面向电力系统暂态稳定性的联邦学习拜占庭节点检测  

Byzantine Node Detection of Federated Learning for Transient Stability Analysis of Power System

作　　者：王子璇 吕娜[1,2] 王瀚璇 周学财 WANG Zi-Xuan;LYU Na;WANG Han-Xuan;ZHOU Xue-Cai(College of Future Technology,Xi’an Jiaotong University,Xi’an 710049,China;College of Automation,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]西安交通大学未来技术学院,西安710049 [2]西安交通大学自动化学院,西安710049

出　　处：《计算机系统应用》2024年第9期235-244,共10页Computer Systems & Applications

基　　金：国家重点研发计划(2021YFB2400800)。

摘　　要：针对分布式智能电网各电力系统区域联合进行暂态稳定性判定和可能遇到的网络攻击问题,提出了一种基于联邦学习的分布式电力系统暂态稳定判别算法及拜占庭节点检测算法.联邦学习框架中,各区域电网独立采用神经网络进行判稳,中央服务器综合训练梯度并反馈更新.为了提高该联邦学习框架的安全性,通过对各区域电网的更新梯度进行聚类,从而甄别离群点,即受到攻击的区域电网,实现拜占庭节点检测.考虑到梯度的高维特性,直接聚类会出现距离度量不准确的问题,因此通过在线训练自编码器降维,并对降维后的梯度进行密度聚类,选择包含节点数目少的类别作为拜占庭节点集合,并永久剔除拜占庭节点提供的梯度.采用功角稳定机电暂态仿真算例进行验证,结果表明,本方法解决了电力系统暂稳判定时遇到的网络攻击问题,相比其他方法具有明显提升的平均准确率和稳定性,能有效避免判别准确率跳变情况.This study proposes a federated learning algorithm for transient stability in a distributed power system and a Byzantine node detection algorithm to assess the transient stability of various regions in a distributed smart grid and address potential network attacks.In the federated learning framework,each regional power grid independently uses neural networks to assess its transient stability,while the central server integrates the training gradients,provides feedback,and updates them.To improve the security of the framework,the model constructed in this study clusters the updated gradients of each regional power grid to identify outliers,which refer to regional power grids that are under attack,so as to detect Byzantine nodes.Considering the high-dimensional characteristics of gradients,direct clustering will lead to inaccurate distance measurement.Therefore,an autoencoder is trained online to reduce the dimension of the gradients.Density clustering is then performed on the lower-dimensional gradients to select a small number of nodes as a set of Byzantine nodes and permanently eliminate the gradients provided by Byzantine nodes.An example of electromechanical transient simulation for angle stability is used for verification.The results show that this method addresses network attacks while assessing the temporary stability of the power system.Compared with other methods,this method significantly improves the average accuracy and stability,effectively preventing fluctuations in assessment accuracy.

关 键 词：智能电网 分布式学习 联邦学习 网络攻击 暂态稳定 

分 类 号：TM712[电气工程—电力系统及自动化] TM73