A deep learning‐based classification scheme for cyber‐attack detection in power system. Issue 3 (12th August 2021)

• Record Type: Journal Article
• Authors: Ding, Yucheng; Ma, Kang; Pu, Tianjiao; Wang, Xingying; Li, Ran; Zhang, Dongxia
• Other Names: Jiang Tao guestEditor.; Bai Linquan guestEditor.; Mu Yunfei guestEditor.; Venayagamoorthy Kumar guestEditor.; Zhang Yingchen guestEditor.; Teng Fei guestEditor.; Chen Peiyuan guestEditor.; Zhong Haiwang guestEditor.; Yao Wei guestEditor.; Wan Can guestEditor.
• Is Part Of: IET energy systems integration. Volume 3:Issue 3(2021)
• Page Start: 274
• Page End: 284
• Publication Date: 2021-08-12
• Subjects: conditional deep belief network -- cyber security -- deep learning -- false data injection attacks detection -- feature extraction -- smart grids -- state estimation; power system security -- IEEE standards -- belief networks -- time series -- smart power grids -- security of data -- deep learning (artificial intelligence) -- power engineering computing -- power system state estimation; Power resources -- Periodicals; Energy conservation -- Periodicals; Power resources; Energy conservation; Periodicals; 333.79
• DOI: 10.1049/esi2.12034
• Languages: English
• ISSNs: 2516-8401

Abstract

Abstract: A smart grid improves power grid efficiency by using modern information and communication technologies. However, at the same time, the system might become increasingly vulnerable to cyberattacks. Among various emerging security problems, a false data injection attack (FDIA) is a new type of attack against the state estimation. In this article, a deep learning‐based identification scheme is developed to detect and mitigate information corruption. The scheme implements a Conditional Deep Belief Network to analyse time‐series input data and leverages captured features to detect the FDIA. The performance of the detection mechanism is validated by using the IEEE standard test system for simulation. Different attack scenarios and parameters are set to demonstrate the feasibility and effectiveness of the developed scheme. Compared with the support vector machine and the multilayer perceptrons, the experimental analyses indicate that the results of the proposed detection mechanism are better than those of the other two in terms of FDIA detection accuracy and robustness.