Application of artificial neural networks to the dynamic analysis of the voltage stability problem

The problem of assessing the voltage stability in electrical power systems is addressed through the artificial neural network (ANN) approach. The ANN field has undergone rapid development in the past few years and it offers potential advantages regarding efficient computation and ease of knowledge acquisition. A dynamic model of the power system is used to train multilayer perceptron networks to make them capable of indicating if and when a voltage collapse is likely to occur in the immediate future. Problems found during the validation of the proposed methodology are reported and discussed