Resilience Assessment for Power Systems Under Sequential Attacks Using Double DQN With Improved Prioritized Experience Replay

The information and communication technology enhances the performance and efficiency of cyber-physical power systems (CPPSs). However, it makes the topology of CPPSs more exposed to malicious cyber attacks in the meantime. This article proposes a double deep-Q-network (DDQN)-based resilience assessment method for power systems under sequential attacks. The DDQN agent is devoted to identifying the least sequential attacks to the ultimate collapse of the power system under different operating conditions. A cascading failure simulator considering the characteristics of generators is developed to avoid a relatively optimistic assessment result. In addition, a novel resilience index is proposed to reflect the capability of the power system to deliver power under sequential attacks. Then, an improved prioritized experience replay technique is developed to accelerate the convergence rate of the training process for DDQN agent. Simulation results on the IEEE 39-bus, 118-bus, and 300-bus power systems demonstrate the effectiveness of the proposed DDQN-based resilience assessment method.