{"id":"https://openalex.org/W3106519373","doi":"https://doi.org/10.1109/isgt-europe47291.2020.9248800","title":"Benchmarking reinforcement learning algorithms for demand response applications","display_name":"Benchmarking reinforcement learning algorithms for demand response applications","publication_year":2020,"publication_date":"2020-10-26","ids":{"openalex":"https://openalex.org/W3106519373","doi":"https://doi.org/10.1109/isgt-europe47291.2020.9248800","mag":"3106519373"},"language":"en","primary_location":{"id":"doi:10.1109/isgt-europe47291.2020.9248800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isgt-europe47291.2020.9248800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe)","raw_type":"proceedings-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/A5057621400","display_name":"Brida V. Mbuwir","orcid":"https://orcid.org/0000-0001-5523-7783"},"institutions":[{"id":"https://openalex.org/I68522396","display_name":"Flemish Institute for Technological Research","ror":"https://ror.org/04gq0w522","country_code":"BE","type":"facility","lineage":["https://openalex.org/I68522396"]},{"id":"https://openalex.org/I89206478","display_name":"Engie (Belgium)","ror":"https://ror.org/00c97z041","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210124897","https://openalex.org/I89206478"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Brida V. Mbuwir","raw_affiliation_strings":["AMO, Genk, Belgium","ESAT/ELECTA, Leuven, Belgium","AMO, Flemish Institute for Technological Research (VITO), Mol, Belgium"],"affiliations":[{"raw_affiliation_string":"AMO, Genk, Belgium","institution_ids":[]},{"raw_affiliation_string":"ESAT/ELECTA, Leuven, Belgium","institution_ids":["https://openalex.org/I89206478"]},{"raw_affiliation_string":"AMO, Flemish Institute for Technological Research (VITO), Mol, Belgium","institution_ids":["https://openalex.org/I68522396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018961360","display_name":"Carlo Manna","orcid":"https://orcid.org/0000-0001-8815-1628"},"institutions":[{"id":"https://openalex.org/I68522396","display_name":"Flemish Institute for Technological Research","ror":"https://ror.org/04gq0w522","country_code":"BE","type":"facility","lineage":["https://openalex.org/I68522396"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Carlo Manna","raw_affiliation_strings":["AMO, Genk, Belgium","AMO, Flemish Institute for Technological Research (VITO), Mol, Belgium"],"affiliations":[{"raw_affiliation_string":"AMO, Genk, Belgium","institution_ids":[]},{"raw_affiliation_string":"AMO, Flemish Institute for Technological Research (VITO), Mol, Belgium","institution_ids":["https://openalex.org/I68522396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008706525","display_name":"Fred Spiessens","orcid":"https://orcid.org/0000-0002-1493-6745"},"institutions":[{"id":"https://openalex.org/I68522396","display_name":"Flemish Institute for Technological Research","ror":"https://ror.org/04gq0w522","country_code":"BE","type":"facility","lineage":["https://openalex.org/I68522396"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Fred Spiessens","raw_affiliation_strings":["AMO, Genk, Belgium","AMO, Flemish Institute for Technological Research (VITO), Mol, Belgium"],"affiliations":[{"raw_affiliation_string":"AMO, Genk, Belgium","institution_ids":[]},{"raw_affiliation_string":"AMO, Flemish Institute for Technological Research (VITO), Mol, Belgium","institution_ids":["https://openalex.org/I68522396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024462942","display_name":"Geert Deconinck","orcid":"https://orcid.org/0000-0002-2225-3987"},"institutions":[{"id":"https://openalex.org/I89206478","display_name":"Engie (Belgium)","ror":"https://ror.org/00c97z041","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210124897","https://openalex.org/I89206478"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Geert Deconinck","raw_affiliation_strings":["AMO, Genk, Belgium","ESAT/ELECTA, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"AMO, Genk, Belgium","institution_ids":[]},{"raw_affiliation_string":"ESAT/ELECTA, Leuven, Belgium","institution_ids":["https://openalex.org/I89206478"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057621400"],"corresponding_institution_ids":["https://openalex.org/I68522396","https://openalex.org/I89206478"],"apc_list":null,"apc_paid":null,"fwci":0.2055,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5245366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9986000061035156,"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":0.9986000061035156,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9544000029563904,"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":0.8111417293548584},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7419750094413757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722586452960968},{"id":"https://openalex.org/keywords/electricity","display_name":"Electricity","score":0.6662234663963318},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6532124280929565},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5955782532691956},{"id":"https://openalex.org/keywords/photovoltaic-system","display_name":"Photovoltaic