SolarFusionNet: Enhanced Solar Irradiance Forecasting via Automated Multi-Modal Feature Selection and Cross-Modal Fusion
- 21 October 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Energy
- Vol. 16 (2) , 761-773
Abstract
Solar forecasting has emerged as a cost-effective technology to mitigate the negative impacts of intermittent solar power on the power grid. Despite the multitude of deep learning methodologies available for forecasting solar irradiance, there is a notable gap in research concerning the automated selection and holistic utilization of multi-modal features for ultra-short-term regional irradiance forecasting. Our study introduces SolarFusionNet, a novel deep learning architecture that effectively integrates automatic multi-modal feature selection and cross-modal data fusion. SolarFusionNet utilizes two distinct types of automatic variable feature selection units to extract relevant features from multichannel satellite images and multivariate meteorological data, respectively. Long-term dependencies are then captured using three types of recurrent layers, each tailored to the corresponding data modal. In particular, a novel Gaussian kernel-injected convolutional long short-term memory network is specifically designed to isolate the sparse features present in the cloud motion field derived from optical flow. Subsequently, a hierarchical multi-head cross-modal self-attention mechanism is proposed based on the physical-logical dependencies among the three modalities to investigate the coupling correlations among the modalities. The experimental results indicate that SolarFusionNet exhibits robust performance in predicting regional solar irradiance, achieving higher accuracy than other state-of-the-art models and a forecast skill ranging from 37.4% to 47.6% against the smart persistence model for the 4-hour-ahead forecast.Keywords
Funding Information
- Research Grants Council of the Hong Kong (C6003-22Y, 21200424, 25213022)
- Basic and Applied Basic Research Foundation of Guangdong Province (2024A1515010117)
This publication has 34 references indexed in Scilit:
- Improved satellite-based intra-day solar forecasting with a chain of deep learning modelsEnergy Conversion and Management, 2024
- RoFormer: Enhanced transformer with Rotary Position EmbeddingNeurocomputing, 2023
- Global and direct solar irradiance estimation using deep learning and selected spectral satellite imagesApplied Energy, 2023
- A Transformer-based multimodal-learning framework using sky images for ultra-short-term solar irradiance forecastingApplied Energy, 2023
- A 3D ConvLSTM-CNN network based on multi-channel color extraction for ultra-short-term solar irradiance forecastingEnergy, 2023
- A Concise Overview on Solar Resource Assessment and ForecastingAdvances in Atmospheric Sciences, 2022
- Temporal Fusion Transformers for interpretable multi-horizon time series forecastingInternational Journal of Forecasting, 2021
- Intra-hour irradiance forecasting techniques for solar power integration: A reviewiScience, 2021
- Deep learning based solar radiation micro forecast by fusion of infrared cloud images and radiation dataApplied Energy, 2021
- Extensive comparison of physical models for photovoltaic power forecastingApplied Energy, 2021