Artificial neural network-based forecast for electricity consumption in Malaysia

An essential element of electric utility resource planning is the long term forecast of the electricity consumption. This paper presents an approach to forecast annual electricity consumption by using artificial neural network based on historical data for Malaysia. It involves developing several ANN designs and selecting the best network that can produce the best results in terms of its accuracy. The network is developed by means of economical conditions and how the variables are going to be changed in the following years. After obtaining the most reliable model, ANN is used to forecast the electricity consumption. The developed ANN model yields very satisfactory results and as a result, the range of electricity consumption can be successfully obtained.