ANN-based AVC relay for voltage control of distribution network with and without embedded generation

Abstract

Voltage magnitude of distribution networks is usually maintained within statutory limits by using on load tap changer transformers that are controlled by automatic voltage control (AVC) relays. Traditional AVC relay is usually equipped with compounding whose settings are chosen in such away to compensate for the voltage drop along the feeder(s) emanating from source substation. This paper presents an attempt to design an AVC relay based on the application of artificial neural networks (ANNs). The input data file used for the training of the proposed AVC relay is prepared using a power system load flow program, which is written in FORTRAN. In this paper the structure of the proposed ANN-based AVC relay is presented and the test results that show its performance are also presented and discussed.