An application of artificial neural network to dynamic economic load dispatching

Dynamic economic load dispatching is one of the optimization problems in power system operation. Since an optimization is required under severe constraints, all constraints cannot be taken into account. In this paper, the dynamic economic load dispatching is formulated using an artificial neural network as against a formulation by which a solution had to be obtained by nonlinear programming. The present method uses a probabilistic artificial neural network and effectively handles constraints by a heuristic method. It outputs a suboptimal and feasible result by applying load patterns simulating a real load to a reduced 3 thermal generating unit system.<>