Forecasting of electricity consumption: a comparative analysis of regression and artificial neural network models

Several authors have formulated regression models to forecast electricity consumption. Also, more recently, several authors have attempted to formulate artificial neural network models to forecast electricity consumption. The authors have attempted in this paper to formulate and estimate both regression and artificial neural network models to forecast the electricity consumption for Hong Kong. They found that artificial neural network model forecasts are generally at least as good as those generated by the multiple linear regression model