Wind Speed Prediction via Collaborative Filtering on Virtual Edge Expanding Graphs

Xiang Ying, Keke Zhao, Zhiqiang Liu, Jie Gao, Dongxiao He, Xuewei Li and Wei Xiong
Additional contact information
Xiang Ying: College of Intelligence and Computing, Tianjin University, Tianjin 300072, China
Keke Zhao: Tianjin International Engineering Institute, Tianjin University, Tianjin 300072, China
Zhiqiang Liu: College of Intelligence and Computing, Tianjin University, Tianjin 300072, China
Jie Gao: College of Intelligence and Computing, Tianjin University, Tianjin 300072, China
Dongxiao He: College of Intelligence and Computing, Tianjin University, Tianjin 300072, China
Xuewei Li: College of Intelligence and Computing, Tianjin University, Tianjin 300072, China
Wei Xiong: TCU School of Civil Engineering, Tianjin Chengjian University, Tianjin 300384, China

Mathematics, 2022, vol. 10, issue 11, 1-16

Abstract: Accurate and stable wind speed prediction is crucial for the safe operation of large-scale wind power grid connections. Existing methods are typically limited to a certain fixed area when learning the information of the wind speed sequence, which cannot make full use of the spatiotemporal correlation of the wind speed sequence. To address this problem, in this paper we propose a new wind speed prediction method based on collaborative filtering against a virtual edge expansion graph structure in which virtual edges enrich the semantics that the graph can express. It is an effective extension of the dataset, connecting wind turbines of different wind farms through virtual edges to ensure that the spatial correlation of wind speed sequences can be effectively learned and utilized. The new collaborative filtering on the graph is reflected in the processing of the wind speed sequence. The wind speed is preprocessed from the perspective of pattern mining to effectively integrate various information, and the k -d tree is used to match the wind speed sequence to achieve the purpose of collaborative filtering. Finally, a model with long short-term memory (LSTM) as the main body is constructed for wind speed prediction. By taking the wind speed of the actual wind farm as the research object, we compare the new approach with four typical wind speed prediction methods. The mean square error is reduced by 16.40%, 11.78%, 9.57%, and 18.36%, respectively, which demonstrates the superiority of the proposed new method.

Keywords: wind speed prediction; virtual edge expanding graphs; collaborative filtering; pattern mining; LSTM network (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/11/1943/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/11/1943/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:11:p:1943-:d:832497

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().