Fault reconfiguration control strategy of islanded marine ranching power supply system based on deep reinforcement learning
•A fault reconstruction method is proposed for island-mode marine ranching power systems.•The method uses an improved Noisy-Dueling DQN for fast, autonomous power topology adjustment.•It accounts for both clean energy and complex marine environmental influences.•Noise networks improve exploration an...
Uloženo v:
| Vydáno v: | International journal of electrical power & energy systems Ročník 169; s. 110796 |
|---|---|
| Hlavní autoři: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.08.2025
Elsevier |
| Témata: | |
| ISSN: | 0142-0615 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | •A fault reconstruction method is proposed for island-mode marine ranching power systems.•The method uses an improved Noisy-Dueling DQN for fast, autonomous power topology adjustment.•It accounts for both clean energy and complex marine environmental influences.•Noise networks improve exploration and generalization in real-time reconstruction control.•Transfer learning accelerates model training by reusing knowledge from different operation states.
When the islanded marine ranching power system fails, a rapid and accurate control strategy is crucial to maintain continuous power supply to critical loads and maximize the restoration of lost load power. To ensure the safe operation of the marine ranching power system, a fault reconstruction control method based on an improved Noisy-Dueling Deep Q-Network (Noisy-Dueling DQN) algorithm is proposed. Firstly, a reinforcement learning environment for reconstructing the marine ranching power system, including distributed generation (DG), is constructed. This enables the agent to continuously update model parameters through interaction with the environment in order to learn the optimal reconstruction strategy. To enhance convergence efficiency and generalization capability of the algorithm, noise networks are used to improve exploration ability of dueling DQN algorithm by implementing linear layers with learnable noise using an adaptive noise model. Finally, through analysis of fault reconstruction cases in different operating conditions of the marine ranching power system, it is demonstrated that this proposed algorithm can provide optimal reconstruction strategies within as short as 70 ms while achieving objectives such as maximum load recovery, minimum switching times, and minimum network losses. To illustrate, in the event of a fault occurring on lines b7, b18, and b25 at 8:00, resulting in the withdrawal of 58 kW of loads from operation, the proposed algorithm is configured to restore all the lost loads and minimise the network loss to 0.0112 kW. |
|---|---|
| AbstractList | •A fault reconstruction method is proposed for island-mode marine ranching power systems.•The method uses an improved Noisy-Dueling DQN for fast, autonomous power topology adjustment.•It accounts for both clean energy and complex marine environmental influences.•Noise networks improve exploration and generalization in real-time reconstruction control.•Transfer learning accelerates model training by reusing knowledge from different operation states.
When the islanded marine ranching power system fails, a rapid and accurate control strategy is crucial to maintain continuous power supply to critical loads and maximize the restoration of lost load power. To ensure the safe operation of the marine ranching power system, a fault reconstruction control method based on an improved Noisy-Dueling Deep Q-Network (Noisy-Dueling DQN) algorithm is proposed. Firstly, a reinforcement learning environment for reconstructing the marine ranching power system, including distributed generation (DG), is constructed. This enables the agent to continuously update model parameters through interaction with the environment in order to learn the optimal reconstruction strategy. To enhance convergence efficiency and generalization capability of the algorithm, noise networks are used to improve exploration ability of dueling DQN algorithm by implementing linear layers with learnable noise using an adaptive noise model. Finally, through analysis of fault reconstruction cases in different operating conditions of the marine ranching power system, it is demonstrated that this proposed algorithm can provide optimal reconstruction strategies within as short as 70 ms while achieving objectives such as maximum load recovery, minimum switching times, and minimum network losses. To illustrate, in the event of a fault occurring on lines b7, b18, and b25 at 8:00, resulting in the withdrawal of 58 kW of loads from operation, the proposed algorithm is configured to restore