Application of Artificial Neural Networks in Controlling Voltage and Reactive Power

This paper presents an application of Artificial Neural Networks (ANN) to control the voltage and reactive power in power systems. The technique is based on using a feed-forward artificial neural network with an error back-propagation training algorithm, based on the Levenberg-Marquardt method to train the networks. The training data is obtained by solving several abnormal conditions using Linear Programming (LP). Generator voltages, reactive power sources and transformer taps are considered as control variables and load bus voltages and generator reactive powers as dependent variables. The method presented in this paper has been tested on IEEE 14-bus and 30-bus standard systems. The obtained results clearly indicate that the trained neural networks are capable of controlling the voltage and reactive power in power systems with a high level of precision and speed.