Neural networks in forecasting electrical energy consumption: Univariate and multivariate approaches

Neural networks in forecasting electrical energy consumption: Univariate and multivariate approaches

0.00 Avg rating0 Votes
Article ID: iaor20032865
Country: United States
Volume: 26
Issue: 1
Start Page Number: 67
End Page Number: 78
Publication Date: Jan 2002
Journal: International Journal of Energy Research
Authors: , ,
Keywords: neural networks
Abstract:

This paper presents an artificial neural network (ANN) approach to electric energy consumption (EEC) forecasting in Lebanon. In order to provide the forecasted energy consumption, the ANN interpolates among the EEC and its determinants in a training data set. In this study, four ANN models are presented and implemented on real EEC data. The first model is a univariate model based on past consumption values. The second model is a multivariate model based on EEC time series and a weather-dependent variable, namely, degree days (DD). The third model is also a multivariate model based on EEC and a gross domestic product (GDP) proxy, namely, total imports (TI). Finally, the fourth model combines EEC, DD and TI. Forecasting performance measures such as mean square errors, mean absolute deviations, mean percentage square errors and mean absolute percentage errors are presented for all models.

Reviews

Required fields are marked *. Your email address will not be published.