Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch

Xu, Chang; Hayashi, Naoki; Inuiguchi, Masahiro; Raymond, Wong Jee Keen; Mokhlis, Hazlie; Illias, Hazlee Azil

doi:https://doi.org/10.1038/s41598-025-27320-2

Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch

Xu, Chang; Hayashi, Naoki; Inuiguchi, Masahiro et al.

Scientific Reports, 2025, 15, 43610

アクセス数:35件（2026-02-16 13:15 集計）

固定URL: https://hdl.handle.net/11094/103689

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
SciRep_15_43610	pdf	なし	2.62 MB	10	2026.01.30

Creative Commons : 表示 - 非営利 - 改変禁止

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch
著者	著者名 Xu, Chang
	NRID 1000080637752 1000080637752 researchmap permalink zu3rv2h zu3rv2h Scopus Author ID 30967580300 30967580300 著者名 Hayashi, Naoki
	NRID 1000060193570 1000060193570 ORCID 0000-0001-9970-1621 0000-0001-9970-1621 researchmap permalink read0054744 read0054744 Scopus Author ID 7004106068 7004106068 著者名 Inuiguchi, Masahiro
	著者名 Raymond, Wong Jee Keen
	著者名 Mokhlis, Hazlie
	著者名 Illias, Hazlee Azil
内容	Xu C., Hayashi N., Inuiguchi M., et al. Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch. Scientific Reports 15, 43610 (2025); https://doi.org/10.1038/s41598-025-27320-2.
抄録	Integrating renewable energy into power systems introduces significant challenges in balancing generation costs and grid stability, necessitating advanced solutions for the Economic Dispatch Problem (EDP). While classical mathematical and meta-heuristic methods face scalability and computational efficiency limitations, reinforcement learning (RL) offers a promising alternative due to its adaptability to high-dimensional and dynamic environments. This study employs Twin Delayed DDPG (TD3), an enhanced version of Deep Deterministic Policy Gradient (DDPG). TD3 integrates Prioritized Experience Replay (PER) and Noisy Networks (Noisy Nets) for the EDP in a regional microgrid with photovoltaic (PV) generation. PER improves sample efficiency by prioritizing high-error transitions, while Noisy Nets enhance exploration through adaptive parameter noise. Experiments demonstrate that combining these techniques with TD3 achieves a 54.6% reduction in testing operation cost and a 95.3% decrease in cumulative power unbalance compared to the baseline TD3. The improvements are validated across various deterministic and stochastic RL models, with TD3+PER+Noisy Nets outperforming others in cost efficiency and stability. The findings demonstrate the proposed approach’s capability to optimize microgrid dispatch while providing a scalable and practical framework for power system control.
出版者	Nature Research
収録物名	Scientific Reports
巻(号)	15
ページ	43610
刊行年月	2025-12-10
言語	英語
ハンドルURL	https://hdl.handle.net/11094/103689
eISSN	20452322
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1038/s41598-025-27320-2
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Scientific Reports. 2025, 15, p. 43610
DC.title	Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch
DC.creator	Xu, Chang
	Hayashi, Naoki
	Inuiguchi, Masahiro
	Raymond, Wong Jee Keen
	Mokhlis, Hazlie
	Illias, Hazlee Azil
DC.publisher	Nature Research
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-12-10
DC.identifier	https://doi.org/10.1038/s41598-025-27320-2
DC.description	Xu C., Hayashi N., Inuiguchi M., et al. Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch. Scientific Reports 15, 43610 (2025); https://doi.org/10.1038/s41598-025-27320-2.
DCTERMS.abstract	Integrating renewable energy into power systems introduces significant challenges in balancing generation costs and grid stability, necessitating advanced solutions for the Economic Dispatch Problem (EDP). While classical mathematical and meta-heuristic methods face scalability and computational efficiency limitations, reinforcement learning (RL) offers a promising alternative due to its adaptability to high-dimensional and dynamic environments. This study employs Twin Delayed DDPG (TD3), an enhanced version of Deep Deterministic Policy Gradient (DDPG). TD3 integrates Prioritized Experience Replay (PER) and Noisy Networks (Noisy Nets) for the EDP in a regional microgrid with photovoltaic (PV) generation. PER improves sample efficiency by prioritizing high-error transitions, while Noisy Nets enhance exploration through adaptive parameter noise. Experiments demonstrate that combining these techniques with TD3 achieves a 54.6% reduction in testing operation cost and a 95.3% decrease in cumulative power unbalance compared to the baseline TD3. The improvements are validated across various deterministic and stochastic RL models, with TD3+PER+Noisy Nets outperforming others in cost efficiency and stability. The findings demonstrate the proposed approach’s capability to optimize microgrid dispatch while providing a scalable and practical framework for power system control.
DC.rights	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
DC.format	103689
citation_title	Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch
citation_author	Xu, Chang
	Hayashi, Naoki
	Inuiguchi, Masahiro
	Raymond, Wong Jee Keen
	Mokhlis, Hazlie
	Illias, Hazlee Azil
citation_publisher	Nature Research
citation_language	英語
citation_date	2025-12-10
citation_journal_title	Scientific Reports
citation_volume	15
citation_firstpage	43610
citation_doi	https://doi.org/10.1038/s41598-025-27320-2
citation_public_url	https://hdl.handle.net/11094/103689

Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch

閲覧可能ファイル

論文情報

論文詳細を表示