Wind power has a big influence on the safe operation and rational management of electric power system. It is useful to grasp the distribution characteristics of wind power prediction error for the large-scale development and utilization of wind energy. Two chaos ultra-short-term forecasting methods are used to predict wind power. The wind power data of a northeast wind farm is taken as an example to analyze the probability distribution of single-step prediction error of wind power, the relationship between the wind power prediction error and the prediction step number, the relationship between the wind power prediction error and the wind farm output power, and the relationship between the wind power prediction error and the installed capacity. It lays the theoretical foundation for the analysis of the composition and correction of the wind power prediction error. This work is supported by National Key Basic Research Program of China (973 Program) (No. 2013CB228201), National Natural Science Foundation of China (No. 51307017), Science and Technology Development Program of Jilin Province (No. 20140520129JH), and Special Program of Industrial Technology Research and Development of Jilin Province (No. 2014Y124).