基于自适应UKF算法的虚假数据注入攻击检测研究  

Research on false data injection attack detection based on adaptive unscented Kalman filter algorithm

作　　者：伍虹 杨超[1] 鲁杰 徐立立 WU Hong;YANG Chao;LU Jie;XU Lili(College of Electrical Engineering,Guizhou University,Guiyang 550025,China;Power China Guiyang Engineering Corporation Limited,Guiyang,550081,China)

机构地区：[1]贵州大学电气工程学院,贵阳550025 [2]中国电建贵阳勘测设计研究院,贵阳550081

出　　处：《智能计算机与应用》2023年第6期168-173,共6页Intelligent Computer and Applications

基　　金：贵州省科学技术基金(黔科合基础-ZK[2021]一般277)。

摘　　要：虚假数据注入攻击利用电力系统不良数据辨识机制的漏洞,通过攻击量测值进而影响系统状态估计值,成为影响电力系统安全和稳定运行的严重隐患。针对不良数据检测机制漏洞,本文提出一种基于自适应无迹卡尔曼滤波的虚假数据检测方法,在获得静态状态估计加权最小二乘法和自适应无迹卡尔曼滤波二者状态估计结果的基础上,采用欧几里得距离公式计算二者状态估计偏差值,并根据全局节点欧氏距离设定检测阈值,判断当前时刻是否受到虚假数据注入攻击。以IEEE-14标准节点系统进行仿真分析,仿真结果表明自适应无迹卡尔曼滤波能够弥补不良数据检测机制的缺陷,并成功检测出虚假数据的注入。False data injection attack utilizes the vulnerability of the bad data detection mechanism of power system to affect the result of state estimation by tampering the state estimation,which poses a serious threat to the security and stable operation of power system.Aiming at the vulnerability of bad data detection mechanism,this paper proposes a false data detection method based on adaptive unscented Kalman filter.Based on the results of static state estimation weighted least square method and adaptive unscented Kalman filter,the Euclidean distance is accustomed to calculate the deviation of the two estimates,and the detection threshold is set according to the Euclidean distance of global node to judge whether the system is attacked by false data injection in real-time.The IEEE-14 standard node system is used for simulation analysis.The simulation results show that the adaptive unscented Kalman filter can make up for the defects of the bad data detection mechanism and successfully detect the injection of false data.

关 键 词：虚假数据注入攻击 自适应无迹卡尔曼滤波 状态估计 欧几里得距离 

分 类 号：TM932[电气工程—电力电子与电力传动]