基于混合自适应核密度估计的风电波动特性分析

Analysis of wind power fluctuation characteristics based on hybrid adaptive kernel density estimation

分析掌握风电出力波动特性的内在规律有利于提高风电出力的预测精度,进而指导电网调度部门合理安排发电计划,提高系统运行的经济性。为描述风电出力波动的概率密度分布特性,文章首先分别修正由经验法及无偏交叉验证法得到的固定带宽,建立两种自适应带宽核密度估计模型;然后,将上述两种模型进行组合优化;最后,建立基于混合自适应核密度估计(HAKDE)的风电出力波动量概率密度分布模型。采用多种概率密度分布模型对华北某省风电场的不同时空尺度下的风电出力波动量进行拟合,算例结果表明,HAKDE模型的拟合效果最优,从而验证了HAKDE模型的有效性。

The analysis and mastery of the inner law of the fluctuation characteristics of wind power output is conducive to improving the prediction accuracy of wind power output,thus guiding the power grid scheduling department to reasonably arrange the power generation plan and improve the economy of system operation.To characterize the probability density distribution of wind power output fluctuations,two adaptive bandwidth kernel density estimation models are developed by modifying the fixed bandwidths obtained from the empirical method and the unbiased cross-validation method.Then,the above two models are combined and optimized,and finally the probability density distribution model of wind power output fluctuation based on hybrid adaptive kernel density estimation(HAKDE)is established.A variety of probability density distribution models were used to fit the fluctuations of wind power output at different spatial and temporal scales in a province in North China.The results show that the fitting effect of the HAKDE model is the best,which verifies the effectiveness of the HAKDE model.