混合Copula模型选择策略及其在风电功率中的应用

Mixed Copula Model Selection Strategy and Its Application in Wind Power

本文提出了混合Copula模型中Copula函数的选择策略,针对目前多数文献集中于阿基米德族进行选择,导致性质相似、共性较强的局限,扩大了选择范围,增加椭圆族作为备选,利用频率直方图,结合单一Copula函数的AIC值从中筛选,进而确定出引入混合Copula模型的函数,并将此方法应用于风电功率相关性分析中,得出由椭圆族和阿基米德族中的t-Copula、Clayton Copula、Frank Copula组成的混合Copula模型相较于阿基米德族混合Copula模型AIC值更小,拟合效果更优的结论,证明了该方法的有效性。

Aiming at the limitations caused by similarity and great commonality as most of litera-ture select from Archimedes Copula family, this paper proposes a mixed Copula model selection strate-gy from Copula functions which expands the range of selection and increases the ellipse family as an al-ternative, that is, combines frequency histogram with AIC value of a single Copula function to deter-mine the Copula functions which form a mixed Copula model. Then applies this method to wind powercorrelation analysis, comparing with the traditional mixed Copula model which consists of ArchimedesCopula family, the mixed Copula model of optimum strategy which is composed of t-Copula, ClaytonCopula, Frank Copula selected from ellipse family and Archimedes Copula family has a smaller AICvalue and a better fitting effect, thus demonstrates the effectiveness of this method.