High-Fidelity Full-Sky Video Prediction for Photovoltaic Ramp Event Forecasting
For grid operators and solar energy systems, this work provides a high-fidelity method to forecast rapid PV output changes under cloudy conditions, improving grid stability and reducing reliance on reserve capacity.
This paper introduces a generative forecasting framework combining a future sky video prediction model (PhyDiffNet) and a ramp-aware PV output forecasting model (RaPVFormer) to predict photovoltaic ramp events up to 16 minutes ahead at 1-minute resolution. The framework achieves state-of-the-art performance, with a 10% increase in Critical Success Index for ramp detection.
Accurate ultra-short-term forecasting of photovoltaic (PV) ramp events is essential for maintaining grid stability in solar-integrated power systems, particularly under rapidly changing cloud conditions. This paper presents a generative forecasting framework that integrates a future sky video prediction model (PhyDiffNet) with a ramp aware PV output forecasting model (RaPVFormer). Based on the relatively slow yet chaotic dynamics of cloud motion, the system forecasts ramp events up to 16 minutes in advance at a 1-minute resolution by capturing fine-grained spatiotemporal cloud patterns and generating high-fidelity full-sky video frames. Interpretability is enhanced through attention visualization, highlighting cloud occlusion regions that significantly influence irradiance variability. Supported by extensive quantitative evaluation, the proposed framework demonstrates state-of-the-art performance in both full-sky video prediction and PV output forecasting. It delivers consistent improvements in structural, perceptual, and temporal video quality, along with a 10% increase in Critical Success Index (CSI) for PV ramp detection. These results demonstrate the capability of AI driven multimodal sensing for ultra short term solar forecasting, supporting more reliable renewable integration and potentially reducing dependence on reserve capacity.