Survey of machine learning methods for detecting false data injection attacks in power systems. Issue 5 (6th October 2020)

• Record Type: Journal Article
• Authors: Sayghe, Ali; Hu, Yaodan; Zografopoulos, Ioannis; Liu, XiaoRui; Dutta, Raj Gautam; Jin, Yier; Konstantinou, Charalambos
• Is Part Of: IET smart grid. Volume 3:Issue 5(2020)
• Page Start: 581
• Page End: 595
• Publication Date: 2020-10-06
• Subjects: security of data -- power grids -- power system security -- power engineering computing -- power system measurement -- energy management systems -- power system state estimation -- binary decision diagrams -- learning (artificial intelligence); power system state estimation -- system data -- energy management system -- unknown state variables -- system redundant measurements -- data detection algorithms -- FDIA -- malicious data vectors -- data‐driven solutions -- machine learning algorithms -- sensor data -- power system SE algorithms -- false data injection attacks -- power systems -- cyber attacks -- cyber‐attacks -- power grid monitoring systems; Smart power grids -- Periodicals; Computer science -- Periodicals; Energy industries -- Periodicals; Broadcasting -- Periodicals; 333.79110285
• DOI: 10.1049/iet-stg.2020.0015
• Languages: English
• ISSNs: 2515-2947

Abstract

Abstract : Over the last decade, the number of cyber attacks targeting power systems and causing physical and economic damages has increased rapidly. Among them, false data injection attacks (FDIAs) are a class of cyber‐attacks against power grid monitoring systems. Adversaries can successfully perform FDIAs to manipulate the power system state estimation (SE) by compromising sensors or modifying system data. SE is an essential process performed by the energy management system towards estimating unknown state variables based on system redundant measurements and network topology. SE routines include bad data detection algorithms to eliminate errors from the acquired measurements, e.g. in case of sensor failures. FDIAs can bypass BDD modules to inject malicious data vectors into a subset of measurements without being detected, and thus manipulate the results of the SE process. To overcome the limitations of traditional residual‐based BDD approaches, data‐driven solutions based on machine learning algorithms have been widely adopted for detecting malicious manipulation of sensor data due to their fast execution times and accurate results. This study provides a comprehensive review of the most up‐to‐date machine learning methods for detecting FDIAs against power system SE algorithms.