all the lost loads and minimise the network loss to 0.0112 kW. When the islanded marine ranching power system fails, a rapid and accurate control strategy is crucial to maintain continuous power supply to critical loads and maximize the restoration of lost load power. To ensure the safe operation of the marine ranching power system, a fault reconstruction control method based on an improved Noisy-Dueling Deep Q-Network (Noisy-Dueling DQN) algorithm is proposed. Firstly, a reinforcement learning environment for reconstructing the marine ranching power system, including distributed generation (DG), is constructed. This enables the agent to continuously update model parameters through interaction with the environment in order to learn the optimal reconstruction strategy. To enhance convergence efficiency and generalization capability of the algorithm, noise networks are used to improve exploration ability of dueling DQN algorithm by implementing linear layers with learnable noise using an adaptive noise model. Finally, through analysis of fault reconstruction cases in different operating conditions of the marine ranching power system, it is demonstrated that this proposed algorithm can provide optimal reconstruction strategies within as short as 70 ms while achieving objectives such as maximum load recovery, minimum switching times, and minimum network losses. To illustrate, in the event of a fault occurring on lines b7, b18, and b25 at 8:00, resulting in the withdrawal of 58 kW of loads from operation, the proposed algorithm is configured to restore all the lost loads and minimise the network loss to 0.0112 kW. |
| ArticleNumber | 110796 |
| Author | Liu, Hao Wang, Rongjie Cui, Yabo Zhang, Bo Sun, Zhouyang Wang, Yichun Desong, Jiang |
| Author_xml | – sequence: 1 givenname: Yichun orcidid: 0009-0008-9908-3526 surname: Wang fullname: Wang, Yichun organization: School of Marine Engineering, Jimei University, Xiamen 361021, China – sequence: 2 givenname: Bo surname: Zhang fullname: Zhang, Bo organization: School of Marine Engineering, Jimei University, Xiamen 361021, China – sequence: 3 givenname: Rongjie surname: Wang fullname: Wang, Rongjie organization: School of Marine Engineering, Jimei University, Xiamen 361021, China – sequence: 4 givenname: Jiang surname: Desong fullname: Desong, Jiang organization: School of Marine Engineering, Jimei University, Xiamen 361021, China – sequence: 5 givenname: Yabo surname: Cui fullname: Cui, Yabo organization: School of Marine Engineering, Jimei University, Xiamen 361021, China – sequence: 6 givenname: Zhouyang surname: Sun fullname: Sun, Zhouyang organization: School of Marine Engineering, Jimei University, Xiamen 361021, China – sequence: 7 givenname: Hao surname: Liu fullname: Liu, Hao organization: School of Marine Engineering, Jimei University, Xiamen 361021, China |
| BookMark | eNqFkUtrWzEQhbVwoHbSf9CF_oBdPe7D6qJQTPOAQDfpWugxcnW5li6SnGD65yP7hi6ySFfDHOZ8MOes0CLEAAh9oWRDCe2-Dhs_wAR5wwhrN5SSXnQLtCS0YWvS0fYTWuU8EFL1hi3R31t1HAtOYGJwfn9MqvgYcN1KiiPOpQqwP-HosM-jChYsPqjkA-Ckgvnjwx5P8QUSzsdpGk84n3KBA9Yq18tKsgBTxfvgYjJwgFDwCCqFarxBV06NGT6_zWv0-_bn0-5-_fjr7mH343FtGkbKmltOgPMG-m1rhWXWcehpx4HqTgsOltCt6I1hW2111yujOCG616wzjd1awq_Rw8y1UQ1ySr4-cJJReXkRYtpLlYo3I0jXagXCUiuUazShygla6QIME6ZjbWU1M8ukmHMC949HiTwXIAc5FyDPBci5gGr79s5mfLlEXQP24__M32cz1JCePSSZjYdgwPraW6lf-I8Br0qtrBs |
| CitedBy_id | crossref_primary_10_1016_j_rineng_2025_107398 |
| Cites_doi | 10.1109/TIFS.2019.2960657 10.1016/j.egyai.2023.100241 10.1109/ICMSP53480.2021.9513376 10.1016/j.apenergy.2020.115900 10.1016/j.energy.2018.01.111 10.1016/j.future.2023.10.002 10.1109/TPEL.2021.3128409 10.1109/ICPSAsia55496.2022.9949762 10.32604/ee.2024.054662 10.1016/j.ocecoaman.2022.106387 10.1109/AICIT55386.2022.9930296 10.1016/j.epsr.2021.107707 10.1109/TSG.2018.2850358 10.1109/ACCESS.2021.3089625 10.1088/1742-6596/2418/1/012101 10.1016/0378-7796(95)00991-4 10.1016/j.advengsoft.2023.103487 10.1109/ACCESS.2018.2798505 10.1016/j.jenvman.2023.117515 10.1109/CEECT55960.2022.10030706 10.1109/ACCESS.2021.3109247 10.1016/j.ocecoaman.2023.106821 10.1016/j.eswa.2023.121880 10.1109/CAC57257.2022.10054880 10.1016/j.jer.2023.09.001 10.23919/JSEE.2022.000048 |
| ContentType | Journal Article |
| Copyright | 2025 The Authors |
| Copyright_xml | – notice: 2025 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.ijepes.2025.110796 |
| 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 |
| Discipline | Engineering |
