Cyber-Attack Detection: Modeling and Roof-PV Generation System Protection

Abstract

The continuous increase of the renewable energy installation in the power system such as roof-PV systems, is decreasing the system inertia that challenges the system operation stability. However, with the increasing number of cyber attack events reported in the world, the operation of the roof-PV systems may threaten their connected AC system operation during the contingency. Utilizing the grid-connected converters (GCCs), its fast regulating characteristic could rapidly increase or decrease the solar generation output in seconds, which will bring significant influences to the system operation once the cyber attack happens. To solve this problem, this paper proposed a cyber attack detection model to eliminate its effect on the roof- PV generation system. In this model, the synchrosqueezed wavelet transforms (SWT) is first applied to extract the time-frequency information of frequency measurement. Then a recurrent layer aggregation-based convolutional neural network is introduced to identify the features of cyber attack using the results from SWT. The comparison experiments indicate that the proposed model have profound performance on the detection accuracy that could be utilized in the roof-PV generation system for cyber attack detection.