Optimal operation of regional integrated energy system based on multi-agent deep deterministic policy gradient algorithm

The complex energy coupling and uncertainties of renewable energy and load make the dynamic scheduling of the integrated energy system (IES) very difficult. Therefore, an optimal operation method based on the multi-agent deep deterministic policy gradient algorithm (MADDPG) is proposed. Firstly, the...

Full description

Saved in:
Bibliographic Details
Published in:Energy reports Vol. 8; pp. 932 - 939
Main Authors: Xu, Bohan, Xiang, Yue
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.11.2022
Elsevier
Subjects:
ISSN:2352-4847, 2352-4847
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The complex energy coupling and uncertainties of renewable energy and load make the dynamic scheduling of the integrated energy system (IES) very difficult. Therefore, an optimal operation method based on the multi-agent deep deterministic policy gradient algorithm (MADDPG) is proposed. Firstly, the IES model is established, and the optimal scheduling problem is transformed into the Markov decision problem; Then, the action-space, state-space and reward function of agents are designed which control energy conversion equipment and energy storage equipment respectively. Furtherly, a multi-agent framework is established based on the MADDPG; Finally, a scheduling simulation example was carried out. The simulation results indicate that compared with the single agent, the multi-agent framework can improve the stability of training for agents and the ability to explore the optimal solution.
AbstractList The complex energy coupling and uncertainties of renewable energy and load make the dynamic scheduling of the integrated energy system (IES) very difficult. Therefore, an optimal operation method based on the multi-agent deep deterministic policy gradient algorithm (MADDPG) is proposed. Firstly, the IES model is established, and the optimal scheduling problem is transformed into the Markov decision problem; Then, the action-space, state-space and reward function of agents are designed which control energy conversion equipment and energy storage equipment respectively. Furtherly, a multi-agent framework is established based on the MADDPG; Finally, a scheduling simulation example was carried out. The simulation results indicate that compared with the single agent, the multi-agent framework can improve the stability of training for agents and the ability to explore the optimal solution.
Author Xu, Bohan
Xiang, Yue
Author_xml – sequence: 1
  givenname: Bohan
  surname: Xu
  fullname: Xu, Bohan
– sequence: 2
  givenname: Yue
  surname: Xiang
  fullname: Xiang, Yue
  email: xiang@scu.edu.cn
BookMark eNp9Uctq3TAQFSGFpkl-oCv9gN2xrOgB2ZTQRyCQTbMWsjR2dbEtI6kh_vvq5pZSushmZjjMOcyc84Gcr3FFQj520HbQiU-HFqc9tQwYa0G1IMQZuWD9DWu44vL8n_k9uc75AACdZsBFf0FeHrcSFjvTuGGyJcSVxpEmnOpU0bAWnCqOnuKKadpp3nPBhQ42V6xuL7_mEho74VqoR9xqKZiWsIZcgqNbnIPbadXw4bhi5ymmUH4uV-TdaOeM13_6JXn6-uXH3ffm4fHb_d3nh8bxDkrT2VGh5RJlr7xABSNXSnrpmB6G0fEb1BqFZ8ikGC0w6zQgQ6WlAK_l0F-S-5Ouj_ZgtlSfTbuJNphXIKbJ2FQvndGAGyzvuO3F4LmUTGtdi5LANFcCZNViJy2XYs4Jx796HZhjFOZgjlGYYxQGlKlRVJL6j-RCeXW6JBvmt6m3JypWg54DJpNdddGhDwldqR-Et-i_AWjHqTw
CitedBy_id crossref_primary_10_3390_app13010274
crossref_primary_10_1016_j_ijhydene_2023_03_056
crossref_primary_10_3390_info16080662
crossref_primary_10_3390_pr13010268
crossref_primary_10_1016_j_cie_2024_110143
crossref_primary_10_1016_j_epsr_2022_108979
crossref_primary_10_1016_j_ijhydene_2024_09_164
crossref_primary_10_25729_esr_2025_02_0006
crossref_primary_10_1016_j_energy_2023_127087
crossref_primary_10_1016_j_psep_2024_09_123
Cites_doi 10.1016/j.apenergy.2015.12.089
10.1109/TSG.2020.3034827
10.1016/j.apenergy.2018.09.042
ContentType Journal Article
Copyright 2022 The Author(s)
Copyright_xml – notice: 2022 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.egyr.2022.08.066
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
EISSN 2352-4847
EndPage 939
ExternalDocumentID oai_doaj_org_article_0cba414a36bd47729997298702948607
10_1016_j_egyr_2022_08_066
S2352484722014949
GroupedDBID 0R~
0SF
4.4
457
5VS
6I.
