基于混合Copula函数的风电功率相关性分析

Wind Power Correlation Analysis Based on Hybrid Copula

风电功率作为电力系统调度运行中不可忽视的随机输入变量,其相关性分析直接影响电力系统的不确定性和运行风险评估。文中从风电功率相关结构的角度出发分析风电功率的相关性,分析了风电功率间的尾部特征,提出利用混合Copula函数建模分析风电功率相关性的方法。该方法依据风电功率测量数据的相关结构,以线性加权的方式构造能够描述不对称尾部特征的混合Copula函数,并利用期望最大化(EM)方法对相关参数进行估计,研究结果表明,混合Copula函数能够很好地刻画风电功率间的相关结构和尾部特征,同时基于Copula函数的相关性测度理论能够方便地求取反映相关程度的指标。

Wind power is a new stochastic variable in the power system operation and dispatch,the correlation of wind power generation should be quantified to determine the variability of power flows,the system uncertainty and operational risk. This paper analyzes the tail dependency of wind power first,and then improves a hybrid Copula method to model the wind power dependency considering the dependency structure. The method constructs a hybrid Copula which can describe the tail characteristic by linear weight,then uses the expectation maximization（ EM） algorithm to evaluate the parameter,the analysis results of two typical wind farms show that hybrid Copula can accurately describe the correlation structure of wind power,and the correlation index and tail correlation index can be easily calculated based on the correlation measure theory of Copula.