Advanced RNN-Based Model Variants for Short-Term Solar Power Forecasting
Journal of Daylighting · 2026-12 · 13 (2) · 698-721
DOI: 10.15627/jd.2026.38 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Daylighting, 2026-12. Verfasst von Ngoc-Trung Nguyen und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Many existing solar power forecasting studies still focus on a single, fixed forecasting resolution, with limited investigation into how model performance changes when temporal data are aggregated to coarser time scales and formulated as single-step predictions, or how related Recurrent Neural Network (RNN) architectures compare across multiple short-term forecasting intervals. Therefore, this study is conducted to evaluate the performance of four advanced RNN architectures including GRU, BiGRU, LSTM, and BiLSTM, for short-term solar power forecasting using a single-step forecasting formulation across multiple temporally aggregated time resolutions: 5, 15, 30, and 60 minutes. The results demonstrated that all RNN-based models achieved reasonable accuracy in short-term prediction, with BiGRU consistently outperforming the others at most intervals. Notably, for the 5-minute resolution, BiGRU achieved an R² of approximately 0.94 and a NMAPE of just 3.41%, confirming its adaptability and precision. Its performance remained strong for 15- and 30-minute forecasts; although a gradual decline was observed as the temporal resolution became coarser. At the 1-hour mark, BiLSTM outperformed BiGRU slightly, achieving R² = 0.85 and NMAPE = 7.01%, indicating its better ability to model long-term dependencies in aggregated solar power data. These findings not only extend the practical applications of bidirectional RNNs in renewable energy forecasting but also provide a solid foundation for developing more intelligent and efficient power scheduling systems.
Zitieren
APA
Nguyen, N., Nguyen, T., Pham, M., Vu, M., & Nguyen, T. (2026). Advanced RNN-Based Model Variants for Short-Term Solar Power Forecasting. Journal of Daylighting, 13(2), 698-721. https://doi.org/10.15627/jd.2026.38
Vancouver
Nguyen N, Nguyen T, Pham M, Vu M, Nguyen T. Advanced RNN-Based Model Variants for Short-Term Solar Power Forecasting. Journal of Daylighting. 2026;13(2):698-721. doi:10.15627/jd.2026.38
BibTeX
@article{Nguyen2026,
author = {Nguyen, Ngoc-Trung and Nguyen, Thanh-Trung and Pham, Manh-Hai and Vu, Minh-Phap and Nguyen, Tuan-Anh},
title = {Advanced RNN-Based Model Variants for Short-Term Solar Power Forecasting},
journal = {Journal of Daylighting},
year = {2026},
volume = {13},
number = {2},
pages = {698--721},
doi = {10.15627/jd.2026.38}
}
EUVIMED