基于WGAN状态重构的智能电网虚假数据注入攻击检测
Detection of False Data Injection Attack in Smart Grid Based on WGAN State Reconfiguration
摘要: 针对虚假数据定位检测适应性低、篡改量测影响系统状态精确感知的问题，提出一种基于WGAN (Wasserstein generative adversarial networks, WGAN)状态重构的智能电网虚假数据检测与修正模型。首先，根据历史状态变量的概率分布，初步锁定并剔除具有潜在攻击风险的状态变量。然后，采用Wasserstein生成对抗网络重构缺失变量，WGAN通过Wasserstein距离衡量生成分布与真实分布之间的差异，能够生成有意义的梯度以优化网络模型参数。最后，以重构状态作为一种状态参考，精确定位攻击节点，并结合网络拓扑参数修正篡改量测值。将纽约州数据用在IEEE-14节点测试系统，进一步验证所提方法的可行性与有效性。
Abstract: Aiming at the problems of low adaptability of false data location detection and the influence of tamper measurement on the accurate state awareness for the power system, a false data detection and correction model of smart grid based on state reconstruction of Wasserstein Generative Adver-sarial Networks (WGAN) was proposed. Firstly, the state variables with potential attack risk are ini-tially locked and eliminated according to the probability distribution of historical state variables. Then, the missing state variables are reconstructed by Wasserstein generative adversarial net-works. WGAN measures the difference between the generated distribution and the real distribution through Wasserstein distance, which can generate meaningful gradients to optimize the parame-ters of the network model. Finally, the reconstructed variables are used as a state reference to lo-cate the attacked bus, and to correct the measurement data combined with the network topology parameters. The feasibility and validity of the proposed method are further verified in IEEE-14 bus test system with the New York data.
文章引用：张笑, 孙越. 基于WGAN状态重构的智能电网虚假数据注入攻击检测[J]. 建模与仿真, 2023, 12(3): 2182-2196. https://doi.org/10.12677/MOS.2023.123200

参考文献

[1] 别朝红, 林超凡, 李更丰, 等. 能源转型下弹性电力系统的发展与展望[J]. 中国电机工程学报, 2020, 40(9): 2735-2745.
[2] 倪明, 颜诘, 柏瑞, 等. 电力系统防恶意信息攻击的思考[J]. 电力系统自动化, 2016, 40(5): 1-4.
[3] Liu, Y., Ning, P. and Reiter, M.K. (2011) False Data Injection Attacks against State Estimation in Electric Power Grids. ACM Transactions on Information and System Security, 14, 13-21. [Google Scholar] [CrossRef] 
[4] 王文钰, 任洲洋, 孙义豪, 等. 基于小波-稀疏自编码器的输电网虚假数据检测方法[J]. 电工电能新技术, 2022, 41(1): 51-59.
[5] Bi, S.Z. and Zhang, Y.J. (2014) Graphical Methods for Defense against False-Data Injection Attacks on Power System State Estimation. IEEE Transactions on Smart Grid, 5, 1216-1227. [Google Scholar] [CrossRef] 
[6] Chao, P., Yang, X. and Wei, L.S. (2020) PMU Placement Protection against Coordinated False Data Injection Attacks in Smart Grid. IEEE Transactions on Industry Application, 56, 4381-4393.
[7] 刘鑫蕊, 吴泽群. 面向智能电网的空间隐蔽型恶性数据注入攻击在线防御研究[J]. 中国电机工程学报, 2020, 40(8): 2546-2559.
[8] Gu, C.J., Panida, J. and Mehul, M. (2015) Detecting False Data Injection Attacks in AC State Estimation. IEEE Transactions on Smart Grid, 6, 2476-2483. [Google Scholar] [CrossRef] 
[9] Wang, D.F., Wang, X.J., Zhang, Y., et al. (2019) Detection of Power Grid Disturbances and Cyber-Attacks Based on Machine Learn-ing. Journal of Information Security and Applications, 46, 42-52. [Google Scholar] [CrossRef] 
[10] Xue, D.B. and Jing, X.R. (2019) Detection of False Data Injection Attacks in Smart Grid Utilizing ELM-Based OCON Framework. IEEE Access, 7, 31762-31733. [Google Scholar] [CrossRef] 
[11] 朱杰, 张葛祥. 基于历史数据库的电力系统状态估计欺诈性数据防御[J]. 电网技术, 2016, 40(6): 1772-1778.
[12] 杨怡, 王勇. 基于AUKF的分布式电源系统虚假数据攻击检测方法[J]. 电工电能新技术, 2021, 40(12): 48-55.
[13] 杨玉莲, 齐林海, 王红, 等. 基于生成对抗网络和双重语义感知的配电网量测数据缺失重构[J]. 电力系统自动化, 2020, 44(18): 46-54.
[14] 王守相, 陈海文, 潘志新, 等. 采用改进生成式对抗网络的电力系统量测缺失数据重建方法[J]. 中国电机工程学报, 2019, 39(1): 56-64.
[15] 郑文迪, 聂建雄, 邵振国, 等. 智能配电网状态估计研究现状和展望[J]. 电力系统及其自动化学报, 2021, 33(4): 8-16.
[16] 王电钢, 黄林, 刘捷, 等. 考虑负荷虚假数据注入攻击的电力信息物理系统防御策略[J]. 电力系统保护与控制, 2019, 47(1): 28-34.
[17] 赵丽莉, 刘忠喜, 孙国强, 等. 基于非线性状态估计的虚假数据注入攻击代价分析[J]. 电力系统保护与控制, 2019, 47(19): 38-45.
[18] Ledig, C. and Theis, L. (2017) Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 105-114. [Google Scholar] [CrossRef] 
[19] Qian, S., Liu, H., Liu, C., et al. (2018) Adaptive Activation Func-tions in Convolutional Neural Networks. Neurocomputing, 272, 204-212. [Google Scholar] [CrossRef] 
[20] Load Data: Market and Operational Data (NYISO).
http://www.energyonline.com/Data/GenericData.aspx?DataId=13&NYISO___Hourly_Actual_Load

为你推荐