Forecasting future oil demand in Iran using GSA (Gravitational Search Algorithm)

Growing energy demand of the world, made the major oil and gas exporting countries to have critical role in the energy supply. The geostrategic situation of Iran and its access to the huge hydrocarbon resources placed the country among important areas and resulted in the investment development of oil and gas industry. In this study, a novel approach for oil consumption modeling is presented. Three demand estimation models are developed to forecast oil consumption based on socio-economic indicators using GSA (Gravitational Search Algorithm). In first model (PGIE) oil consumption is estimated based on population, GDP, import and export. In second model (PGML) population, GDP, export minus import, and number of LDVs (light-duty vehicles) are used to forecast oil consumption and in third one (PGMH) population, GDP, export minus import, and number of HDVs (heavy-duty vehicles) are used to estimate oil consumption. Linear and non-linear forms of equations are developed for each model. In order to show the accuracy of the algorithm, a comparison is made with the GA (Genetic Algorithm) and PSO (Particle Swarm Optimization) estimation models which are developed for the same problem. Oil demand in Iran is forecasted up to year 2030. (C) 2011 Elsevier Ltd. All rights reserved.