In multi-purpose reservoirs, to achieve optimal operation, sophisticated models are\nrequired to forecast reservoir inflow in both short- and long-horizon times with an acceptable\naccuracy, particularly for peak flows. In this study, an auto-regressive hybrid model is proposed for\nlong-horizon forecasting of daily reservoir inflow. The model is examined for a one-year horizon\nforecasting of high-oscillated daily flow time series. First, a Fourier-Series Filtered Autoregressive\nIntegrated Moving Average (FSF-ARIMA) model is applied to forecast linear behavior of daily flow\ntime series. Second, a Recurrent Artificial Neural Network (RANN) model is utilized to forecast\nFSF-ARIMA modelâ??s residuals. The hybrid model follows the detail of observed flow time variation\nand forecasted peak flow more accurately than previous models. The proposed model enhances\nthe ability to forecast reservoir inflow, especially in peak flows, compared to previous linear and\nnonlinear auto-regressive models. The hybrid model has a potential to decrease maximum and\naverage forecasting error by 81% and 80%, respectively. The results of this investigation are useful\nfor stakeholders and water resources managers to schedule optimum operation of multi-purpose\nreservoirs in controlling floods and generating hydropower.
Loading....