AACTN
AAEDT
AAEDW
AAFTH
AAIKJ
AALRI
AAXUO
ABMAC
ACGFS
ADBBV
ADEZE
AEXQZ
AFTJW
AGHFR
AITUG
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
BCNDV
EBS
EJD
FDB
GROUPED_DOAJ
KQ8
M41
M~E
NCXOZ
O9-
OK1
ROL
SSZ
AAYWO
AAYXX
ACVFH
ADCNI
ADVLN
AEUPX
AFJKZ
AFPUW
AIGII
AKBMS
AKRWK
AKYEP
APXCP
CITATION
ID FETCH-LOGICAL-c410t-1af8ea47e738d6e80f4887d7c29bbfc45e99e6d2e276fa02ac90e2e89760d97b3
IEDL.DBID DOA
ISICitedReferencesCount 11
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000865597700051&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2352-4847
IngestDate Fri Oct 03 12:53:43 EDT 2025
Thu Nov 13 04:28:43 EST 2025
Tue Nov 18 21:53:30 EST 2025
Wed May 17 01:48:01 EDT 2023
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Integrated energy system
Deep deterministic policy gradient algorithm
Multi-agent scheduling
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c410t-1af8ea47e738d6e80f4887d7c29bbfc45e99e6d2e276fa02ac90e2e89760d97b3
OpenAccessLink https://doaj.org/article/0cba414a36bd47729997298702948607
PageCount 8
ParticipantIDs doaj_primary_oai_doaj_org_article_0cba414a36bd47729997298702948607
crossref_primary_10_1016_j_egyr_2022_08_066
crossref_citationtrail_10_1016_j_egyr_2022_08_066
elsevier_sciencedirect_doi_10_1016_j_egyr_2022_08_066
PublicationCentury 2000
PublicationDate November 2022
2022-11-00
2022-11-01
PublicationDateYYYYMMDD 2022-11-01
PublicationDate_xml – month: 11
  year: 2022
  text: November 2022
PublicationDecade 2020
PublicationTitle Energy reports
PublicationYear 2022
Publisher Elsevier Ltd
Elsevier
Publisher_xml – name: Elsevier Ltd
– name: Elsevier
References Yang, Hu, Ai, Wu, Yang (b2) 2020; 130
An, Wang, Yuan (b8) 2020; 8
Munos, Stepleton, Harutyunyan, Bellemare (b9) 2016
Zhang, Li, Gao, Zhou (b7) 2019; 42
Zhang, Dehghanpour, Wang (b6) 2021; 12
Foruzan, Leen-Kiat, Soh, Sohrab, Asgarpoor (b4) 2018; 25
Wang, Lv, Peng, Song, Li, Xu (b1) 2018; 230
Ji Wang, Xu, Fang, Zhang (b5) 2019; 12
Mckenna, Thomson (b10) 2016; 165
Zhang, Zhang, Qiu (b3) 2020; 6
An (10.1016/j.egyr.2022.08.066_b8) 2020; 8
Zhang (10.1016/j.egyr.2022.08.066_b3) 2020; 6
Munos (10.1016/j.egyr.2022.08.066_b9) 2016
Mckenna (10.1016/j.egyr.2022.08.066_b10) 2016; 165
Zhang (10.1016/j.egyr.2022.08.066_b6) 2021; 12
Wang (10.1016/j.egyr.2022.08.066_b1) 2018; 230
Foruzan (10.1016/j.egyr.2022.08.066_b4) 2018; 25
Yang (10.1016/j.egyr.2022.08.066_b2) 2020; 130
Ji Wang (10.1016/j.egyr.2022.08.066_b5) 2019; 12
Zhang (10.1016/j.egyr.2022.08.066_b7) 2019; 42
References_xml – volume: 165
  start-page: 445
  year: 2016
  end-page: 461
  ident: b10
  article-title: High-resolution stochastic integrated thermal–electrical domestic demand model
  publication-title: Appl Energy
– volume: 12
  start-page: 1048
  year: 2021
  end-page: 1062
  ident: b6
  article-title: Multi-agent safe policy learning for power management of networked microgrids
  publication-title: IEEE Trans Smart Grid
– volume: 25
  start-page: 876
  year: 2018
  end-page: 889
  ident: b4
  article-title: Reinforcement learning approach for optimal distributed energy management in a microgrid
