吴莉艳,孙开元,陈坤,岑海凤,叶小晖,王新宇
WU Liyan,SUN Kaiyuan,CHEN kun,CEN Haifeng,YE Xiaohui,WANG Xinyu

• 1:信发集团有限公司
• 2:广东电网有限责任公司广州供电局
• 3:燕山大学

摘要(Abstract)：

新型信息物理电力系统是实现双碳目标的关键环节，但针对状态估计的新型虚假数据攻击可以欺骗现有安全检测机制，给电力系统安全运行带来巨大挑战。为检测状态估计中虚假数据，以电网交流模型为研究对象分析恶意攻击的欺骗特性，结合CNN（卷积神经网络）提取数据的空间特征优势和LSSVM（最小二乘支持向量机）的数据分类能力，构建了基于CNN-LSSVM的攻击检测模型。基于IEEE 14总线电力系统数据验证了所提出的CNN-LSSVM检测模型的有效性，其检测准确率达到94.6%。
The new cyber-physical power system is crucial for achieving dual carbon goals. However, novel false data injection attacks targeting state estimation can bypass existing security detection mechanisms, significantly challenging the secure operation of power systems. To detect false data in state estimation, the deceptive characteristics of malicious attacks are analyzed using the AC power grid model as the research object. By combining the data spatial feature extraction capabilities of convolutional neural networks(CNN) with the data classification abilities of least squares support vector machine(LSSVM), this paper develops an attack detection model using CNN-LSSVM. The model's effectiveness is verified using data from IEEE 14-bus power system, achieving a detection accuracy of 94.6%.

关键词(KeyWords)： 信息物理电力系统;攻击检测;CNN;LSSVM
cyber-physical power system;attack detection;CNN;LSSVM

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金青年项目（62103357）

作者(Author): 吴莉艳,孙开元,陈坤,岑海凤,叶小晖,王新宇
WU Liyan,SUN Kaiyuan,CHEN kun,CEN Haifeng,YE Xiaohui,WANG Xinyu

DOI: 10.19585/j.zjdl.202411010

参考文献(References)：

• [1]龚立，王先培，田猛，等.电力信息物理系统韧性的概念与提升策略研究进展[J].电力系统保护与控制，2023,51(14):169-187.GONG Li,WANG Xianpei,TIAN Meng,et al.Concepts and research progress on enhancement strategies for cyber physical power system resilience[J]. Power System Protection and Control,2023,51(14):169-187.
• [2]赵洪磊，徐正阳，谷毅，等.配电信息物理系统的架构与规划综述[J].电力建设，2023,44(6):61-69.ZHAO Honglei,XU Zhengyang,GU Yi,et al.Review of architecture and planning of cyber-physical distribution system[J].Electric Power Construction,2023,44(6):61-69.
• [3]杨安，孙利民，王小山，等.工业控制系统入侵检测技术综述[J].计算机研究与发展，2016,53(9):2039-2054.YANG An,SUN Limin,WANG Xiaoshan,et al.Intrusion detection techniques for industrial control systems[J].Journal of Computer Research and Development,2016,53(9):2039-2054.
• [4]王琦，邰伟，汤奕，等.面向电力信息物理系统的虚假数据注入攻击研究综述[J].自动化学报，2019,45(1):72-83.WANG Qi,TAI Wei,TANG Yi,et al.A review on false data injection attack toward cyber-physical power system[J].Acta Automatica Sinica,2019,45(1):72-83.
• [5] LIU Y,NING P,REITER M K.False data injection attacks against state estimation in electric power grids[J].ACM Transactions on Information and System Security,2011,14(1):1-33.
• [6]张明月，王新宇.基于残差观测器的智能电网虚假数据攻击检测研究[J].电气工程学报，2023,18(1):111-117.ZHANG Mingyue,WANG Xinyu.Detection of false data attack in smart grid based on residual observer[J].Journal of Electrical Engineering,2023,18(1):111-117.
• [7] AO W,SONG Y D,WEN C Y.Adaptive cyber-physical system attack detection and reconstruction with application to power systems[J]. IET Control Theory Appl,2016,10(12):458-1468.
• [8]高洋，任望，吴润浦，等.信息物理系统的攻击检测与安全状态估计[J].清华大学学报（自然科学版），2021,61(11):1234-1239.GAO Yang,REN Wang,WU Renpu,et al.Attack detection and security state estimation of cyber-physical systems[J].Journal of Tsinghua University(Science and Technology),2021,61(11):1234-1239.
• [9]张雯阳，唐明珠，郭胜辉.信息物理系统区间观测器设计及攻击检测应用[J].系统科学与数学，2021,41(9):2379-2389.ZHANG Wenyang,TANG Mingzhu,GUO Shenghui.Interval observer design for cyber-physical systems and application to attack detection[J]. Journal of Systems Science and Mathematical Sciences,2021,41(9):2379-2389.
• [10] LU R T,WANG J,WANG Z Q. Distributed observerbased finite-time control of AC microgrid under attack[J].IEEE Transactions on Smart Grid,2021,12(1):157-168.
• [11]李苑，王国胤，李智星，等.基于序列注意力机制的卷积神经网络异常检测[J].郑州大学学报（理学版），2019,51(2):17-22.LI Yuan,WANG Guoyin,LI Zhixing,et al.A sequential attention based convolutional neural network for anomaly detection[J]. Journal of Zhengzhou University(Natural Science Edition),2019,51(2):17-22.
• [12] DONG H,PENG D G.Research on abnormal detection of ModbusTCP/IP protocol based on one-class SVM[C]//2018 33rd Youth Academic Annual Conference of Chinese Association of Automation(YAC). May 18-20,2018. Nanjing,China. IEEE,2018.
• [13]马锐，刘玉树，杜彦辉.基于BP网络的入侵检测方法[J].计算机工程与应用，2003,39(26):156-157.MA Rui,LIU Yushu,DU Yanhui. A back-propagation neural network-based intrusion detection Ap proach[J].Computer Engineering and Applications,2003,39(26):156-157.
• [14]陈虹，王闰婷，肖成龙，等.基于DBN-XGBDT的入侵检测模型研究[J].计算机工程与应用，2020,56(22):83-91.CHEN Hong,WANG Runting,XIAO Chenglong,et al.Research on intrusion detection model based on DBNXGBDT[J]. Computer Engineering and Applications,2020,56(22):83-91.
• [15]王新宇，王相杰，张明月，等.基于改进自适应免疫遗传算法的智能电网虚假数据攻击检测方法[J].浙江电力，2023,42(10):84-89.WANG Xinyu,WANG Xiangjie,ZHANG Mingyue,et al.A false data attack detection method for power grid based on an improved AIGA[J].Zhejiang Electric Power,2023,42(10):84-89.
• [16]蒋正威，张超，孙伟乐，等.基于神经网络的电网假数据注入攻击检测方法研究[J].浙江电力，2020,39(11):45-50.JIANG Zhengwei,ZHANG Chao,SUN Weile,et al.Detection method of false data injection attack on power grid based on neural networks[J]. Zhejiang Electric Power,2020,39(11):45-50.
• [17] LIU Y,WANG Z D,HE X,et al.Minimum-variance recursive filtering over sensor networks with stochastic sensor gain degradation:algorithms and performance analysis[J].IEEE Transactions on Control of Network Systems,2016,3(3):265-274.
• [18] ESMALIFALAK M,LIU L C,NGUYEN N,et al.Detecting stealthy false data injection using machine learning in smart grid[J]. IEEE Systems Journal,2017,11(3):1644-1652.