Next day peak load forecasting using an artificial neural network with modified backpropagation learning algorithm
Takashi Onoda · 1994
This paper presents a method of next day peak load forecasting using an artificial neural network (ANN). The author combines the DSC search method (Davis, Swann, Campey search method) with the backpropagation learning algorithm (Bp) to reduce the training time and avoid converging at local minima as much as possible. The forecasting results by ANN is as good as human experts results end is better than the forecasting results by the regression model. The training time by the author's approach is less than that by the general backpropagation in experiments. In the author's problem, the general backpropagation could not converge at the criteria in any cases. But the author's approach could converge at the criteria in the same cases.>