Power system state forecasting using artificial neural networks

This paper presents a new method for power system state forecasting using a rtificial neural networks (ANN). The state forecasting problem has been sol ved in two steps: the filtering step and the forecasting step in an open lo op configuration. Because under normal operating conditions the power syste m behaves in a quasi-static manner, a simplified model of the dynamic behav ior of the power system states is considered. Two different ANN models have been used for these two steps of power system state forecasting problem. F or the filtering step, a functional link network (FLN), and for the forecas ting step, a time delay neural network (TDNN) have been used to simulate th e dynamic behavior of the power system states. The proposed method has been tested on two IEEE test systems, and a practical Indian system and results have been compared with an extended Kalman filter (EKF) based technique [L eite da Silva et al., 1983].