一种基于改进的HHT短期风电功率预测方法  

An improved short-term wind power prediction method based on HHT

作　　者：宁康 廖晓辉[1] Ning Kang;Liao Xiaohui(School of Electrical Engineering,Zhengzhou University,Zhengzhou 450001,China)

机构地区：[1]郑州大学电气工程学院,郑州450001

出　　处：《电测与仪表》2018年第15期86-90,共5页Electrical Measurement & Instrumentation

基　　金：河南省科技项目(162102410071)

摘　　要：风电功率短期预测对于电力系统稳定性和电能质量的提高具有非常重要的意义。文章采取一种基于Hilbert-Huang变换风电的短期预测方法。首先,对经验模态分解(EMD)中原始数据存在的端点效应利用提出的延拓抑制方法进行了抑制,然后,用经验模态分解的方法将风电场历史功率数据分解得到了七个具有不同规律特征的分量,进行希尔伯特变换,并在对各个成分的特点分析的基础上分别搭建了不同的预测模型,然后结合多个预测模型对风电场历史功率数据进行组合预测。仿真实验预测结果表明该方法使得风电预测精度大大提高,具有很好的应用前景。Wind power short-term forecast for power system stability and the improvement of power quality has very important significance. According to the existing prediction methods,this paper puts forward a kind of wind power short-term forecast method based on Hilbert Huang transform. First of all,the continuation inhibition method is put forward to restrain the endpoint of the empirical mode decomposition（ EMD） existed in the original data. Then,the empirical mode decomposition method is adopted to resolve wind power history data and get seven different characteristics of the components. And on the basis of analyzing the characteristics of the components,different prediction models are set up respectively and the Hilbert transform is performed. Then,combined multiple prediction models forecast are conducted combing with the wind power history data. Simulation experimental results show that this method makes wind power prediction accuracy greatly increased,and it has the very good application prospect.

关 键 词：短期风电功率 HILBERT-HUANG变换 端点效应 组合预测 

分 类 号：TM933[电气工程—电力电子与电力传动]