A new method for short term electric load forecasting

Abstract

An integrated genetic algorithm (GA)/tabu search (TS) and neural fuzzy network (NFN) method for load forecasting is presented In this work. A neural fuzzy network (NFN) was used for the initial load forecasting. Then we used CGA and TS to find the optimal solution of the parameters of the NFN, instead of back-propagation (BP). First the GA generates a set of feasible solution parameters and then puts the solution into the TS. We combined both methods to try and obtain both advantages, and in doing so eliminate the drawback of the traditional ANN training by BP.