An artificial neural network based application to reactive power dispatch problem

The optimal reactive power dispatch problem is important for power systems to operate in a reliable and economic way. Many linear and nonlinear optimization techniques may be used to solve this problem. In this study, an artificial neural network approach (ANN) to optimal reactive power dispatch problem is proposed. A multilayer feedforward ANN with an error backpropagation algorithm is used. The proposed method is tested on a sample system and the results are compared with the ones obtained by classical optimization techniques.