Power system voltage stability assessment using a self-organizing neural network classifier

This paper presents a neural network based method for voltage stability assessment. By use of the voltage collapse margin (VCM) method, a self-organizing network is trained to give the power margin of the weak area of power systems from voltage collapse. Based on a Kohonen network which consists of a Kohonen and backpropagation network, the self-organizing network clusters input patterns with similar features and hence increase the efficiency of training phase. The generalization capability of the self-organizing network can cope with vagarious load/generation patterns which have not been encountered during the training phase. The effectiveness of the proposed network has been demonstrated on the IEEE 30-bus test system.