Transport Energy Demand Forecasting Using Neural Networks: Case Study Iran

In this paper, the energy demand of transport sector from 1386 to 1400 was forecasted using artificial neural networks (ANN) approach considering economic and social indicators. Feed forward supervised neural networks to forecast and back propagation algorithm to train networks were used. In order to analyze the influence of economic and social indicators on energy demand of transport sector, Gross Domestic Product (GDP), population and the total number of vehicles in 1347-1385 were taken into consideration. The obtained results as compared with the multiple regression method, revealed much less mistakes. The average absolute error percentage was decreased from 15.52% to 6.05%. .