The forecasting energy demand of Turkey by particle swarm optimization and genetic algorithm until 2050

Particle swarm optimization (PSO) and Genetic algorithm (GA) are the most important optimization techniques among various modern heuristic optimization techniques. The study purpose forecast the energy demand in Turkey until the year 2050 using PSO and GA models. The annual data provided by the Ministry of Energy and Natural Resources, IEA (International Energy Agency), OECD, Turkish Statistical Instıtute were used in the study. PSO and GA energy demand forecasting models are developed using population, import, export and gross domestic product (GDP). All models are proposed in linear and quadratic form Turkey's energy demand is projected according to four different scenarios. According the results, we found to for the PSO analysis the〖 R〗^2 values in the linear model was % 91,71, in the quadratic model was % 93,07 at the same time for the GA analysis R^2 values in the linear model was % 91,71, in the quadratic model was % 94,06. Also, in the quadratic model, the mean absolute percent errors were 22.52% for PSO and 22.74% for GA. According to Lewis, these values show that the models are acceptable. It was observed that PSO model values gave better estimation results than GA.