A hybrid artificial neural network (ANN) and Ward equivalent approach for on-line power system voltage security assessment

Abstract

Abstract This paper presents a novel hybrid artificial neural network (ANN) and Ward-type equivalent approach for fast, on-line voltage security assessment of power systems. The proposed approach possesses the good properties of Ward equivalent method and can update the parameters of the equivalent model for representing real-time topology change of the external system. Moreover, the boundary equivalent power injection can be quickly matched using hybrid ANN. Test results demonstrate that the new equivalent model is efficient and has accurate response.