Ultra-short-term photovoltaic (PV) power forecasting is vital for power systems with high renewable penetration. Under volatile weather, PV output is dominated by short-term fluctuations, while long-range history becomes weakly informative or even noisy. However, most forecasters rely on fixed temporal receptive fields, failing to adapt their dependency span to changing meteorological regimes. This paper proposes a State-Guided Continuous Temporal-Range Modulation Network (SGTRM) to dynamically regulate the usable temporal context according to evolving weather states. SGTRM first employs a hierarchical causal temporal encoder to extract multi-scale representations from historical PV and NWP sequences. It then introduces a differentiable distance-decay bias into the attention weights, so that distant observations are adaptively down-weighted and the effective temporal range can be adjusted continuously rather than by switching among predefined scales. Experiments show that SGTRM consistently outperforms strong baselines across seasons and weather regimes. Compared with the Transformer baseline, SGTRM reduces the average nRMSE by 35.9% and performs robustly under rainy conditions. Visualization further supports its consistency with atmospheric evolution. These findings suggest that modeling temporal dependency as a continuously regulated and meteorology-conditioned process provides a more flexible and physically interpretable framework for robust ultra-short-term PV forecasting under complex weather environments.
Dong et al. (Sun,) studied this question.