Comparison of Neuro-Fuzzy, Artificial Neural Network and Multivariate Regression for Prediction energy consumption in the country

Abstract

Energy besides Other factors production is considered the main factor in the growth and economic development and in the performance of different sectors economic can play beneficial roles. Hence, the country authorities should try to predict anything more precise energy consumption in the proper planning and guidance consumption, to control the way they desired energy demand and supply parameters. The aim of this paper reviews Comparison of Neuro-Fuzzy, Artificial Neural Network and Multivariate Regression for Prediction energy consumption in the country. Case study is energy consumption in transportation sector of Iran. So for this review, were used the annual data energy consumption of transport as a variable output of forecast models and data from the entire country's annual population, GDP and the number of vehicle as the input variables. The end results were assessed with of different models (RSE), (ME) and (RMSE). Models evaluation results showed that Neuro-Fuzzy (ANFIS), compared to other models with the highest accuracy is in predicting energy consumption.

Keywords

• energy consumption
• multivariate regression
• artificial neural networks
• neuro-fuzzy