Daily Peak Load Forecasting Using an Artificial Neural Network and Its Improving Method of Reducing the Forecasting Errors

Abstract

This paper proposes a forecasting method of short-term peak load using a 3-layer neural network of locally active units. Each unit in the hidden layer of the neural network is activated only by input vectors in a bounded domain of vector space. This characteristic enables additional learning. Furthermore, it is supposed to provide the network structure information which would help improving the forecasting accuracy. In simulations, the neural network is applied to daily peak load forecasting in summer. The results show that the proposed method is superior to a conventional neural network with back propagation algorithm. In order to make the best use of the neural network, an error oriented method of parameter modification is also examined.