Power system transient classification for protection relaying

Abstract

This paper investigates the applicability of decision tree based classifiers and hidden Markov model based classifiers to distinguish the transients originating from the faults from the transients due to normal switching events. Current signals due to different types of events such as faults, load switching, and capacitor bank switching were generated using a high voltage transmission system simulated in PSCAD/EMTDC simulation software. Simulated transients were used to train and test the classifiers. The feature vectors for the investigated techniques.