Delta-Bar-Delta and Directed Random Search Algorithms to Study Capacitor Banks Switching Overvoltages

Abstract

This paper introduces an approach to analyse transient overvoltages during capacitor banks switching based on artificial neural networks (ANN). Three learning algorithms, delta-bar-delta (DBD), extended delta-bar-delta (EDBD) and directed random search (DRS) were used to train the ANNs. The ANN training is based on equivalent parameters of the network and therefore, a trained ANN is applicable to every studied system. The developed ANN is trained with extensive simulated results and tested for typical cases. The new algorithms are presented and demonstrated for a partial 39-bus New England test system. The simulated results show the proposed technique can accurately estimate the peak values of switching overvoltages.