Environments","display_name":"Performance and Cost-Efficient Spark Job Scheduling Based on Deep Reinforcement Learning in Cloud Computing Environments","publication_year":2021,"publication_date":"2021-11-02","ids":{"openalex":"https://openalex.org/W3216235925","doi":"https://doi.org/10.1109/tpds.2021.3124670","mag":"3216235925"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3124670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3124670","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5036540153","display_name":"Muhammed Tawfiqul Islam","orcid":"https://orcid.org/0000-0003-4922-7807"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Muhammed Tawfiqul Islam","raw_affiliation_strings":["Cloud Computing and Distributed Systems (CLOUDS) Lab, School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Cloud Computing and Distributed Systems (CLOUDS) Lab, School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021381399","display_name":"Shanika Karunasekera","orcid":"https://orcid.org/0000-0001-7080-5064"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shanika Karunasekera","raw_affiliation_strings":["Cloud Computing and Distributed Systems (CLOUDS) Lab, School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Cloud Computing and Distributed Systems (CLOUDS) Lab, School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014716105","display_name":"Rajkumar Buyya","orcid":"https://orcid.org/0000-0001-9754-6496"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rajkumar Buyya","raw_affiliation_strings":["Cloud Computing and Distributed Systems (CLOUDS) Lab, School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Cloud Computing and Distributed Systems (CLOUDS) Lab, School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036540153"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":21.6218,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.99480559,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"33","issue":"7","first_page":"1695","last_page":"1710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9976000189781189,"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9900000095367432,"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":0.8383537530899048},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7795489430427551},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.746553897857666},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7057897448539734},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6360605955123901},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5577549934387207},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5370337963104248},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5063201189041138},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.4951764643192291},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4543239176273346},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.42886143922805786},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4112969934940338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2415393590927124},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22642531991004944},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.17819640040397644},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.09251493215560913},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.08387196063995361}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8383537530899048},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7795489430427551},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.746553897857666},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7057897448539734},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6360605955123901},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5577549934387207},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5370337963104248},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5063201189041138},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.4951764643192291},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4543239176273346},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.42886143922805786},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4112969934940338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2415393590927124},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22642531991004944},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.17819640040397644},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.09251493215560913},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.08387196063995361},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2021.3124670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3124670","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1890643295","https://openalex.org/W2087946700","https://openalex.org/W2102849319","https://openalex.org/W2105947650","https://openalex.org/W2119717200","https://openalex.org/W2119738171","https://openalex.org/W2131975293","https://openalex.org/W2145339207","https://openalex.org/W2150478767","https://openalex.org/W2153304308","https://openalex.org/W2155014525","https://openalex.org/W2160121678","https://openalex.org/W2163961697","https://openalex.org/W2306821251","https://openalex.org/W2525414919","https://openalex.org/W2528415359","https://openalex.org/W2542459869","https://openalex.org/W2546571074","https://openalex.org/W2597068831","https://openalex.org/W2735420144","https://openalex.org/W2756859730","https://openalex.org/W2757024591","https://openalex.org/W2766447205","https://openalex.org/W2892315936","https://openalex.org/W2892464762","https://openalex.org/W2918523967","https://openalex.org/W2919897868","https://openalex.org/W2941015387","https://openalex.org/W2948467663","https://openalex.org/W2968986602","https://openalex.org/W2975330064","https://openalex.org/W2978949425","https://openalex.org/W2982346115","https://openalex.org/W3000090293","https://openalex.org/W3003781497","https://openalex.org/W3027455131","https://openalex.org/W3033555278","https://openalex.org/W3100711529","https://openalex.org/W3138125150","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6639249596","https://openalex.org/W6679815717","https://openalex.org/W6684084819","https://openalex.org/W6727576777","https://openalex.org/W6762257222","https://openalex.org/W6778017900"],"related_works":["https://openalex.org/W1975949872","https://openalex.org/W3191926225","https://openalex.org/W4246264554","https://openalex.org/W3112375919","https://openalex.org/W2962431048","https://openalex.org/W4233648438","https://openalex.org/W2969378954","https://openalex.org/W2793083950","https://openalex.org/W4213304158","https://openalex.org/W2510748453"],"abstract_inverted_index":{"Big":[0],"data":[1,42],"frameworks":[2],"such":[3,62],"as":[4,63],"Spark":[5,104],"and":[6,18,67,82,89,106,125,192],"Hadoop":[7],"are":[8,26,33],"widely":[9],"adopted":[10],"to":[11,28,84,114,147,178,183,212],"run":[12],"analytics":[13],"jobs":[14,152,177],"in":[15,52,134],"both":[16,185],"research":[17,75],"industry.":[19],"Cloud":[20],"offers":[21],"affordable":[22],"compute":[23],"resources":[24],"which":[25],"easier":[27],"manage.":[29],"Hence,":[30],"many":[31],"organizations":[32],"shifting":[34],"towards":[35],"a":[36,49,102,108,144,180],"cloud":[37,159],"deployment":[38],"of":[39,55,72,101,151,158,173,176],"their":[40],"big":[41],"computing":[43],"clusters.":[44],"However,":[45],"job":[46,68,98,195],"scheduling":[47,99,140],"is":[48],"complex":[50],"problem":[51,100],"the":[53,73,86,97,116,121,149,155,164,170,186,193,201,207],"presence":[54],"various":[56],"Service":[57],"Level":[58],"Agreement":[59],"(SLA)":[60],"objectives":[61,80],"monetary":[64],"cost":[65,191,210],"reduction,":[66],"performance":[69],"improvement.":[70],"Most":[71],"existing":[74],"does":[76],"not":[77],"address":[78],"multiple":[79],"together":[81],"fail":[83],"capture":[85],"inherent":[87,171],"cluster":[88,105,123,188],"workload":[90],"characteristics.":[91],"In":[92,162],"this":[93],"article,":[94],"we":[95],"formulate":[96],"cloud-deployed":[103],"propose":[107],"novel":[109],"Reinforcement":[110],"Learning":[111,130],"(RL)":[112],"model":[113,157],"accommodate":[115],"SLA":[117],"objectives.":[118],"We":[119],"develop":[120],"RL":[122],"environment":[124],"implement":[126],"two":[127],"Deep":[128],"Reinforce":[129],"(DRL)":[131],"based":[132],"schedulers":[133],"TF-Agents":[135],"framework.":[136],"The":[137,197],"proposed":[138,202],"DRL-based":[139,165,203],"agents":[141,166],"work":[142],"at":[143],"fine-grained":[145],"level":[146],"place":[148],"executors":[150],"while":[153],"leveraging":[154],"pricing":[156],"VM":[160,189,208],"instances.":[161],"addition,":[163],"can":[167,205],"also":[168],"learn":[169],"characteristics":[172],"different":[174],"types":[175],"find":[179],"proper":[181],"placement":[182],"reduce":[184,206],"total":[187],"usage":[190,209],"average":[194],"duration.":[196],"results":[198],"show":[199],"that":[200],"algorithms":[204],"up":[211],"30%.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":16}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}