A non-linear multivariable regression model for midterm energy forecasting of power systems

The objective of this paper is to describe a non-linear multivariable regression method for midterm energy forecasting of power systems in annual time base. This method performs an extensive search in order to select the appropriate transformation functions of input variables, the weighting factors and the training periods to be used, by taking into consideration the correlation analysis of the selected input variables. With this procedure the best forecasting model is formed. Results are presented that are obtained applying the described method for the Greek power system and for different categories of low voltage customers. These results are also compared to those obtained from the application of standard regression methods.