Comparing least squares support vector machine and probabilistic neural network in transient stability assessment of a large-scale power system

Abstract

This paper presents transient stability assessment of a large practical power system using two artificial neural network techniques which are the probabilistic neural network (PNN) and the least squares support vector machine (LS-SVM). The large power system is divided into five smaller areas depending on the coherency of the areas when subjected to disturbances. This is to reduce the number of data sets collected for the respective areas. Transient stability of the power system is first determined based on the generator relative rotor angles obtained from time domain simulation outputs. Simulations were carried out on the test system considering three phase faults at different loading conditions. The data collected from the time domain simulations are then used as inputs to the PNN and LS-SVM. Both networks are used as classifiers to determine whether the power system is stable or unstable. Classification results show that the PNN gives faster and more accurate transient stability assessment compared to the LS-SVM.