Intelligent Operation Modeling of Reservoirs Using Group Method of Data Handling (GMDH)

Recently a lot of attention has been directed to advanced techniques of reservoir operation. The continuous evolution of the information technology (software and hardware) and the development of new techniques including soft computing, intelligent techniques, and evolutionary algorithms created a good environment for reality-based methods and tools. From the Theoretical point of view, modeling a system requires explicit mathematical relationships between inputs and outputs (variables). Since these relations are unknown in many systems, developing such an explicit model is very difficult. In this case, soft computing methods that are based on imprecise conditions and evolutionary algorithms provide capabilities in defining many nonlinear systems and identifying control issues. One of these heuristic selforganization methods is Group Method of Data Handling (GMDH) that produce increasingly complex models during the performance evaluation of input and output sets. Based on GMDH, in this research we have developed a model for the operation of reservoirs in the Tehran-Karaj plane including Lar, Latian and Karaj reservoirs. The GMDH is selected for reservoir operation based on the sufficiency of sampling, characteristics of reservoir in the region of study, and suitability of this technique in the data driven systems. Results of modeling showed high performance of GMDH in reservoir operation.