CHEN Guoqi,WEI Yinghao,LIU Yi,et al.Optimal Operation Strategy for Source-Grid-Load-Storage in Rural Microgrids Based on Improved TD3[J].Southern Power System Technology,2026,20(08):89-103.
CHEN Guoqi,WEI Yinghao,LIU Yi,et al.Optimal Operation Strategy for Source-Grid-Load-Storage in Rural Microgrids Based on Improved TD3[J].Southern Power System Technology,2026,20(08):89-103.DOI: 10.13648/j.cnki.issn1674-0629.2026.08.008.
Optimal Operation Strategy for Source-Grid-Load-Storage in Rural Microgrids Based on Improved TD3
摘要
农村微电网作为支撑“双碳”目标落地、赋能乡村振兴战略实施的重要载体,通过整合分布式能源与传统发电资源,能够有效提升系统整体的运行效率。为此,提出了一种基于改进双延迟深度确定性策略梯度(twin delayed deep deterministic policy gradient,TD3)的农村微电网源网荷储优化运行策略。首先,综合考虑运行成本和可再生能源利用率,构建了含沼气的农村微电网源网荷储优化运行模型。其次,构建了基于复合评分机制的注意力加权评论家网络(CASA-Critic),动态提取并聚焦关键状态特征以提升价值网络的评估精度。然后,采用动态感知策略,基于训练阶段在时间进程与环境状态的不确定性特征动态调节动作探索强度,改善算法在探索与利用之间的平衡。最后,基于典型的农村微网源网荷储运行场景进行仿真分析,仿真结果表明,相较于其他基于深度强化学习的优化运行策略,所提方法具有更好的收敛性和寻优效果,在提升系统运行经济性、促进可再生能源消纳方面具有明显的优越性。
Abstract
As a crucial carrier for supporting the implementation of the "dual carbon" goals and empowering rural revitalization
rural microgrids can effectively enhance overall system operational efficiency by integrating distributed energy with traditional power generation resources. To this end
this paper proposes a optimal operation strategy for source-grid-load-storage in rural microgrids based on an improved twin delayed deep deterministic policy gradient (TD3) algorithm. Firstly
an optimal operation model for rural microgrids incorporating biogas is constructed by comprehensively considering operating costs and renewable energy utilization. Secondly
a compound assessment scored attention-weighted critic(CASA-Critic)is designed to dynamically extract and focus on key state features
thereby enhancing the evaluation accuracy of the value network. Then
a dynamic perception strategy is introduced to adaptively adjust the intensity of action exploration based on the temporal progression and environmental state uncertainties during training
improving the balance between exploration and exploitation. Finally
simulation analysis is conducted based on a typical rural microgrids source-grid-load-storage operation scenario. The results demonstrate that
compared to optimization strategies based on other deep reinforcement learning
the proposed method exhibits better convergence and optimization performance
while also showing significant superiority in improving system operational economy and promoting renewable energy accommodation.
LING Kai , WANG Can , ZHANG Gaorui , et al . Three-layer energy optimization strategy for CHP microgrid [J]. Electric Power , 2023 , 56 ( 2 ): 102 - 113 .
ZHANG Lin , XIE Hongtu , ZHAO Lulu , et al . Energy optimization and control strategy for a hybrid energy DC microgrid [J]. Power System Protection and Control , 2024 , 52 ( 3 ): 141 - 151 .
WANG Can , ZHANG Xuefei , LING Kai , et al . Two-stage adaptive robust optimal scheduling based on the interval probability uncertainty set for microgrids [J]. Proceedings of the CSEE , 2024 , 44 ( 5 ): 1750 - 1764 .
ZHANG Jinliang , CHENG Jia . Dual layer optimization model for capacity configuration of rural multi-microgrid system with biogas energy generation [J]. Electric Power Construction , 2025 , 46 ( 10 ): 73 - 87 .
ZHANG Cheng , KUANG Yu , LIU Jiajing , et al . Two-stage optimal scheduling of a wind, photovoltaic, gas turbine, fuel cell and storage energy microgrid considering demand-side management [J]. Power System Protection and Control , 2022 , 50 ( 24 ): 13 - 22 .
ZANG Yunfan , XIA Sheng , LI Jiawen , et al . A robust game optimization scheduling method for shared energy storage micro electric network group distribution [J]. Power System Protection and Control , 2023 , 51 ( 24 ): 90 - 101 .
