{"id":"https://openalex.org/W4415594509","doi":"https://doi.org/10.1109/tvt.2025.3625594","title":"Federated Reinforcement Learning for Distributed Dependent Task Offloading With Batch Processing in CPU-GPU Heterogeneous MEC","display_name":"Federated Reinforcement Learning for Distributed Dependent Task Offloading With Batch Processing in CPU-GPU Heterogeneous MEC","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415594509","doi":"https://doi.org/10.1109/tvt.2025.3625594"},"language":null,"primary_location":{"id":"doi:10.1109/tvt.2025.3625594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2025.3625594","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"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 Vehicular Technology","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/A5002941898","display_name":"Hualong Huang","orcid":"https://orcid.org/0000-0003-2176-3931"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hualong Huang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0009-2676-140X","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051676438","display_name":"Zhekai Duan","orcid":"https://orcid.org/0000-0002-0283-8419"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Zhekai Duan","raw_affiliation_strings":["University College London, London, U.K","China Telecom Corporation Limited Sichuan Branch, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London, London, U.K","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"China Telecom Corporation Limited Sichuan Branch, China","institution_ids":["https://openalex.org/I4210136246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043425375","display_name":"Wenhan Zhan","orcid":"https://orcid.org/0000-0002-1851-7185"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Zhan","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1851-7185","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770003","display_name":"Geyong Min","orcid":"https://orcid.org/0000-0003-1395-7314"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geyong Min","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K","Department of Computer Science, University of Exeter, Exeter, UK"],"raw_orcid":"https://orcid.org/0000-0003-1395-7314","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]},{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, UK","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051248627","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0002-3210-1653"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-3210-1653","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113157786","display_name":"Yuchuan Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchuan Lei","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","China Telecom Corporation Limited Sichuan Branch, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"China Telecom Corporation Limited Sichuan Branch, China","institution_ids":["https://openalex.org/I4210136246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25642628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":"5","first_page":"8304","last_page":"8319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9595999717712402,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9031999707221985,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6484000086784363},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5964999794960022},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/mobile-edge-computing","display_name":"Mobile edge computing","score":0.49309998750686646},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4546000063419342},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.44510000944137573},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.438400000333786},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.421999990940094},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4115000069141388},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.40230000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264999985694885},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6676999926567078},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6484000086784363},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5964999794960022},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.49309998750686646},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4546000063419342},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.438400000333786},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.421999990940094},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4115000069141388},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.3806999921798706},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.33219999074935913},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3100999891757965},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvt.2025.3625594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2025.3625594","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"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 Vehicular Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"By":[0],"offloading":[1,35],"tasks":[2,41],"to":[3,17,74,89,103,125],"proximal":[4],"edge":[5,8],"servers,":[6],"mobile":[7,24],"computing":[9],"(MEC)":[10],"has":[11],"emerged":[12],"as":[13,56],"a":[14,43,57,63],"promising":[15],"paradigm":[16],"enable":[18],"computation-intensive":[19],"and":[20,36,62,80,98,152],"latency-sensitive":[21],"applications":[22],"on":[23,39,131],"devices.":[25],"This":[26],"paper":[27],"investigates":[28],"the":[29,76,94,145,154,161],"challenging":[30],"problem":[31,53],"of":[32,118,157],"joint":[33],"computation":[34],"resource":[37],"scheduling":[38],"dependent":[40],"in":[42,143],"heterogeneous":[44],"CPU-GPU":[45],"MEC":[46],"environment":[47],"with":[48],"batch":[49],"processing.":[50],"The":[51],"optimization":[52],"is":[54,72,138],"modeled":[55],"Markov":[58],"decision":[59],"process":[60],"(MDP),":[61],"distributed":[64],"Transformer":[65],"based":[66],"Federated":[67],"Soft":[68],"Actor-Critic":[69],"(TFSAC)":[70],"framework":[71],"proposed":[73],"minimize":[75],"overall":[77],"task":[78,95],"latency":[79],"energy":[81],"consumption.":[82],"Graph":[83],"attention":[84],"networks":[85],"(GATs)":[86],"are":[87,101],"leveraged":[88],"extract":[90],"high-dimensional":[91],"features":[92],"from":[93],"dependency":[96],"graph,":[97],"transformer":[99],"encoders":[100],"applied":[102],"learn":[104],"contextual":[105],"relationships":[106],"between":[107],"agents.":[108],"Rather":[109],"than":[110],"simply":[111],"averaging":[112],"weights,":[113],"TFSAC":[114,137],"helps":[115],"selective":[116],"aggregation":[117],"relevant":[119],"knowledge":[120],"during":[121],"federated":[122],"model":[123],"training":[124],"preserve":[126],"agents'":[127],"privacy.":[128],"Extensive":[129],"experiments":[130],"real-world":[132],"trace":[133],"data":[134],"demonstrate":[135],"that":[136],"superior":[139],"over":[140],"other":[141],"benchmarks":[142],"maximizing":[144],"quality":[146],"of-service":[147],"(QoS)":[148],"across":[149],"multiple":[150],"configurations":[151],"enables":[153],"seamless":[155],"onboarding":[156],"new":[158],"agents":[159],"into":[160],"federation.":[162]},"counts_by_year":[],"updated_date":"2026-05-20T06:11:20.791850","created_date":"2025-10-28T00:00:00"}