{"id":"https://openalex.org/W4206459747","doi":"https://doi.org/10.1109/tsg.2022.3141625","title":"Two-Stage Reinforcement Learning Policy Search for Grid-Interactive Building Control","display_name":"Two-Stage Reinforcement Learning Policy Search for Grid-Interactive Building Control","publication_year":2022,"publication_date":"2022-01-10","ids":{"openalex":"https://openalex.org/W4206459747","doi":"https://doi.org/10.1109/tsg.2022.3141625"},"language":"en","primary_location":{"id":"doi:10.1109/tsg.2022.3141625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsg.2022.3141625","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":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1841140","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100362472","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-4857-2318"},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["Computational Science Center, National Renewable Energy Laboratory, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Computational Science Center, National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029240873","display_name":"Yue Chen","orcid":"https://orcid.org/0000-0003-1070-7192"},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Chen","raw_affiliation_strings":["Power Systems Engineering Center, National Renewable Energy Laboratory, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Power Systems Engineering Center, National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017202620","display_name":"Andrey Bernstein","orcid":"https://orcid.org/0000-0003-4489-8388"},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrey Bernstein","raw_affiliation_strings":["Power Systems Engineering Center, National Renewable Energy Laboratory, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Power Systems Engineering Center, National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045032215","display_name":"Rohit Chintala","orcid":"https://orcid.org/0000-0001-9143-9788"},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Chintala","raw_affiliation_strings":["Building Technologies and Science Center, National Renewable Energy Laboratory, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Building Technologies and Science Center, National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008431584","display_name":"Peter Gr\u00e4f","orcid":"https://orcid.org/0000-0003-3150-3404"},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Graf","raw_affiliation_strings":["Computational Science Center, National Renewable Energy Laboratory, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Computational Science Center, National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070648432","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-7746-5955"},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Building Technologies and Science Center, National Renewable Energy Laboratory, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Building Technologies and Science Center, National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000527374","display_name":"David Biagioni","orcid":"https://orcid.org/0000-0001-6140-1957"},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Biagioni","raw_affiliation_strings":["Computational Science Center, National Renewable Energy Laboratory, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Computational Science Center, National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100362472"],"corresponding_institution_ids":["https://openalex.org/I1297288678"],"apc_list":null,"apc_paid":null,"fwci":2.3022,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.88116334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"13","issue":"3","first_page":"1976","last_page":"1987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T14011","display_name":"Elevator Systems and Control","score":0.9943000078201294,"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/T10223","display_name":"Microgrid Control and Optimization","score":0.9908000230789185,"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":0.8302320241928101},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.711501955986023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6869901418685913},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.656377375125885},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6303174495697021},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5196341276168823},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46208426356315613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39911043643951416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3343026638031006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12723508477210999},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.0982675850391388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8302320241928101},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.711501955986023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869901418685913},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.656377375125885},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6303174495697021},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5196341276168823},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46208426356315613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39911043643951416