{"id":"https://openalex.org/W7129005313","doi":"https://doi.org/10.1109/tsg.2026.3665037","title":"HVAC Control With Optimization-Guided Behavior Cloning and Restricted Residual Policy Learning","display_name":"HVAC Control With Optimization-Guided Behavior Cloning and Restricted Residual Policy Learning","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129005313","doi":"https://doi.org/10.1109/tsg.2026.3665037"},"language":null,"primary_location":{"id":"doi:10.1109/tsg.2026.3665037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsg.2026.3665037","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/A5064437242","display_name":"Shuhua Gao","orcid":"https://orcid.org/0000-0003-3208-9620"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhua Gao","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-3208-9620","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102640875","display_name":"Hailong WEN","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hailong Wen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-3392-3234","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126086352","display_name":"Feng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["State Grid Shandong Electric Power Company Electric Power Research Institute, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Electric Power Research Institute, Jinan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013136628","display_name":"Kun\u2010Yi Yang","orcid":"https://orcid.org/0000-0001-8823-1521"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunmeng Yang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071977235","display_name":"Cheng Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xiang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-1229-6860","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1912,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91957768,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"17","issue":"4","first_page":"3112","last_page":"3125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.4726000130176544,"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":0.4726000130176544,"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/T10603","display_name":"Smart Grid Energy Management","score":0.304500013589859,"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":0.018300000578165054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7056000232696533},{"id":"https://openalex.org/keywords/hvac","display_name":"HVAC","score":0.6640999913215637},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5238999724388123},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4731999933719635},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4180000126361847},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.4083000123500824},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.3912999927997589},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.36059999465942383},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3418000042438507}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7056000232696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680999994277954},{"id":"https://openalex.org/C122346748","wikidata":"https://www.wikidata.org/wiki/Q1798773","display_name":"HVAC","level":3,"score":0.6640999913215637},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.4083000123500824},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.350600004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34360000491142273},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C2780150128","wikidata":"https://www.wikidata.org/wiki/Q21948731","display_name":"Extreme learning machine","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C187819001","wikidata":"https://www.wikidata.org/wiki/Q187665","display_name":"Thermostat","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2791999876499176},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsg.2026.3665037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsg.2026.3665037","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9120757579803467,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2694168084","display_name":null,"funder_award_id":"ZR2023QF048","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G5199318212","display_name":null,"funder_award_id":"2023HWYQ-003","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"HVAC":[0,90,216],"control":[1,21,91,168],"can":[2,221],"be":[3,222],"formulated":[4],"as":[5,18],"an":[6,88,100,107,128],"optimization":[7,81,147,201],"problem":[8],"balancing":[9],"energy":[10,191],"consumption":[11,192],"and":[12,37,59,82,105,135,141,152,184,193,211],"occupant":[13],"comfort.":[14],"Model-based":[15],"approaches":[16],"such":[17],"model":[19,35,104],"predictive":[20],"(MPC)":[22],"deliver":[23],"strong":[24],"performance":[25,176],"when":[26],"accurate":[27],"thermal":[28,103],"models":[29],"are":[30],"available":[31],"but":[32],"degrade":[33],"under":[34],"mismatch":[36],"require":[38],"costly":[39],"system":[40],"identification.":[41],"Learning-based":[42],"methods,":[43],"notably":[44],"reinforcement":[45],"learning":[46,121,206],"(RL),":[47],"avoid":[48],"explicit":[49],"modeling":[50],"yet":[51],"often":[52],"incurs":[53],"unsafe":[54],"exploration,":[55],"poor":[56],"initial":[57,108],"performance,":[58],"slow":[60],"convergence":[61],"in":[62],"practice.":[63],"We":[64],"propose":[65],"Optimization-Guided":[66],"Behavioral":[67],"Cloning":[68],"with":[69,127],"Restricted":[70],"Residual":[71],"Policy":[72],"Learning":[73],"(OGBC+RRPL),":[74],"a":[75,95,122,208],"hybrid":[76],"framework":[77],"that":[78,164,199],"unites":[79],"model-based":[80],"data-driven":[83],"adaptation.":[84,158],"OGBC":[85],"first":[86],"builds":[87],"optimization-based":[89],"expert":[92],"by":[93,120,132],"solving":[94],"linear":[96],"program":[97],"derived":[98],"from":[99],"approximate":[101],"autoregressive":[102],"trains":[106],"policy":[109,118,126],"offline":[110,186],"via":[111],"behavioral":[112],"cloning.":[113],"RRPL":[114],"then":[115],"refines":[116],"this":[117],"online":[119,157,181,205],"compensating":[123],"lightweight":[124],"residual":[125,204],"actor-critic":[129],"algorithm":[130],"enhanced":[131],"action":[133],"clipping":[134],"critic":[136],"regularization":[137],"to":[138],"ensure":[139],"stable":[140],"safe":[142,212],"updates.":[143],"This":[144],"design":[145],"preserves":[146],"knowledge,":[148],"mitigates":[149],"catastrophic":[150],"forgetting,":[151],"constrains":[153],"risky":[154],"exploration":[155],"during":[156],"Experiments":[159],"on":[160,189],"CityLearn":[161],"v2":[162],"demonstrate":[163],"OGBC+RRPL":[165],"delivers":[166],"high-quality":[167],"immediately":[169],"upon":[170],"deployment,":[171],"attains":[172],"comparable":[173],"or":[174],"better":[175],"far":[177],"faster":[178],"than":[179],"standard":[180],"RL":[182,187],"algorithms,":[183],"outperforms":[185],"methods":[188],"both":[190],"temperature-violation":[194],"metrics.":[195],"The":[196],"results":[197],"indicate":[198],"infusing":[200],"guidance":[202],"into":[203],"provides":[207],"practical,":[209],"data-efficient,":[210],"approach":[213],"for":[214],"real-world":[215],"control.":[217],"Our":[218],"implementation":[219],"code":[220],"found":[223],"at":[224],"https://github.com/HailongW0818/HVAC-OGBC-RRPL.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2026-02-17T00:00:00"}