Transient stability evaluation using an artificial neural network (power systems)

Abstract

This paper describes a power system transient stability evaluation method using an artificial neural network (ANN). To improve the accuracy of the evaluation, the authors propose a new type of training signal which is a reciprocal of the action time of a step-out relay (SOR) after the fault occurrence. In simulation results of a 16-bus system, the evaluation accuracy of the ANN trained using the proposed training signal is about 20 percent more accurate than that of an ANN trained using the conventional 0/1 digital signal.<>