Civil Engineering / Environmental / Architecture / Planning Session:

Title:            Operating policies using genetic algorithm - Ukai reservoir as a case study
Authors:       S. S. Shiyekar, P. L. Patel
Abstract:      During last two decades, water resources planning and management profession has seen a dramatic increase in the development and application of various types of evolutionary algorithms (EAs). This observation is especially true for application of genetic algorithms, arguably the most popular of the several types of EAs. Generally speaking, EAs repeatedly prove to be flexible and powerful tools in solving an array of complex water resources problems. In reservoir operation, appropriate methodology for deriving reservoir operating rules should be selected and operating rules should then be formulated. In the present study, Genetic Algorithm (GA) has been used to optimize the operation of existing multipurpose reservoir in India, and also to derive reservoir operating rules for optimal reservoir operations. The fitness function used is minimization of irrigation deficit i.e minimize sum of squared deviation of releases from demands of irrigation. The decision variables are monthly releases from the reservoir for irrigation and initial storages in reservoir at beginning of the month. The constraints considered for this optimization are reservoir capacity and bounds for decision variables. Results show that, even during the low flow condition, the present GA model if applied to the Ukai reservoir in Gujarat State, India, can satisfy downstream irrigation demand. Hence based on the present case study it can be concluded that GA model has the capability to perform efficiently, if applied in real world operation of the reservoir.

Keywords:     Evolutionary algorithms (EA), Genetic algorithms (GA), constraints, fitness function
Pages:            184-187

Download Full Paper