COMPARISON BETWEEN GENETIC ALGORITHM, PARTICLE SWARM OPTIMIZATION AND ANT COLONY OPTIMIZATION TECHNIQUES FOR NOX EMISSION FORECASTING IN IRAN

Urbanization, industrialization, rapid traffic growth, and increasing levels of anthropogenic emissions have resulted in a substantial deterioration of air quality over the globe. Global climate change due to Greenhouse gas (GHGs) emissions is an issue of international concern that primarily attributed to fossil fuels. In this study, Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) techniques are applied for analyzing NOX emission in Iran based on the values of oil, natural gas, coal, and primary energy consumptions, as energy indicators. Linear and non-linear forms of equations are developed to forecast NOx emission using GA, PSO, and ACO. The related data between 1981 and 2009 were used, partly for installing the models (finding candidates of the best weighting factors for each model, 1981-2002) and partly for testing the models (2003-2009). Eventually, NOX emission in Iran is estimated up to year 2025.