Skip to Main Content
The objective of this paper is to present a new methodology for midterm energy forecasting in the framework of a data mining procedure. The method includes the development of a database that contains historical relevant data, such as values for energy consumption, weather parameters, statistical indices etc. The data is mined from the database, filtered, preprocessed and converted to desired forms. Data knowledge discovery is succeeded by constructing a non-linear multivariable regression model which takes in consideration correlation analysis on the selected variables. Results of the method for two types of customers, i.e. high voltage industries and residential customers are compared to standard regression methods.