NEURAL-NETWORK-BASED WATER INFLOW FORECASTING

Water inflow forecasting is usually based on precipitation data collec ted by the ombrometer stations in the river basin. Solution of this pr oblem is rather complex, due to the highly non-linear relation between the amount of precipitation at different locations and the water infl ow into the head hydro power plant reservoir. In this paper, a new app roach to forecasting water inflow, based on neural networks, is presen ted. First, selection of input parameters is discussed. Next, the most appropriate architecture of the neural networks, is chosen. Finally, the efficacy of the proposed method is tested for a practical case, an d some results are presented. (C) 1998 Elsevier Science Ltd. AII right s reserved.