{"id":"https://openalex.org/W4285254953","doi":"https://doi.org/10.1109/tsg.2022.3179567","title":"An Assessment of Multistage Reward Function Design for Deep Reinforcement Learning-Based Microgrid Energy Management","display_name":"An Assessment of Multistage Reward Function Design for Deep Reinforcement Learning-Based Microgrid Energy Management","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4285254953","doi":"https://doi.org/10.1109/tsg.2022.3179567"},"language":"en","primary_location":{"id":"doi:10.1109/tsg.2022.3179567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsg.2022.3179567","pdf_url":null,"source":{"id":"https://openalex.org/S59604973","display_name":"IEEE Transactions on Smart Grid","issn_l":"1949-3053","issn":["1949-3053","1949-3061"],"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 Smart Grid","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/A5000520484","display_name":"Hui Hwang Goh","orcid":"https://orcid.org/0000-0003-3220-7631"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Hwang Goh","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0000-0003-3220-7631","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103158590","display_name":"Yifeng Huang","orcid":"https://orcid.org/0000-0001-8548-630X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Huang","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031444979","display_name":"Chee Shen Lim","orcid":"https://orcid.org/0000-0003-3033-4688"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chee Shen Lim","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3033-4688","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416390","display_name":"Dongdong Zhang","orcid":"https://orcid.org/0000-0003-4332-3873"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Zhang","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387559","display_name":"Hui Liu","orcid":"https://orcid.org/0000-0002-2676-9171"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739112","display_name":"Wei Dai","orcid":"https://orcid.org/0000-0002-8581-8711"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Dai","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070104049","display_name":"Tonni Agustiono Kurniawan","orcid":"https://orcid.org/0000-0003-1362-6339"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tonni Agustiono Kurniawan","raw_affiliation_strings":["Key Laboratory of the Coastal and Wetland Ecosystems, Ministry of Education, College of the Environment and Ecology, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0003-1362-6339","affiliations":[{"raw_affiliation_string":"Key Laboratory of the Coastal and Wetland Ecosystems, Ministry of Education, College of the Environment and Ecology, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054429264","display_name":"Saifur Rahman","orcid":"https://orcid.org/0000-0001-6226-8406"},"institutions":[{"id":"https://openalex.org/I4210134033","display_name":"Advanced Research Institute","ror":"https://ror.org/03e1yhr47","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210134033"]},{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saifur Rahman","raw_affiliation_strings":["Department of Advanced Research Institute, Virginia Polytechnic Institute and State University, Arlington, VA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6226-8406","affiliations":[{"raw_affiliation_string":"Department of Advanced Research Institute, Virginia Polytechnic Institute and State University, Arlington, VA, USA","institution_ids":["https://openalex.org/I4210134033","https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.9757,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.98351681,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"13","issue":"6","first_page":"4300","last_page":"4311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10223","display_name":"Microgrid Control and Optimization","score":0.9998000264167786,"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":0.9998000264167786,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9993000030517578,"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8144384622573853},{"id":"https://openalex.org/keywords/microgrid","display_name":"Microgrid","score":0.8032686710357666},{"id":"https://openalex.org/keywords/energy-management","display_name":"Energy management","score":0.5726588368415833},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5693984031677246},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5578730702400208},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5290020108222961},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5027875900268555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3704555630683899},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.35475456714630127},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3434460461139679},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.30035164952278137},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10337063670158386}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8144384622573853},{"id":"https://openalex.org/C2776784348","wikidata":"https://www.wikidata.org/wiki/Q5762595","display_name":"Microgrid","level":3,"score":0.8032686710357666},{"id":"https://openalex.org/C7817414","wikidata":"https://www.wikidata.org/wiki/Q1779504","display_name":"Energy