{"id":"https://openalex.org/W4225917661","doi":"https://doi.org/10.1109/jiot.2022.3164023","title":"MBRL-MC: An HVAC Control Approach via Combining Model-Based Deep Reinforcement Learning and Model Predictive Control","display_name":"MBRL-MC: An HVAC Control Approach via Combining Model-Based Deep Reinforcement Learning and Model Predictive Control","publication_year":2022,"publication_date":"2022-04-01","ids":{"openalex":"https://openalex.org/W4225917661","doi":"https://doi.org/10.1109/jiot.2022.3164023"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2022.3164023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2022.3164023","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5100729607","display_name":"Liangliang Chen","orcid":"https://orcid.org/0000-0002-9594-640X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liangliang Chen","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004137944","display_name":"Fei Meng","orcid":"https://orcid.org/0000-0001-9225-040X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fei Meng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386001","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0001-5246-2141"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100729607"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":4.9665,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.96068176,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"9","issue":"19","first_page":"19160","last_page":"19173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.996399998664856,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9940000176429749,"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":0.9628000259399414,"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":0.8045817613601685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7415236234664917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6211821436882019},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5678563117980957},{"id":"https://openalex.org/keywords/hvac","display_name":"HVAC","score":0.5588997602462769},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.519268274307251},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.48451846837997437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45673298835754395},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.45089179277420044},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2264249324798584},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18308201432228088},{"id":"https://openalex.org/keywords/air-conditioning","display_name":"Air conditioning","score":0.1758340299129486},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09279614686965942}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8045817613601685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415236234664917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6211821436882019},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5678563117980957},{"id":"https://openalex.org/C122346748","wikidata":"https://www.wikidata.org/wiki/Q1798773","display_name":"HVAC","level":3,"score":0.5588997602462769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.519268274307251},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.48451846837997437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45673298835754395},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.45089179277420044},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2264249324798584},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18308201432228088},{"id":"https://openalex.org/C103742991","wikidata":"https://www.wikidata.org/wiki/Q173725","display_name":"Air conditioning","level":2,"score":0.1758340299129486},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09279614686965942},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2022.3164023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2022.3164023","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2237156097","display_name":null,"funder_award_id":"1837021","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"}],"funders":[{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1973944436","https://openalex.org/W1980035368","https://openalex.org/W2018842385","https://openalex.org/W2069263165","https://openalex.org/W2145339207","https://openalex.org/W2154989258","https://openalex.org/W2584986912","https://openalex.org/W2625874945","https://openalex.org/W2736601468","https://openalex.org/W2887407101","https://openalex.org/W2889109362","https://openalex.org/W2892262816","https://openalex.org/W2902098903","https://openalex.org/W2953708620","https://openalex.org/W2962872206","https://openalex.org/W2974232099","https://openalex.org/W2979476646","https://openalex.org/W2987901555","https://openalex.org/W2989847975","https://openalex.org/W2999298400","https://openalex.org/W3038822267","https://openalex.org/W3109235893","https://openalex.org/W3118210634","https://openalex.org/W3123856535","https://openalex.org/W3130417286","https://openalex.org/W3162079807","https://openalex.org/W4200140111","https://openalex.org/W4214717370","https://openalex.org/W4324106947","https://openalex.org/W6631190155","https://openalex.org/W6674872077","https://openalex.org/W6677939520","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6702989015","https://openalex.org/W6740836278","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6751494529","https://openalex.org/W6752059651","https://openalex.org/W6753807341","https://openalex.org/W6754447547","https://openalex.org/W6754471908","https://openalex.org/W6755459763","https://openalex.org/W6756463683","https://openalex.org/W6760405395","https://openalex.org/W6763990646","https://openalex.org/W6764980988","https://openalex.org/W6779911313"],"related_works":["https://openalex.org/W2112866972","https://openalex.org/W4240233711","https://openalex.org/W2900606913","https://openalex.org/W1534274833","https://openalex.org/W4320003279","https://openalex.org/W2326910963","https://openalex.org/W3111008797","https://openalex.org/W4392628806","https://openalex.org/W4287552621","https://openalex.org/W4376649626"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"a":[3,32,42,51],"novel":[4],"learning-based":[5],"control":[6,29],"strategy,":[7],"named":[8],"MBRL-MC,":[9],"for":[10],"the":[11,37,48,61,79,87,91,96,107,111,116,127,140,144,147,153,157],"heating,":[12],"ventilation,":[13],"and":[14,26,68],"air":[15],"conditioning":[16],"(HVAC)":[17],"system":[18],"by":[19,41,102],"combining":[20],"model-based":[21],"deep":[22],"reinforcement":[23,65],"learning":[24,44,66,92,117],"(DRL)":[25],"model":[27,35],"predictive":[28],"(MPC).":[30],"First,":[31],"thermal":[33],"dynamic":[34],"of":[36,63,81,110,146,159],"zone":[38],"is":[39,57,74,99,122],"learned":[40,49],"supervised":[43],"algorithm.":[45,149],"Based":[46],"on":[47],"model,":[50],"neural":[52],"network":[53],"(NN)":[54],"planning":[55,72],"framework":[56],"designed":[58],"which":[59,85,114],"leverages":[60],"ideas":[62],"both":[64],"(RL)":[67],"MPC.":[69],"The":[70,119,150],"proposed":[71,148],"algorithm":[73,104,129],"directly":[75],"obtained":[76],"without":[77],"imitating":[78],"results":[80],"MPC":[82],"random":[83],"shooting,":[84],"avoids":[86],"compounding":[88],"error":[89],"during":[90],"procedure.":[93],"In":[94],"addition,":[95],"bootstrapping":[97],"technique":[98],"not":[100],"employed":[101],"our":[103],"when":[105],"constructing":[106],"update":[108],"target":[109],"critic":[112],"network,":[113],"improves":[115],"stability.":[118],"cross-entropy":[120],"method":[121],"further":[123],"used":[124],"to":[125,132],"augment":[126],"RL":[128],"in":[130,139],"order":[131],"avoid":[133],"potential":[134],"divergence.":[135],"Finally,":[136],"simulation":[137],"experiments":[138],"EnergyPlus":[141],"environment":[142],"demonstrate":[143],"effectiveness":[145],"comparisons":[151],"with":[152],"existing":[154],"algorithms":[155],"show":[156],"advantages":[158],"MBRL-MC.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}