{"id":"https://openalex.org/W4200183347","doi":"https://doi.org/10.1109/smartgridcomm51999.2021.9632339","title":"Solving Unit Commitment Problems with Multi-step Deep Reinforcement Learning","display_name":"Solving Unit Commitment Problems with Multi-step Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W4200183347","doi":"https://doi.org/10.1109/smartgridcomm51999.2021.9632339"},"language":"en","primary_location":{"id":"doi:10.1109/smartgridcomm51999.2021.9632339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smartgridcomm51999.2021.9632339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","raw_type":"proceedings-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/A5103171435","display_name":"Jingtao Qin","orcid":"https://orcid.org/0000-0002-7645-7547"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jingtao Qin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, California, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, California, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029525096","display_name":"Nanpeng Yu","orcid":"https://orcid.org/0000-0001-5086-5465"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nanpeng Yu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, California, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, California, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024852124","display_name":"Yuanqi Gao","orcid":"https://orcid.org/0000-0003-4078-6143"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanqi Gao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, California, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, California, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103171435"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":1.2033,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79061913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":1.0,"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":1.0,"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/T10424","display_name":"Electric Power System Optimization","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/T10223","display_name":"Microgrid Control and Optimization","score":0.9983000159263611,"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":0.755867600440979},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7172237038612366},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6900789737701416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6638807058334351},{"id":"https://openalex.org/keywords/economic-dispatch","display_name":"Economic dispatch","score":0.572695255279541},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5387995839118958},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4439488351345062},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4343963861465454},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.42867574095726013},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4286131262779236},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4144611358642578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37492209672927856},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3275172710418701},{"id":"https://openalex.org/keywords/electric-power-system","display_name":"Electric power system","score":0.2575162947177887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.230709969997406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19499534368515015}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.755867600440979},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7172237038612366},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6900789737701416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638807058334351},{"id":"https://openalex.org/C187633118","wikidata":"https://www.wikidata.org/wiki/Q1317949","display_name":"Economic dispatch","level":4,"score":0.572695255279541},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5387995839118958},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4439488351345062},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4343963861465454},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.42867574095726013},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4286131262779236},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4144611358642578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37492209672927856},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3275172710418701},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.2575162947177887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.230709969997406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19499534368515015},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smartgridcomm51999.2021.9632339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smartgridcomm51999.2021.9632339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W226605842","https://openalex.org/W2011559788","https://openalex.org/W2074513827","https://openalex.org/W2082261096","https://openalex.org/W2204963357","https://openalex.org/W2335865153","https://openalex.org/W2471802579","https://openalex.org/W2514912047","https://openalex.org/W2739833396","https://openalex.org/W2757802645","https://openalex.org/W2789731659","https://openalex.org/W2892124637","https://openalex.org/W2895627464","https://openalex.org/W2952348579","https://openalex.org/W2963730561","https://openalex.org/W3114999473"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W4389475841","https://openalex.org/W2952594763","https://openalex.org/W4285537323","https://openalex.org/W2903299703","https://openalex.org/W4385342861","https://openalex.org/W4281791088","https://openalex.org/W2117282672","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Solving":[0],"the":[1,36,40,49,67,87,91,103,121],"unit":[2],"commitment":[3],"(UC)":[4],"problem":[5,69],"in":[6,59,135],"a":[7,12,56,71,77,110],"computationally":[8],"efficient":[9],"manner":[10],"is":[11,55,146],"critical":[13],"issue":[14],"of":[15,43,51,128,132,137,142,151],"electricity":[16],"market":[17],"operations.":[18],"Optimization-based":[19],"methods":[20,45],"such":[21],"as":[22,70,130],"heuristics,":[23],"dynamic":[24],"programming,":[25],"and":[26,75,97,124],"mixed-integer":[27],"quadratic":[28],"programming":[29],"(MIQP)":[30],"often":[31],"yield":[32],"good":[33],"solutions":[34],"to":[35,85,101],"UC":[37,68],"problem.":[38,88],"However,":[39],"computation":[41,140],"time":[42,141],"optimization-based":[44],"grows":[46],"exponentially":[47],"with":[48,94],"number":[50],"generating":[52],"units,":[53],"which":[54],"major":[57],"bottleneck":[58],"practice.":[60],"To":[61],"address":[62],"this":[63],"issue,":[64],"we":[65],"formulate":[66],"Markov":[72],"decision":[73],"process":[74],"propose":[76],"novel":[78],"multi-step":[79],"deep":[80,122],"reinforcement":[81],"learning":[82],"(RL)-based":[83],"algorithm":[84,100,118,145],"solve":[86],"We":[89],"approximate":[90],"action-value":[92],"function":[93],"neural":[95],"networks":[96],"design":[98],"an":[99],"determine":[102],"feasible":[104],"action":[105],"space.":[106],"Numerical":[107],"studies":[108],"on":[109],"5-generator":[111],"test":[112],"case":[113],"show":[114],"that":[115,131,150],"our":[116,143],"proposed":[117,144],"significantly":[119],"outperforms":[120],"Q-learning":[123],"yields":[125],"similar":[126],"level":[127],"performance":[129],"MIQP-based":[133,152],"optimization":[134,153],"terms":[136],"optimality.":[138],"The":[139],"much":[147],"shorter":[148],"than":[149],"methods.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}