system","score":0.5712149739265442},{"id":"https://openalex.org/keywords/demand-response","display_name":"Demand response","score":0.47745707631111145},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.46776124835014343},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4495493471622467},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3613213896751404},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3556874990463257},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3479312062263489},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13310542702674866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09697353839874268}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8111417293548584},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7419750094413757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722586452960968},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.6662234663963318},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6532124280929565},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5955782532691956},{"id":"https://openalex.org/C41291067","wikidata":"https://www.wikidata.org/wiki/Q1897785","display_name":"Photovoltaic system","level":2,"score":0.5712149739265442},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.47745707631111145},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.46776124835014343},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4495493471622467},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3613213896751404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3556874990463257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3479312062263489},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13310542702674866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09697353839874268},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isgt-europe47291.2020.9248800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isgt-europe47291.2020.9248800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324551","display_name":"Vlaamse Instelling voor Technologisch Onderzoek","ror":"https://ror.org/04gq0w522"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1626155273","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2155968351","https://openalex.org/W2586852908","https://openalex.org/W2605267926","https://openalex.org/W2613191681","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2767535599","https://openalex.org/W2803890045","https://openalex.org/W2901645090","https://openalex.org/W2963317745","https://openalex.org/W2979599048","https://openalex.org/W2990232357","https://openalex.org/W2990380687","https://openalex.org/W3011120880","https://openalex.org/W6677737365","https://openalex.org/W6741002519","https://openalex.org/W6769408332","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"Through":[0],"many":[1],"recent":[2],"successes":[3],"in":[4,23,106,152,174,187,193],"simulation":[5,150],"and":[6,32,76,79,87,124,145,171,179,190],"real-world":[7],"projects,":[8],"reinforcement":[9],"learning":[10,28],"(RL)":[11],"has":[12],"emerged":[13],"as":[14],"a":[15,30,60,83,92,99,107,110,184],"promising":[16],"approach":[17],"for":[18,103],"demand":[19],"response":[20],"applications":[21],"especially":[22],"the":[24,96,131,154,165,169,201],"residential":[25],"setting.":[26],"Reinforcement":[27],"is":[29,116,197],"self-learning":[31],"self-adaptive":[33],"technique":[34],"that":[35],"can":[36],"be":[37],"used":[38],"to":[39,200],"control":[40],"flexibility":[41],"providing":[42],"devices":[43],"by":[44],"relying":[45],"mainly":[46],"on":[47,54,149],"historical":[48],"and/or":[49],"real-time":[50],"data":[51],"rather":[52],"than":[53],"system":[55],"models.":[56],"This":[57],"paper":[58],"presents":[59],"benchmark":[61],"of":[62,94,98,120,133,157,176],"five":[63],"RL":[64,167],"algorithms":[65],"-":[66,78],"fitted":[67,162],"Q-iteration,":[68],"policy":[69],"iteration":[70],"with":[71,82,109,118],"Q-functions,":[72],"double":[73],"Q-learning,":[74],"REINFORCE":[75],"actor-critic":[77],"compares":[80],"these":[81,134],"model-based":[84],"optimal,":[85],"rule-based":[86,172],"naive":[88,170],"control.":[89,203],"We":[90],"consider":[91],"task":[93],"controlling":[95],"operation":[97],"heat":[100],"pump":[101],"(HP)":[102],"space":[104],"heating":[105],"building":[108],"photovoltaic":[111],"(PV)":[112],"installation.":[113],"The":[114],"HP":[115],"controlled":[117],"goal":[119],"maximizing":[121],"PV":[122,141,177,188],"self-consumption":[123,178,189],"consequently,":[125],"minimizing":[126],"electricity":[127,143,181,195],"cost.":[128,182],"To":[129],"evaluate":[130],"performance":[132],"algorithms,":[135,168],"three":[136],"main":[137],"indicators":[138],"are":[139,160],"considered:":[140],"self-consumption,":[142],"cost":[144,196],"computation":[146],"time.":[147],"Based":[148],"results":[151],"which":[153],"same":[155],"number":[156],"training":[158],"samples":[159],"considered,":[161],"Q-iteration":[163],"outperforms":[164],"other":[166],"controls":[173],"terms":[175],"net":[180,194],"However,":[183],"7.6%":[185],"decrease":[186],"77%":[191],"increase":[192],"observed":[198],"compared":[199],"optimal":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
