{"id":"https://openalex.org/W4285291487","doi":"https://doi.org/10.1109/tii.2022.3183802","title":"Reward Shaping-Based Actor\u2013Critic Deep Reinforcement Learning for Residential Energy Management","display_name":"Reward Shaping-Based Actor\u2013Critic Deep Reinforcement Learning for Residential Energy Management","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4285291487","doi":"https://doi.org/10.1109/tii.2022.3183802"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2022.3183802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2022.3183802","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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/A5087579932","display_name":"Renzhi Lu","orcid":"https://orcid.org/0000-0001-6845-1711"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]},{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]},{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]},{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renzhi Lu","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, China","Key Laboratory of Industrial Internet of Things and Networked Control, Chongqing University of Posts and Telecommunications, Chongqing, China","Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China","State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6845-1711","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I43922553"]},{"raw_affiliation_string":"Key Laboratory of Industrial Internet of Things and Networked Control, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]},{"raw_affiliation_string":"State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing, China","institution_ids":["https://openalex.org/I153473198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018312985","display_name":"Zhenyu Jiang","orcid":"https://orcid.org/0000-0001-9267-6996"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Jiang","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049269026","display_name":"Huaming Wu","orcid":"https://orcid.org/0000-0002-4761-9973"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaming Wu","raw_affiliation_strings":["Center for Applied Mathematics, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-4761-9973","affiliations":[{"raw_affiliation_string":"Center for Applied Mathematics, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066043485","display_name":"Yuemin Ding","orcid":"https://orcid.org/0000-0001-7697-2197"},"institutions":[{"id":"https://openalex.org/I88155538","display_name":"Universidad de Navarra","ror":"https://ror.org/02rxc7m23","country_code":"ES","type":"education","lineage":["https://openalex.org/I88155538"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Yuemin Ding","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Navarra, San Sebastian, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7697-2197","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Navarra, San Sebastian, Spain","institution_ids":["https://openalex.org/I88155538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391459","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-2493-1032"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China","School of Control Science and Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-2493-1032","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Control Science and Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hai-Tao Zhang","orcid":"https://orcid.org/0000-0002-8819-8829"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai-Tao Zhang","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","State Key Lab of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-8819-8829","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"State Key Lab of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8853,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.97467651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"19","issue":"3","first_page":"2662","last_page":"2673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11954","display_name":"Energy Efficiency and Management","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8902953863143921},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7508364915847778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6508466005325317},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.6008412837982178},{"id":"https://openalex.org/keywords/energy-management","display_name":"Energy management","score":0.5812889337539673},{"id":"https://openalex.org/keywords/electricity","display_name":"Electricity","score":0.5658088326454163},{"id":"https://openalex.org/keywords/electricity-pricing","display_name":"Electricity pricing","score":0.5072376728057861},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48621025681495667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45808613300323486},{"id":"https://openalex.org/keywords/demand-response","display_name":"Demand response","score":0.45238494873046875},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.45224297046661377},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44127795100212097},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.4394184350967407},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.3358737528324127},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26759058237075806},{"id":"https://openalex.org/keywords/electricity-market","display_name":"Electricity market","score":0.18819716572761536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8902953863143921},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7508364915847778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6508466005325317},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.6008412837982178},{"id":"https://openalex.org/C7817414","wikidata":"https://www.wikidata.org/wiki/Q1779504","display_name":"Energy management","level":3,"score":0.5812889337539673},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.5658088326454163},{"id":"https://openalex.org/C2779280359","wikidata":"https://www.wikidata.org/wiki/Q870344","display_name":"Electricity