| ExternalDocumentID | oai_doaj_org_article_f5bae9d1d9af4b01af911899ec29c625 10_1016_j_ijepes_2025_110796 S0142061525003448 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1~. 1~5 29J 4.4 457 4G. 5GY 5VS 6I. 7-5 71M 8P~ 9JN AAEDT AAEDW AAFTH AAHCO AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARJD AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFS ACNNM ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO ADTZH ADVLN AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AFXIZ AGCQF AGHFR AGQPQ AGRNS AGUBO AGYEJ AHHHB AHIDL AHJVU AHZHX AI. AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP ASPBG AVWKF AXJTR AZFZN BELTK BJAXD BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EFKBS EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ GROUPED_DOAJ HVGLF HZ~ IHE J1W JARJE JJJVA K-O KOM LY6 LY7 M41 MO0 O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SAC SDF SDG SDP SES SET SEW SPC SPCBC SSR SST SSV SSZ T5K VH1 WUQ ZMT ZY4 ~02 ~G- 9DU AAYXX ACLOT CITATION EFLBG ~HD |
| ID | FETCH-LOGICAL-c420t-3d30e334e785d9d2df3e7163e1b6b93ed01897cc28bdb67aca300b7b26c4d8d03 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001506820800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0142-0615 |
| IngestDate | Fri Oct 03 12:45:18 EDT 2025 Tue Nov 18 22:32:30 EST 2025 Sat Nov 29 07:46:45 EST 2025 Sat Aug 09 17:31:02 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Markov modeling Island AC power supply system Deep reinforcement learning Fault recovery and reconstruction |
| Language | English |
| License | This is an open access article under the CC BY-NC license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c420t-3d30e334e785d9d2df3e7163e1b6b93ed01897cc28bdb67aca300b7b26c4d8d03 |
| ORCID | 0009-0008-9908-3526 |
| OpenAccessLink | https://doaj.org/article/f5bae9d1d9af4b01af911899ec29c625 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_f5bae9d1d9af4b01af911899ec29c625 crossref_primary_10_1016_j_ijepes_2025_110796 crossref_citationtrail_10_1016_j_ijepes_2025_110796 elsevier_sciencedirect_doi_10_1016_j_ijepes_2025_110796 |
| PublicationCentury | 2000 |
| PublicationDate | August 2025 2025-08-00 2025-08-01 |
| PublicationDateYYYYMMDD | 2025-08-01 |
| PublicationDate_xml | – month: 08 year: 2025 text: August 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | International journal of electrical power & energy systems |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | He Y, Guo Y. Fault Reconstruction of Medium Voltage DC Power System in Ships Based on Simulated Annealing Particle Swarm Algorithm. Conference Fault Reconstruction of Medium Voltage DC Power System in Ships Based on Simulated Annealing Particle Swarm Algorithm. p. 140-4. Li B, Li W, Pan J, Luo J. Self-Healing Fault Reconstruction Strategy for Island Emergency Power Grid Based on Floyd-MPSO. Conference Self-Healing Fault Reconstruction Strategy for Island Emergency Power Grid Based on Floyd-MPSO. p. 2096-100. Ding, Qu, Wu, Qin, Yang, Blaabjerg (b0060) 2020; 15 Gallego, Martín, Díaz, Garrido (b0140) 2023; 13 Yang, Zhang, Zhang, Cheng, Li, Zhou (b0050) 2024; 121 Wang GY, Jiang CM. Fault Reconstruction Method of Ship Power Grid based on Improved Gray Wolf Optimizer. Conference Fault Reconstruction Method of Ship Power Grid based on Improved Gray Wolf Optimizer. p. 1447-51. Jin, Quan (b0010) 2023; 244 Zhang, Meng, Liu (b0080) 2019; 47 Zhang X, Xiao J, Wang X. Research on fault reconstruction algorithm of electric shipboard power system. Conference Research on fault reconstruction algorithm of electric shipboard power system. p. 164-8. Huang J, Research on Universal Algorithm for Shipboard Power System network reconfiguration. Huazhong University of Science and Technology Wuhan, Hubei 430074, P. R. China January, 2011. Li, Xiao, Chen, Tan, Cao (b0180) 2019; 10 Mahdavi, Alhelou, Bagheri, Djokic, Ramos (b0125) 2021; 9 Zhang, Chen, Wang, Li (b0160) 2024; 48 Zhang Q, Wen X, Lai J. Research on Fault Recovery and Reconstruction Algorithm of Distribution Network with Distributed Generation. Conference Research on Fault Recovery and Reconstruction Algorithm of Distribution Network with Distributed Generation. p. 1-4. Hou, Agos Jawaddi, Ismail (b0175) 2024; 151 Chen, Dai, Zhou, Sun, Shen (b0185) 2013; 37 Xu, Guerrero, Lashab, Wei, Bazmohammadi, Vasquez (b0065) 2022; 37 Zhang, Wu, Li, Yamashita, Huang (b0105) 2022; 205 Wang, Hu, Yang (b0145) 2022; 33 Wan, Li, Zhang, Zhang, Wang (b0015) 2023; 231 Li, Zheng (b0075) 2018; 40 Long, Shi (b0085) 2023; 2418 Shang, Fu, Bao, Xiao, Xu, Liu (b0150) 2023 Jiao, Yue, Suo, Zhang, Li, Xu (b0005) 2023; 335 Ma, Zhang, Ren (b0205) 2018; 44 Jiang, Jiang, Qiao (b0195) 2011; 31 Rahmati, Taherinasab (b0100) 2023; 5 Han, Yang, Zhan, Wu (b0190) 2020; 48 Oh, Yoon, Kim (b0135) 2020; 280 Tang, Li, Wu, Liu, Yang (b0170) 2024; 238 Mu (b0040) 2017; 39 Zhang, Sun, Liu, Zhang (b0200) 2018; 40 Hao Qirun. Research on Power Flow and Reconfiguration Algorithm of Ship MVDC Power Systems [D]. Dalian Maritime University, 2022. The DOI: 10.26989 /, dc nki. Gdlhu. 