JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE A

Accepted manuscript available online (unedited version)

An optimization scheduling strategy for electric-heat-hydrogen integrated energy systems based on memory-enhanced deep reinforcement learning

Author(s): Zhongli BAI^1, ², Qiang GAO^1, ^2, ³, Hongzhi ZHANG^1, ², Junjie LIU^1, ², Yuehui JI^1, ², Yu SONG^1, ², Xu CHENG^1, ⁴
Affiliation(s): ¹Tianjin Key Laboratory of New Energy Power Conversion, Transmission, and Intelligent Control, Tianjin University of Technology, Tianjin 300384, China ²School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, China ³Maritime College, Tianjin University of Technology, Tianjin 300384, China ⁴School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, China
Corresponding email(s): Yu SONG, jasonsongrain@hotmail.com Xu CHENG xu.cheng@ieee.org
Key Words: Integrated energy system; Electric-heat-hydrogen; LSTM-SAC; Reinforcement learning; Scheduling strategy

Share this article to： More <<< Previous Paper \|Next Paper >>>

Zhongli BAI^1,², Qiang GAO^1,^2,³, Hongzhi ZHANG^1,², Junjie LIU^1,², Yuehui JI^1,², Yu SONG^1,², Xu CHENG^1,⁴. An optimization scheduling strategy for electric-heat-hydrogen integrated energy systems based on memory-enhanced deep reinforcement learning[J]. Journal of Zhejiang University Science A,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.A2500598

@article{title="An optimization scheduling strategy for electric-heat-hydrogen integrated energy systems based on memory-enhanced deep reinforcement learning",
author="Zhongli BAI^1,², Qiang GAO^1,^2,³, Hongzhi ZHANG^1,², Junjie LIU^1,², Yuehui JI^1,², Yu SONG^1,², Xu CHENG^1,⁴",
journal="Journal of Zhejiang University Science A",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.A2500598"
}

%0 Journal Article
%T An optimization scheduling strategy for electric-heat-hydrogen integrated energy systems based on memory-enhanced deep reinforcement learning
%A Zhongli BAI^1
%A²
%A Qiang GAO^1
%A^2
%A³
%A Hongzhi ZHANG^1
%A²
%A Junjie LIU^1
%A²
%A Yuehui JI^1
%A²
%A Yu SONG^1
%A²
%A Xu CHENG^1
%A⁴
%J Journal of Zhejiang University SCIENCE A
%P
%@ 1673-565X
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.A2500598"

TY - JOUR
T1 - An optimization scheduling strategy for electric-heat-hydrogen integrated energy systems based on memory-enhanced deep reinforcement learning
A1 - Zhongli BAI^{1
A1 -}²
A1 - Qiang GAO^{1
A1 -}^{2
A1 -}³
A1 - Hongzhi ZHANG^{1
A1 -}²
A1 - Junjie LIU^{1
A1 -}²
A1 - Yuehui JI^{1
A1 -}²
A1 - Yu SONG^{1
A1 -}²
A1 - Xu CHENG^{1
A1 -}⁴
J0 - Journal of Zhejiang University Science A
SP -
EP -
%@ 1673-565X
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.A2500598"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: High wind-solar penetration drives integrated energy systems (IES) to act as cross-vector buffers that absorb surplus electricity via hybrid storage, or convert it into heat and hydrogen for cross-medium energy peak shaving. However, conventional mixed-integer linear programming (MILP) solvers and static incentive schemes often struggle with the high-dimensional, strongly coupled, non-convex, and time-varying nature of electric-heat-hydrogen scheduling. Thus, we propose an end-to-end optimization framework for a renewable electric-heat-hydrogen IES, and evaluate it through offline dispatch computations and cost settlement on a 24-hour simulated case study. The proposed framework incorporates a coupled power-state of charge (SOC) dual penalty mechanism to ensure consistent storage operation over time. Additionally, it includes a bidirectional incentive-based demand response (B-IDR) mapping that is differentiable and can capture asymmetric feedback in response to price fluctuations. Furthermore, a long-term short-term memory (LSTM)-augmented maximum-entropy Soft Actor-Critic (SAC) scheduler is utilized for stable and efficient control in this continuous and high-dimensional setting. Comparisons with other methods under identical settings show that the proposed method achieves lower operating costs and carbon emissions, as well as improved training stability.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference