
1.河海大学电气与动力工程学院,江苏省南京市 211100
2.国网江苏省电力有限公司电力科学研究院,江苏省南京市 211103
Received:22 June 2026,
Revised:2026-08-27,
Online First:09 October 2026,
移动端阅览
孙祎,张宸宇,臧海祥等.计及源荷不确定性的配电网软开关分布鲁棒模型预测控制[J/OL].电力系统自动化, http://dx.doi.org/10.7500/AEPS20260622001.
SUN Yi,ZHANG Chenyu,ZANG Haixiang,et al.Distributionally Robust Model Predictive Control for Soft Open Points in Distribution Networks Considering Source-Load Uncertainty[J/OL].Automation of Electric Power Systems, http://dx.doi.org/10.7500/AEPS20260622001.
孙祎,张宸宇,臧海祥等.计及源荷不确定性的配电网软开关分布鲁棒模型预测控制[J/OL].电力系统自动化, http://dx.doi.org/10.7500/AEPS20260622001. DOI:
SUN Yi,ZHANG Chenyu,ZANG Haixiang,et al.Distributionally Robust Model Predictive Control for Soft Open Points in Distribution Networks Considering Source-Load Uncertainty[J/OL].Automation of Electric Power Systems, http://dx.doi.org/10.7500/AEPS20260622001. DOI:
源荷不确定性加剧了配电网电压越限与网损问题,现有优化及数据驱动方法难以兼顾不确定性适应能力、运行经济性与控制策略的物理可行性。为此,提出一种面向不确定性的柔性配电网分布鲁棒模型预测控制方法,将Wasserstein分布鲁棒优化与滚动时域控制应用于软开关(SOP)及新能源并网变流器的协同调节,构建兼顾电压安全、网络损耗和控制平滑性的多时段优化模型。算例结果表明,所提方法的平均在线控制周期计算时间为0.168 s,电压越限率为3.157%。在相同分布鲁棒模型预测控制(DRO-MPC)模型下,多智能体软演员-评论家算法(MASAC)的热启动较冷启动进一步缩短了优化器求解时间,体现了学习辅助机制的计算加速作用。SOP控制平滑度进一步降低,说明所提方法通过优化-学习协同机制,实现了在线计算效率、电压安全、运行经济性和控制可执行性的综合提升。
The source-load uncertainty exacerbates voltage limit violations and network loss issues in distribution networks. Existing optimization and data-driven methods struggle to balance uncertainty adaptability
operational economy
and the physical feasibility of control strategies. To address this challenge
this paper proposes a Wasserstein distributionally robust model predictive control method for flexible distribution networks under uncertainty. Wasserstein distributionally robust optimization and receding horizon control are adopted for the coordinated regulation of soft open points (SOPs) and grid-connected converters of renewable energy sources. A multi-time-period optimization model is established
taking voltage security
network loss
and control smoothness into account. Case study results demonstrate that the proposed method achieves an average computation time of 0.168 s per online control period
with a voltage violation rate of 3.157%. Under the same distributionally robust model predictive control (DRO-MPC) model
the multi-agent soft actor-critic (MASAC) algorithm with warm start further reduces the optimizer solving time compared with the cold start
verifying the computational acceleration effect of the learning-aided mechanism. The control smoothness of SOPs is further improved
indicating that the proposed optimization-learning collaborative mechanism achieves comprehensive enhancements in online computational efficiency
voltage security
operational economy
and control implementability.
Sharma V , Aziz S M , Haque M H , et al . Effects of high solar photovoltaic penetration on distribution feeders and the economic impact [J]. Renewable and Sustainable Energy Reviews , 2020 , 131 : 110021 .
Ding X , Chen X , Yu K , et al . Multi-time-scale voltage control of the distribution network with energy storage equipped soft open points [J]. Frontiers in Energy Research , 2024 , 12 : 1374704 .
黄大为 , 王孝泉 , 于娜 , 等 . 计及光伏出力不确定性的配电网混合时间尺度无功/电压控制策略 [J]. 电工技术学报 , 2022 , 37 ( 17 ): 4377 - 4389 .
Huang Dawei , Wang Xiaoquan , Yu Na , et al . Hybridtimescale voltage/var control in distribution network considering PV power uncertainty [J]. Transactions of China Electrotechnical Society , 2022 , 37 ( 17 ): 4377 - 4389 .
