Application of ANN to determine the OLTC in minimizing the real power losses in a power system

Abstract

This paper presents an artificial neural network (ANN) technique for determining optimum tapping ratio of tap changing transformer, which will in turn minimise real power losses in an electrical power system. Training data containing variety of load patterns, tap changing ratio and real power losses associated with each tapping, are fed into a neural network. By using the Levenberg-Marquardt algorithm, a back propagation network is trained so that it can predict the optimum tap ratio when unseen data are fed into the network. The technique was tested on a 6-bus IEEE system and the results show that the proposed ANN technique is highly accurate, reliable and capable to predict at a faster rate.