Study on forecasting discharge of hydropower station with backwater effect based on improved EBP neural network

In optimal dispatching decision system of hydropower station, discharge of reservoir is forecast usually. However the discharge has complicated nonlinear relations with downriver level and backwater flux when backwater effects exist. It is difficult to get satisfactory forecasting results with traditional linear interpolation method. This paper proposes a nonlinear decision-making method based on error back propagation (EBP) artificial neural network (ANN) to establish forecasting discharge model of reservoir. Improved EBP algorithm is presented to process ANN model training. Simulation results show that the proposed method forecasts discharge with the backwater effect better than traditional linear interpolation method. The ANN model and improved EBP algorithm proposed are also applicable to other similar system.