Developing a Decision Model Based on Decision Tree and Particle Swarm Optimization Algorithms to Identify Optimal Locations for Solar Power Plants Construction in Iran

Sustainable energy sources such as solar energy are the most common renewable alternatives to fossil fuels. The first step in expanding the use of solar energy is to identify high-potential locations for the construction of solar power plants. This study aims to assess and compare the performance of decision tree and particle swarm optimization (PSO) algorithms in identifying optimal solar power locations. High-potential regions are extracted using multiple-criteria decision making (MCDM), which are used in the decision tree and PSO algorithms for recognizing optimal locations. The results indicate the potential of the study area for establishing solar power plants based on three-level of suitability. The comparison of optimization methods showed that the prediction rate for the very high potential class belonged to the decision tree (0.29) and PSO (0.13), respectively. Therefore, the decision tree method offers a better solution for detecting potential areas for solar energy development in the study area. The research results provide a useful resource for planning and decision-making concerning the development of renewable energy in the future. The used decision tree in the present study can also be used in other parts of the world to select optimal locations for constructing renewable energy plants. • A new approach to identify optimal locations for solar power plants in Iran. • The decision tree and PSO are used for the first time in solar energy assessment. • Raster and vector spatial criteria are considered to assess site feasibility. • The results show the efficiency of the decision tree for finding solar power plants.