Turbines allocation optimization in hydro plants via computational intelligence

Abstract

In the last decades, due to environmental concerns and the decentralization of the electrical systems around the world, the share of Hydroelectric Power Plants (HPP) in the electricity matrix has grown year by year. Therefore, it is necessary to determine the operational planning of the hydro plants to schedule the optimum number of turbines on operation on a daily planning horizon aiming at supplying the generation goals at the lowest possible cost. The main goal of this work is to evaluate and compare the performance of two recent computational intelligence techniques, Grey Wolf Optimizer (GWO) and the Sine Cosine Algorithm (SCA), on obtaining the optimized dispatch of hydro plants regarding the Turbine Allocation Planning (TAP) problem. Mathematically, TAP is classified as a multimodal non-linear problem with mixed-integer variables. In order to test the aforementioned metaheuristic techniques, one HPP composed of five turbines on a 24-h planning horizon was considered. The results point to a better performance of the GWO technique on the HPP daily operation.