Ultra-short-term Wind Power Forecasting Method Combining Multiple Clustering and Hierarchical Clustering

被引：0
|
作者：
Peng C. [1 ]
Chen N. [2 ,3 ]
Gao B. [1 ]
机构：
[1] School of Electrical Engineering, Southeast University, Nanjing
[2] State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems, Nanjing
[3] China Electric Power Research Institute (Nanjing), Nanjing
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2020年 / 44卷 / 02期
基金：
中国国家自然科学基金;
关键词：
Classification modeling; Covariance; Feature matching; Multiple clustering; Neural network model; Ultra-short-term wind power forecasting;
D O I：
10.7500/AEPS20190105003
中图分类号：
学科分类号：
摘要：
An ultra-short-term wind power forecasting method combining multiple clustering algorithm and hierarchical clustering algorithm is proposed. To deal with the dynamic condition of training samples and identify the samples that are similar to the characteristics of the period to be predicted, the historical power series and historical meteorological series are clustered separately. The clustering index of the power series consists of Euclidean distance and covariance, and the layer-by-layer method is used for meteorological series clustering. Two clustering results are combined into multiple sample subsets. Multiple neural network forecasting models based on particle swarm optimization and back propagation (PSO-BP) are established by using the method of classification modeling and feature matching. And the model with the most similar characteristics to the predicted period are used. The proposed forecasting approach has been applied in actual wind generation data tracking in Qinghai province of China. The simulation results show that it can improve the forecasting accuracy of ultra-short-term wind power. © 2020 Automation of Electric Power Systems Press.
引用
收藏
页码：173 / 180
页数：7
相关论文
共 25 条
  • [1] Xue Y., Yu C., Zhao J., Et al., A review on short-term and ultra-short-term wind power prediction, Automation of Electric Power Systems, 39, 6, pp. 141-151, (2015)
  • [2] Qian Z., Pei Y., Cao L., Et al., Review of wind power forecasting method, High Voltage Engineering, 42, 4, pp. 1047-1060, (2016)
  • [3] Feng S., Wang W., Liu C., Et al., Study on the physical approach to wind power prediction, Proceedings of the CSEE, 30, 2, pp. 1-6, (2010)
  • [4] Yang H., Feng S., Wang B., Et al., Study of the MOS method based on linear regression for wind power prediction, Proceedings of the CSU-EPSA, 25, 4, pp. 14-17, (2013)
  • [5] Wang C., Lu Z., Qiao Y., Et al., Short-term wind power forecast based on non-parametric regression model, Automation of Electric Power Systems, 34, 16, pp. 78-82, (2010)
  • [6] Xu L., Wang W., Zhang T., Et al., Ultra-short-term wind power prediction based on neural network and mean impact value, Automation of Electric Power Systems, 41, 21, pp. 40-45, (2017)
  • [7] Ling W., Hang N., Li R., Short-term wind power forecasting based on cloud SVM model, Electric Power Automation Equipment, 33, 7, pp. 34-38, (2013)
  • [8] Wang Z., Ji Z., Grey-identification model based wind power generation short-term prediction, Power System Protection and Control, 41, 12, pp. 79-85, (2013)
  • [9] Wang H., Hu Z., Chen Z., Et al., A hybrid model for wind power forecasting based on ensemble empirical mode decomposition and wavelet neural networks, Transactions of China Electrotechnical Society, 28, 9, pp. 137-144, (2013)
  • [10] Ye L., Zhu Q., Zhao Y., Dynamic optimal combination model considering adaptive exponential for ultra-short term wind power prediction, Automation of Electric Power Systems, 39, 20, pp. 12-18, (2015)
123