Dispatch of hydroelectric generating units using multiobjective evolutionary algorithms

This paper proposes the use of multiobjective evolutionary algorithms (MOEAs) to solve an optimal multiobjective dispatch of hydroelectric generating units. The considered objectives are: maximization of the system efficiency and minimization of the startup/shutdown cost of generating units. Two representative MOEAs were combined with a heuristic approach to solve an optimal dispatch problem applied to a hydroelectric plant. Implemented algorithms are: the Strength Pareto Evolutionary algorithm (SPEA) and the Nondominated Sorting Genetic Algorithm II (NSGA-II). Experimental results show that MOEAs are able to provide several alternative schedules to the decision maker. In addition, for the considered dispatch problem, SPEA proposes a large set of alternative schedules than the NSGA-II.