An Optimization Method for Multi-Factor Wind Farm Siting Based on the Adaptive GA-PSO Algorithm

Wind farm siting optimization involves multiple interrelated factors, and traditional methods often struggle to balance energy utilization efficiency with unit power generation cost, especially under complex terrain and varying environmental conditions. To address these challenges, this paper proposes a multi-factor micro-siting optimization method based on an Adaptive Genetic Algorithm-Particle Swarm Optimization (GAPSO) algorithm. An initial turbine layout is generated using the Wind Atlas Analysis and Application Program (WASP), followed by optimization targeting cost minimization and output maximization. The model integrates key environmental variables-wind speed, surface roughness, temperature, and air pressure-enhancing adaptability to complex scenarios. By combining the global search capability of the Genetic Algorithm (GA) with the local refinement of Particle Swarm Optimization (PSO) and incorporating adaptive weight adjustment, the algorithm significantly improves convergence speed and solution quality. Case studies show that the proposed method reduces unit generation cost to 2016 yuan/GWh and increases annual output to 82.633 GWh.