A stacking-based short-term wind power forecasting method by CBLSTM and ensemble learning

doi:10.1063/5.0097757

	A stacking-based short-term wind power forecasting method by CBLSTM and ensemble learning
	Wang, Nier; Li, Zhanming
	2022-07
发表期刊	Journal of Renewable and Sustainable Energy
ISSN	1941-7012
卷号	14 期号:4
摘要	Aiming at the problem that the traditional wind power forecasting is difficult to deal with a large amount of strong volatility data and limited processing capacity of time series, a wind power forecasting method based on multi-model combination under stacking framework was proposed. First, the wind turbine data are cleaned by density-based spatial clustering of applications with the noise clustering method. Considering the differences of data observation and training principles, the proposed stacking method embedded multiple machine learning algorithms to utilize their diversified strength. The stacking base-learner includes the CBLSTM model, which has the advantages of deep architecture feature extraction, and takes into account data timing and nonlinear relationship as well as XGBoost and other tree ensemble learning models that were suitable for complex data modeling. The feasibility of the algorithm was verified by using the actual wind power data of two wind farms in Northeast and Western China. Experimental results show that the stacking ensemble learning method proposed has better forecasting performance and stability than other single forecasting models, which is of great significance to guide wind power dispatching operation and improve wind power consumption capacity. © 2022 Author(s).
关键词	Data handling Decision trees Electric load dispatching Machine learning Weather forecasting Wind farm Ensemble learning Forecasting methods Large amounts Multi-model combination Processing capacities Short-term wind power forecasting Stacking framework Stackings Times series
DOI	10.1063/5.0097757
收录类别	EI ; SCIE
语种	英语
WOS研究方向	Science & Technology - Other Topics ; Energy & Fuels
WOS类目	Green & Sustainable Science & Technology ; Energy & Fuels
WOS记录号	WOS:000838389600001
出版者	American Institute of Physics Inc.
EI入藏号	20223512664226
EI主题词	Learning systems
EI分类号	443 Meteorology ; 615.8 Wind Power (Before 1993, use code 611 ) ; 706.1.1 Electric Power Transmission ; 723.2 Data Processing and Image Processing ; 723.4 Artificial Intelligence ; 921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory ; 961 Systems Science
来源库	WOS
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/159714
专题	电气工程与信息工程学院
通讯作者	Wang, Nier
作者单位	Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou 730050, Peoples R China
第一作者单位	电气工程与信息工程学院
通讯作者单位	电气工程与信息工程学院
第一作者的第一单位	电气工程与信息工程学院
推荐引用方式 GB/T 7714	Wang, Nier,Li, Zhanming. A stacking-based short-term wind power forecasting method by CBLSTM and ensemble learning[J]. Journal of Renewable and Sustainable Energy,2022,14(4).
APA	Wang, Nier,&Li, Zhanming.(2022).A stacking-based short-term wind power forecasting method by CBLSTM and ensemble learning.Journal of Renewable and Sustainable Energy,14(4).
MLA	Wang, Nier,et al."A stacking-based short-term wind power forecasting method by CBLSTM and ensemble learning".Journal of Renewable and Sustainable Energy 14.4(2022).