2022.001415. Mishra, Tripathy, Ray (b0055) 2024; 12 Chu, Huang (b0070) 2017; 25 Ćurčić, Özveren, Crowe, Lo (b0045) 1995; 35 Babaei, Shi, Abdelwahed (b0030) 2018; 6 Azizivahed, Narimani, Fathi, Naderi, Safarpour, Narimani (b0120) 2018; 147 Marugán (b0165) 2023; 183 Wang, Zhu, Xu, Bao, Di (b0155) 2021; 9 Xu (b0025) 2023 Yang (10.1016/j.ijepes.2025.110796_b0050) 2024; 121 Xu (10.1016/j.ijepes.2025.110796_b0065) 2022; 37 Jiao (10.1016/j.ijepes.2025.110796_b0005) 2023; 335 Mishra (10.1016/j.ijepes.2025.110796_b0055) 2024; 12 Ćurčić (10.1016/j.ijepes.2025.110796_b0045) 1995; 35 Zhang (10.1016/j.ijepes.2025.110796_b0200) 2018; 40 Mu (10.1016/j.ijepes.2025.110796_b0040) 2017; 39 Han (10.1016/j.ijepes.2025.110796_b0190) 2020; 48 10.1016/j.ijepes.2025.110796_b0095 Zhang (10.1016/j.ijepes.2025.110796_b0160) 2024; 48 Ding (10.1016/j.ijepes.2025.110796_b0060) 2020; 15 Gallego (10.1016/j.ijepes.2025.110796_b0140) 2023; 13 10.1016/j.ijepes.2025.110796_b0130 Ma (10.1016/j.ijepes.2025.110796_b0205) 2018; 44 Babaei (10.1016/j.ijepes.2025.110796_b0030) 2018; 6 Rahmati (10.1016/j.ijepes.2025.110796_b0100) 2023; 5 10.1016/j.ijepes.2025.110796_b0090 Wang (10.1016/j.ijepes.2025.110796_b0145) 2022; 33 Hou (10.1016/j.ijepes.2025.110796_b0175) 2024; 151 Mahdavi (10.1016/j.ijepes.2025.110796_b0125) 2021; 9 Azizivahed (10.1016/j.ijepes.2025.110796_b0120) 2018; 147 Xu (10.1016/j.ijepes.2025.110796_b0025) 2023 Oh (10.1016/j.ijepes.2025.110796_b0135) 2020; 280 10.1016/j.ijepes.2025.110796_b0110 10.1016/j.ijepes.2025.110796_b0035 Shang (10.1016/j.ijepes.2025.110796_b0150) 2023 10.1016/j.ijepes.2025.110796_b0115 Chu (10.1016/j.ijepes.2025.110796_b0070) 2017; 25 Wang (10.1016/j.ijepes.2025.110796_b0155) 2021; 9 Jin (10.1016/j.ijepes.2025.110796_b0010) 2023; 244 Tang (10.1016/j.ijepes.2025.110796_b0170) 2024; 238 Wan (10.1016/j.ijepes.2025.110796_b0015) 2023; 231 Chen (10.1016/j.ijepes.2025.110796_b0185) 2013; 37 Long (10.1016/j.ijepes.2025.110796_b0085) 2023; 2418 10.1016/j.ijepes.2025.110796_b0020 Li (10.1016/j.ijepes.2025.110796_b0075) 2018; 40 Jiang (10.1016/j.ijepes.2025.110796_b0195) 2011; 31 Zhang (10.1016/j.ijepes.2025.110796_b0105) 2022; 205 Marugán (10.1016/j.ijepes.2025.110796_b0165) 2023; 183 Li (10.1016/j.ijepes.2025.110796_b0180) 2019; 10 Zhang (10.1016/j.ijepes.2025.110796_b0080) 2019; 47 |
| References_xml | – volume: 121 start-page: 3487 year: 2024 end-page: 3547 ident: b0050 article-title: A Critical Review of Active Distribution Network Reconfiguration: Concepts, Development, and Perspectives publication-title: Energy Eng – volume: 39 start-page: 55 year: 2017 end-page: 57 ident: b0040 article-title: Research on ship power system based on intelligent reconfiguration algorithm publication-title: SHIP SCIENCE AND TECHNOLOGY – volume: 44 start-page: 33 year: 2018 end-page: 38 ident: b0205 article-title: Shipboard power grid reconstruction based on environment Pareto dominated selection differential evolution algorithm publication-title: J Dalian Maritime Univ – volume: 35 start-page: 73 year: 1995 end-page: 86 ident: b0045 article-title: Electric power distribution network restoration: a survey of papers and a review of the restoration problem publication-title: Electr Pow Syst Res – volume: 6 start-page: 9430 year: 2018 end-page: 9441 ident: b0030 article-title: A survey on fault detection, isolation, and reconfiguration methods in electric ship power systems publication-title: IEEE Access – volume: 31 start-page: 118 year: 2011 end-page: 124 ident: b0195 article-title: Intelligent Service Restoration of Shipboard Power Network Using Nature Multiobjective Evolutionary Algorithm publication-title: Proc CSEE – volume: 48 start-page: 151 year: 2024 end-page: 158 ident: b0160 article-title: Distribution network fault recovery decision based on graph reinforcement learning publication-title: Automation of Electric Power Systems – volume: 280 year: 2020 ident: b0135 article-title: Online reconfiguration scheme of self-sufficient distribution network based on a reinforcement learning approach publication-title: Appl Energy – volume: 12 start-page: 173 year: 2024 end-page: 181 ident: b0055 article-title: A survey on different techniques for distribution network reconfiguration publication-title: Journal of Engineering Research – reference: Huang J, Research on Universal Algorithm for Shipboard Power System network reconfiguration. Huazhong University of Science and Technology Wuhan, Hubei 430074, P. R. China January, 2011. – volume: 183 year: 2023 ident: b0165 article-title: Applications of Reinforcement Learning for maintenance of engineering systems: A review publication-title: Adv Eng Softw – volume: 238 year: 2024 ident: b0170 article-title: A Systematic