{"id":"https://openalex.org/W4402260803","doi":"https://doi.org/10.23919/acc60939.2024.10644697","title":"Constrained Reinforcement Learning for Building Demand Response","display_name":"Constrained Reinforcement Learning for Building Demand Response","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402260803","doi":"https://doi.org/10.23919/acc60939.2024.10644697"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10644697","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5009150716","display_name":"Jerson Sanchez","orcid":"https://orcid.org/0009-0007-7387-0655"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerson Sanchez","raw_affiliation_strings":["School of Aerospace and Mechanical Engineering, University of Oklahoma,Norman,OK,73072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aerospace and Mechanical Engineering, University of Oklahoma,Norman,OK,73072","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028032867","display_name":"Jie Cai","orcid":"https://orcid.org/0000-0002-2622-0445"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Cai","raw_affiliation_strings":["School of Aerospace and Mechanical Engineering, University of Oklahoma,Norman,OK,73072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aerospace and Mechanical Engineering, University of Oklahoma,Norman,OK,73072","institution_ids":["https://openalex.org/I8692664"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8692664"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4813","last_page":"4818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9984999895095825,"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":0.9984999895095825,"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/T12546","display_name":"Smart Parking Systems Research","score":0.9828000068664551,"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"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9807999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7428404092788696},{"id":"https://openalex.org/keywords/demand-response","display_name":"Demand response","score":0.6141878962516785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.612684965133667},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4974854290485382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24572306871414185},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16193830966949463},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.08023473620414734},{"id":"https://openalex.org/keywords/electricity","display_name":"Electricity","score":0.07527372241020203},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06728905439376831}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7428404092788696},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.6141878962516785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.612684965133667},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4974854290485382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24572306871414185},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16193830966949463},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.08023473620414734},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.07527372241020203},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06728905439376831}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc60939.2024.10644697","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G364953215","display_name":"CAREER: CAS- Climate: An altruistic game theoretic framework to characterize environmental responsiveness of residential electricity consumption","funder_award_id":"2238381","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W2034725503","https://openalex.org/W2049107400","https://openalex.org/W2162205235","https://openalex.org/W2398461964","https://openalex.org/W2736601468","https://openalex.org/W2974232099","https://openalex.org/W3047508891","https://openalex.org/W3048008723","https://openalex.org/W3087355053","https://openalex.org/W3095810316","https://openalex.org/W3130417286","https://openalex.org/W3184866585","https://openalex.org/W3216772467","https://openalex.org/W4293545785","https://openalex.org/W6638018090","https://openalex.org/W6737893269","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2555175041","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2032085210","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,29],"constrained":[4,99],"reinforcement":[5,17],"learning-based":[6],"control":[7,65],"strategy":[8,39,76,101],"for":[9],"building":[10],"demand":[11],"response.":[12],"Compared":[13],"to":[14,52,107,111,125],"conventional":[15,86],"(unconstrained)":[16,87],"learning":[18],"(RL)":[19],"controllers":[20,83,123],"where":[21],"indoor":[22],"comfort":[23,30],"constraints":[24,42],"are":[25],"addressed":[26],"by":[27,44],"adding":[28],"violation":[31],"penalty":[32,59,136],"in":[33],"the":[34,37,41,47,54,74,98,112,120,135],"reward":[35],"function,":[36],"proposed":[38,75],"handles":[40],"explic-itly,":[43],"upper":[45],"bounding":[46],"expected":[48],"cumulative":[49],"constraint":[50,117,131],"violation,":[51,118],"avoid":[53],"use":[55],"of":[56,73],"arbitrarily":[57],"set":[58],"factors":[60],"that":[61,97],"can":[62],"significantly":[63],"affect":[64],"performance.":[66],"To":[67],"demonstrate":[68],"its":[69],"efficacy,":[70],"simulation":[71,94],"tests":[72,95],"as":[77,79],"well":[78],"baseline":[80],"model":[81],"predictive":[82],"(MPC)":[84],"and":[85],"policy":[88],"optimization":[89],"methods":[90],"were":[91],"conducted.":[92],"The":[93],"show":[96],"RL":[100,122],"achieved":[102],"utility":[103,128],"cost":[104],"savings":[105],"up":[106],"22":[108],"%,":[109],"similar":[110],"MPC":[113],"baselines,":[114],"with":[115],"minimum":[116],"while":[119],"un-constrained":[121],"led":[124],"either":[126],"high":[127],"costs":[129],"or":[130],"violations,":[132],"depending":[133],"on":[134],"factor":[137],"setting.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}