A critical review on intelligent-based techniques for detection and mitigation of cyberthreats and cascaded failures in cyber-physical power systems

Abstract

The advent of advanced technologies in power and energy systems is fortifying the grid’s resilience and enhancing the availability of power supply through a network of electrical and communication apparatus. The notable technologies include cyber-physical power systems (CPPS) and transactive energy systems (TES). The CPPS, a derivative of cyber-physical system (CPS), is for operational enhancement, and to boost performance. TES is an energy solution that uses economic and control techniques that enhance the dynamic balance between the supplied energy and energy demand across the electrical infrastructure. Integration of intelligence systems and information and communication technologies has brought new objections and threats to CPPS and TES, where adversaries capitalize on the vulnerabilities in cyber systems to manipulate the system deceitfully. Furthermore, the susceptibility of CPPS to information attacks inherently has the potential to cause cascading failures. Researchers have extensively focused their searchlight on applications of advanced technologies within CPPS. However, leaving out the impact of cascaded failures on the CPPS’ efficiency. This work critically assesses intelligent-based techniques used for cyber threat detection and mitigation. It offers insights on how to guide against some of the approaches adopted by cyber-attackers, identifies corresponding gaps, and presents future research directions. Also presented is the conceptualization of applying CPS models for the cyber-security enhancement of TES solutions. The articles selected for this review were evaluated based on recency and the application of intelligent approaches for intrusion and cyberattack detection in CPPS. It was uncovered from the review that topological models are often used to describe cyberattack processes in CPPS. Also, researchers based their investigation on False-Data Injection Attacks and IEEE-118 Bus systems for validation. It was discovered that the deep Reinforcement Learning-based Graph Convolutional Network is a promising solution for intrusion and cyberattack detection in TES owing to its security, detection accuracy, reliability, and scalability.