An application of artificial neural network for determining the tap change ratio of OLTC in minimizing real power loss in a power system / Nor Haidar Hashim

This project 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 electrical power system. Training data containing variety of load patterns, tap changing transformer 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 predict the optimum tap ratio when unseen data are fed into the network. The technique was tested on 6-bus IEEE system and the result obtained shows that the proposed ANN technique is highly accurate, reliable and capable to predict at faster rate