Developing operating rules for reservoirs considering the water quality issues: Application of ANFIS-based surrogate models

  • Authors:

  • Foad Soltani;Reza Kerachian;Ehsan Shirangi

  • Affiliations:

  • School of Civil Engineering, Institute of Civilization and Development, Hamedan, Iran;Center of Excellence for Engineering and Management of Infrastructures, School of Civil Engineering, University of Tehran, Tehran, Iran;Islamic Azad University, Karaj Branch, Karaj, Iran

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2010

Quantified Score

Hi-index 12.05

Visualization

Abstract

In this study, a methodology combining a water quality simulation model and a hybrid genetic algorithm (HGA) is developed for determining optimal operating policies for different reservoir outlets. The water quality simulation model is based on an adaptive neural fuzzy inference system (ANFIS), which is trained using the results of a numerical water quality simulated model. This ANFIS-based simulation model has an acceptable run-time and can be easily linked to the HGA-based optimization model. To further reduce the model run-time, the main problem is decomposed to a long-term and some annual optimization models. ANFIS is also utilized to develop monthly operating rules for reservoir outlets. To evaluate the efficiency of the proposed methodology, it is applied to the 15-Khordad dam located in the central part of Iran. The results show that this ANFIS-based model can significantly reduce the run-time of the previously developed models while it dose not reduce the accuracy of the reservoir operation policies. The ANFIS-based operating rules can be effectively used for real-time reservoir operation.