Multi-scale Fusion Prediction Method for Wind Power Cluster Power Based on Spatio-Temporal Graph Spectral Clustering and Time-Series 2D-Reshaping Transformer

[Objective] To address limitations in spatio-temporal feature extraction and the integration of multi-scale features in wind power cluster prediction， this paper proposes a multi-scale fusion prediction method based on spatio-temporal graph spectral clustering （ST-SpecCluster） and a time-series 2D-r...

ver descrição completa

Detalhes bibliográficos

Autor principal:	ZHU Jianing, WANG Zhao, LI Yitao, YANG Mao, JIANG Renxian
Formato:	Artigo
Idioma:	Chinês
Publicado em:	Editorial Department of Electric Power Construction 2026-03-01
coleção:	Dianli jianshe
Assuntos:	wind power prediction|spatio-temporal graph spectral clustering（st-speccluster）|stl decomposition|t2dformer|spatio temporal multi-scale fusion
Acesso em linha:	https://www.cepc.com.cn/fileup/1000-7229/PDF/1772431772854-640491655.pdf
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!