Deep reinforcement learning control approach to mitigating actuator attacks

This paper investigates the deep reinforcement learning based secure control problem for cyber–physical systems (CPS) under false data injection attacks. We describe the CPS under attacks as a Markov decision process (MDP), based on which the secure controller design for CPS under attacks is formulated as an action policy learning using data....

Robust Adaptive Back-Stepping Control Approach Using Quadratic Lyapunov Functions for MMC-Based HVDC Digital Twins

Due to its excellent performance, VSC-based high voltage direct current (HVDC) power systems draw significant attention. They are being heavily used in modern industrial applications, such as onshore and offshore wind farms, and for interconnection between asynchronous networks. However, the traditional proportional-integral (PI) control...