{"id":"https://openalex.org/W4410868564","doi":"https://doi.org/10.1007/s11227-025-07396-3","title":"Optimizing HPC scheduling: a hierarchical reinforcement learning approach for intelligent job selection and allocation","display_name":"Optimizing HPC scheduling: a hierarchical reinforcement learning approach for intelligent job selection and allocation","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4410868564","doi":"https://doi.org/10.1007/s11227-025-07396-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-025-07396-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-07396-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-07396-3.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-07396-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100741802","display_name":"Lingfei Wang","orcid":"https://orcid.org/0000-0001-9175-7006"},"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":"Lingfei Wang","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, 3010, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, 3010, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032796449","display_name":"Maria A. Rodriguez","orcid":"https://orcid.org/0000-0002-2831-8526"},"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":"Maria A. Rodriguez","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, 3010, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, 3010, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066445402","display_name":"Nir Lipovetzky","orcid":"https://orcid.org/0000-0002-8667-3681"},"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":"Nir Lipovetzky","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, 3010, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, 3010, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100741802"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":13.1441,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.98807836,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"81","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9965999722480774,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.920828104019165},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8146284818649292},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5406938791275024},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5222806930541992},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46608206629753113},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.45675334334373474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4178524911403656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.341083824634552},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3344089984893799},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1424485445022583},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11538189649581909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.920828104019165},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8146284818649292},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5406938791275024},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5222806930541992},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46608206629753113},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.45675334334373474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4178524911403656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.341083824634552},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3344089984893799},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1424485445022583},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11538189649581909},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"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:10.1007/s11227-025-07396-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-07396-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-07396-3.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11227-025-07396-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-07396-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-07396-3.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320974","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410868564.pdf","grobid_xml":"https://content.openalex.org/works/W4410868564.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W124529591","https://openalex.org/W1596936080","https://openalex.org/W1965218064","https://openalex.org/W2098512873","https://openalex.org/W2098646592","https://openalex.org/W2104741073","https://openalex.org/W2118449103","https://openalex.org/W2147598193","https://openalex.org/W2233997862","https://openalex.org/W2360786640","https://openalex.org/W2546571074","https://openalex.org/W2552361262","https://openalex.org/W2613195858","https://openalex.org/W2758864532","https://openalex.org/W2767210617","https://openalex.org/W2767921504","https://openalex.org/W2911552803","https://openalex.org/W2934568283","https://openalex.org/W2963761387","https://openalex.org/W2966274836","https://openalex.org/W2968986602","https://openalex.org/W3021027963","https://openalex.org/W3037164854","https://openalex.org/W3064921302","https://openalex.org/W3085797255","https://openalex.org/W3097054188","https://openalex.org/W3129362935","https://openalex.org/W3168892396","https://openalex.org/W3176930059","https://openalex.org/W3206396201","https://openalex.org/W4214935753","https://openalex.org/W4225745299","https://openalex.org/W4244430623","https://openalex.org/W4280520053","https://openalex.org/W4283367935","https://openalex.org/W4302773446","https://openalex.org/W4312572335","https://openalex.org/W4362724039","https://openalex.org/W4388581266","https://openalex.org/W4393141682"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W44553394","https://openalex.org/W3047653192"],"abstract_inverted_index":{"Abstract":[0],"High-performance":[1],"computing":[2],"(HPC)":[3],"systems":[4],"face":[5],"increasing":[6],"challenges":[7],"in":[8,33,45,65,157,187,213],"job":[9,60,80,124,159,164,215],"scheduling":[10,169],"due":[11,37],"to":[12,38,54,85,167,196,203],"the":[13,20,52,79,97,173],"evolving":[14],"complexity":[15],"of":[16,25,47,100],"computational":[17],"tasks":[18],"and":[19,23,50,82,106,129,144,162,201],"growing":[21],"diversity":[22],"heterogeneity":[24],"resources.":[26],"Job":[27],"allocation":[28,61,84,108],"is":[29,62,181],"a":[30,114,210],"critical":[31],"aspect":[32],"contemporary":[34],"HPC":[35,102,135,214],"systems,":[36],"compute":[39],"nodes":[40],"possessing":[41],"an":[42],"increased":[43],"capacity":[44],"terms":[46],"physical":[48],"resources":[49],"having":[51],"capability":[53],"execute":[55],"multiple":[56],"jobs":[57,77],"simultaneously.":[58],"However,":[59],"often":[63],"overlooked":[64],"existing":[66],"reinforcement":[67,117],"learning":[68,118],"(RL)-based":[69],"schedulers":[70],"that":[71],"mainly":[72],"focus":[73],"on":[74],"selecting":[75],"suitable":[76],"from":[78],"queue":[81],"leave":[83],"overly":[86],"simplistic":[87],"policies,":[88],"such":[89],"as":[90],"first-available":[91],"allocation.":[92],"The":[93],"bin-packing":[94],"nature":[95],"at":[96,122],"node":[98],"level":[99],"modern":[101,134],"necessitates":[103],"more":[104],"refined":[105],"intelligent":[107,123],"strategies.":[109],"This":[110,191],"paper":[111],"introduces":[112],"HeraSched,":[113],"novel":[115],"hierarchical":[116],"(HRL)-based":[119],"scheduler,":[120],"adept":[121],"selection":[125],"without":[126],"separate":[127],"backfilling":[128],"heterogeneity-aware":[130],"allocation,":[131],"tailored":[132],"for":[133],"environments.":[136],"It":[137],"efficiently":[138],"manages":[139],"diverse":[140],"workloads":[141,200],"across":[142],"CPU":[143,189],"GPU":[145],"cluster":[146],"partitions.":[147,190],"We":[148],"evaluate":[149],"HeraSched":[150],"using":[151],"real-world":[152],"workloads,":[153],"demonstrating":[154],"significant":[155],"improvements":[156],"reducing":[158],"waiting":[160,176],"times":[161],"preventing":[163],"starvation":[165],"compared":[166,179],"27":[168],"combinations.":[170],"In":[171],"validation,":[172],"best":[174],"maximum":[175],"time":[177],"among":[178],"methods":[180],"78%":[182],"higher":[183],"than":[184],"HeraSched\u2019s":[185,194],"result":[186],"overloaded":[188],"performance":[192],"demonstrates":[193],"ability":[195],"manage":[197],"intensely":[198],"stressed":[199],"adapt":[202],"previously":[204],"unseen,":[205],"high-demand":[206],"scenarios,":[207],"thereby":[208],"establishing":[209],"new":[211],"standard":[212],"scheduling.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}