{"id":"https://openalex.org/W4416088820","doi":"https://doi.org/10.3390/bdcc9110284","title":"Efficient Scheduling for GPU-Based Neural Network Training via Hybrid Reinforcement Learning and Metaheuristic Optimization","display_name":"Efficient Scheduling for GPU-Based Neural Network Training via Hybrid Reinforcement Learning and Metaheuristic Optimization","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416088820","doi":"https://doi.org/10.3390/bdcc9110284"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc9110284","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9110284","pdf_url":"https://www.mdpi.com/2504-2289/9/11/284/pdf?version=1762781058","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/9/11/284/pdf?version=1762781058","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112300433","display_name":"Nana Du","orcid":"https://orcid.org/0009-0003-0689-4279"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nana Du","raw_affiliation_strings":["School of Computer, Northwest University, Xi\u2019an 710100, China","School of Computer, Northwest University, Xi'an 710100, China"],"raw_orcid":"https://orcid.org/0009-0003-0689-4279","affiliations":[{"raw_affiliation_string":"School of Computer, Northwest University, Xi\u2019an 710100, China","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"School of Computer, Northwest University, Xi'an 710100, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054307870","display_name":"Chase Q. Wu","orcid":"https://orcid.org/0000-0002-8218-1209"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chase Wu","raw_affiliation_strings":["Department of Data Science, New Jersey Institute of Technology, Newark, NJ 07102, USA"],"raw_orcid":"https://orcid.org/0000-0002-8218-1209","affiliations":[{"raw_affiliation_string":"Department of Data Science, New Jersey Institute of Technology, Newark, NJ 07102, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003285723","display_name":"Aiqin Hou","orcid":"https://orcid.org/0000-0002-0802-7991"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Aiqin Hou","raw_affiliation_strings":["School of Computer, Northwest University, Xi\u2019an 710100, China","School of Computer, Northwest University, Xi'an 710100, China"],"raw_orcid":"https://orcid.org/0000-0002-0802-7991","affiliations":[{"raw_affiliation_string":"School of Computer, Northwest University, Xi\u2019an 710100, China","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"School of Computer, Northwest University, Xi'an 710100, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028239186","display_name":"Weike Nie","orcid":"https://orcid.org/0000-0003-2092-3083"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weike Nie","raw_affiliation_strings":["School of Computer, Northwest University, Xi\u2019an 710100, China","School of Computer, Northwest University, Xi'an 710100, China"],"raw_orcid":"https://orcid.org/0000-0003-2092-3083","affiliations":[{"raw_affiliation_string":"School of Computer, Northwest University, Xi\u2019an 710100, China","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"School of Computer, Northwest University, Xi'an 710100, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058865881","display_name":"Ruiqi Song","orcid":"https://orcid.org/0000-0001-8617-5474"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Song","raw_affiliation_strings":["School of Computer, Northwest University, Xi\u2019an 710100, China","School of Computer, Northwest University, Xi'an 710100, China"],"raw_orcid":"https://orcid.org/0000-0001-8617-5474","affiliations":[{"raw_affiliation_string":"School of Computer, Northwest University, Xi\u2019an 710100, China","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"School of Computer, Northwest University, Xi'an 710100, China","institution_ids":["https://openalex.org/I37802460"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003285723","https://openalex.org/A5028239186"],"corresponding_institution_ids":["https://openalex.org/I37802460"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.0044,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82143706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"9","issue":"11","first_page":"284","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.4481000006198883,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.4481000006198883,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.0982000008225441,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0697999969124794,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6550999879837036},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.628000020980835},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5250999927520752},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4652999937534332},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.4571000039577484},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.44339999556541443},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.4390999972820282},{"id":"https://openalex.org/keywords/rate-monotonic-scheduling","display_name":"Rate-monotonic