On-line Voltage Stability Assessment using Artificial Neural Networks

Voltage stability has become one of the major concerns of many electric utilities all over the world. This paper presents an Artificial Neural Network (ANN) based model for on-line voltage stability assessment. Maximum L-index of the load buses in the system is taken as the indicator of voltage instability. Pre-contingency state power flows are taken as the input to the neural network. The key feature of the proposed method is the use of dimensionality reduction techniques to improve the performance of the developed network. Two types of dimensionality techniques are proposed such as feature extraction through the use of Principal Component Analysis (PCA) and feature selection by mutual information. The effectiveness of the proposed approach is demonstrated through voltage stability assessment in IEEE 30-bus system and is compared with the results obtained using AC load flow. Experimental results show that the proposed method reduces the training time and improves the generalization capability of the network.