{"id":"https://openalex.org/W4293498985","doi":"https://doi.org/10.1016/j.energy.2022.125290","title":"Data-driven Offline Reinforcement Learning for HVAC-systems","display_name":"Data-driven Offline Reinforcement Learning for HVAC-systems","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4293498985","doi":"https://doi.org/10.1016/j.energy.2022.125290"},"language":"en","primary_location":{"id":"doi:10.1016/j.energy.2022.125290","doi":"https://doi.org/10.1016/j.energy.2022.125290","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.energy.2022.125290","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0360544222021739/pdf","source":{"id":"https://openalex.org/S2497375143","display_name":"Energy","issn_l":"0360-5442","issn":["0360-5442","1873-6785"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-b","jufo-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Energy","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.sciencedirect.com/science/article/pii/S0360544222021739/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037200283","display_name":"Christian Blad","orcid":"https://orcid.org/0000-0001-8718-9886","observed_orcids":["https://orcid.org/0000-0001-8718-9886"]},"institutions":[{"id":"https://openalex.org/I4210161280","display_name":"Grundfos (Denmark)","ror":"https://ror.org/05rdv5n40","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210161280","https://openalex.org/I4392738325"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Christian Blad","raw_affiliation_strings":["Grundfos A/S, Poul Due Jensens Vej 7, Bjerringbro, DK-8850, Denmark","Robotics & Automation Group Department of Materials and Production, Aalborg University, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-8718-9886","affiliations":[{"raw_affiliation_string":"Grundfos A/S, Poul Due Jensens Vej 7, Bjerringbro, DK-8850, Denmark","institution_ids":["https://openalex.org/I4210161280"]},{"raw_affiliation_string":"Robotics & Automation Group Department of Materials and Production, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048839097","display_name":"Simon B\u00f8gh","orcid":"https://orcid.org/0000-0002-5960-4365","observed_orcids":["https://orcid.org/0000-0002-5960-4365"]},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Simon B\u00f8gh","raw_affiliation_strings":["Robotics & Automation Group Department of Materials and Production, Aalborg University, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-5960-4365","affiliations":[{"raw_affiliation_string":"Robotics & Automation Group Department of Materials and Production, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045171559","display_name":"Carsten Skovmose Kalles\u00f8e","orcid":"https://orcid.org/0000-0002-4197-6777","observed_orcids":["https://orcid.org/0000-0002-4197-6777"]},"institutions":[{"id":"https://openalex.org/I4210161280","display_name":"Grundfos (Denmark)","ror":"https://ror.org/05rdv5n40","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210161280","https://openalex.org/I4392738325"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Carsten Skovmose Kalles\u00f8e","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark","Grundfos A/S, Poul Due Jensens Vej 7, Bjerringbro, DK-8850, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Grundfos A/S, Poul Due Jensens Vej 7, Bjerringbro, DK-8850, Denmark","institution_ids":["https://openalex.org/I4210161280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5037200283"],"corresponding_institution_ids":["https://openalex.org/I4210161280","https://openalex.org/I891191580"],"apc_list":{"value":3710,"currency":"USD","value_usd":3710},"apc_paid":{"value":3710,"currency":"USD","value_usd":3710},"fwci":5.0966,"has_fulltext":true,"cited_by_count":71,"citation_normalized_percentile":{"value":0.9603215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"261","issue":null,"first_page":"125290","last_page":"125290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9771000146865845,"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":0.9771000146865845,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.01549999974668026,"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/T11529","display_name":"Refrigeration and Air Conditioning Technologies","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/hvac-control","display_name":"HVAC control","score":0.9789999723434448},{"id":"https://openalex.org/keywords/floor-heating","display_name":"floor