Large-scale deep reinforcement learning method for energy management of power supply units considering regulation mileage payment

To improve automatic generation control (AGC) performance and reduce the wastage of regulation resources in interconnected grids including high-proportion renewable energy, a multi-area integrated AGC (MAI-AGC) framework is proposed to solve the coordination problem of secondary frequency regulation...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Frontiers in energy research Ročník 11
Hlavní autoři: Qian, Ting, Yang, Cheng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Frontiers Media S.A 14.03.2024
Témata:
ISSN:2296-598X, 2296-598X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract To improve automatic generation control (AGC) performance and reduce the wastage of regulation resources in interconnected grids including high-proportion renewable energy, a multi-area integrated AGC (MAI-AGC) framework is proposed to solve the coordination problem of secondary frequency regulation between different areas. In addition, a cocktail exploration multi-agent deep deterministic policy gradient (CE-MADDPG) algorithm is proposed as the framework algorithm. In this algorithm, the controller and power distributor of an area are combined into a single agent which can directly output the power generation command of different units. Moreover, the cocktail exploration strategy as well as various other techniques are introduced to improve the robustness of the framework. Through centralized training and decentralized execution, the proposed method can nonlinearly and adaptively derive the optimal coordinated control strategies for multiple agents and is verified on the two-area LFC model of southwest China and the four-area LFC model of the China Southern Grid (CSG).
AbstractList To improve automatic generation control (AGC) performance and reduce the wastage of regulation resources in interconnected grids including high-proportion renewable energy, a multi-area integrated AGC (MAI-AGC) framework is proposed to solve the coordination problem of secondary frequency regulation between different areas. In addition, a cocktail exploration multi-agent deep deterministic policy gradient (CE-MADDPG) algorithm is proposed as the framework algorithm. In this algorithm, the controller and power distributor of an area are combined into a single agent which can directly output the power generation command of different units. Moreover, the cocktail exploration strategy as well as various other techniques are introduced to improve the robustness of the framework. Through centralized training and decentralized execution, the proposed method can nonlinearly and adaptively derive the optimal coordinated control strategies for multiple agents and is verified on the two-area LFC model of southwest China and the four-area LFC model of the China Southern Grid (CSG).
Author Yang, Cheng
Qian, Ting
Author_xml – sequence: 1
  givenname: Ting
  surname: Qian
  fullname: Qian, Ting
– sequence: 2
  givenname: Cheng
  surname: Yang
  fullname: Yang, Cheng
BookMark eNp9kc9q3DAQh0VIIWmaF-hJL-Ct_tiyfAwhTQMLvSSQmxhLI1fBlozkpewxbx7vbiihh5xmmJnvO8zvKzmPKSIh3znbSKm7Hx5jHjaCCbnhcp2I9oxcCtGpqun08_mH_oJcl_LCGONSNDVnl-R1C3nAqlgYkTrEmWYM0adsccK40BEhxxAHOuHyJzm6bihGzMOeThBhOF0lT-f0FzMtu3ke93QXw1KoTbEEh_mAZxx2IywhRTqFVTognWF_gL-RLx7Ggtfv9Yo8_bx7vP1VbX_fP9zebCsrm3apsHNMqa7pm5Z7Jj13oLnS3HHm0ftOud4JzmurUVnfg-z7upYI0IrG1k7JK_Jw8roEL2bOYYK8NwmCOQ5SHgzkJdgRTd8hsxq04qquVdOAhU60yLX3oJzC1SVOLptTKRn9Px9n5pCJOWZiDpmY90xWSP8H2bAcX7JkCONn6BuXXJmF
CitedBy_id crossref_primary_10_3390_biomimetics10060375
Cites_doi 10.3389/fenrg.2023.1259067
10.1016/j.automatica.2012.05.043
10.1109/TPWRS.2010.2102372
10.1061/(asce)ey.1943-7897.0000017
10.1016/j.advengsoft.2013.12.007
10.1109/TPWRS.2014.2357079
10.1016/j.apenergy.2020.116386
10.1109/TPWRS.2022.3166264
10.1016/j.ijhydene.2022.12.194
10.1016/j.enconman.2016.05.039
10.1109/TASE.2023.3263005
10.1016/j.ijepes.2021.107471
10.1109/JIOT.2023.3253693
10.1016/j.knosys.2015.12.022
10.1016/j.energy.2014.05.065
10.1016/j.enconman.2015.06.030
10.1061/(ASCE)EY.1943-7897.0000275
10.1016/j.engappai.2023.105818
10.1109/TPWRS.2022.3145907
10.1109/TSTE.2019.2958361
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.3389/fenrg.2023.1333827