scheduling","score":0.4124999940395355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319000005722046},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.628000020980835},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.4390999972820282},{"id":"https://openalex.org/C127456818","wikidata":"https://www.wikidata.org/wiki/Q238879","display_name":"Rate-monotonic scheduling","level":4,"score":0.4124999940395355},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4004000127315521},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.39160001277923584},{"id":"https://openalex.org/C109718341","wikidata":"https://www.wikidata.org/wiki/Q1385229","display_name":"Metaheuristic","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C119948110","wikidata":"https://www.wikidata.org/wiki/Q7858726","display_name":"Two-level scheduling","level":4,"score":0.3637000024318695},{"id":"https://openalex.org/C175893541","wikidata":"https://www.wikidata.org/wiki/Q1196582","display_name":"Round-robin scheduling","level":4,"score":0.336899995803833},{"id":"https://openalex.org/C122141398","wikidata":"https://www.wikidata.org/wiki/Q5456330","display_name":"Fixed-priority pre-emptive scheduling","level":5,"score":0.3294999897480011},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C158336966","wikidata":"https://www.wikidata.org/wiki/Q3074426","display_name":"Flow shop scheduling","level":4,"score":0.2818000018596649},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/bdcc9110284","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9110284","pdf_url":"https://www.mdpi.com/2504-2289/9/11/284/pdf?version=1762781058","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:06753c4bfbfd4c7bbf83035bb363d05d","is_oa":true,"landing_page_url":"https://doaj.org/article/06753c4bfbfd4c7bbf83035bb363d05d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 9, Iss 11, p 284 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc9110284","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9110284","pdf_url":"https://www.mdpi.com/2504-2289/9/11/284/pdf?version=1762781058","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416088820.pdf","grobid_xml":"https://content.openalex.org/works/W4416088820.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"On":[0],"GPU-based":[1],"clusters,":[2],"the":[3,127,134],"training":[4],"workloads":[5,37],"of":[6,35,131,137],"machine":[7],"learning":[8],"(ML)":[9],"models,":[10],"particularly":[11],"neural":[12],"networks":[13],"(NNs),":[14],"are":[15],"often":[16],"structured":[17],"as":[18,45,66,121],"Directed":[19],"Acyclic":[20],"Graphs":[21],"(DAGs)":[22],"and":[23,56,73,89,116,187],"typically":[24],"deployed":[25],"for":[26,40,108,182],"parallel":[27],"execution":[28,46],"across":[29],"heterogeneous":[30],"GPU":[31,52],"resources.":[32],"Efficient":[33],"scheduling":[34,62,109,151,186,199],"these":[36],"is":[38,74],"crucial":[39],"optimizing":[41],"performance":[42],"metrics":[43],"such":[44],"time,":[47],"under":[48],"various":[49],"constraints":[50],"including":[51],"heterogeneity,":[53],"network":[54],"capacity,":[55],"data":[57],"dependencies.":[58],"DAG-structured":[59,183],"ML":[60,165,184],"workload":[61,166,185],"could":[63],"be":[64,77],"modeled":[65],"a":[67,81,103,145],"Nonlinear":[68],"Integer":[69],"Program":[70],"(NIP)":[71],"problem,":[72],"shown":[75],"to":[76,101,120,148,157,193],"NP-complete.":[78],"By":[79],"leveraging":[80],"positive":[82],"correlation":[83],"between":[84],"Scheduling":[85],"Plan":[86],"Distance":[87],"(SPD)":[88],"Finish":[90],"Time":[91,105],"Gap":[92,106],"(FTG)":[93],"identified":[94],"through":[95],"an":[96],"empirical":[97],"study,":[98],"we":[99,143],"propose":[100],"develop":[102],"Running":[104],"Strategy":[107],"based":[110],"on":[111,163,171],"Whale":[112],"Optimization":[113],"Algorithm":[114],"(WOA)":[115],"Reinforcement":[117],"Learning,":[118],"referred":[119],"WORL-RTGS.":[122],"The":[123],"proposed":[124],"method":[125],"integrates":[126],"global":[128],"search":[129],"capabilities":[130],"WOA":[132],"with":[133,196],"adaptive":[135],"decision-making":[136],"Double":[138],"Deep":[139],"Q-Networks":[140],"(DDQN).":[141],"Particularly,":[142],"derive":[144],"novel":[146],"function":[147],"generate":[149],"effective":[150],"plans":[152],"using":[153],"DDQN,":[154],"enhancing":[155],"adaptability":[156],"complex":[158],"DAG":[159],"structures.":[160],"Comprehensive":[161],"evaluations":[162],"practical":[164],"traces":[167],"collected":[168],"from":[169],"Alibaba":[170],"simulated":[172],"GPU-enabled":[173],"platforms":[174],"demonstrate":[175],"that":[176],"WORL-RTGS":[177],"significantly":[178],"improves":[179],"WOA\u2019s":[180],"stability":[181],"reduces":[188],"completion":[189],"time":[190],"by":[191],"up":[192],"66.56%":[194],"compared":[195],"five":[197],"state-of-the-art":[198],"algorithms.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-11-10T00:00:00"}