Optimal Reservoir Operation Considering the Water Quality Issues: Application of Adaptive Neuro-Fuzzy Inference Systems (ANFIS)

In this study, an algorithm combining an ANFIS-based water quality simulation model and a GA-based optimization technique is developed for determining optimal reservoir operating rules. In this paper, the Nash bargaining theory is used to resolve the existing conflict of interests as different decision-makers and stakeholders are involved in the reservoir operation. The utility functions of the proposed models are developed based on the reliability of water supply to downstream demands, water storage, and the quality of the withdrawn water. A numerical water quality simulation model is also developed to simulate the thermal stratification cycle and the reservoir discharge quality through a selective withdrawal structure. As the water quality simulation model has a considerable run-time, an ANFIS-based simulation model is trained using the results of multiple simulation runs of the numerical water quality simulation model. Then the trained ANSIS model is linked with the Dynamic Genetic Algorithm (DGA). DGA can reduce the computational burden of the classical GAs and the ANFIS model reduces the simulation time. Therefore, total model run time is considerably reduced in the proposed model. The developed model is applied to the 15-Khordad Reservoir in the central part of Iran. The results show that the model can reduce the salinity of the allocated water to different water demands as well as the salinity build-up in the reservoir.