On-Line Voltage Stability Assessment using Least Squares Support Vector Machine with Reduced Input Features

In this paper, Least Squares Support Vector Machine (LS-SVM) is used for a fast and accurate estimation of the power system loading margin for multiple contingencies with reduced input features. The input variables considered are the real and reactive power demand at the load buses. The training data for the LS-SVM are generated by using the Continuation Power Flow (CPF) method. The proposed method uses dimensionality reduction techniques for improving the performance of the developed network with less training time. Principal Component Analysis (PCA) based feature extraction and Mutual Information (MI) based feature selection technique are used to reduce the input dimension which makes the LS-SVM approach applicable for a large scale power system. IEEE 30-bus and IEEE 57-bus systems are considered for a demonstration of effectiveness of the proposed methodology under various loading conditions considering single line contingencies. Simulation results validate the proposed LS-SVM with reduced input features for fast and accurate on-line voltage stability assessment.