Forecasting Energy Demand in Iran Using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) Methods

Abstract

The main objective of this research is to estimate energy demand in Iran using intelligence techniques based on the structure of Iran's industry and economic conditions. This study develops a scenario to analyze energy consumption and makes future projections based on particle swarm optimization (PSO) and genetic algorithm (GA) methods. The models are developed in two forms (exponential and linear) and applied to forecast energy demand in Iran. PSO and GA demand estimation models are developed to estimate the future energy demand values based on population, gross domestic product, import, and export data. Energy consumption in Iran from 1981–2005 is considered as the case of this study. The available data is partly used for finding the optimal, or near optimal, values of the weighting parameters (1981–1999) and partly for testing the models (2000–2005). Energy demand in Iran is forecasted up to year 2030.

Keywords:

• energy
• genetic algorithm
• Iran
• particle swarm optimization
• projection

Notes

^aMboe: Million barrel of oil equivalents.

1 barrels of oil equivalent (boe) = 6,119 × 10⁶ joule (J).