Transient Voltage Stability and Voltage Sag Discrimination by Matching Pursuit-Based Transient Modeling and Neural Networks

Abstract

This article presents a method to discriminate between transient voltage stability and voltage sag. Transient modeling based on matching pursuit with an overcomplete dictionary of wavelet functions is a powerful tool in the analysis of the transient phenomena in power systems because of its ability to accurately represent them in both time and frequency domains with a minimum amount of information. This is a desirable feature when looking for accuracy and computational cost, as discrimination is performed by combining the information provided by the signal analysis tool with a neural network. In our approach, the information provided by the matching pursuit-based transient modeling stage is applied to train a neural network in a fast and accurate fashion. The simulated results presented clearly show that the proposed technique can discriminate accurately between transient voltage stability and voltage sag in power system protection with low computation cost.