Improved Ant Colony Optimization Algorithm for Reservoir Operation

In this paper, an improved Ant Colony Optimization (ACO) algorithm is proposed for reservoir operation. Through a collection of cooperative agents called ants, the near-optimum solution to the reservoir operation can be e ectively achieved. To apply the proposed ACO algorithm, the problem is approached by considering a nite horizon with a time series of in ow, classifying the reservoir volume to several intervals and deciding for releases at each period, with respect to a prede ned optimality criterion. Pheromone promotion, explorer ants and a local search are included in the standard ACO algorithm for a single reservoir, deterministic, nite-horizon problem and applied to the Dez reservoir in Iran. The results demonstrate that the proposed ACO algorithm provides improved estimates of the optimal releases of the Dez reservoir, as compared to traditional state-of-the-art Genetic Algorithms. It is anticipated that further tuning of the algorithmic parameters will further improve the computational e ciency and robustness of the proposed method.