基于概率分布对巴音郭楞蒙古自治州风速特征的研究

Study of Wind Speed Characteristics in Bayingol Mongolian Autonomous Prefecture Based on Probability Distribution

基于新疆巴音郭楞蒙古自治州风速数据,讨论了分布参数估计方法和分布模型选择准则,发现混合威布尔分布是一个非常灵活的分布.采用极大似然方法和最小二乘方法,并运用四种优化算法找到参数最优估计值.同时,使用8种测度指标多重判断分布的适用性.对于混合威布尔分布,采用最小二乘法估计模型参数时,得到的分布能较好地拟合该地区风速.结果对相关部门实际分析巴音郭楞蒙古自治州风速特征和风能潜力具有参考价值.

Based on the wind speed data in Bayingol Mongolian Autonomous Prefecture of Xinjiang,the estimation of distribution parameters and the selection of models are discussed,and it is found that the two-parameter mixture Weibull distribution is a very flexible one.The maximum likelihood method,the least squares method and four optimization algorithms are used to find the optimal estimation values of the model parameters.At the same time,the applicability of the mixture Weibull distribution is evaluated by using eight kinds of model selection criteria.The parameters of the mixture Weibull distribution are estimated by the least square method,and the obtained model can well fit the wind speed in this region.The results of this paper have important reference value for related departments to analyze wind speed characteristics and wind energy potential of Bayingol Mongolian Autonomous Prefecture.