准确的风电功率预测有利于含大规模风电电力系统的安全可靠、持续稳定运行，掌握风电功率预测误差的分布特征，对风电大规模并网有重要意义。以吉林省某风电场的实测数据为例，对风电功率进行超短期预测，利用非参数估计对预测误差分布进行拟合，分析了非参数估计与预测方法、预测时间间隔、预测误差概率分布形态以及风电场装机容量的关系，验证了所提出方法的有效性。(Accurate wind power prediction is conducive to safe, reliable, continuous and stable operation of large-scale wind power systems. It is important to grasp the distribution characteristics of wind power prediction errors, which is of great significance for large-scale grid connection of wind power. Taking the measured data of a wind farm in Jilin Province as an example, the ultra-short-term prediction of wind power is used. The non-parametric estimation is used to fit the prediction error distribution. The non-parametric estimation and prediction method, the prediction time interval and the prediction error probability distribution are analyzed. The relationship between the installed capacity of wind farms and the effectiveness of the proposed method is verified.)