{"id":"https://openalex.org/W7124846070","doi":"https://doi.org/10.1109/cloudcom67567.2025.11331504","title":"Cooperative Resource Optimization in Wireless Multi-UAV Networks: A Teammate-Advisory Reinforcement Learning Approach","display_name":"Cooperative Resource Optimization in Wireless Multi-UAV Networks: A Teammate-Advisory Reinforcement Learning Approach","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W7124846070","doi":"https://doi.org/10.1109/cloudcom67567.2025.11331504"},"language":null,"primary_location":{"id":"doi:10.1109/cloudcom67567.2025.11331504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom67567.2025.11331504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","raw_type":"proceedings-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/A5123392280","display_name":"Shuai Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuai Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407591","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0001-9727-5569"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123439378","display_name":"Xuehe Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehe Wang","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-sen University,Zhuhai,Guangdong"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University,Zhuhai,Guangdong","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080171254","display_name":"Long Shi","orcid":"https://orcid.org/0000-0001-6124-5173"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Shi","raw_affiliation_strings":["School of Electronic and Optical Engineering, Nanjing University of Science and Technology,Nanjing"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Optical Engineering, Nanjing University of Science and Technology,Nanjing","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5123392280"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77626662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.9828000068664551,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11133","display_name":"UAV Applications and Optimization","score":0.9828000068664551,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0027000000700354576,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.0012000000569969416,"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/markov-decision-process","display_name":"Markov decision process","score":0.7476999759674072},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6506999731063843},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.6363999843597412},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5995000004768372},{"id":"https://openalex.org/keywords/telecommunications-link","display_name":"Telecommunications link","score":0.5860999822616577},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5730000138282776},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5406000018119812},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.45649999380111694},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44040000438690186},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.43369999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241999745368958},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7476999759674072},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6506999731063843},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5995000004768372},{"id":"https://openalex.org/C138660444","wikidata":"https://www.wikidata.org/wiki/Q5607897","display_name":"Telecommunications link","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5730000138282776},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5432000160217285},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5406000018119812},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C153646914","wikidata":"https://www.wikidata.org/wiki/Q535695","display_name":"Cellular network","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C56685638","wikidata":"https://www.wikidata.org/wiki/Q2300474","display_name":"Power control","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C65422117","wikidata":"https://www.wikidata.org/wiki/Q358527","display_name":"Transmitter power output","level":4,"score":0.26840001344680786},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C187633118","wikidata":"https://www.wikidata.org/wiki/Q1317949","display_name":"Economic dispatch","level":4,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cloudcom67567.2025.11331504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom67567.2025.11331504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5170955061912537,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G3051548928","display_name":null,"funder_award_id":"62202232,62206320,62371239","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2963035841","https://openalex.org/W2964023906","https://openalex.org/W3193428479","https://openalex.org/W4285107918","https://openalex.org/W4285247160","https://openalex.org/W4294311006","https://openalex.org/W4313476493","https://openalex.org/W4384028570","https://openalex.org/W4391093022","https://openalex.org/W4391547575","https://openalex.org/W4391951745","https://openalex.org/W4400071229","https://openalex.org/W4401070237","https://openalex.org/W4401070502","https://openalex.org/W4401387154","https://openalex.org/W4401452427","https://openalex.org/W4405303679","https://openalex.org/W4407212669","https://openalex.org/W4407937610","https://openalex.org/W4408399569","https://openalex.org/W4409640935","https://openalex.org/W4409723478"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,45,50,60,75,90,98,105,128,135,140,167,182,189,204],"resource":[2,32,62],"constrained":[3],"unmanned":[4],"aerial":[5],"vehicle":[6],"(UAV)":[7],"assisted":[8],"communication":[9,23,47,145,160,205],"networks,":[10],"a":[11,28,36,65,112,156],"major":[12],"challenge":[13],"is":[14],"how":[15],"to":[16,49,88,138],"achieve":[17],"efficient":[18],"multi-UAV":[19,37],"cooperation":[20,163],"with":[21,54,166],"minimal":[22],"overhead.":[24,146,206],"This":[25,125],"paper":[26],"proposes":[27],"teammate":[29,113],"modeling":[30,114],"based":[31,115],"allocation":[33,63],"scheme":[34],"for":[35],"network,":[38],"where":[39],"multiple":[40],"co-channel":[41],"UAVs":[42,76],"cooperatively":[43],"provide":[44],"downlink":[46],"services":[48],"ground":[51],"users":[52],"(GUs)":[53],"temporal-correlated":[55],"task":[56],"demands.":[57],"We":[58],"formulate":[59],"cooperative":[61],"as":[64],"decentralized":[66],"partially":[67,106],"observable":[68,107],"Markov":[69],"decision":[70],"process":[71],"(Dec-POMDP),":[72],"in":[73,194],"which":[74],"jointly":[77],"optimize":[78],"their":[79],"trajectory":[80],"planning,":[81],"power":[82],"allocation,":[83],"and":[84,162,177],"user":[85],"association":[86],"policies":[87],"maximize":[89],"system's":[91],"cumulative":[92,197],"achievable":[93],"sum":[94,198],"rate.":[95],"To":[96],"address":[97],"non-stationarity":[99],"introduced":[100],"by":[101],"parallel":[102],"decision-making":[103],"among":[104,134],"UAV":[108,136],"agents,":[109],"we":[110],"propose":[111],"multi-agent":[116],"reinforcement":[117],"learning":[118],"algorithm,":[119],"named":[120],"teammate-advisory":[121],"advantage":[122],"actor-critic":[123],"(TAA2C).":[124],"algorithm":[126,154],"facilitates":[127],"exchange":[129],"of":[130,170,196,203],"low-dimensional":[131],"advisory":[132],"information":[133],"agents":[137],"enhance":[139],"inter-Uavcollaboration":[141],"while":[142],"maintaining":[143],"low":[144],"Simulation":[147],"results":[148],"demonstrate":[149],"that,":[150],"our":[151],"proposed":[152],"TAA2C":[153,186],"achieves":[155],"better":[157],"trade-off":[158],"between":[159],"overhead":[161],"efficiency,":[164],"compared":[165],"baseline":[168,192],"algorithms":[169],"Independent":[171],"A2C":[172,175,179],"(IA2C),":[173],"Federated":[174],"(FA2C),":[176],"Multi-Agent":[178],"(MAA2C).":[180],"As":[181],"network":[183],"scale":[184],"increases,":[185],"even":[187],"surpasses":[188],"centralized":[190],"training":[191],"MAA2C":[193],"terms":[195],"rate,":[199],"at":[200],"only":[201],"10%":[202]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-21T00:00:00"}