heating","score":0.9760000109672546},{"id":"https://openalex.org/keywords/air-to-water-heat-pump","display_name":"air-to-water heat pump","score":0.9929999709129333},{"id":"https://openalex.org/keywords/black-box-modeling","display_name":"black-box models","score":0.4959999918937683},{"id":"https://openalex.org/keywords/online-fine-tuning","display_name":"online fine-tuning","score":0.875},{"id":"https://openalex.org/keywords/lstm","display_name":"LSTM","score":0.45500001311302185},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.9909999966621399},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9120000004768372},{"id":"https://openalex.org/keywords/heating-cost-reduction","display_name":"heating cost reduction","score":0.8199999928474426},{"id":"https://openalex.org/keywords/building-energy-efficiency","display_name":"building energy efficiency","score":0.625}],"concepts":[{"id":"https://openalex.org/C122346748","wikidata":"https://www.wikidata.org/wiki/Q1798773","display_name":"HVAC","level":3,"score":0.8776440024375916},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.786614179611206},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.614392876625061},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6109942197799683},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.586898148059845},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5832939743995667},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5274527072906494},{"id":"https://openalex.org/C103742991","wikidata":"https://www.wikidata.org/wiki/Q173725","display_name":"Air conditioning","level":2,"score":0.5132262706756592},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4078384041786194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4027898609638214},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.394264280796051},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3142622113227844},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.14064371585845947},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.energy.2022.125290","doi":"https://doi.org/10.1016/j.energy.2022.125290","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.energy.2022.125290","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0360544222021739/pdf","source":{"id":"https://openalex.org/S2497375143","display_name":"Energy","issn_l":"0360-5442","issn":["0360-5442","1873-6785"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-b","jufo-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Energy","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/b2df990b-ee97-4384-bffb-b894f07a8388","doi":null,"is_oa":true,"landing_page_url":"https://vbn.aau.dk/files/485246413/1_s2.0_S0360544222021739_main.pdf","pdf_url":"https://vbn.aau.dk/ws/files/485246413/1_s2.0_S0360544222021739_main.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Blad, C, B\u00f8gh, S & Kalles\u00f8e, C 2022, 'Data-Driven Offline Reinforcement Learning for HVAC-Systems', Energy, vol. 261, no. Part B, 125290. https://doi.org/10.1016/j.energy.2022.125290","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:RePEc:eee:energy:v:261:y:2022:i:pb:s0360544222021739","doi":null,"is_oa":false,"landing_page_url":"http://www.sciencedirect.com/science/article/pii/S0360544222021739","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.energy.2022.125290","doi":"https://doi.org/10.1016/j.energy.2022.125290","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.energy.2022.125290","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0360544222021739/pdf","source":{"id":"https://openalex.org/S2497375143","display_name":"Energy","issn_l":"0360-5442","issn":["0360-5442","1873-6785"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-b","jufo-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Energy","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.75,"id":"https://metadata.un.org/sdg/7"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313796","display_name":"Innovationsfonden","ror":"https://ror.org/00daj4111"},{"id":"https://openalex.org/F4320330079","display_name":"Poul Due Jensens Fond","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293498985.pdf","grobid_xml":"https://content.openalex.org/works/W4293498985.