Short-term load forecasting using Kalman filter and Elman neural network

In view of the dynamic nonlinear characteristics of power system loads, a short-term load forecasting (STLF) method for power system is proposed based on Wiener model, and Elman recursive neural network is used to fit in with its nonlinear part in this paper. Kalman filter is introduced to overcome the unknown disturbance in the linear part of the systems during loads prediction. Then, Elman neural network is applied to carry out the nonlinear loads prediction. The studies indicate that the proposed method possesses high learning efficiency, strong adaptability and high forecast precision, and is very suitable to short-term load forecast. At last, a simulation example indicates the availability of the method.