Open access
Aug 2026
A Cross-Variable Time-Series Transformer Architecture Integrating Physical Features for Photovoltaic Energy Forecasting
This study introduces a Cross-Variable Attention mechanism to explicitly reconstruct nonlinear photothermal couplings via dynamic attention weights and provides an accurate, generalizable, and physically interpretable solution for collaborative multi-station distributed PV energy forecasting.
Chen Xie, Mingju Chen, Yuyan Wang et al.
· Algorithms · 0 citations