Application of Particle Swarm Optimization and Genetic Algorithm for Estimation of Total Electricity Consumption in Iran Using Socio-Economic Indicators

Energy planning, formulating strategies and recommending energy policies are the most important reasons of electricity consumption estimating. The main objective of this research is to find the relationship between socio-economic indicators and electricity consumption in Iran using intelligent methods. This study develops Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) demand estimation models based on population, number of customers, gross domestic product (GDP), and price figures. Electricity consumption in Iran from 1979 to 2013 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 (1979-2007) and partly for testing the models (2008–2013). For the best results (PSO-exponential), relative error average was 4.99 %.

Keywords:

Particle Swarm Optimization , Genetic Algorithm , Socio-Economic Indicators , Electricity Consumption