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2296-598X
ExternalDocumentID oai_doaj_org_article_b9e0c8a861644655aca927e18ffa6d6e
10_3389_fenrg_2023_1333827
GroupedDBID 5VS
9T4
AAFWJ
AAYXX
ACGFS
ADBBV
AFPKN
ALMA_UNASSIGNED_HOLDINGS
BCNDV
CITATION
GROUPED_DOAJ
KQ8
M~E
OK1
ID FETCH-LOGICAL-c357t-e9d06695b571f03f1da81681d10feff96dbd2114c8e6cfba3bb443eaa725c4d63
IEDL.DBID DOA
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001192109900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2296-598X
IngestDate Fri Oct 03 12:51:49 EDT 2025
Sat Nov 29 03:07:10 EST 2025
Tue Nov 18 22:00:35 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c357t-e9d06695b571f03f1da81681d10feff96dbd2114c8e6cfba3bb443eaa725c4d63
OpenAccessLink https://doaj.org/article/b9e0c8a861644655aca927e18ffa6d6e
ParticipantIDs doaj_primary_oai_doaj_org_article_b9e0c8a861644655aca927e18ffa6d6e
crossref_primary_10_3389_fenrg_2023_1333827
crossref_citationtrail_10_3389_fenrg_2023_1333827
PublicationCentury 2000
PublicationDate 2024-03-14
PublicationDateYYYYMMDD 2024-03-14
PublicationDate_xml – month: 03
  year: 2024
  text: 2024-03-14
  day: 14
PublicationDecade 2020
PublicationTitle Frontiers in energy research
PublicationYear 2024
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Li (B5) 2022; 136
Yu (B21) 2012; 48
Li (B6) 2021; 285
Qu (B12) 2022; 37
Yu (B19); 26
Yu (B18) 2016; 142
Li (B3); 120
Yu (B17) 2015; 30
Li (B4); 48
Mirjalili (B10) 2016; 96
Qu (B13) 2023; 38
Li (B8); 2023
Li (B7) 2023; 10
Xi (B14) 2020; 11
B9
Mirjalili (B11) 2014; 69
Bahrami (B1) 2014; 72
Xi (B15) 2015; 103
Huan (B2) 2023; 11
Yu (B20); 137
Xi (B16) 2016; 122
References_xml – ident: B9
– volume: 11
  year: 2023
  ident: B2
  article-title: Multi-stage low-carbon planning of an integrated energy system considering demand response
  publication-title: Front. Energy Res.
  doi: 10.3389/fenrg.2023.1259067
– volume: 48
  start-page: 2130
  year: 2012
  ident: B21
  article-title: R(λ) imitation learning for automatic generation control of interconnected power grids
  publication-title: Automatica
  doi: 10.1016/j.automatica.2012.05.043
– volume: 26
  start-page: 1272
  ident: B19
  article-title: Stochastic optimal relaxed automatic generation control in non-markov environment based on multi-step $Q(\lambda)$ learning
  publication-title: IEEE Trans. Power Syst.
  doi: 10.1109/TPWRS.2010.2102372
– volume: 137
  start-page: 116
  ident: B20
  article-title: Stochastic optimal CPS relaxed control methodology for interconnected power systems using Q-learning method
  publication-title: J.
  doi: 10.1061/(asce)ey.1943-7897.0000017
– volume: 69
  start-page: 46
  year: 2014
  ident: B11
  article-title: Grey wolf optimizer
  publication-title: Adv. Eng. Softw.
  doi: 10.1016/j.advengsoft.2013.12.007
– volume: 30
  start-page: 1669
  year: 2015
  ident: B17
  article-title: Multi-agent correlated equilibrium Q(λ) learning for coordinated smart generation control of interconnected power grids
  publication-title: IEEE Trans. Power Syst.
  doi: 10.1109/TPWRS.2014.2357079
– volume: 285
  start-page: 116386
  year: 2021
  ident: B6
  article-title: Efficient experience replay based deep deterministic policy gradient for AGC dispatch in integrated energy system
  publication-title: Appl. Energ.
  doi: 10.1016/j.apenergy.2020.116386
– volume: 38
  start-page: 818
  year: 2023
  ident: B13
  article-title: Environmental-economic unit commitment with robust diffusion control of gas pollutants
  publication-title: IEEE Trans. Power Syst.
  doi: 10.1109/TPWRS.2022.3166264
– volume: 48
  start-page: 14053
  ident: B4
  article-title: Optimal dual-model controller of solid oxide fuel cell output voltage using imitation distributed deep reinforcement learning
  publication-title: Int. J. Hydrogen Energy
  doi: 10.1016/j.ijhydene.2022.12.194
– volume: 122
  start-page: 10
  year: 2016
  ident: B16
  article-title: Wolf pack hunting strategy for automatic generation control of an islanding smart distribution network
  publication-title: Energ Convers. Manage
  doi: 10.1016/j.enconman.2016.05.039
– volume: 2023
  start-page: 1
  ident: B8
  article-title: Brain-inspired deep meta-reinforcement learning for active coordinated fault-tolerant load frequency control of multi-area grids
  publication-title: IEEE Trans. Automation Sci. Eng.
