Step-adaptive multimodal fusion network with multi-scale cloud feature learning for ultra-short-term solar irradiance forecasting
For photovoltaic system operators, this method improves short-term irradiance prediction accuracy, aiding grid stability, but the improvement is incremental over existing deep learning approaches.
The paper tackles ultra-short-term solar irradiance forecasting by proposing a multi-source data fusion model that integrates multi-scale cloud features from ground-based images with meteorological time-series data, using a step-adaptive low-frequency compensation unit. Experiments on the NREL dataset and real PV stations show the model outperforms state-of-the-art methods.
Ultra-short-term solar irradiance prediction is critical for photovoltaic system dispatch and power grid stability. Existing approaches suffer from three key shortcomings: single time-series models cannot capture the spatial dynamics of clouds under complex conditions, standard convolutions inadequately represent multi-scale cloud features, and fixed low-frequency compensation strategies fail to adapt to different prediction steps. To address these issues, this proposes a multi-source data fusion model for ultra-short-term irradiance prediction. The model first employs InceptionNeXt to extract multi-scale, multi-directional spatial features from ground-based cloud images. A step-adaptive low-frequency compensation unit is then introduced to dynamically modulate global low-frequency information based on the prediction step. Eventually, the enhanced image features are combined with meteorological time-series features, and a TempAttnLSTM network captures global temporal dependencies for multi-step prediction. Experiments on the public NREL dataset and practical photovoltaic stations in Shandong illustrate the effectiveness of the proposed method compared with several state-of-the-art approaches.