Forecasting the Effect of Renewable Energy Consumption on Economic Welfare: Using Artificial Neural Networks

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