YUE Jiaming , ZHONG Jianwei , ZHU Zhanchun , et al . Data center participates in optimal scheduling of a wind-solar-pumped-storage hybrid microgrid [J]. Electrotechnics Electric , 2025 ( 5 ): 13 - 20,71 .
YAO Mingming , ZHANG Xin , YANG Peihong , et al . Low-carbon optimal scheduling of source-grid-load-storage based on improved wind-solar scene clustering combined with virtual energy storage [J]. Power System Protection and Control , 2024 , 52 ( 15 ): 115 - 130 .
GRONAUER S , DIEPOLD K . Multi-agent deep reinforcement learning: a survey [J]. Artificial Intelligence Review , 2022 , 55 ( 2 ): 895 - 943 .
ZHANG Fan , WU Donghao , CHEN Yuping , et al . Economic scheduling strategy for integrated energy system in distributed parks based on multi-agent deep reinforcement learning [J]. Proceedings of the CSU-EPSA , 2022 , 34 ( 12 ): 18 - 26 .
MA Chongchong , WANG Yizheng , WANG Kun , et al . Deep reinforcement learning based dispatch strategy for microgrid eenergy management considering uncertainty of source and load [J]. Chinese High Technology Letters , 2023 , 33 ( 1 ): 79 - 87 .
LIN Wenshuo , LI Xin , ZHOU Rongsheng , et al . A low-carbon optimal operation method for microgrids based on deep reinforcement learning [J]. Modern Electric Power , 2025 , 42 ( 6 ): 1131 - 1142 .
WANG Lindao , LIU Daming . Research on microgrid transaction and scheduling based on improved PPO algorithm [J]. Computer Simulation , 2025 , 42 ( 5 ): 84 - 91 .
ZENG Lei , DING Quan , CHEN Xiaoyu , et al . A DRL-based optimization method for microgrid operation [J]. Zhejiang Electric Power , 2025 , 44 ( 6 ): 31 - 40 .
WANG C , ZHANG J , WANG A , et al . Prioritized sum-tree experience replay TD3 DRL-based online energy management of a residential microgrid [J]. Applied Energy , 2024 (368): 123471.1 - 123471.10.
LUO Yongjian , LIU Chengxi , DONG Xuzhu . Day ahead economic dispatching of multi energy complementary micro grid based on deep reinforcement learning architecture [J]. Engineering Journal of Wuhan University , 2023 , 56 ( 11 ): 1393 - 1404 .
YANG Di , WANG Hui , YANG Ruitong , et al . Spatio-temporal dispatch strategy of mobile energy storage based on multi-agent deep reinforcement learning with adaptive reward function [J/OL]. Proceedings of the CSEE , 1 - 13[ 2025 - 8 -23]. https://doi.org/10.13334/j.0258 - 8013.pcsee.251329.
LI Jiawen , YU Tao , ZHANG Xiaoshun , et al . AGC power generation command allocation method based on improved deep deterministic policy gradient algorithm [J]. Proceedings of the CSEE , 2021 , 41 ( 21 ): 7198 - 7212 .
LIANG Tao , CHAI Lulu , TAN Jianxin , et al . Optimal scheduling of hydrogen coupled electrothermal integrated energy system based on deep reinforcement learning algorithm [J]. Electric Power Automation Equipment , 2025 , 45 ( 1 ): 59 - 66 .
WANG Hong , GUO Zhitao , ZHANG Sen , et al . Dual-attention LSTM RUL prediction network with Kalman filter [J]. Modern Electronic Technique , 2025 , 48 ( 22 ): 160 - 166 .
LUO Linlin , WANG Xiao , HE Zhiqin , et al . Multi-load forecasting model for integrated energy system based on rolling mode decomposition and GCN-DABiLSTM [J]. Guangdong Electric Power , 2025 , 38 ( 9 ): 130 - 138 .
CUI Xing , LI Jinguo , ZHANG Zhaobei , et al . The short-term power load forecasting based on NIWPSO-LSTM neural network [J]. Electrical Measurement & Instrumentation , 2024 , 61 ( 1 ): 131 - 136 .
CUI Zhikun , WANG Qingliang , LIU Jingqing , et al . Evaluation of the electricity markets index system based on fuzzy set theory and order relationship analysis [J]. Electrical Measurement & Instrumentation , 2024 , 61 ( 5 ): 31 - 37 .
WANG Siqi 1 , CAO Fang, YAO Li. Time-of-use pricing model considering the risk of cost transmission in multi-level market agent electricity purchase [J]. Electric Power , 2025, 58 ( 11 ): 25 - 37 .