李勇 , 凌锋 , 乔学博 , 等 . 基于网侧资源协调的自储能柔性互联配电系统日前-日内优化 [J]. 电工技术学报 , 2024 , 39 ( 3 ): 758 - 773 .
Li Yong , Ling Feng , Qiao Xuebo , et al . Day-ahead and intra-day optimization of flexible interconnected distribution system with self-energy storage based on the grid-side resource coordination [J]. Transactions of China Electrotechnical Society , 2024 , 39 ( 3 ): 758 - 773 .
Yu S X , Dong X M , Wang C F , et al . Distributionally robust optimal scheduling of flexible distribution networks considering dynamic spatio-temporal correlation of renewable energy [J]. International Journal of Electrical Power & Energy Systems , 2025 , 169 : 110770 .
Chang J X , Zhang J D , Liao X B , et al . Distributed reactive power optimization of flexible distribution network based on probability scenario-driven [J]. Energy Reports , 2025 , 13 : 68 - 81 .
Lee X Y , Sarkar S , Wang Y B . A graph policy network approach for volt-var control in power distribution systems [J]. Applied Energy , 2022 , 323 : 119530 .
Wang R H , Bi X W , Bu S Q . Real-time coordination of dynamic network reconfiguration and volt-var control in active distribution network: a graph-aware deep reinforcement learning approach [J]. IEEE Transactions on Smart Grid , 2024 , 15 ( 3 ): 3288 - 3302 .
Zhao Y C , Zhang G Z , Hu W H , et al . Meta-learning based voltage control strategy for emergency faults of active distribution networks [J]. Applied Energy , 2023 , 349 : 121399 .
ZHANG B , CAO D , GHIAS A , et al . Physics-informed multi-agent deep reinforcement learning enabled distributed voltage control for active distribution network using PV inverters [J]. International Journal of Electrical Power & Energy Systems , 2024 , 155 : 109641 .
Li B D , Xu Q W . A machine learning-assisted distributed optimization method for inverter-based volt-var control in active distribution networks [J]. IEEE Transactions on Power Systems , 2024 , 39 ( 2 ): 2668 - 2681 .
Abbas G , Zhi W , Ali A . A two-stage reactive power optimization method for distribution networks based on a hybrid model and data-driven approach [J]. IET Renewable Power Generation , 2024 , 18 ( 16 ): 3967 - 3979 .
杨浩 , 王佳怡 , 易文飞 , 等 . 知识-数据融合驱动的配电网光伏逆变器电压/无功优化自适应控制 [J]. 中国电机工程学报 , 2025 , 45 ( 22 ): 8691 - 8706 .
Yang Hao , Wang Jiayi , Yi Feiwen , et al . Hybrid knowledge-data driven adaptive voltage/var optimization control of photovoltaic inverters in distribution networks [J]. Proceedings of the CSEE , 2025 , 45 ( 22 ): 8691 - 8706 .
Cao K , Liu Y T , Wang C Y . Deep learning-assisted distributionally robust optimization of shared energy storage for distribution network resilience enhancement [J]. Engineering Applications of Artificial Intelligence , 2026 , 167 : 113834 .
陈继明 , 于馨玮 , 仉志华 , 等 . 柔性互联配电系统SNOP选址与运行优化策略 [J]. 电力工程技术 , 2025 , 44 ( 4 ): 71 - 79 .
Chen Jiming , Yu Xinwei , Zhang Zhihua , et al . SNOP siting and operation optimization strategy for flexible interconnected distribution systems [J]. Electric Power Engineering Technology , 2025 , 44 ( 4 ): 71 - 79 .
Long C , Wu J Z , Thomas L , et al . Optimal operation of soft open points in medium voltage electrical distribution networks with distributed generation [J]. Applied Energy , 2016 , 184 : 427 - 437 .
陈宇星 , 梁芙蓉 , 尤炜 , 等 . 含分布式光伏的配电网模型预测控制优化方法 [J]. 电力工程技术 , 2023 , 42 ( 6 ): 100 - 109 .
