Application of genetic algorithm to choose the best scenario for energy demand forecasting of residential and commercial sectors in Iran

Developing energy estimation models is one of the most important steps in macro-planning for providing sustainable energy with the purpose of economic development and social welfare. Also, it has always been noted by energy policymakers and analysts. Residential and commercial sectors are the largest energy consumers in Iran and it is very important to estimate energy demand of the sectors. In the present study energy demand of residential and commercial sectors of Iran has been estimated using linear and exponential functions and the coefficients are obtained from genetic algorithm. 54 different scenarios with various inputs have been investigated. Data from the years 1968 to 2011 are used to develop models and select the suitable scenario. Results show that an exponential model with inputs including total value added minus that of the oil sector, value of made buildings, total number of households and consumer energy price index is the most suitable model. Using the selected scenario, energy demand of residential and commercial sectors is estimated up to the year 2032. The results show that the energy demand of the sectors will achieve a level of about 1180 million barrel of oil equivalent per year by 2023.