logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

A deep time–frequency augmented wind power forecasting model

delete2025-07-01
delete0
PRE
AI
Y
Yunxuan Dong
B
Binggui Zhou
H
Hongcai Zhang
G
Guanghua Yang
S
Shaodan Ma
DOI：10.1016/j.renene.2025.123550delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Proposed DTFA-WPF model effectively reduces wind power forecasting errors. • Verified CEEMD-Hilbert frequency augmentation captures non-stationary dynamics. • DTFA-WPF achieved average MAPE of 3.81%, outperforming existing methods. • Demonstrated GPU acceleration enables real-time wind forecasting applications.

Journal

Renewable Energy cover
Renewable Energy
IF:
9.1
Papers:
2.6W
Citations:
12.1W

Organization

No organization information available