Yan Zhao

Robustness of Deep Learning Models for PV Power Forecasting under NWP Forecast Errors: A Spatiotemporal and Physically Interpretable Analysis

This study presents a physically constrained robustness evaluation framework, using virtual PV power as a controlled response variable to isolate the propagation of input uncertainty from confounders at the plant level, and shows that sequence models provide stronger noise filtering and temporal resilience than a strong tabular baseline under medium to high disturbance regimes.