management","level":3,"score":0.5726588368415833},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5693984031677246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5578730702400208},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5290020108222961},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5027875900268555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3704555630683899},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.35475456714630127},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3434460461139679},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30035164952278137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10337063670158386},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/tsg.2022.3179567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsg.2022.3179567","pdf_url":null,"source":{"id":"https://openalex.org/S59604973","display_name":"IEEE Transactions on Smart Grid","issn_l":"1949-3053","issn":["1949-3053","1949-3061"],"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 Smart Grid","raw_type":"journal-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/118472","is_oa":false,"landing_page_url":"https://hdl.handle.net/10919/118472","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article - Refereed"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8700000047683716}],"awards":[{"id":"https://openalex.org/G3633993224","display_name":null,"funder_award_id":"A30 20051008","funder_id":"https://openalex.org/F4320327522","funder_display_name":"Guangxi University"},{"id":"https://openalex.org/G8372840296","display_name":null,"funder_award_id":"2019YFE0118000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320327522","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1965539925","https://openalex.org/W1976377787","https://openalex.org/W1980364886","https://openalex.org/W2022571395","https://openalex.org/W2024998154","https://openalex.org/W2036778492","https://openalex.org/W2080048739","https://openalex.org/W2125612430","https://openalex.org/W2127761430","https://openalex.org/W2209308027","https://openalex.org/W2322860138","https://openalex.org/W2341328782","https://openalex.org/W2343217767","https://openalex.org/W2525707554","https://openalex.org/W2726187156","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2884320687","https://openalex.org/W2899639849","https://openalex.org/W2926295867","https://openalex.org/W2949816299","https://openalex.org/W2953334758","https://openalex.org/W2961479565","https://openalex.org/W2963317745","https://openalex.org/W2963723202","https://openalex.org/W2963864421","https://openalex.org/W2974854012","https://openalex.org/W2990466689","https://openalex.org/W3005335721","https://openalex.org/W3092554980","https://openalex.org/W3095430690","https://openalex.org/W3105693230","https://openalex.org/W3108765643","https://openalex.org/W3116243680","https://openalex.org/W3150570724","https://openalex.org/W3156714352","https://openalex.org/W3170196437","https://openalex.org/W3171527702","https://openalex.org/W3183512612","https://openalex.org/W3202048231","https://openalex.org/W4214717370","https://openalex.org/W4232284745","https://openalex.org/W4288314327","https://openalex.org/W6683001934","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6740222838","https://openalex.org/W6763578722"],"related_works":["https://openalex.org/W1574359403","https://openalex.org/W2057975886","https://openalex.org/W4308700935","https://openalex.org/W4210780382","https://openalex.org/W2333017163","https://openalex.org/W2347673489","https://openalex.org/W2964937504","https://openalex.org/W2169268775","https://openalex.org/W1590827513","https://openalex.org/W2371966636"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,105],"based":[2],"energy":[3,79,88,157],"management":[4,80,158],"strategy":[5],"has":[6,179],"been":[7,153],"an":[8],"active":[9],"research":[10],"subject":[11],"in":[12,50,75,99,145,160,174],"the":[13,19,24,36,48,60,70,87,120,129,133,138,141,150,175,180],"past":[14],"few":[15],"years.":[16],"Different":[17],"from":[18,72],"baseline":[20],"reward":[21,31,95],"function":[22,96],"(BRF),":[23],"work":[25],"proposes":[26],"and":[27,39,44,92,112,136,167],"investigates":[28],"a":[29,54],"multi-stage":[30],"mechanism":[32],"(MSRM)":[33],"that":[34,124],"scores":[35],"agent\u2019s":[37,61],"step":[38],"final":[40],"performance":[41,81],"during":[42],"training":[43,62],"returns":[45],"it":[46],"to":[47,68,127],"agent":[49,71,142],"real":[51],"time":[52],"as":[53],"reward.":[55],"MSRM":[56,125],"will":[57],"also":[58],"improve":[59,128],"through":[63],"expert":[64],"intervention":[65],"which":[66],"aims":[67],"prevent":[69],"being":[73,143],"trapped":[74,144],"sub-optimal":[76],"strategies.":[77,147],"The":[78,94,170],"considered":[82],"by":[83],"MSRM-based":[84],"algorithm":[85],"includes":[86],"balance,":[89],"economic":[90],"cost,":[91,164],"reliability.":[93],"is":[97],"assessed":[98,154],"conjunction":[100],"with":[101,118,155],"two":[102],"deep":[103,108],"reinforcement":[104],"algorithms:":[106],"double":[107],"Q-learning":[109],"network":[110],"(DDQN)":[111],"policy":[113],"gradient":[114],"(PG).":[115],"Upon":[116],"benchmarking":[117],"BRF,":[119],"numerical":[121],"simulation":[122],"shows":[123],"tends":[126],"convergence":[130],"characteristic,":[131],"reduce":[132,137],"explained":[134],"variance,":[135],"tendency":[139],"of":[140,162],"suboptimal":[146],"In":[148],"addition,":[149],"methods":[151],"have":[152],"MPC-based":[156],"strategies":[159],"terms":[161],"relative":[163],"self-balancing":[165],"rate,":[166],"computational":[168],"time.":[169],"assessment":[171],"concludes":[172],"that,":[173],"given":[176],"context,":[177],"PG-MSRM":[178],"best":[181],"overall":[182],"performance.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}