Detection of Fault and Cyber Attack in Cyber-Physical System Based on Ensemble Convolutional Neural Network

Ensuring the security of alternating current networks is crucial for maintaining a stable energy supply. With modern power grids integrating both cyber and physical layers, they are increasingly vulnerable to cyberattacks. This study introduces a one-dimensional Convolutional Neural Network (1D CNN) for detecting cyberattacks in power systems. The proposed model is evaluated using an Industrial Control System dataset and achieves superior accuracy and F1-scores compared to traditional methods such as Support Vector Machines (SVM), Multi-Layer Perceptron (MLP), and Decision Trees (DT).