pricing","level":4,"score":0.5072376728057861},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48621025681495667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45808613300323486},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.45238494873046875},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.45224297046661377},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44127795100212097},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.4394184350967407},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3358737528324127},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26759058237075806},{"id":"https://openalex.org/C146733006","wikidata":"https://www.wikidata.org/wiki/Q676081","display_name":"Electricity market","level":3,"score":0.18819716572761536},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2022.3183802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2022.3183802","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G1462086917","display_name":null,"funder_award_id":"2022SMECP03","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G234363305","display_name":null,"funder_award_id":"62003143","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2867432779","display_name":null,"funder_award_id":"LAPS21006","funder_id":"https://openalex.org/F4320327677","funder_display_name":"State Key Laboratory Of Alternate Electrical Power System With Renewable Energy Sources"},{"id":"https://openalex.org/G372449780","display_name":null,"funder_award_id":"U2141235","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3814470461","display_name":null,"funder_award_id":"HUST 2020kfyXJJS084","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327677","display_name":"State Key Laboratory Of Alternate Electrical Power System With Renewable Energy Sources","ror":null},{"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":35,"referenced_works":["https://openalex.org/W2024998154","https://openalex.org/W2059049926","https://openalex.org/W2277948250","https://openalex.org/W2615310036","https://openalex.org/W2780336025","https://openalex.org/W2788455270","https://openalex.org/W2795276745","https://openalex.org/W2806493089","https://openalex.org/W2885580746","https://openalex.org/W2904635416","https://openalex.org/W2926295867","https://openalex.org/W2963317745","https://openalex.org/W2973229164","https://openalex.org/W3000626617","https://openalex.org/W3005355833","https://openalex.org/W3006765757","https://openalex.org/W3007687131","https://openalex.org/W3010036076","https://openalex.org/W3015872947","https://openalex.org/W3023506947","https://openalex.org/W3031018183","https://openalex.org/W3037631072","https://openalex.org/W3038624044","https://openalex.org/W3040994746","https://openalex.org/W3088616480","https://openalex.org/W3097281440","https://openalex.org/W3106066138","https://openalex.org/W3167696941","https://openalex.org/W3170196437","https://openalex.org/W3194824107","https://openalex.org/W3202758697","https://openalex.org/W3207258242","https://openalex.org/W6638088447","https://openalex.org/W6738796088","https://openalex.org/W6757324869"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W4281812492","https://openalex.org/W3105579180","https://openalex.org/W2970347269","https://openalex.org/W3167472281","https://openalex.org/W4400868993","https://openalex.org/W2146763310"],"abstract_inverted_index":{"Residential":[0],"energy":[1,9,60,75,161],"consumption":[2,61,162],"continues":[3],"to":[4,12,25,30,56,95,157,172],"climb":[5],"steadily,":[6],"requiring":[7],"intelligent":[8],"management":[10,76],"strategies":[11,28],"reduce":[13],"power":[14],"system":[15],"pressures":[16],"and":[17,39,78,106,125,130,150,153,198],"residential":[18,59,80],"electricity":[19,35,132],"bills.":[20],"However,":[21],"it":[22],"is":[23,82,134,143],"challenging":[24],"design":[26],"such":[27],"due":[29],"the":[31,58,67,71,74,97,110,116,120,131,148,159,174,177,184],"random":[32,105],"nature":[33],"of":[34,176,193],"pricing,":[36],"appliance":[37],"demand,":[38],"user":[40],"behavior.":[41],"This":[42],"article":[43],"presents":[44],"a":[45,85,91,137],"novel":[46],"reward":[47,126],"shaping":[48],"(RS)-based":[49],"actor\u2013critic":[50],"deep":[51],"reinforcement":[52],"learning":[53,194],"(ACDRL)":[54],"algorithm":[55,142,186],"manage":[57],"profile":[62],"with":[63],"limited":[64],"information":[65],"about":[66],"uncertain":[68],"factors.":[69],"Specifically,":[70],"interaction":[72],"between":[73],"center":[77],"various":[79],"loads":[81],"modeled":[83],"as":[84,136],"Markov":[86],"decision":[87],"process":[88],"that":[89,183],"provides":[90],"fundamental":[92],"mathematical":[93],"framework":[94],"represent":[96],"decision-making":[98],"in":[99,114,191],"situations":[100],"where":[101],"outcomes":[102],"are":[103,127,170],"partially":[104,107],"influenced":[108],"by":[109],"decision-maker":[111],"control":[112],"signals,":[113],"which":[115],"key":[117],"elements":[118],"containing":[119],"agent,":[121],"environment,":[122],"state,":[123],"action,":[124],"carefully":[128],"designed,":[129],"price":[133],"considered":[135],"stochastic":[138],"variable.":[139],"An":[140],"RS-ACDRL":[141],"then":[144],"developed,":[145],"incorporating":[146],"both":[147],"actor":[149],"critic":[151],"network":[152],"an":[154],"RS":[155],"mechanism,":[156],"learn":[158],"optimal":[160],"schedules.":[163],"Several":[164],"case":[165],"studies":[166],"involving":[167],"real-world":[168],"data":[169],"conducted":[171],"evaluate":[173],"performance":[175],"proposed":[178,185],"algorithm.":[179],"Numerical":[180],"results":[181],"demonstrate":[182],"outperforms":[187],"state-of-the-art":[188],"RL":[189],"methods":[190],"terms":[192],"speed,":[195],"solution":[196],"optimality,":[197],"cost":[199],"reduction.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}