Chen Yuxing , Liang Furong , You Wei , et al . Model predictive control optimization method for distribution network containing distributed photovoltaics [J]. Electric Power Engineering Technology , 2023 , 42 ( 6 ): 100 - 109 .
Yang C , Sun Y P , Zou Y J , et al . Optimal power flow in distribution network: a review on problem formulation and optimization methods [J]. Energies , 2023 , 16 ( 16 ): 1 - 42 .
Behbahani M R , Jalilian A . Optimal operation of soft open point devices and distribution network reconfiguration in a harmonically polluted distribution network [J]. Electric Power Systems Research , 2024 , 237 : 110967 .
蒋春容 , 朱博汶 , 周旭峰 , 等 . 基于分布式光伏集群控制的主动配电网电压优化策略 [J]. 电力工程技术 , 2025 , 44 ( 3 ): 188 - 200 .
Jiang Chunrong , Zhu Bowen , Zhou Xufeng , et al . Voltage optimization strategy for active distribution network based on distributed photovoltaic cluster control [J]. Electric Power Engineering Technology , 2025 , 44 ( 3 ): 188 - 200 .
Liu J , Chen Y F , Duan C , et al . Distributionally robust optimal reactive power dispatch with wasserstein distance in active distribution network [J]. Journal of Modern Power Systems and Clean Energy , 2020 , 8 ( 3 ): 426 - 436 .
葛少云 , 侯亭玉 , 吴鸣 , 等 . 柔性互联配电网分布式电源承载能力分布鲁棒优化模型 [J]. 电力系统自动化 , 2023 , 47 ( 13 ): 140 - 148 .
Ge Shaoyun , Hou Tingyu , Wu Ming , et al . Distributionally robust optimization model of hosting capability for distributed generators in flexible interconnected distribution network [J]. Automation of Electric Power Systems , 2023 , 47 ( 13 ): 140 - 148 .
Yu N P , Zhang S R , Qin J T , et al . Data-driven control, optimization, and decision-making in active power distribution networks [J]. Applied Energy , 2025 , 397 : 126253 .
倪爽 , 崔承刚 , 杨宁 , 等 . 基于深度强化学习的配电网多时间尺度在线无功优化 [J]. 电力系统自动化 , 2021 , 45 ( 10 ): 77 - 85 .
Ni Shuang , Cui Chenggang , Yang Ning , et al . Multi-time-scale on line optimization for reactive power of distribution network based on deep reinforcement learning [J]. Automation of Electric Power Systems , 2021 , 45 ( 10 ): 77 - 85 .
钱立群 , 魏卿 , 胡鹏飞 , 等 . 基于数据驱动预测控制的低感知度配电网在线无功优化方法 [J]. 电力系统自动化 , 2025 , 49 ( 13 ): 61 - 69 .
Qian Liqun , Wei Qing , Hu Pengfei , et al . On line reactive power optimization method based on data-driven predictive control for distribution network withlow situation awareness [J]. Automation of Electric Power Systems , 2025 , 49 ( 13 ): 61 - 69 .
Dong L , Lin H , Qiao J , et al . A coordinated active and reactive power optimization approach for multi-microgrids connected to distribution networks with multi-actor-attention-critic deep reinforcement learning [J]. Applied Energy , 2024 , 373 : 123870 .
Gao Y B , Ekomwenrenren E , Tang Z Y , et al . Data-driven local voltage control design for active distribution networks considering various operation conditions [J]. Electric Power Systems Research , 2025 , 248 : 111902 .
Wu T , Wang J H , Lu X N , et al . AC/DC hybrid distribution network reconfiguration with microgrid formation using multi-agent soft actor-critic [J]. Applied Energy , 2022 , 307 : 118189 .
范士雄 , 刘幸蔚 , 魏智慧 , 等 . 基于智能体群组强化学习的电网无功电压调控方法 [J]. 电力工程技术 , 2020 , 39 ( 2 ): 10 - 17 .
Fan Sixiong , Liu Xingwei , Wei Zhihui , et al . Reactive voltage regulation method based on agents group using reinforcement learning [J]. Electric Power Engineering Technology , 2020 , 39 ( 2 ): 10 - 17 .
Qu Y , Ma J M , Wu F . Safety constrained multi-agent reinforcement learning for active voltage control [C]// Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI) , 2024 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621