A Fast and Effective Automated Wavelet-Deep learning-based Method to Detect Cyberattacks in Microgrids with EV Fast Charging Stations

The electric vehicles within the microgrid operate in a vehicle-to-grid (V2G) mode to provide ancillary services to support the operation of renewable energy resources (RERs). However, the threat of cyberattacks on electric vehicle fast charging stations (EVFCSs) is a pressing concern. When these attacks occur, they disable the EVFCSs, rendering them inaccessible and hindering the ancillary service provision, which in turn disrupts the operation of the microgrid. In response to this, this paper presents a novel and effective approach to detect cyberattacks targeting EVFCSs in microgrids embedded with RERs. The proposed method combines wavelets and convolution neural networks (CNNs) to detect such attacks quickly and effectively. The results have shown that the proposed approach detected cyberattacks with a high detection accuracy of 99.39 % and a low computational time of 3.5 seconds.