Applying Deep Convolutional Neural Network for Fast Security Assessment with N-1 Contingency

The increasing penetration of renewable energy into the power system has aggravated the uncertainties during grid operation. Hence fast security assessment method has become highly imperative for system operators. In this paper, a deep convolutional neural network (deep CNN) is developed as an efficient tool to implement fast static security assessment, which classifies system security status via data mining. The multiple convolutional layers within the deep CNN can automatically extract features from the raw data and formulate an approximated mapping between the input and the output without intensive numerical computation. Applying the proposed deep CNN on standard IEEE test cases verifies its accuracy and efficiency for system operation security classification, which indicates its considerable potential for future online application.