基于非参数核密度估计的风电功率区间预测  

Wind Power Interval Prediction Based on Non-parametric Kernel Density Estimation

作　　者：孙建波[1] 吴小珊[2] 张步涵[2] 

机构地区：[1]湖北电力调度通信中心,湖北武汉430077 [2]华中科技大学强电磁工程与新技术国家重点实验室,湖北武汉430074

出　　处：《水电能源科学》2013年第9期233-235,54,共4页Water Resources and Power

基　　金：国家高技术研究发展计划(863计划)基金资助项目(2011AA05A101);国家重点基础研究发展计划(973计划)基金资助项目(2010CB227206)

摘　　要：由于风电的高度随机性和波动性,且风电功率的预测精度仍较低,因此传统的风电功率点预测不足以描绘风电的不确定性。在风电功率点预测值的基础上,采用非参数核密度估计方法计算风电功率预测误差的概率密度,并采用三次样条插值拟合预测误差的概率分布曲线,继而得出满足一定置信概率的风电功率预测区间。结果表明,采用风电功率区间预测能提供风电功率预测曲线和该曲线的变化范围,更有利于风电的不确定性建模。As the high randomness and fluctuation of wind power, as well as the low precision of the power predic- tion, the traditional prediction of wind power point is not able to describe the uncertainty of wind power. In this article, non-parametric kernel density estimation is adopted to calculate the probability density error of wind power prediction. In addition, we get a wind power prediction interval with the method of three spline interpolation which satisfies the certain confidence interval. The results show that wind power interval forecasting can provide wind power prediction curve and its variation range. Thus, it is more suitable for wind power uncertainty modeling.

关 键 词：风电功率预测 置信区间 非参数核密度估计 预测误差分布 

分 类 号：TM715[电气工程—电力系统及自动化]