Elham Naeimi - M.Sc. Student, School of Industrial Engineering, Islamic Azad University,South Tehran Branch, Tehran, Iran
Mohammad Hossein Askariazad - Assistant Prof. School of Industrial Engineering, Islamic Azad University,South Tehran Branch, Tehran, Iran
Kaveh Khalili-Damghani - Assistant Prof. School of Industrial Engineering, Islamic Azad University,South Tehran Branch, Tehran, Iran

Energy as a production process input has an effective role on economicindicators such as gross domestic production (GDP). Limitations in fossil fueland nuclear energy sources urge utilizing renewable energies. In this paper, theimpact of renewable energy consumption on economic welfare indicators (i.e.GDP, GDP per capita, annual income of urban households, and annual incomeof rural households) is investigated. For this purpose, 41 annual data sets arecollected, from 1971 to 2011, mostly from Iran’s Statistical Yearbook andIran’s Balance Sheet. Artificial neural networks (ANNs) are used forforecasting the effect of renewable energy consumption on economic welfareindicators. Advantages in using the proposed ANN-based method aredemonstrated by comparing its results with the multi-layer regression (MLR)model. The comparison between the artificial neural network and the multilayerregression model demonstrates that the artificial neural network has moreaccurate results than the multi-layer regression model. Both ANN and MLRmodels show significant effect of using renewable energies on the economicwelfare. Results demonstrate the importance of using the proposed model forpolicy makers in implementing new policies for renewable energies. The ANNprediction results show that GDP, GDP per capita, annual income of urbanhouseholds, and annual income of rural households will grow by 35.63%,62.59%, 167.61% and 143.19%, respectively, from 2007 to 2016.

Economic welfare, renewable energy consumption, artificialneural networks, multi-layer regression model