Literature Review of Reinforcement Learning-based Knowledge Graph Research publication-title: Expert Syst Appl – volume: 37 start-page: 82 year: 2013 end-page: 88 ident: b0185 article-title: Distribution System Reconfiguration Considering Distributed Generators and Plug-in Electric Vehicles publication-title: Power System Technology – volume: 37 start-page: 4105 year: 2022 end-page: 4120 ident: b0065 article-title: A Review of DC Shipboard Microgrids—Part II: Control Architectures, Stability Analysis, and Protection Schemes publication-title: IEEE Trans Power Electron – reference: Zhang X, Xiao J, Wang X. Research on fault reconstruction algorithm of electric shipboard power system. Conference Research on fault reconstruction algorithm of electric shipboard power system. p. 164-8. – volume: 147 start-page: 896 year: 2018 end-page: 914 ident: b0120 article-title: Multi-objective dynamic distribution feeder reconfiguration in automated distribution systems publication-title: Energy – volume: 48 start-page: 14 year: 2020 end-page: 21 ident: b0190 article-title: Fault reconfiguration strategy of a shipboard power system considering reliability constraints publication-title: Power System Protection and Control – reference: Zhang Q, Wen X, Lai J. Research on Fault Recovery and Reconstruction Algorithm of Distribution Network with Distributed Generation. Conference Research on Fault Recovery and Reconstruction Algorithm of Distribution Network with Distributed Generation. p. 1-4. – start-page: 1 - year: 2023 ident: b0150 article-title: Dynamic Fault Reconfiguration of Distribution Networks in Ship Power Systems Based on Deep Reinforcement Learning Approach publication-title: IEEE Trans Transp Electrif – volume: 9 start-page: 90358 year: 2021 end-page: 90365 ident: b0155 article-title: Distribution Network Reconfiguration Based on NoisyNet Deep Q-Learning Network publication-title: IEEE Access – reference: Li B, Li W, Pan J, Luo J. Self-Healing Fault Reconstruction Strategy for Island Emergency Power Grid Based on Floyd-MPSO. Conference Self-Healing Fault Reconstruction Strategy for Island Emergency Power Grid Based on Floyd-MPSO. p. 2096-100. – volume: 231 year: 2023 ident: b0015 article-title: Sustainable collaborative innovation capability enhancement paths of marine ranching: Supernetwork analysis perspective publication-title: Ocean Coast Manag – volume: 335 year: 2023 ident: b0005 article-title: Construction and influencing factors of an early warning system for marine ranching ecological security: Experience from China's coastal areas publication-title: J Environ Manage – year: 2023 ident: b0025 article-title: Ship Power System Network Reconfiguration Based on Improved Particle Swarm Algorithm publication-title: Master – volume: 2418 year: 2023 ident: b0085 article-title: Research on fault reconstruction of ship regional distribution System based on improved genetic algorithm publication-title: J Phys Conf Ser – volume: 40 start-page: 73 year: 2018 end-page: 75 ident: b0200 article-title: Research on power supply recovery of ship power system based on genetic algorithm publication-title: Ship Sci Technol – volume: 244 year: 2023 ident: b0010 article-title: Assessment of marine ranching ecological development using DPSIR-TOPSIS and obstacle degree analysis: A case study of Zhoushan publication-title: Ocean Coast Manag – volume: 47 start-page: 90 year: 2019 end-page: 96 ident: b0080 article-title: Reconstruction of ship power system network fault based on improved two particle swarm algorithm publication-title: Power System Protection and Control – volume: 9 start-page: 122872 year: 2021 end-page: 122906 ident: b0125 article-title: A Comprehensive Review of Metaheuristic Methods for the Reconfiguration of Electric Power Distribution Systems and Comparison With a Novel Approach Based on Efficient Genetic Algorithm publication-title: IEEE Access – volume: 5 year: 2023 ident: b0100 article-title: The importance of reconfiguration of the distribution network to achieve minimization of energy losses using the dragonfly algorithm. e-Prime - Advances in Electrical Engineering publication-title: Electronics and Energy – volume: 15 start-page: 3443 year: 2020 end-page: 3453 ident: b0060 article-title: Defense Strategy for Resilient Shipboard Power Systems Considering Sequential Attacks publication-title: IEEE Trans Inf Forensics Secur – reference: Hao Qirun. Research on Power Flow and Reconfiguration Algorithm of Ship MVDC Power Systems [D]. Dalian Maritime University, 2022. The DOI: 10.26989 /, dc nki. Gdlhu. 