中国电机工程学报2026，Vol.46Issue(3)：957-969,中插8,14.DOI:10.13334/j.0258-8013.pcsee.241907
基于自适应联邦学习的输配网动-静态综合状态估计方法研究
Integrated Dynamic-static State Estimation Method for Transmission and Distribution Networks Based on Self-adaptive Federated Learning
摘要
Abstract
As the operational characteristics of power systems undergo profound changes,traditional segregated state estimation methods for transmission and distribution networks struggle to achieve effective coordination.Additionally,with the rapid development of the internet,the problem of data privacy breaches in power systems has become increasingly prominent.To address these challenges,this paper proposes a self-adaptive federated learning-based integrated dynamic-static state estimation method for transmission and distribution networks.This method enhances the coordinated control of transmission and distribution networks,enabling rapid state sensing and privacy protection.First,this paper proposes an integrated dynamic-static state estimation method for transmission and distribution networks.Based on Monte Carlo simulations,state estimation dataset is constructed.Then,a self-adaptive federated learning model is developed and trained on the power system state estimation dataset.Finally,the proposed method is validated by simulations on the IEEE 39-and 123-bus systems.The results show that,compared with the traditional federated learning method,the proposed method improves the accuracy of voltage angle and magnitude state estimation by 10.73%and 13.49%,respectively,demonstrating the effectiveness of the method.关键词
自适应联邦学习/动态状态估计/静态状态估计/隐私保护/输配网协同Key words
self-adaptive federated learning/dynamic state estimation/static state estimation/privacy preservation/transmission and distribution coordination分类
信息技术与安全科学引用本文复制引用
韩一宁,崔明建,罗光浩,张剑,贾宏杰..基于自适应联邦学习的输配网动-静态综合状态估计方法研究[J].中国电机工程学报,2026,46(3):957-969,中插8,14.基金项目
国家重点研发计划项目(2023YFB2407500) （2023YFB2407500）
国家自然科学基金项目(52207130).National Key R&D Program of China(2023YFB2407500) （52207130）
Project Supported by National Natural Science Foundation of China(52207130). （52207130）
