{"id":"https://openalex.org/W3191550197","doi":"https://doi.org/10.24963/ijcai.2021/401","title":"Multi-Agent Reinforcement Learning for Automated Peer-to-Peer Energy Trading in Double-Side Auction Market","display_name":"Multi-Agent Reinforcement Learning for Automated Peer-to-Peer Energy Trading in Double-Side Auction Market","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3191550197","doi":"https://doi.org/10.24963/ijcai.2021/401","mag":"3191550197"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/401","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/401","pdf_url":"https://www.ijcai.org/proceedings/2021/0401.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0401.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061759570","display_name":"Dawei Qiu","orcid":"https://orcid.org/0000-0003-0497-6089"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dawei Qiu","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658372","display_name":"Jianhong Wang","orcid":"https://orcid.org/0000-0002-7375-8387"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianhong Wang","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650242","display_name":"Junkai Wang","orcid":"https://orcid.org/0000-0001-8033-4163"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junkai Wang","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014643856","display_name":"Goran \u0160trbac","orcid":"https://orcid.org/0000-0001-7421-3947"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Goran Strbac","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":4.1289,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.94724176,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2913","last_page":"2920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":1.0,"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/T10603","display_name":"Smart Grid Energy Management","score":1.0,"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/T10424","display_name":"Electric Power System Optimization","score":0.996999979019165,"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/T11182","display_name":"Auction Theory and Applications","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bidding","display_name":"Bidding","score":0.8312873840332031},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7471350431442261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6574426293373108},{"id":"https://openalex.org/keywords/electricity-market","display_name":"Electricity market","score":0.5814957022666931},{"id":"https://openalex.org/keywords/double-auction","display_name":"Double auction","score":0.571224570274353},{"id":"https://openalex.org/keywords/market-clearing","display_name":"Market clearing","score":0.5417384505271912},{"id":"https://openalex.org/keywords/peer-to-peer","display_name":"Peer-to-peer","score":0.47071048617362976},{"id":"https://openalex.org/keywords/profit","display_name":"Profit (economics)","score":0.4644351899623871},{"id":"https://openalex.org/keywords/market-mechanism","display_name":"Market mechanism","score":0.4616588056087494},{"id":"https://openalex.org/keywords/computational-economics","display_name":"Computational economics","score":0.45635583996772766},{"id":"https://openalex.org/keywords/electricity","display_name":"Electricity","score":0.4545523226261139},{"id":"https://openalex.org/keywords/ebidding","display_name":"Ebidding","score":0.436681866645813},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4177311658859253},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3615439534187317},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.30828726291656494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2581751346588135},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.22784647345542908},{"id":"https://openalex.org/keywords/common-value-auction","display_name":"Common value auction","score":0.22336000204086304},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.15504571795463562},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10835108160972595}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.8312873840332031},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7471350431442261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6574426293373108},{"id":"https://openalex.org/C146733006","wikidata":"https://www.wikidata.org/wiki/Q676081","display_name":"Electricity market","level":3,"score":0.5814957022666931},{"id":"https://openalex.org/C2539976","wikidata":"https://www.wikidata.org/wiki/Q12163285","display_name":"Double auction","level":3,"score":0.571224570274353},{"id":"https://openalex.org/C14981831","wikidata":"https://www.wikidata.org/wiki/Q1713661","display_name":"Market clearing","level":2,"score":0.5417384505271912},{"id":"https://openalex.org/C534932454","wikidata":"https://www.wikidata.org/wiki/Q161410","display_name":"Peer-to-peer","level":2,"score":0.47071048617362976},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.4644351899623871},{"id":"https://openalex.org/C2777137687","wikidata":"https://www.wikidata.org/wiki/Q5730923","display_name":"Market mechanism","level":2,"score":0.4616588056087494},{"id":"https://openalex.org/C2776142066","wikidata":"https://www.wikidata.org/wiki/Q3610415","display_name":"Computational economics","level":2,"score":0.45635583996772766},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.4545523226261139},{"id":"https://openalex.org/C143989560","wikidata":"https://www.wikidata.org/wiki/Q17011617","display_name":"Ebidding","level":3,"score":0.436681866645813},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4177311658859253},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3615439534187317},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.30828726291656494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2581751346588135},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.22784647345542908},{"id":"https://openalex.org/C163239763","wikidata":"https://www.wikidata.org/wiki/Q5153637","display_name":"Common value auction","level":2,"score":0.22336000204086304},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.15504571795463562},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10835108160972595},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2021/401","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/401","pdf_url":"https://www.ijcai.org/proceedings/2021/0401.