2022.001415. – volume: 25 start-page: 37 year: 2017 end-page: 41 ident: b0070 article-title: Reconfiguration of shipboard power system based on double sub-swarms particle swarm optimization publication-title: Electronic Design Engineering – volume: 10 start-page: 4138 year: 2019 end-page: 4150 ident: b0180 article-title: Service Restoration Model With Mixed-Integer Second-Order Cone Programming for Distribution Network With Distributed Generations publication-title: IEEE Trans Smart Grid – reference: He Y, Guo Y. Fault Reconstruction of Medium Voltage DC Power System in Ships Based on Simulated Annealing Particle Swarm Algorithm. Conference Fault Reconstruction of Medium Voltage DC Power System in Ships Based on Simulated Annealing Particle Swarm Algorithm. p. 140-4. – volume: 13 year: 2023 ident: b0140 article-title: Maintaining flexibility in smart grid consumption through deep learning and deep reinforcement learning publication-title: Energy AI – volume: 40 start-page: 79 year: 2018 end-page: 81 ident: b0075 article-title: Research on reconstruction algorithm of fault recovery in power distribution network of ship power system publication-title: Ship Science and Technology – volume: 151 start-page: 214 year: 2024 end-page: 231 ident: b0175 article-title: Energy efficient task scheduling based on deep reinforcement learning in cloud environment: A specialized review publication-title: Futur Gener Comput Syst – volume: 205 year: 2022 ident: b0105 article-title: A fault reconfiguration strategy based on adjustable space operator discrete state transition algorithm for ship microgrid system publication-title: Electr Pow Syst Res – reference: Wang GY, Jiang CM. Fault Reconstruction Method of Ship Power Grid based on Improved Gray Wolf Optimizer. Conference Fault Reconstruction Method of Ship Power Grid based on Improved Gray Wolf Optimizer. p. 1447-51. – volume: 33 start-page: 489 year: 2022 end-page: 496 ident: b0145 article-title: Multi-agent and ant colony optimization for ship integrated power system network reconfiguration publication-title: J Syst Eng Electron – volume: 15 start-page: 3443 year: 2020 ident: 10.1016/j.ijepes.2025.110796_b0060 article-title: Defense Strategy for Resilient Shipboard Power Systems Considering Sequential Attacks publication-title: IEEE Trans Inf Forensics Secur doi: 10.1109/TIFS.2019.2960657 – volume: 13 year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0140 article-title: Maintaining flexibility in smart grid consumption through deep learning and deep reinforcement learning publication-title: Energy AI doi: 10.1016/j.egyai.2023.100241 – ident: 10.1016/j.ijepes.2025.110796_b0020 doi: 10.1109/ICMSP53480.2021.9513376 – volume: 280 year: 2020 ident: 10.1016/j.ijepes.2025.110796_b0135 article-title: Online reconfiguration scheme of self-sufficient distribution network based on a reinforcement learning approach publication-title: Appl Energy doi: 10.1016/j.apenergy.2020.115900 – volume: 147 start-page: 896 year: 2018 ident: 10.1016/j.ijepes.2025.110796_b0120 article-title: Multi-objective dynamic distribution feeder reconfiguration in automated distribution systems publication-title: Energy doi: 10.1016/j.energy.2018.01.111 – volume: 5 year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0100 article-title: The importance of reconfiguration of the distribution network to achieve minimization of energy losses using the dragonfly algorithm. e-Prime - Advances in Electrical Engineering publication-title: Electronics and Energy – ident: 10.1016/j.ijepes.2025.110796_b0035 – volume: 151 start-page: 214 year: 2024 ident: 10.1016/j.ijepes.2025.110796_b0175 article-title: Energy efficient task scheduling based on deep reinforcement learning in cloud environment: A specialized review publication-title: Futur Gener Comput Syst doi: 10.1016/j.future.2023.10.002 – volume: 47 start-page: 90 issue: 09 year: 2019 ident: 10.1016/j.ijepes.2025.110796_b0080 article-title: Reconstruction of ship power system network fault based on improved two particle swarm algorithm publication-title: Power System Protection and Control – volume: 40 start-page: 73 issue: 06 year: 2018 ident: 10.1016/j.ijepes.2025.110796_b0200 article-title: Research on power supply recovery of ship power system based on genetic algorithm publication-title: Ship Sci Technol – volume: 37 start-page: 4105 issue: 4 year: 2022 ident: 10.1016/j.ijepes.2025.110796_b0065 article-title: A Review of DC Shipboard Microgrids—Part II: Control Architectures, Stability Analysis, and Protection Schemes publication-title: IEEE Trans Power Electron doi: 10.1109/TPEL.2021.3128409 – volume: 39 start-page: 55 issue: 22 year: 2017 ident: 10.1016/j.ijepes.2025.110796_b0040 article-title: Research on ship power system based on intelligent reconfiguration algorithm publication-title: SHIP SCIENCE AND TECHNOLOGY – ident: 10.1016/j.ijepes.2025.110796_b0115 