Artificial neural network as application for estimating energy dependency trend

Konferenz: ANNA '18 - Advances in Neural Networks and Applications 2018
15.09.2018 - 17.09.2018 in St. St. Konstantin and Elena Resort, Bulgaria

Tagungsband: ANNA '18

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Arnaudov, Simeon V. (Department of Literature and Programming, Asenevtsi Publishing, Sofia, Bulgaria)
Spassov, Kamen (Faculty of Informatics and Mathematics, Sofia University St. Kliment Ohridski, Sofia, Bulgaria)

Domestic economic performance depends on various microeconomic factors, such as net import and export of energy resources or country trade balance. The goal of the current research is to revise the feasibility of popular neural network packages in projecting future energy dependency trends based on primary energy consumption and imported energy resources. For this purpose two different models build on artificial neural network (ANN) technique are proposed. ModelOne was built on main energy indicators (such as total energy generation). ModelTwo was build on sectored electricity consumption per capita. The results showed that ModelOne had better accuracy, which made it more suitable to be used to forecast the country’s future energy dependency index. The results suggested that neuronet is a fine programmed model for forecasting energy dependency.