FORECASTING THE NET ENERGY DEMAND OF TURKEY BY ARTIFICIAL NEURAL NETWORKS

Es H. A., Kalender F. Y., Hamzacebi C.

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, vol.29, no.3, pp.495-504, 2014 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 29 Issue: 3
  • Publication Date: 2014
  • Journal Name: JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
  • Page Numbers: pp.495-504
  • Keywords: ANN, Energy, Multiple linear regressions, COLONY OPTIMIZATION APPROACH, GENETIC ALGORITHM APPROACH, ELECTRICITY CONSUMPTION, RENEWABLE ENERGY, GREY MODEL, PREDICTION, REGRESSION, FUEL, GDP
  • Karadeniz Technical University Affiliated: Yes

Abstract

In this study, the net energy demand of Turkey has been predicted by artificial neural networks (ANN). In order to forecast net energy demand of Turkey, Gross Domestic Product (GDP), population, import, export, area of the building and vehicles number data was used as input of ANN model. The prediction performance of built ANN model has been demonstrated in comparison with a multiple linear regression technique. The comparisons are shown the superiority of ANN. By using the model which is acceptable and high accuracy, the net energy demand of Turkey has been predicted that between the years of 2011-2025.