doi: 10.1109/ICPSAsia55496.2022.9949762 – volume: 121 start-page: 3487 issue: 12 year: 2024 ident: 10.1016/j.ijepes.2025.110796_b0050 article-title: A Critical Review of Active Distribution Network Reconfiguration: Concepts, Development, and Perspectives publication-title: Energy Eng doi: 10.32604/ee.2024.054662 – volume: 231 year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0015 article-title: Sustainable collaborative innovation capability enhancement paths of marine ranching: Supernetwork analysis perspective publication-title: Ocean Coast Manag doi: 10.1016/j.ocecoaman.2022.106387 – ident: 10.1016/j.ijepes.2025.110796_b0095 doi: 10.1109/AICIT55386.2022.9930296 – volume: 205 year: 2022 ident: 10.1016/j.ijepes.2025.110796_b0105 article-title: A fault reconfiguration strategy based on adjustable space operator discrete state transition algorithm for ship microgrid system publication-title: Electr Pow Syst Res doi: 10.1016/j.epsr.2021.107707 – volume: 10 start-page: 4138 issue: 4 year: 2019 ident: 10.1016/j.ijepes.2025.110796_b0180 article-title: Service Restoration Model With Mixed-Integer Second-Order Cone Programming for Distribution Network With Distributed Generations publication-title: IEEE Trans Smart Grid doi: 10.1109/TSG.2018.2850358 – volume: 37 start-page: 82 issue: 01 year: 2013 ident: 10.1016/j.ijepes.2025.110796_b0185 article-title: Distribution System Reconfiguration Considering Distributed Generators and Plug-in Electric Vehicles publication-title: Power System Technology – volume: 9 start-page: 90358 year: 2021 ident: 10.1016/j.ijepes.2025.110796_b0155 article-title: Distribution Network Reconfiguration Based on NoisyNet Deep Q-Learning Network publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3089625 – volume: 2418 year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0085 article-title: Research on fault reconstruction of ship regional distribution System based on improved genetic algorithm publication-title: J Phys Conf Ser doi: 10.1088/1742-6596/2418/1/012101 – volume: 40 start-page: 79 issue: 06 year: 2018 ident: 10.1016/j.ijepes.2025.110796_b0075 article-title: Research on reconstruction algorithm of fault recovery in power distribution network of ship power system publication-title: Ship Science and Technology – volume: 35 start-page: 73 issue: 2 year: 1995 ident: 10.1016/j.ijepes.2025.110796_b0045 article-title: Electric power distribution network restoration: a survey of papers and a review of the restoration problem publication-title: Electr Pow Syst Res doi: 10.1016/0378-7796(95)00991-4 – start-page: 1 - year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0150 article-title: Dynamic Fault Reconfiguration of Distribution Networks in Ship Power Systems Based on Deep Reinforcement Learning Approach publication-title: IEEE Trans Transp Electrif – volume: 183 year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0165 article-title: Applications of Reinforcement Learning for maintenance of engineering systems: A review publication-title: Adv Eng Softw doi: 10.1016/j.advengsoft.2023.103487 – year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0025 article-title: Ship Power System Network Reconfiguration Based on Improved Particle Swarm Algorithm publication-title: Master – volume: 25 start-page: 37 issue: 05 year: 2017 ident: 10.1016/j.ijepes.2025.110796_b0070 article-title: Reconfiguration of shipboard power system based on double sub-swarms particle swarm optimization publication-title: Electronic Design Engineering – volume: 6 start-page: 9430 year: 2018 ident: 10.1016/j.ijepes.2025.110796_b0030 article-title: A survey on fault detection, isolation, and reconfiguration methods in electric ship power systems publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2798505 – volume: 335 year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0005 article-title: Construction and influencing factors of an early warning system for marine ranching ecological security: Experience from China's coastal areas publication-title: J Environ Manage doi: 10.1016/j.jenvman.2023.117515 – ident: 10.1016/j.ijepes.2025.110796_b0090 doi: 10.1109/CEECT55960.2022.10030706 – volume: 9 start-page: 122872 year: 2021 ident: 10.1016/j.ijepes.2025.110796_b0125 article-title: A Comprehensive Review of Metaheuristic Methods for the Reconfiguration of Electric Power Distribution Systems and Comparison With a Novel Approach Based on Efficient Genetic Algorithm publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3109247 – volume: 244 year: 2023 ident: 10.1016/j.ijepes.2025.110796_b0010 article-title: Assessment of marine ranching ecological development using DPSIR-TOPSIS and obstacle degree analysis: A case study of Zhoushan