  publication-title: IEEE Trans Power Syst
– volume: 12
  start-page: 2291
  year: 2019
  end-page: 2303
  ident: b5
  article-title: Real-time energy management of a microgrid using deep reinforcement learning
  publication-title: Energies
– volume: 230
  start-page: 1242
  year: 2018
  end-page: 1254
  ident: b1
  article-title: Modeling and optimal operation of community integrated energy systems: a case study from China
  publication-title: Appl Energy
– volume: 42
  start-page: 1077
  year: 2019
  end-page: 1089
  ident: b7
  article-title: Distributed optimal energy management for energy internet
  publication-title: IEEE Trans Ind Inf
– volume: 6
  start-page: 213
  year: 2020
  end-page: 225
  ident: b3
  article-title: Deep reinforcement learning for power system applications: An overview
  publication-title: CSEE J Power Energy Syst
– volume: 8
  start-page: 1166
  year: 2020
  end-page: 1179
  ident: b8
  article-title: Real-time optimal operation control of micro energy grid coupling with electricity- thermal -gas considering prosumer characteristics
  publication-title: IEEE Access
– year: 2016
  ident: b9
  article-title: Safe and efficient off-policy reinforcement learning
– volume: 130
  start-page: 1102
  year: 2020
  end-page: 1114
  ident: b2
  article-title: Transactive energy supported economic operation for multi-energy complementary microgrids
  publication-title: IEEE Trans Smart Grid
– volume: 165
  start-page: 445
  issue: 2016
  year: 2016
  ident: 10.1016/j.egyr.2022.08.066_b10
  article-title: High-resolution stochastic integrated thermal–electrical domestic demand model
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2015.12.089
– volume: 130
  start-page: 1102
  issue: 2020
  year: 2020
  ident: 10.1016/j.egyr.2022.08.066_b2
  article-title: Transactive energy supported economic operation for multi-energy complementary microgrids
  publication-title: IEEE Trans Smart Grid
– volume: 12
  start-page: 1048
  issue: 2021
  year: 2021
  ident: 10.1016/j.egyr.2022.08.066_b6
  article-title: Multi-agent safe policy learning for power management of networked microgrids
  publication-title: IEEE Trans Smart Grid
  doi: 10.1109/TSG.2020.3034827
– volume: 12
  start-page: 2291
  issue: 2019
  year: 2019
  ident: 10.1016/j.egyr.2022.08.066_b5
  article-title: Real-time energy management of a microgrid using deep reinforcement learning
  publication-title: Energies
– volume: 25
  start-page: 876
  issue: 2018
  year: 2018
  ident: 10.1016/j.egyr.2022.08.066_b4
  article-title: Reinforcement learning approach for optimal distributed energy management in a microgrid
  publication-title: IEEE Trans Power Syst
– volume: 8
  start-page: 1166
  issue: 2020
  year: 2020
  ident: 10.1016/j.egyr.2022.08.066_b8
  article-title: Real-time optimal operation control of micro energy grid coupling with electricity- thermal -gas considering prosumer characteristics
  publication-title: IEEE Access
– volume: 230
  start-page: 1242
  issue: 2018
  year: 2018
