Short-term wind power prediction based on SVD and Kalman filter correction of multi-position NWP

被引：0

作者：

Wang L. ^{[1
]}

Liu T. ^{[2
]}

Wang B. ^{[3
]}

Hao Y. ^{[1
]}

Wang Z. ^{[3
]}

Zhang Y. ^{[4
]}

机构：

[1] School of Automation, Beijing Information Science & Technology University, Beijing

[2] State Grid Beijing Changping Power Supply Company, Beijing

[3] China Electric Power Research Institute, Beijing

[4] State Grid Shandong Electric Power Company, Jinan

来源：

Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2022年 / 43卷 / 12期

关键词：

Extreme random forest; Kalman filter; Numerical weather prediction; Singular value decomposition; Wind power prediction;

D O I：

10.19912/j.0254-0096.tynxb.2021-0597

中图分类号：

学科分类号：

摘要：

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. © 2022, Solar Energy Periodical Office Co., Ltd. All right reserved.

引用

页码：392 / 398

页数：6

共 14 条

[1] HAN Z F, JING Q M, ZHANG Y K., A summary of wind power forecasting methods and new trends, Power system and protection control, 47, 24, pp. 178-187, (2019)
[2] WANG L J, WANG B, WANG Z, Et al., Wind power short-term prediction based on mathematical morphology cluster analysis and fruit fly optimization, Acta energiae solaris sinica, 40, 12, pp. 3621-3627, (2019)
[3] FENG S L., Forecasting technology of renewable power generation, (2018)
[4] SONG J K, PENG Y G, CAI H D, Et al., Research on short-term wind power forecasting considering multi-location NWP and atypical characteristics, Power grid technology, 42, 10, pp. 3234-3242, (2018)
[5] KHALID M, SAVKIN A V., A method for short-term wind power prediction with multiple observation points, IEEE transactions on power systems, 27, 2, pp. 579-586, (2012)
[6] WANG L J, DONG L, GAO S., Short-term prediction of wind power based on multi-location NWP and principal component analysis, Journal of electrical engineering, 30, 5, pp. 79-84, (2015)
[7] RANABOLDO M., Multiple linear regression MOS for short-term wind power forecast, (2011)
[8] XIAO Q Y, HU F, FAN S J., Research on model output statistics(MOS) of numerical forecast of wind energy, Resources science, 39, 1, pp. 116-124, (2017)
[9] CHEN H, ZHANG J Z, XU C, Et al., Short-term wind power prediction based on multiple outlier smooth transition autoregressive model, Power system protection and control, 47, 1, pp. 73-79, (2019)
[10] CHEN Y, WU H, SHI J Y, Et al., Application of singular value decomposition method in daily load curve dimensionality reduction clustering analysis, Power system automation, 42, 3, pp. 105-110, (2018)

← 1 2 →