https://doi.org/10.65770/VVBQ3503
The rapid growth of renewable energy adoption has heightened the need for accurate solar energy prediction to ensure grid stability, particularly in regions with high solar penetration. However, traditional forecasting methods relying on historical meteorological data often fail to address short term fluctuations caused by dynamic cloud movements, limiting real time adaptability. To overcome this challenge, this study proposes a deep learning framework integrating convolutional neural networks (CNNs) with attention mechanisms to predict photovoltaic (PV) output from radiance sky images. Two datasets capturing diverse sky conditions were used to evaluate three architectures: a baseline CNN, CNN with Squeeze-and-Excitation (SE) Attention, and CNN with Spatial Attention. The CNN with SE-Attention model significantly outperformed baseline models, reducing prediction errors and improving explanatory power, as validated by metrics including RMSE, MAE, and R². Gradient-weighted Class Activation Mapping (GradCAM) further demonstrated the model’s ability to prioritize meteorologically critical regions, such as cloud edges and solar disk areas, with distinct attention patterns for sunny and cloudy scenarios. The framework’s practical utility was enhanced through deployment in an interactive web-based Graphical User Interface, enabling real-time solar potential simulations for energy operators. By combining attention mechanisms with interpretable design, this work advances short-term solar forecasting accuracy while providing actionable insights for grid management. Future research directions include multi-modal data fusion and hybrid transformer-CNN architectures to improve robustness across diverse climatic conditions.
References
- [1] Pérez-Rodríguez, S. A. et al., “Metaheuristic Algorithms for Solar Radiation Prediction: A Systematic Analysis,” IEEE Access, vol. 12, pp. 100134-100148, Jul. 2024, doi: 10.1109/ACCESS.2024.3429073.
- [2] El Alani, O.et al., “Short term solar irradiance forecasting using sky images hybrid CNN-MLP,” Energy Reports, vol. 7, pp. 888–900, doi: https://doi.org/10.1016/j.egyr.2021.07.053
- [3] Martinez Lopez V. A. et al. , “Using sky-classification to improve the short-term prediction of irradiance with sky images and convolutional neural networks,” Solar Energy, vol. 269, pp. 112320, Jan. 2024, doi: 10.1016/j.solener.2024.112320.
- [4] Q. et al., “Advances in solar forecasting: Computer vision with deep learning,” Advances in Applied Energy, vol. 11, 100150, Aug. 2023, doi: 10.1016/j.adapen.2023.100150.
- [5] M and Martínez-Ramón. M, “Deep learning algorithms for very short-term solar irradiance forecasting: A survey,” Renewable and Sustainable Energy Reviews, vol. 182, 113362, 2023, doi: 10.1016/j.rser.2023.113362.
- [6] Y. et al., “The cost of day-ahead solar forecasting errors in the United States,” Solar Energy, vol. 231, pp. 846-856, Jan. 2022, doi: 10.1016/j.solener.2021.12.012
- [7] Y. et al., “Open-source sky image datasets for solar forecasting with deep learning: A comprehensive survey,” Renewable and Sustainable Energy Reviews, vol. 189, 113977, 2024, doi: 10.1016/j.rser.2023.113977.
- [8] H and Liu. M., “Short-Term Solar Irradiance Prediction From Sky Images With a Clear Sky Model,” Australian National University, Canberra, Australia, 2024.
- [9] C and Zhang. J, “SolarNet: A sky image-based deep convolutional neural network for intra-hour solar forecasting,” Solar Energy, vol. 204, pp. 71-78, Apr. 2020, doi: 10.1016/j.solener.2020.03.083.
- E. A. et al., “Deep Learning-Based Image Regression for Short-Term Solar Irradiance Forecasting on the Edge,” Electronics, vol. 11, no. 22, 3794, Nov. 2022, doi: 10.3390/electronics11223794.
- Q. et al., “Benchmarking of deep learning irradiance forecasting models from sky images: An in-depth analysis,” Solar Energy, vol. 224, pp. 855–867, 2021, doi: 10.1016/j.solener.2021.05.056.
Download all article in PDF
