Risk evaluation of power system communication based on PCA and RBF neural network

Based on principal component analysis (PCA) and radial basic function (RBF) neural network (NN), this paper proposes an approach to evaluate the risk of power system communication, in which the complexity of influencing factor and difficulty to describe evaluation in models of mathematics is overcome. Concretely, the original input space is reconstructed by principal component analysis(PCA) and the structure of the network is determined according to the contributions from the principal components respectively, so the ability of training speed and evaluation are improved. The effectiveness of the proposed algorithm is verified by the practical data for the power system communication.