.png){kind=icon}
.png){kind=icon}
Return
A cross-variable spectral coherence-enhanced transformer for high-precision photovoltaic power forecasting
.png){kind=icon}
PRE
AI
Y
Z
Y
DOI：10.1016/j.neucom.2026.134702.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposes CVSC-Transformer, a novel frequency-domain model for PV power forecasting. • Introduces cross-variable spectral dependency to capture phase-shifted meteorological relationships. • Achieves state-of-the-art performance on five real-world datasets. • Features an adaptive frequency weighting mechanism for inherent interpretability. • Demonstrates particular advantages in medium-to-long-term forecasting tasks on multivariate data.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers