Optimal Operation of Mula Reservoir with Combined Use of Dynamic Programming and Genetic Algorithm

Genetic algorithm (GA) has been used repeatedly in reservoir operation studies during last two decades. GAs require trying different alternatives, different GA parameter values, and select those which perform best for a particular application. Besides this, there are chances of getting trapped into local optima, since GA starts with randomly generated initial population within the entire search space. Therefore, GA’s search process is slow and time-consuming. GA’s process may be speeded up if initial population is generated in a narrowed search space. This process may save time spent on sensitivity analysis of parameters. Discrete dynamic programming (DP) provides global optimal solutions, but discreteness and dimensionality are the main disadvantages in reservoir operation applications. To overcome these deficiencies a hybrid approach combining DP and GA (DP–GA) is proposed to study a single reservoir operation problem. Where DP provides the narrowed search space within which the optimal solution for the problem is expected. GA then search to achieve the possible optimal solution within this space avoiding any discreteness of variables. Proposed DP–GA approach was found to outperform both GA and DP in terms of less computational requirement and quality of the solution, respectively.