Deep Reinforcement Learning-Based Cyberattack Mitigation for Smart Voltage Source Converter-Enabled Power Grid

Smart Inverters (SIs) of the Distributed Energy Resources (DERs) can enable cloud computing, condition monitoring, result visualization, remote control, and peer-to-peer energy trading in advanced power systems. However, cyberattacks in the SI can cause devastating consequences. This work proposes a Deep Reinforcement Learning (DRL) based reference tracking data injection cyberattack mitigation technique for the smart Voltage Source Converters (VSC) of the wind generators. The proposed mitigation technique is based on tracking and rectifying the control signals of the grid side converter. To verify the effectiveness of the proposed mitigation technique, its performance is compared with that of another Proximal Policy optimization (PPO) based deep reinforcement learning. Effectiveness of the proposed method has been tested and verified in a hybrid wind farm integrated system using MATLAB/SIMULINK environment.