复杂地形风电场微观选址的GA-PSO混合算法研究

HYBRID GA-PSO ALGORITHM FOR WIND FARM MICRO-SITING IN COMPLEX TERRAIN

提出一种结合改进遗传算法(GA)和粒子群算法(PSO)的GA-PSO混合算法对复杂地形的风力机排布方案进行优化。以湖南省某实际复杂地形为对象,开展风场全风向数值模拟,结合长期观测风资料评估区域的潜在风能分布,提出考虑网格预处理、时变变异率、唯一化和并行化的改进GA(IGA)对风力机排布方案进行优化,在此基础上利用PSO算法进行进一步优化,并针对尾流模型和目标函数对优化结果的影响进行不确定性分析。结果表明,在复杂地形风电场微观选址方面,所提GA-PSO算法比贪婪算法、GA、IGA分别改善16.4%、12.9%和5.1%。

A hybrid GA-PSO algorithm combining improved genetic algorithm(GA)and particle swarm optimization(PSO)is proposed to optimize the wind turbine layout scheme in complex terrain.Taking a real complex terrain in Hunan Province as the target,the full wind direction numerical simulation of the wind farm is carried out,and the potential wind energy distribution of the region is evaluated by combining long-term observed wind data,and the improved GA(IGA)considering grid preprocessing,time-varying mutation rate,uniqueness and parallelization is proposed for cluster optimization of the wind turbine layout scheme,based on which the further optimization is carried out using the PSO algorithm.Uncertainty analysis is performed for the effect of the wake model and objective function model on the optimization results.The results show that the proposed GA-PSO algorithm improves 16.4%,12.9%,and 5.1%over the greedy algorithm,GA,and IGA,respectively,in wind farm micro-siting in complex terrain.