False data injection attacks detection with modified temporal multi-graph convolutional network in smart grids

被引:24
作者
Han, Yinghua [1 ]
Feng, Hantong [1 ]
Li, Keke [1 ]
Zhao, Qiang [2 ]
机构
[1] Northeastern Univ Qinhuangdao, Sch Comp & Commun Engn, Qinhuangdao, Peoples R China
[2] Northeastern Univ Qinhuangdao, Sch Control Engn, Qinhuangdao, Peoples R China
基金
中国国家自然科学基金;
关键词
Power system; Graph convolutional network; Gated recursive unit; False data injection attacks; CLASSIFICATION;
D O I
10.1016/j.cose.2022.103016
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
False Data Injection Attack (FDIA) detection can prevent the tampering of important data in the smart grid. This is of great significance to the operation and control of modern power systems. Since the exist-ing FDIA detection methods are limited by the sequential input of data in Euclidean space, they cannot accurately describe the compelling correlation between data components. Therefore, this paper proposes a novel FDIA localization detection method based on graph data modeling and graph deep learning. The proposed approach tries to disaggregate the primary data into graph structured data with graph topo-logical relationships based on graph theory, then designs specialized networks for data with different graph topologies. Moreover, the designed multi-graph mechanism and temporal correlation layer can bet-ter fully mine the correlation features between data components, with its attribute characteristics, to construct deep learning on the specific graph topology for FDIA detection. Extensive simulation experi-ments and visualization show that the proposed scheme is more effective than the conventional detection model, and its overall accuracy in 14-bus, 118-bus and 30 0-bus systems is 98.3%, 96.4% and 95.8%. It also proves that this scheme has high robustness and generalization ability in different scenarios.(c) 2022 Elsevier Ltd. All rights reserved.
引用
收藏
页数:11
相关论文
共 39 条
[1]  
[Anonymous], 2017, ADV NEURAL INF PROCE
[2]  
[Anonymous], 2020, LOAD DATAMARKET OPER
[3]   Joint Detection and Localization of Stealth False Data Injection Attacks in Smart Grids Using Graph Neural Networks [J].
Boyaci, Osman ;
Narimani, Mohammad Rasoul ;
Davis, Katherine R. ;
Ismail, Muhammad ;
Overbye, Thomas J. ;
Serpedin, Erchin .
IEEE TRANSACTIONS ON SMART GRID, 2022, 13 (01) :807-819
[4]  
Chollet F, 2015, KERAS
[5]   Detection of False Data Injection Attacks in Smart Grids Based on Graph Signal Processing [J].
Drayer, Elisabeth ;
Routtenberg, Tirza .
IEEE SYSTEMS JOURNAL, 2020, 14 (02) :1886-1896
[6]   FUSION OF COGNITIVE WIRELESS NETWORKS AND EDGE COMPUTING [J].
Gai, Keke ;
Xu, Kai ;
Lu, Zhihui ;
Qiu, Meikang ;
Zhu, Liehuang .
IEEE WIRELESS COMMUNICATIONS, 2019, 26 (03) :69-75
[7]   Security and Privacy in Cyber-Physical Systems: A Survey of Surveys [J].
Giraldo, Jairo ;
Sarkar, Esha ;
Cardenas, Alvaro A. ;
Maniatakos, Michail ;
Kantarcioglu, Murat .
IEEE DESIGN & TEST, 2017, 34 (04) :7-17
[8]   Detecting False Data Injection Attacks in AC State Estimation [J].
Gu Chaojun ;
Jirutitijaroen, Panida ;
Motani, Mehul .
IEEE TRANSACTIONS ON SMART GRID, 2015, 6 (05) :2476-2483
[9]  
Hamaguchi T, 2017, PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P1802
[10]   Recurrent Graph Convolutional Network-Based Multi-Task Transient Stability Assessment Framework in Power System [J].
Huang, Jiyu ;
Guan, Lin ;
Su, Yinsheng ;
Yao, Haicheng ;
Guo, Mengxuan ;
Zhong, Zhi .
IEEE ACCESS, 2020, 8 :93283-93296