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3343026638031006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12723508477210999},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0982675850391388},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.1109/tsg.2022.3141625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsg.2022.3141625","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"},{"id":"pmh:oai:osti.gov:1841140","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1841140","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1841140","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1841140","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8846609399","display_name":null,"funder_award_id":"DE-AC36-08GO28308","funder_id":"https://openalex.org/F4320338290","funder_display_name":"National Renewable Energy Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338290","display_name":"National Renewable Energy Laboratory","ror":"https://ror.org/036266993"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1410224781","https://openalex.org/W1522301498","https://openalex.org/W1973944436","https://openalex.org/W1997898472","https://openalex.org/W2149479912","https://openalex.org/W2151049413","https://openalex.org/W2160327646","https://openalex.org/W2228052882","https://openalex.org/W2255511049","https://openalex.org/W2277948250","https://openalex.org/W2557699706","https://openalex.org/W2596367596","https://openalex.org/W2597453992","https://openalex.org/W2625874945","https://openalex.org/W2736601468","https://openalex.org/W2747432554","https://openalex.org/W2811374584","https://openalex.org/W2886474253","https://openalex.org/W2887464323","https://openalex.org/W2903697572","https://openalex.org/W2925206436","https://openalex.org/W2957897705","https://openalex.org/W2963317745","https://openalex.org/W2963382853","https://openalex.org/W2967727187","https://openalex.org/W2972879618","https://openalex.org/W2987901555","https://openalex.org/W2998790326","https://openalex.org/W3004691725","https://openalex.org/W3010036076","https://openalex.org/W3045748774","https://openalex.org/W3045906804","https://openalex.org/W3047508891","https://openalex.org/W3048008723","https://openalex.org/W3082790500","https://openalex.org/W3090789943","https://openalex.org/W3107396186","https://openalex.org/W3108855356","https://openalex.org/W3176354738","https://openalex.org/W3184866585","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6735641298","https://openalex.org/W6741002519","https://openalex.org/W6752963931","https://openalex.org/W6754297394","https://openalex.org/W6757053730","https://openalex.org/W6773029903","https://openalex.org/W6780559895","https://openalex.org/W6784595459"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W1498872724","https://openalex.org/W4306904969","https://openalex.org/W4233149903","https://openalex.org/W4293864700","https://openalex.org/W2914522629"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"an":[3,81,171],"intelligent":[4],"grid-interactive":[5],"building":[6,10,31,138],"controller,":[7],"which":[8],"optimizes":[9],"operation":[11],"during":[12],"both":[13],"normal":[14],"hours":[15,194],"and":[16,26,39,102,166,191],"demand":[17],"response":[18],"(DR)":[19],"events.":[20],"To":[21],"avoid":[22],"costly":[23],"on-demand":[24],"computation":[25],"to":[27,29,55,64,91,99,105,119,125],"adapt":[28],"non-linear":[30],"models,":[32],"the":[33,78,94,103,121,128,140,143,154,168,186],"controller":[34,164,187],"utilizes":[35],"reinforcement":[36],"learning":[37,148],"(RL)":[38],"makes":[40],"real-time":[41],"decisions":[42],"based":[43,84],"on":[44,85,133],"a":[45,51,57,69,134,159,178],"near-optimal":[46],"control":[47,156],"policy.":[48],"Learning":[49],"such":[50],"policy":[52,74,96,114,157],"typically":[53],"amounts":[54],"solving":[56],"hard":[58],"non-convex":[59],"optimization":[60],"problem.":[61,131],"We":[62],"propose":[63],"address":[65],"this":[66],"problem":[67],"with":[68],"novel":[70],"<italic":[71],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">global-local":[73],"search</i>":[75],"method.":[76],"In":[77],"first":[79],"stage,":[80],"RL":[82],"algorithm":[83],"zero-order":[86],"gradient":[87],"estimation":[88],"is":[89,115],"leveraged":[90],"search":[92],"for":[93],"optimal":[95],"globally,":[97],"due":[98],"its":[100],"scalability":[101],"potential":[104],"escape":[106],"some":[107],"poor":[108],"performing":[109],"local":[110],"optima.":[111],"The":[112],"obtained":[113],"then":[116],"fine-tuned":[117],"locally":[118],"bring":[120],"first-stage":[122],"solution":[123],"closer":[124],"that":[126,153,185],"of":[127,142,170,195],"original":[129],"unsmoothed":[130],"Experiments":[132],"simulated":[135],"five-zone":[136],"commercial":[137],"demonstrate":[139,184],"advantages":[141],"proposed":[144],"method":[145],"over":[146],"existing":[147],"approaches.":[149],"They":[150],"also":[151],"show":[152],"learned":[155,190],"outperforms":[158],"pragmatic":[160],"linear":[161],"model":[162],"predictive":[163],"(MPC)":[165],"approaches":[167],"performance":[169],"oracle":[172],"MPC":[173],"in":[174],"testing":[175],"scenarios.":[176],"Using":[177],"state-of-the-art":[179],"advanced":[180],"computing":[181],"system,":[182],"we":[183],"can":[188],"be":[189],"deployed":[192],"within":[193],"training.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}