  ident: 10.1016/j.egyr.2022.08.066_b1
  article-title: Modeling and optimal operation of community integrated energy systems: a case study from China
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2018.09.042
– volume: 42
  start-page: 1077
  issue: 2019
  year: 2019
  ident: 10.1016/j.egyr.2022.08.066_b7
  article-title: Distributed optimal energy management for energy internet
  publication-title: IEEE Trans Ind Inf
– volume: 6
  start-page: 213
  issue: 2020
  year: 2020
  ident: 10.1016/j.egyr.2022.08.066_b3
  article-title: Deep reinforcement learning for power system applications: An overview
  publication-title: CSEE J Power Energy Syst
– year: 2016
  ident: 10.1016/j.egyr.2022.08.066_b9
SSID ssj0001920463
Score 2.3040328
Snippet The complex energy coupling and uncertainties of renewable energy and load make the dynamic scheduling of the integrated energy system (IES) very difficult....
SourceID doaj
crossref
elsevier
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 932
SubjectTerms Deep deterministic policy gradient algorithm
Integrated energy system
Multi-agent scheduling
Title Optimal operation of regional integrated energy system based on multi-agent deep deterministic policy gradient algorithm
URI https://dx.doi.org/10.1016/j.egyr.2022.08.066
https://doaj.org/article/0cba414a36bd47729997298702948607
Volume 8
WOSCitedRecordID wos000865597700051&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: 2352-4847
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001920463
  issn: 2352-4847
  databaseCode: DOA
  dateStart: 20150101
  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: 2352-4847
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001920463
  issn: 2352-4847
  databaseCode: M~E
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwELYqxKEXBCpVl5d84IaiOo7Xdo6AQD0A7aGt9hb5MYFFsLta0gou_HZm7Oxqe1kuvViK5YytmUnmszTzDWPHEbyDKGwRVZCFiqoqrAy-wCcAqSrRJiLt31fm5saORvWPlVZflBOW6YGz4r6K4J0qlau0j4qgIFV64kVZyJr6J6U6cmHqlcvUfcYtRIWVOssN8Qz4D-4rZnJyF9y-EBmolJm_U_8TlRJ5_0pwWgk4l9tsq0eK_DSfcId9gMkn9vwdP_FHnJ7OINuOT1tO3RUIUfMl-UPkkIr6eGZq5hSsIsfVKYGwcFRQxSPADIecD5MIm_ks0QRzlEGZYB13D7fT-bi7e9xlvy4vfp5_K_rmCUVQpeiK0rUWnDJgKhs1WFK6NdEEWXvfBjWEugYdJUijWyekC7UACRbhiYi18dVntjGZTuAL4-Uw4C0ltqrVoHRU1pcRJSN0cMajeQesXCivCT2zODW4eGgWKWT3DSm8IYU31PVS6wE7Wb4zy7waa1efkU2WK4kTO02gpzS9pzTvecqADRcWbXp4kWEDihqv2Xzvf2y-zz6SyFzFeMA2uvkfOGSb4W83fpofJefF8fr14g3GOfP0
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=Optimal+operation+of+regional+integrated+energy+system+based+on+multi-agent+deep+deterministic+policy+gradient+algorithm&rft.jtitle=Energy+reports&rft.au=Xu%2C+Bohan&rft.au=Xiang%2C+Yue&rft.date=2022-11-01&rft.issn=2352-4847&rft.eissn=2352-4847&rft.volume=8&rft.spage=932&rft.epage=939&rft_id=info:doi/10.1016%2Fj.egyr.2022.08.066&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_egyr_2022_08_066
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2352-4847&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2352-4847&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2352-4847&client=summon