基于奇异值分解与卡尔曼滤波修正多位置NWP的短期风电功率预测

SHORT-TERM WIND POWER PREDICTION BASED ON SVD AND KALMAN FILTER CORRECTION OF MULTI-POSITION NWP

考虑到数值天气预报网格点位置和系统误差对短期风电功率预测精度的影响,提出一种基于奇异值分解与卡尔曼滤波修正多位置数值天气预报的短期风电功率预测模型。首先通过奇异值分解对多位置数值天气预报数据进行特征提取与降维处理;然后使用卡尔曼滤波方法修正数值天气预报风速数据,降低数值天气预报的系统误差;最后基于极端随机森林算法,利用修正的数值天气预报数据搭建短期风电功率预测模型。通过对某风电场进行仿真,并与单位置、未降维、未修正模型比较,结果表明降维修正模型的预测效果最好,平均误差和均方根误差分别为7.94%和9.96%。

In consideration of the influences of positional and systematic errors in numerical weather prediction(NWP)grid point on the short-term wind power prediction accuracy,this paper puts forward a short-term wind power prediction model for the correction of multi-position NWP based on the singular value decomposition(SVD)and Kalman filtering,which firstly conducts the feature extraction as well as dimension-reduction process on the multi-position NWP,uses Kalman filtering method to correct the data of wind speed in NWP and to reduce the systematic error of NWP,and finally uses the corrected NWP data to build the short-term wind power prediction model based on the extreme random forest algorithm.Through the simulation of one wind farm as well as the comparison with single-position,non-dimension-reduction and uncorrected models,the results indicate that the dimension-reduction and corrected models have the best prediction effects,and the average error and root-mean-square error(RMSE)are 7.94% and 9.96%,respectively.