电力系统自动化2025，Vol.49Issue(13)：61-69,9.DOI:10.7500/AEPS20240912001
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
Online Reactive Power Optimization Method Based on Data-driven Predictive Control for Distribution Network with Low Situation Awareness
摘要
Abstract
The extensive access to distributed generators makes the problems of power flow fluctuation and voltage violation of the distribution network more and more prominent,especially bringing great challenges to the reactive power optimization of distribution networks with low situation awareness and unknown topology,insufficient observation,and low data quality.This paper introduces a data-driven predictive control algorithm and proposes an online reactive power optimization method for distribution networks with low situation awareness.First,the historical operation data is utilized to construct an equivalent agent model of the distribution network.Then,the online reactive power optimization problem for distribution networks is modeled using regularization techniques.Finally,a solver is used to solve and give reactive power optimization strategies during the rolling optimization process.The proposed method based on behavioral system theory has good interpretability,requires no prior model training,and has high solving efficiency.It can also track the distribution network state and update the equivalent agent model online in real time,which is robust and suitable for distribution networks with low situation awareness and variable switching states.The effectiveness of the proposed method is verified by the case simulation of a modified IEEE 33-bus system.关键词
配电网/数据驱动/预测控制/无功优化/分布式电源/可解释性/鲁棒性Key words
distribution network/data-driven/predictive control/reactive power optimization/distributed generator/interpretability/robustness引用本文复制引用
钱立群,魏卿,胡鹏飞,杨再欣..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):61-69,9.基金项目
内蒙古自治区自然科学基金资助项目(2023YFHH0054). This work is supported by Natural Science Foundation of Inner Mongolia Autonomous Region of China(No.2023YFHH0054). （2023YFHH0054）
