A neural-based redispatch approach to dynamic generation allocation

Abstract

A redispatch approach based on the Hopfield neural network is proposed for solving the dynamic generation allocation problem. This paper considers the dynamic dispatch problem that involve the allocation of system generation optimally among dispatchable generating units while tracking a load curve and observing power ramping response rate limits of the units, system spinning reserve requirements. The solution algorithm for solving the dynamic economic dispatch problem is divided into two major stages. First, the lambda-iteration method is employed to obtain the static economic dispatch as the base case. Then, the dynamic economic dispatch problem is linearized about this base case and is solved using the Hopfield neural network redispatch approach. This method has been successfully applied to a utility system. The results are given to show the efficiency of the proposed method.