{"id":"https://openalex.org/W3174056649","doi":"https://doi.org/10.1109/tcyb.2021.3082639","title":"Distributed <i>Q</i>-Learning Algorithm for Dynamic Resource Allocation With Unknown Objective Functions and Application to Microgrid","display_name":"Distributed <i>Q</i>-Learning Algorithm for Dynamic Resource Allocation With Unknown Objective Functions and Application to Microgrid","publication_year":2021,"publication_date":"2021-06-24","ids":{"openalex":"https://openalex.org/W3174056649","doi":"https://doi.org/10.1109/tcyb.2021.3082639","mag":"3174056649","pmid":"https://pubmed.ncbi.nlm.nih.gov/34166215"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2021.3082639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3082639","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100705693","display_name":"Pengcheng Dai","orcid":"https://orcid.org/0000-0003-1455-7216"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Dai","raw_affiliation_strings":["Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1455-7216","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627758","display_name":"Wenwu Yu","orcid":"https://orcid.org/0000-0003-3755-179X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Yu","raw_affiliation_strings":["Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038398834","display_name":"Duxin Chen","orcid":"https://orcid.org/0000-0002-3194-2258"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duxin Chen","raw_affiliation_strings":["Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3194-2258","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":1.6887,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.83935806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"52","issue":"11","first_page":"12340","last_page":"12350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","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/T10603","display_name":"Smart Grid Energy Management","score":0.9930999875068665,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/resource-allocation","display_name":"Resource allocation","score":0.6402108669281006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6081171035766602},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5922221541404724},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5779287815093994},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5093163251876831},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.503424346446991},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.45564162731170654},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.4462687075138092},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44382500648498535},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.4271460771560669},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3864002525806427},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3473578691482544},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2057490348815918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16863328218460083},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.08221942186355591}],"concepts":[{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6402108669281006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6081171035766602},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5922221541404724},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5779287815093994},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5093163251876831},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.503424346446991},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.45564162731170654},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.4462687075138092},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44382500648498535},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4271460771560669},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3864002525806427},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3473578691482544},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2057490348815918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16863328218460083},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.08221942186355591},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2021.3082639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3082639","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:34166215","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34166215","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2027255153","display_name":null,"funder_award_id":"2242019K40111","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4949000581","display_name":null,"funder_award_id":"62073076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5787787241","display_name":null,"funder_award_id":"61903079","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1571403844","https://openalex.org/W2022255443","https://openalex.org/W2044212084","https://openalex.org/W2057929279","https://openalex.org/W2094336028","https://openalex.org/W2114791779","https://openalex.org/W2145339207","https://openalex.org/W2154645018","https://openalex.org/W2164642931","https://openalex.org/W2215067230","https://openalex.org/W2273484141","https://openalex.org/W2286179039","https://openalex.org/W2293710996","https://openalex.org/W2324861975","https://openalex.org/W2339452580","https://openalex.org/W2342863306","https://openalex.org/W2345097924","https://openalex.org/W2611497108","https://openalex.org/W2726938673","https://openalex.org/W2753220394","https://openalex.org/W2766228189","https://openalex.org/W2769909638","https://openalex.org/W2796434525","https://openalex.org/W2801053168","https://openalex.org/W2954968417","https://openalex.org/W2963649943","https://openalex.org/W2966633400","https://openalex.org/W2986487687","https://openalex.org/W4213362702","https://openalex.org/W4214717370","https://openalex.org/W4232896595","https://openalex.org/W4298857966","https://openalex.org/W6633472260"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W1531601525","https://openalex.org/W2132793452","https://openalex.org/W4300046793","https://openalex.org/W2963702538","https://openalex.org/W2037120413","https://openalex.org/W3135071881"],"abstract_inverted_index":{"Dynamic":[0],"resource":[1,11,66,120],"allocation":[2,97],"problem":[3],"(DRAP)":[4],"with":[5,46,60,114],"unknown":[6,10,61,65,115,119],"cost":[7,30,62,116],"functions":[8,13,31,63,68,117,122],"and":[9,64,118,142],"transition":[12,67,121],"is":[14,24,76,136,169,178],"studied":[15],"in":[16,36],"this":[17],"article.":[18],"The":[19],"goal":[20],"of":[21,29,83,153,157,167,179,201],"the":[22,27,80,87,102,112,150,154,164,184,189,199,202],"agents":[23,84,168],"to":[25,182,197],"minimize":[26],"sum":[28],"over":[32],"given":[33],"time":[34,106,174],"periods":[35],"a":[37,53,95,130],"distributed":[38,54,88,132,143],"way,":[39],"that":[40,79,99,149,163],"is,":[41,100],"by":[42,86],"only":[43],"exchanging":[44],"information":[45],"their":[47],"neighboring":[48],"agents.":[49],"First,":[50],"we":[51,109],"propose":[52],"Q":[55,89,133],"-learning":[56,90,134],"algorithm":[57,91,135],"for":[58],"DRAP":[59,113],"under":[69,123],"discrete":[70],"local":[71,125,155],"feasibility":[72,126],"constraints":[73,103,127],"(DLFCs).":[74],"It":[75,145],"theoretically":[77],"proved":[78],"joint":[81,165],"policy":[82,156,166,187],"produced":[85],"can":[92,160],"always":[93],"provide":[94],"feasible":[96],"(FA),":[98],"satisfying":[101],"at":[104,172],"each":[105,158,173],"period.":[107,175],"Then,":[108],"also":[110,161],"study":[111],"continuous":[124],"(CLFCs),":[128],"where":[129],"novel":[131],"proposed":[137,203],"based":[138],"on":[139],"function":[140],"approximation":[141],"optimization.":[144],"should":[146],"be":[147],"noted":[148],"update":[151],"rule":[152],"agent":[159],"ensure":[162],"an":[170],"FA":[171],"Such":[176],"property":[177],"vital":[180],"importance":[181],"execute":[183],"\u03b5":[185],"-greedy":[186],"during":[188],"whole":[190],"training":[191],"process.":[192],"Finally,":[193],"simulations":[194],"are":[195],"presented":[196],"demonstrate":[198],"effectiveness":[200],"algorithms.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2021-07-05T00:00:00"}