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1209078686","https://openalex.org/W1968167335","https://openalex.org/W1973944436","https://openalex.org/W1997055709","https://openalex.org/W2011938518","https://openalex.org/W2012072009","https://openalex.org/W2032589491","https://openalex.org/W2042317950","https://openalex.org/W2064675550","https://openalex.org/W2079761644","https://openalex.org/W2136848157","https://openalex.org/W2145339207","https://openalex.org/W2154989258","https://openalex.org/W2163121678","https://openalex.org/W2186879020","https://openalex.org/W2189364073","https://openalex.org/W2341171179","https://openalex.org/W2565272409","https://openalex.org/W2597866042","https://openalex.org/W2617368349","https://openalex.org/W2625632007","https://openalex.org/W2625874945","https://openalex.org/W2767174536","https://openalex.org/W2810785043","https://openalex.org/W2914396823","https://openalex.org/W2944851425","https://openalex.org/W2971097632","https://openalex.org/W2979476646","https://openalex.org/W2992088755","https://openalex.org/W3012383807","https://openalex.org/W3021878289","https://openalex.org/W3022566517","https://openalex.org/W3037631072","https://openalex.org/W3119186746","https://openalex.org/W3212208322","https://openalex.org/W4214717370","https://openalex.org/W4237037746","https://openalex.org/W4245302924","https://openalex.org/W4256640597","https://openalex.org/W4288837025","https://openalex.org/W6686783779"],"related_works":["https://openalex.org/W3021878289","https://openalex.org/W4323032125","https://openalex.org/W4406023348","https://openalex.org/W4309941247","https://openalex.org/W3212208322","https://openalex.org/W4407302529","https://openalex.org/W2747014259","https://openalex.org/W4322730848","https://openalex.org/W7203975406","https://openalex.org/W4404959173"],"abstract_inverted_index":{"This":[0,104],"paper":[1,52,105],"presents":[2,24],"a":[3,25,31,47,129,135,159,174,202,226,265],"novel":[4],"framework":[5,23,68,93,193],"for":[6,15,177],"Offline":[7],"Reinforcement":[8],"Learning":[9],"(RL)":[10],"with":[11,61,158],"online":[12],"fine":[13],"tuning":[14],"Heating":[16,59],"Ventilation":[17],"and":[18,107,124,134],"Air-conditioning":[19],"(HVAC)":[20],"systems.":[21],"The":[22,51],"method":[26,133,149],"to":[27,72,86,94,115,242,264],"do":[28],"pre-training":[29],"in":[30,101,126,191,195,269,273],"black":[32,38],"box":[33,39,79],"model":[34,176],"environment,":[35],"where":[36],"the":[37,55,67,98,147,151,192,245,255,270],"models":[40,190],"are":[41,81,122,166],"built":[42],"on":[43,54],"data":[44,224],"acquired":[45],"under":[46],"traditional":[48,266],"control":[49,75,252,267],"policy.":[50],"focuses":[53],"application":[56],"of":[57,248,257],"Underfloor":[58],"(UFH)":[60],"an":[62,214,233],"air-to-water-based":[63],"heat":[64],"pump.":[65],"However,":[66],"should":[69],"also":[70],"generalize":[71],"other":[73,95],"HVAC":[74],"applications.":[76],"Because":[77],"Black":[78],"methods":[80,114,121],"used":[82],"is":[83,144,169,199,219,231],"there":[84],"little":[85],"no":[87],"commissioning":[88],"time":[89,179],"when":[90,156,262],"applying":[91],"this":[92,102,127,196,274],"buildings/simulations":[96],"beyond":[97],"one":[99],"presented":[100,125,194,272],"study.":[103],"explores":[106],"deploys":[108],"Artificial":[109],"Neural":[110],"Network":[111],"(ANN)":[112],"based":[113,141],"design":[116],"efficient":[117],"controllers.":[118],"Two":[119],"ANN":[120],"tested":[123],"paper;":[128],"Multilayer":[130],"Perceptron":[131],"(MLP)":[132],"Long":[136],"Short":[137],"Term":[138],"Memory":[139],"(LSTM)":[140],"method.":[142],"It":[143,168],"found":[145,170],"that":[146,171,201,221],"LSTM-based":[148],"reduces":[150,254],"prediction":[152],"error":[153],"by":[154,172,259],"45%":[155],"compared":[157,263],"MLP":[160],"model.":[161],"Additionally,":[162],"different":[163],"network":[164],"architectures":[165],"tested.":[167],"creating":[173],"new":[175],"each":[178],"step,":[180],"performance":[181],"can":[182,206,236],"be":[183,207,237],"improved":[184],"additionally":[185],"19%.":[186],"By":[187],"using":[188],"these":[189],"paper,":[197],"it":[198,218],"shown":[200,220],"Multi-Agent":[203],"RL":[204,234],"algorithm":[205],"deployed":[208,238],"without":[209],"ever":[210],"performing":[211],"worse":[212],"than":[213],"industrial":[215],"controller.":[216],"Furthermore,":[217],"if":[222],"building":[223],"from":[225,244],"Building":[227],"Management":[228],"System":[229],"(BMS)":[230],"available,":[232],"agent":[235],"which":[239],"performs":[240],"close":[241],"optimally":[243],"first":[246],"day":[247],"deployment.":[249],"An":[250],"optimal":[251],"policy":[253,268],"cost":[256],"heating":[258],"19.4":[260],"%":[261],"simulation":[271],"paper.":[275]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-08-29T00:00:00"}