Developing real time optimal reservoir operation rules using Bayesian networks: application of group conflict resolution model

In reservoir operation, there are various decision makers and stakeholders with different and varied utilities. In this paper, investigates the conflicts among decision makers and stakeholders and water quality simulation model and Genetic Algorithm (GA) optimization model combined to find the trade-off curve between qualitative and quantitative issues. The group n person conflict resolution theory is used for selecting the best point on trade-off curve. The Bayesian networks as a novel type of learning model is used to develop real-time operating rules. To evaluate the efficiency of the proposed methodology, it is applied to the 15-Khordad dam located in the central part of Iran. The 15-Khordad dam supplies the water demands of three main sectors: domestic, agriculture and environment. These sectors have conflicting interests about the quantity and quality of the allocated water to their demands the test results show that the both conflict resolution model and Bayesian network model can significantly calculate real-time reservoir operating policies.