بهينه سازي بهره برداري از مخازن سدها با كمك يك مدل تطبيقي فازي - عصبي

Inferring reservoir operating rules is a complementary stage in applying long-term or medium-term implicit stochastic models to reservoir operation optimization problems. The method of dynamic programming (DP) has been used as an optimization tool to provide the input-output data set to be used by ordinary least square regression (OLSR) and an adaptive neuro-fuzzy inference system called ANFIS to derive reservoir operating rules. The OLSR and ANFIS based rules are then simulated and compared based on their performance in simulation. The methods are applied to Dez reservoir in along-term planning problem as well as in a medium-term implicit stochastic optimization model. The results indicate that ANFIS does not make a significant improvement over simpler OLSR model in long-term planning problem. However, ANFIS is more beneficial in medium term implicit stochastic optimization as it is able to extract important nonlinear features of the system from the generated input-output set and represent those features as general operating rules. It is emphasized that using ANFIS along with an adaptive learning algorithm would be justified where we face with the problem of knowledge extraction from a nonlinear or ill-defined information existing in the data set of the problem.