Classification of power system voltage stability conditions using Kohonen's self-organising feature map and learning vector quantisation

Abstract

SUMMARY This paper presents an artificial neural network–based approach, in which Kohonen's self-organising feature map technique in association with learning vector quantisation has been applied to classify the power system operating states on the basis of their degree of static voltage stability. The proposed scheme can seamlessly integrate itself within the energy management systems in the smart grid scenario. A self-organising feature map has been considered to be an ideal choice because the state classification problem is a typical multiclass pattern classification problem, which can be efficiently handled by a self-organising feature map with much shorter training time compared with other neural networks. The self-organising feature map provided information about the operating states of the power system and classified them into three categories, namely, normal state, intermediate state and emergency (or alert) state. To augment the classification accuracy of self-organising feature map, a learning vector quantisation–based supervised classification was also adopted. The proposed method was tested on a real 203-bus system of an Indian power utility, and the results obtained has been compared with standard voltage stability indicator–based classical voltage stability assessment results. Copyright © 2011 John Wiley & Sons, Ltd.