Search

Reservoir operation optimization models are based on the hydrological cycle principle. These models determine the inflow and outflow necessary to meet the demands for drinking water, irrigation water, etc. Rather than optimizing each reservoir separately in cascaded reservoir systems, more efficient results are obtained if the reservoirs are optimized as a whole. In this study, the optimal operation rule curves for cascaded reservoirs were obtained by using the cuckoo search algorithm, which is a soft computing method. Both the irrigation and flood control constraints of the Adiguzel and Cindere dams in Denizli (Turkey) were satisfied by utilizing these rule curves, and the total energy production was maximized. In addition, these rule curves considered turbine efficiency, which significantly contributes to published literature. The total energy obtained with the proposed operation rule curves was 14% higher than that currently produced by the Adiguzel and Cindere dams.

A novel architecture for flood routing model has been proposed and its efficiency is validated on several problems by employing support vector machines. The architecture is designed by including the inputs and observed and calculated outflows from the previous time step output. Whole observed data have been used for determining the model parameters in the heuristic methods given in the literature, which constitutes the major disadvantage of the existing approaches. Moreover, using the whole data for training may lead to overtraining problem that causes overfitting of estimations and data. Therefore, in this study, 60–90% of the data are randomly selected for training and then the remaining data are used for validation. In order to take the effects of the measurement errors into consideration, the data are corrupted by some additive noise. The results show that the proposed architecture improves the model performance under noisy and missing data conditions and that support vector machines can be powerful alternative in flood routing modeling.