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/77884806-b6ff-45a8-8f27-11365e3d698d","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/77884806-b6ff-45a8-8f27-11365e3d698d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Qiu, D, Wang, J, Wang, J & Strbac, G 2021, 'Multi-Agent Reinforcement Learning for Automated Peer-to-Peer Energy Trading in Double-Side Auction Market', Paper presented at Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, 19/08/21 - 26/08/21 pp. 2913-2920.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/401","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/401","pdf_url":"https://www.ijcai.org/proceedings/2021/0401.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G135848357","display_name":null,"funder_award_id":"EP/K002252/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2295524898","display_name":null,"funder_award_id":"TS/G002347/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3097466672","display_name":null,"funder_award_id":"EP/L001039/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3460401040","display_name":null,"funder_award_id":"EP/E020798/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5093623366","display_name":"Integrated Development of Low-Carbon Energy Systems (IDLES): A Whole-System Paradigm for Creating a National Strategy","funder_award_id":"EP/R045518/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7376874757","display_name":null,"funder_award_id":"EP/N03466X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3191550197.pdf","grobid_xml":"https://content.openalex.org/works/W3191550197.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1487949011","https://openalex.org/W1528676759","https://openalex.org/W1574326370","https://openalex.org/W1990989674","https://openalex.org/W2029209086","https://openalex.org/W2121863487","https://openalex.org/W2169016885","https://openalex.org/W2173248099","https://openalex.org/W2274443050","https://openalex.org/W2277615321","https://openalex.org/W2313187266","https://openalex.org/W2531399364","https://openalex.org/W2623431351","https://openalex.org/W2736601468","https://openalex.org/W2793859162","https://openalex.org/W2890184754","https://openalex.org/W2892841407","https://openalex.org/W2913739661","https://openalex.org/W2963864421","https://openalex.org/W2965165621","https://openalex.org/W3048775920","https://openalex.org/W4230585469","https://openalex.org/W4299802797","https://openalex.org/W6698611069","https://openalex.org/W6759363029","https://openalex.org/W6791858558"],"related_works":["https://openalex.org/W2788562028","https://openalex.org/W34499488","https://openalex.org/W1532297955","https://openalex.org/W2386087530","https://openalex.org/W3209108050","https://openalex.org/W2148901751","https://openalex.org/W2177969722","https://openalex.org/W2128724203","https://openalex.org/W4254364468","https://openalex.org/W4251160564"],"abstract_inverted_index":{"With":[0],"increasing":[1],"prosumers":[2,51,66,156],"employed":[3],"with":[4,172],"distributed":[5,54],"energy":[6,10,44,163],"resources":[7],"(DER),":[8],"advanced":[9],"management":[11],"has":[12],"become":[13],"increasingly":[14],"important.":[15],"To":[16,56],"this":[17,105,108,112],"end,":[18],"integrating":[19],"demand-side":[20],"DER":[21],"into":[22],"electricity":[23,64,168],"market":[24,36,83,144,169],"is":[25,37,84,128],"a":[26,40,53,62,115],"trend":[27],"for":[28,147],"future":[29],"smart":[30],"grids.":[31],"The":[32,151],"double-side":[33],"auction":[34],"(DA)":[35],"viewed":[38],"as":[39,68,114],"promising":[41],"peer-to-peer":[42],"(P2P)":[43],"trading":[45,77,164,171],"mechanism":[46],"that":[47,127,154],"enables":[48],"interactions":[49],"among":[50],"in":[52,61,107,161],"manner.":[55],"achieve":[57],"the":[58,80,97,102,135,142,166,173,182,189],"maximum":[59],"profit":[60],"dynamic":[63],"market,":[65],"act":[67],"price":[69],"makers":[70],"to":[71,86,91],"simultaneously":[72],"optimize":[73],"their":[74],"operations":[75],"and":[76,96,121,139,176,188,197],"strategies.":[78],"However,":[79],"traditional":[81,183],"DA":[82,143],"difficult":[85],"be":[87],"explicitly":[88],"modelled":[89],"due":[90],"its":[92],"complex":[93],"clearing":[94],"algorithm":[95,124],"stochastic":[98],"bidding":[99],"behaviors":[100],"of":[101],"participants.":[103],"For":[104],"reason,":[106],"paper":[109],"we":[110],"model":[111],"task":[113],"multi-agent":[116],"reinforcement":[117],"learning":[118],"(MARL)":[119],"problem":[120],"propose":[122],"an":[123],"called":[125],"DA-MADDPG":[126,178],"modified":[129],"based":[130],"on":[131],"MADDPG":[132],"by":[133],"abstracting":[134],"other":[136,190],"agents\u2019":[137],"observations":[138],"actions":[140],"through":[141],"public":[145],"information":[146],"each":[148],"agent\u2019s":[149],"critic.":[150],"experiments":[152],"show":[153],"1)":[155],"obtain":[157],"more":[158],"economic":[159],"benefits":[160],"P2P":[162],"w.r.t.":[165],"conventional":[167],"independently":[170],"utility":[174],"company;":[175],"2)":[177],"performs":[179],"better":[180],"than":[181],"Zero":[184],"Intelligence":[185],"(ZI)":[186],"strategy":[187],"MARL":[191],"algorithms,":[192],"e.g.,":[193],"IQL,":[194],"IDDPG,":[195],"IPPO":[196],"MADDPG.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}