{"id":"https://openalex.org/W7108211899","doi":"https://doi.org/10.1109/tase.2025.3638318","title":"Consensus-Based Distributed Reinforcement Learning With Primal\u2013Dual Update for Networked Microgrids On-Line Coordination","display_name":"Consensus-Based Distributed Reinforcement Learning With Primal\u2013Dual Update for Networked Microgrids On-Line Coordination","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7108211899","doi":"https://doi.org/10.1109/tase.2025.3638318"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2025.3638318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3638318","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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":null,"display_name":"Gaochen Cui","orcid":"https://orcid.org/0009-0007-3423-3792"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gaochen Cui","raw_affiliation_strings":["CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-3423-3792","affiliations":[{"raw_affiliation_string":"CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qing-Shan Jia","orcid":"https://orcid.org/0000-0002-4683-7215"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Shan Jia","raw_affiliation_strings":["CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4683-7215","affiliations":[{"raw_affiliation_string":"CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaohong Guan","orcid":"https://orcid.org/0000-0002-8826-0362"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Guan","raw_affiliation_strings":["CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8826-0362","affiliations":[{"raw_affiliation_string":"CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiaozhu Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaozhu Zhai","raw_affiliation_strings":["MOEKLINNS Laboratory, Systems Engineering Institute, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOEKLINNS Laboratory, Systems Engineering Institute, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xianping Guo","orcid":"https://orcid.org/0000-0001-6954-5947"},"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":"Xianping Guo","raw_affiliation_strings":["School of Mathematics, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6954-5947","affiliations":[{"raw_affiliation_string":"School of Mathematics, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I74872605","display_name":"China Southern Power Grid (China)","ror":"https://ror.org/03hkh9419","country_code":"CN","type":"company","lineage":["https://openalex.org/I74872605"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Guo","raw_affiliation_strings":["China Southern Power Grid Electric Power Research Institute, Gaungzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Southern Power Grid Electric Power Research Institute, Gaungzhou, Guangdong, China","institution_ids":["https://openalex.org/I74872605"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5693238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"3916","last_page":"3933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10223","display_name":"Microgrid Control and Optimization","score":0.28769999742507935,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10223","display_name":"Microgrid Control and Optimization","score":0.28769999742507935,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12277","display_name":"Frequency Control in Power Systems","score":0.25589999556541443,"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":0.10029999911785126,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6496000289916992},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5663999915122986},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5246000289916992},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.42730000615119934},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41350001096725464},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4129999876022339},{"id":"https://openalex.org/keywords/state-information","display_name":"State information","score":0.40799999237060547},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4025000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6622999906539917},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6496000289916992},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5347999930381775},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5246000289916992},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.45329999923706055},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2985963534","wikidata":"https://www.wikidata.org/wiki/Q7603704","display_name":"State information","level":3,"score":0.40799999237060547},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C544738498","wikidata":"https://www.wikidata.org/wiki/Q861135","display_name":"Distributed generation","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C187633118","wikidata":"https://www.wikidata.org/wiki/Q1317949","display_name":"Economic