基于电压-功率灵敏度的有源配电网数据驱动电压协调控制策略  

Data-driven Coordinated Voltage Control Strategy for Active Distribution Network Based on Voltage-power Sensitivity

作　　者：张波[1] 文晓君 吴璇[1] ZHANG Bo;WEN Xiaojun;WU Xuan(Key Laboratory of Distributed Energy Storage and Micro-grid in Hebei,North China Electric Power University,Baoding 071003,China)

机构地区：[1]华北电力大学河北省分布式储能与微网重点实验室,保定071003

出　　处：《电力系统及其自动化学报》2025年第1期35-42,共8页Proceedings of the CSU-EPSA

基　　金：河北省自然科学基金资助项目(E2022502059)。

摘　　要：随着分布式光伏渗透率的不断提高,实现配电网电压的快速精确调控变得愈加重要。首先,建立多输入-多输出的电压-功率灵敏度BP神经网络回归预测模型,得到功率参数、节点电压与电压-功率灵敏度间的非线性映射关系;其次,构建高比例光伏有源配电网电压协调控制策略,基于电压-功率灵敏度降序调控原则,通过无功补偿和有功削减结合的两阶段电压调控模式实现配电网节点电压的快速调控;最后,利用IEEE 33和IEEE 141节点典型配电系统的仿真,计算分析验证所提方法的正确性和有效性。With the growing penetration rate of distributed photovoltaic(PV),the realization ofa fast and precise regu-lation of distribution network voltage becomes increasingly important.First,a multi-inputmulti-output voltage-power sensitivity BP neural network regression prediction model is established to obtain the nonlinear mapping relationship be-tween power parameters,node voltage and voltage-power sensitivity.Second,a coordinated voltagecontrol strategy for active distribution network with high-proportion PV is constructed.Based on the principle of descending-order regula-tion of voltage-power sensitivity,the fast regulation of distribution network node voltage is achieved through a two-stage voltage regulationmode combining reactive power compensation and active power reduction.Finally,the correctness and validity of the proposed method are verified by the simulation and computational analysis oftypical IEEE33-node and 141-nodedistribution systems.

关 键 词：BP神经网络 数据驱动 电压-功率灵敏度 电压协调控制 有源配电网 

分 类 号：TM712[电气工程—电力系统及自动化]