  doi: 10.1109/TASE.2023.3263005
– volume: 136
  start-page: 107471
  year: 2022
  ident: B5
  article-title: Coordinated automatic generation control of interconnected power system with imitation guided exploration multi-agent deep reinforcement learning
  publication-title: Int. J. Elec Power
  doi: 10.1016/j.ijepes.2021.107471
– volume: 10
  start-page: 12923
  year: 2023
  ident: B7
  article-title: Evolutionary multi agent deep meta reinforcement learning method for swarm intelligence energy management of isolated multi area microgrid with internet of things
  publication-title: IEEE Internet Things J.
  doi: 10.1109/JIOT.2023.3253693
– volume: 96
  start-page: 120
  year: 2016
  ident: B10
  article-title: SCA: a Sine Cosine Algorithm for solving optimization problems
  publication-title: Knowl-Based Syst.
  doi: 10.1016/j.knosys.2015.12.022
– volume: 72
  start-page: 434
  year: 2014
  ident: B1
  article-title: Short term electric load forecasting by wavelet transform and grey model improved by PSO (particle swarm optimization) algorithm
  publication-title: Energy
  doi: 10.1016/j.energy.2014.05.065
– volume: 103
  start-page: 82
  year: 2015
  ident: B15
  article-title: A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algorithm for smart generation control of interconnected complex power grids
  publication-title: Energ Convers. Manage
  doi: 10.1016/j.enconman.2015.06.030
– volume: 142
  start-page: 04015012
  year: 2016
  ident: B18
  article-title: Multiagent stochastic dynamic game for smart generation control
  publication-title: J. Energ Eng.
  doi: 10.1061/(ASCE)EY.1943-7897.0000275
– volume: 120
  start-page: 105818
  ident: B3
  article-title: Distributed deep reinforcement learning-based gas supply system coordination management method for solid oxide fuel cell
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2023.105818
– volume: 37
  start-page: 4497
  year: 2022
  ident: B12
  article-title: Stochastic robust real-time power dispatch with wind uncertainty using difference-of-convexity optimization
  publication-title: IEEE Trans. Power Syst.
  doi: 10.1109/TPWRS.2022.3145907
– volume: 11
  start-page: 2417
  year: 2020
  ident: B14
  article-title: A novel multi-agent DDQN-AD method-based distributed strategy for automatic generation control of integrated energy systems
  publication-title: IEEE Trans. Sustain Energ
  doi: 10.1109/TSTE.2019.2958361
SSID ssj0001325410
Score 2.2574086
Snippet To improve automatic generation control (AGC) performance and reduce the wastage of regulation resources in interconnected grids including high-proportion...
SourceID doaj
crossref
SourceType Open Website
Enrichment Source
Index Database
SubjectTerms automatic generation control
China Southern Grid
frequency regulation mileage payment
multi-agent deep deterministic policy gradient algorithm
optimal coordinated control
Title Large-scale deep reinforcement learning method for energy management of power supply units considering regulation mileage payment
URI https://doaj.org/article/b9e0c8a861644655aca927e18ffa6d6e
Volume 11
WOSCitedRecordID wos001192109900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2296-598X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001325410
  issn: 2296-598X
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2296-598X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001325410
  issn: 2296-598X
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07TxwxELYilIIUiCQgXkEu6KKF9dnrRwnoEEVAKRLpupUfYxQpHKd7INFE4p8z411OW5GGZotdz8r6PLZnrPH3MXaiA2gTTVM1MuRKRSGr4FWswEsXa0AXsrmITZjbWzuZuJ8DqS-qCevogTvgzoKDOlpvNcb1xPXlo3cjA8Lm7HXSQKsvRj2DZKqcrkhMfETd3ZLBLMydZRyOu1MSCz_FtExakpEZ7EQDwv6ys1xts60-JOTnXVc-sw8w_cI-DYgCv7LnH1SwXS0QUOAJYMbnUChPYznd4732wx3vBKE5fuFQbvXx-3V9C3_IfEaiaHxBUp5PfIXTecFjL9lJ5vNOmR7Hit_jcoGGfOafyHiH_b4a_7q8rnrxhCrKxiwrcAmjCdeExohcyyySJ4kNkUSdIWenU0iY_KloQcccvAxBKQnem1ETVdJyl21MH6awx7ipg21AapOtUKPobO1SUtgyi9qLZPaZeAWyjT2zOAlc_G0xwyDw2wJ-S-C3Pfj77PvaZtbxarzZ-oLGZ92SOLHLC_SUtveU9n-ecvAePzlkm9gxRVVoQh2xjeV8Bd_Yx_i4_LOYHxcnxOfNv_EL-JHnKA
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Large-scale+deep+reinforcement+learning+method+for+energy+management+of+power+supply+units+considering+regulation+mileage+payment&rft.jtitle=Frontiers+in+energy+research&rft.au=Qian%2C+Ting&rft.au=Yang%2C+Cheng&rft.date=2024-03-14&rft.issn=2296-598X&rft.eissn=2296-598X&rft.volume=11&rft_id=info:doi/10.3389%2Ffenrg.2023.1333827&rft.externalDBID=n%2Fa&rft.externalDocID=10_3389_fenrg_2023_1333827
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-598X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-598X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-598X&client=summon