dispatch","level":4,"score":0.2847000062465668},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C36877392","wikidata":"https://www.wikidata.org/wiki/Q1229571","display_name":"Distributed power","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C188573790","wikidata":"https://www.wikidata.org/wiki/Q12705","display_name":"Renewable energy","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3638318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3638318","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1761450871","display_name":null,"funder_award_id":"62073182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G184828240","display_name":null,"funder_award_id":"62192751","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2671578558","display_name":null,"funder_award_id":"2022YFA1004600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5492808859","display_name":null,"funder_award_id":"62125304","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1509805685","https://openalex.org/W1632710410","https://openalex.org/W1974281287","https://openalex.org/W1998345701","https://openalex.org/W2012586594","https://openalex.org/W2064031160","https://openalex.org/W2090135854","https://openalex.org/W2161270100","https://openalex.org/W2281041351","https://openalex.org/W2590644396","https://openalex.org/W2624900029","https://openalex.org/W2771742090","https://openalex.org/W2787084936","https://openalex.org/W2790306973","https://openalex.org/W2790551314","https://openalex.org/W2884469345","https://openalex.org/W2910525828","https://openalex.org/W2931464100","https://openalex.org/W2952326029","https://openalex.org/W2963649943","https://openalex.org/W2964208174","https://openalex.org/W2979982637","https://openalex.org/W3008970204","https://openalex.org/W3016983759","https://openalex.org/W3035587417","https://openalex.org/W3070953475","https://openalex.org/W3091225957","https://openalex.org/W3097422301","https://openalex.org/W3097500757","https://openalex.org/W3108892825","https://openalex.org/W3173913247","https://openalex.org/W3204810118","https://openalex.org/W3211278672","https://openalex.org/W3211464879","https://openalex.org/W4206497039","https://openalex.org/W4213053159","https://openalex.org/W4214759040","https://openalex.org/W4247352111","https://openalex.org/W4302033506","https://openalex.org/W4319338775","https://openalex.org/W4319998017","https://openalex.org/W4320340663","https://openalex.org/W4360584316","https://openalex.org/W4377695283","https://openalex.org/W4389065366","https://openalex.org/W4393139813","https://openalex.org/W4406857807","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"This":[0,150],"paper":[1],"develops":[2],"a":[3,57,106,118,142],"distributed":[4,114],"reinforcement":[5],"learning":[6],"(RL)":[7],"method":[8,51],"to":[9,27,53,65,79,125,171],"coordinate":[10],"cooperative":[11],"microgrids":[12],"(MGs).":[13],"The":[14],"high":[15],"uncertainty":[16],"of":[17,175],"power":[18],"loads":[19],"and":[20,88,132],"renewable":[21],"energy":[22],"sources":[23],"motivate":[24],"the":[25,32,35,72,81,96,100,113,128,134,161,173,176],"operator":[26],"perform":[28],"real-time":[29],"dispatch.":[30],"On":[31,71],"one":[33],"hand,":[34,74],"existing":[36],"online":[37],"methods":[38],"usually":[39],"utilize":[40],"approximate":[41],"models":[42],"that":[43],"result":[44],"in":[45,69],"intractable":[46],"constraint":[47],"violation.":[48],"A":[49],"common":[50],"is":[52,62,103,122,138],"relax":[54],"it":[55,61],"as":[56,105,156],"chance":[58],"constraint,":[59],"while":[60],"still":[63],"hard":[64],"ensure":[66],"its":[67],"satisfaction":[68],"practice.":[70],"other":[73],"some":[75],"MGs":[76],"may":[77],"hope":[78],"preserve":[80,127],"private":[82,130],"information":[83,131],"on":[84],"their":[85],"local":[86,129,143,162],"costs":[87],"states.":[89],"To":[90],"address":[91],"these":[92],"problems,":[93],"we":[94],"make":[95],"following":[97],"contributions.":[98],"First,":[99],"coordination":[101],"problem":[102],"reformulated":[104],"constrained":[107],"multi-agent":[108],"Markov":[109],"decision":[110],"process.":[111],"Second,":[112],"RL":[115],"algorithm":[116,137],"with":[117],"theoretical":[119],"convergence":[120],"guarantee":[121],"developed.":[123],"Third,":[124],"further":[126],"improve":[133],"performance,":[135],"this":[136],"modified":[139,177],"by":[140],"adding":[141],"feature":[144],"extraction":[145],"module":[146,151,159],"for":[147,160],"each":[148],"agent.":[149],"could":[152],"also":[153],"be":[154],"regarded":[155],"an":[157],"encryption":[158],"state":[163],"information.":[164],"Fourth,":[165],"numerical":[166],"experiments":[167],"are":[168],"carried":[169],"out":[170],"validate":[172],"effectiveness":[174],"algorithm.":[178]},"counts_by_year":[],"updated_date":"2026-02-13T13:36:01.753593","created_date":"2025-12-03T00:00:00"}