publication-title: Ocean Coast Manag doi: 10.1016/j.ocecoaman.2023.106821 – volume: 238 year: 2024 ident: 10.1016/j.ijepes.2025.110796_b0170 article-title: A Systematic Literature Review of Reinforcement Learning-based Knowledge Graph Research publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2023.121880 – volume: 31 start-page: 118 issue: 31 year: 2011 ident: 10.1016/j.ijepes.2025.110796_b0195 article-title: Intelligent Service Restoration of Shipboard Power Network Using Nature Multiobjective Evolutionary Algorithm publication-title: Proc CSEE – ident: 10.1016/j.ijepes.2025.110796_b0110 doi: 10.1109/CAC57257.2022.10054880 – ident: 10.1016/j.ijepes.2025.110796_b0130 – volume: 48 start-page: 151 issue: 02 year: 2024 ident: 10.1016/j.ijepes.2025.110796_b0160 article-title: Distribution network fault recovery decision based on graph reinforcement learning publication-title: Automation of Electric Power Systems – volume: 12 start-page: 173 issue: 1 year: 2024 ident: 10.1016/j.ijepes.2025.110796_b0055 article-title: A survey on different techniques for distribution network reconfiguration publication-title: Journal of Engineering Research doi: 10.1016/j.jer.2023.09.001 – volume: 44 start-page: 33 issue: 02 year: 2018 ident: 10.1016/j.ijepes.2025.110796_b0205 article-title: Shipboard power grid reconstruction based on environment Pareto dominated selection differential evolution algorithm publication-title: J Dalian Maritime Univ – volume: 48 start-page: 14 issue: 13 year: 2020 ident: 10.1016/j.ijepes.2025.110796_b0190 article-title: Fault reconfiguration strategy of a shipboard power system considering reliability constraints publication-title: Power System Protection and Control – volume: 33 start-page: 489 issue: 2 year: 2022 ident: 10.1016/j.ijepes.2025.110796_b0145 article-title: Multi-agent and ant colony optimization for ship integrated power system network reconfiguration publication-title: J Syst Eng Electron doi: 10.23919/JSEE.2022.000048 |
| SSID | ssj0007942 |
| Score | 2.4414115 |
| Snippet | •A fault reconstruction method is proposed for island-mode marine ranching power systems.•The method uses an improved Noisy-Dueling DQN for fast, autonomous... When the islanded marine ranching power system fails, a rapid and accurate control strategy is crucial to maintain continuous power supply to critical loads... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Enrichment Source Index Database Publisher |
| StartPage | 110796 |
| SubjectTerms | Deep reinforcement learning Fault recovery and reconstruction Island AC power supply system Markov modeling |
| Title | Fault reconfiguration control strategy of islanded marine ranching power supply system based on deep reinforcement learning |
| URI | https://dx.doi.org/10.1016/j.ijepes.2025.110796 https://doaj.org/article/f5bae9d1d9af4b01af911899ec29c625 |
| Volume | 169 |
| WOSCitedRecordID | wos001506820800001&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 issn: 0142-0615 databaseCode: DOA dateStart: 20240101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: false ssIdentifier: ssj0007942 providerName: Directory of Open Access Journals – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0142-0615 databaseCode: AIEXJ dateStart: 19950201 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0007942 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA6yetCD-MT1RQ5ei2nSNO1xlV1URDwo7K3kMZWK7i77EMQ_b6ZppSe9eC3JpGQmyUz48n2EXEgpBTdMR4bZNEqAmyjLuY_lVMTCd1Ex1Kol9-rhIRuP88eO1BdiwgI9cJi4y1IaDbmLXa7LxLBYl355-iIBLM-tT95x9_VZT1tMNXuwjzIewIsctQtk-2iuRnZVrzADpOrmElHwCgn7O4dSzd3fOZs6581oh2w3iSIdhB_cJWsw2SNbHfrAffI10qu3Ja1r2rJ6WQVn0gZ9TheBePaTTktaLRDBCI6-a3zuR1FOA--e6AxV0ugCtT0_aaB1pniyOeotOYCZN1-Tq9r6HpE2KhMvB-R5NHy6vokaMYXIJpwtI-EEAyESUJl0ueOuFOBrJQGxSU0uwDE_q8panhlnUqWtFowZZXhqE5c5Jg5JbzKdwBGhYMvUcJMoaWXimNV-zQPzlRAIKRSwPhHtbBa2YRpHwYu3ooWUvRbBBwX6oAg-6JPop9csMG380f4KHfXTFnmy6w8-eoomeoq_oqdPVOvmokk5QirhTVW_Dn_8H8OfkE00GQCFp6S3nK_gjGzYj2W1mJ-T9cHtcHx3Xof2N_YR_5s |
| 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=Fault+reconfiguration+control+strategy+of+islanded+marine+ranching+power+supply+system+based+on+deep+reinforcement+learning&rft.jtitle=International+journal+of+electrical+power+%26+energy+systems&rft.au=Yichun+Wang&rft.au=Bo+Zhang&rft.au=Rongjie+Wang&rft.au=Jiang+Desong&rft.date=2025-08-01&rft.pub=Elsevier&rft.issn=0142-0615&rft.volume=169&rft.spage=110796&rft_id=info:doi/10.1016%2Fj.ijepes.2025.110796&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_f5bae9d1d9af4b01af911899ec29c625 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0142-0615&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0142-0615&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0142-0615&client=summon |