Modeling output energy based on fossil fuels and electricity energy consumption on dairy farms of Iran: Application of adaptive neural-fuzzy inference system technique

Abstract

This research examined an adaptive neural-fuzzy inference system to model output energy on the basis of energies of fossil fuels and electricity inputs. Energy use especially non-renewable forms are widely considered in livestock farming management in recent years. Data were collected randomly from 50 dairy farms in Tehran province of Iran in 2011. A review of the published literature indicated that the adaptive neural-fuzzy inference system (ANFIS) has rarely been used or tested to model agricultural energy demand. ANFIS model based on energy consumption was developed for dairy farm units in Tehran province, Iran. In this research, fossil fuels and electrical energy required and energy output produced were treated as inputs and output of ANFIS model, respectively. The computational results demonstrated that ANFIS model is generally comparable with linear regression analysis approach and is promising in modeling fossil fuels and electricity energy consumption. The comparison of the coefficient of determination (R2) (0.79 and 0.11), the root mean square error (RMSE) (0.11 and 0.22) and the mean absolute percentage error (MAPE) (0.007 and 0.014) demonstrated the above mentioned result for both proposed methods, respectively. The accurate model performance is beneficial to predict energy usage as the first step toward energy management and it would be constructive in developing future energy related researches and planning strategies.