IDEAS home Printed from https://ideas.repec.org/a/eee/renene/v238y2025ics0960148124020238.html
   My bibliography  Save this article

A novel U-LSTM-AFT model for hourly solar irradiance forecasting

Author

Listed:
  • Zhu, Leyang
  • Huang, Xiaoqiao
  • Zhang, Zongbin
  • Li, Chengli
  • Tai, Yonghang

Abstract

Countries emphasize the development of renewable energy to combat climate change, ensure energy security, and promote sustainable economic growth. Grid-connected photovoltaic (PV) power generation, a key to energy transition, can significantly reduce power generation costs. Still, its output power is unstable due to the weather, so an accurate solar irradiance forecast is crucial. The current hybrid model mainly suffers from inadequate feature extraction and insufficient time-dependent processing when dealing with complex time series data, which affects prediction accuracy. Therefore, a new solar irradiance forecast model, U-Shaped LSTM-AFT (U-LSTM-AFT) is proposed in this paper, which draws on the architecture and ideas of U-Net. The model improves the efficiency of feature extraction through the up-sampling and down-sampling modules while combining with smaller pooling kernels to optimize feature processing further. In addition, the model introduces the Long Short-Term Memory Network (LSTM) and Attention-Free Transformer (AFT) to enhance prediction accuracy and achieve more efficient forecast performance. The method was validated using three real-world irradiance datasets from diverse US locations representing different climate types. The experimental results demonstrate that the proposed U-LSTM-AFT model achieves higher forecasting accuracy in predicting PV power generation than traditional models like LSTM and U-Net, with significant performance improvements. Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Normalized Root Mean Square Error (nRMSE), R-squared (R2), and Forecast Skill (FSnRMSE) are the performance evaluation metrics of this forecasting scheme. The three datasets reached mean values of 23.076 W/m2, 50.142 W/m2, 0.046, 98.680 %, and 0.238, respectively.

Suggested Citation

  • Zhu, Leyang & Huang, Xiaoqiao & Zhang, Zongbin & Li, Chengli & Tai, Yonghang, 2025. "A novel U-LSTM-AFT model for hourly solar irradiance forecasting," Renewable Energy, Elsevier, vol. 238(C).
  • Handle: RePEc:eee:renene:v:238:y:2025:i:c:s0960148124020238
    DOI: 10.1016/j.renene.2024.121955
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960148124020238
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.renene.2024.121955?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Baharoon, Dhyia Aidroos & Rahman, Hasimah Abdul & Omar, Wan Zaidi Wan & Fadhl, Saeed Obaid, 2015. "Historical development of concentrating solar power technologies to generate clean electricity efficiently – A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 41(C), pages 996-1027.
    2. Li, Kewen & Bian, Huiyuan & Liu, Changwei & Zhang, Danfeng & Yang, Yanan, 2015. "Comparison of geothermal with solar and wind power generation systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 42(C), pages 1464-1474.
    3. Sharma, Amandeep & Kakkar, Ajay, 2018. "Forecasting daily global solar irradiance generation using machine learning," Renewable and Sustainable Energy Reviews, Elsevier, vol. 82(P3), pages 2254-2269.
    4. Akarslan, Emre & Hocaoglu, Fatih Onur & Edizkan, Rifat, 2018. "Novel short term solar irradiance forecasting models," Renewable Energy, Elsevier, vol. 123(C), pages 58-66.
    5. Lim, Bryan & Arık, Sercan Ö. & Loeff, Nicolas & Pfister, Tomas, 2021. "Temporal Fusion Transformers for interpretable multi-horizon time series forecasting," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1748-1764.
    6. Zhang, Lei & Qin, Quande & Wei, Yi-Ming, 2019. "China's distributed energy policies: Evolution, instruments and recommendation," Energy Policy, Elsevier, vol. 125(C), pages 55-64.
    7. Modi, Anish & Bühler, Fabian & Andreasen, Jesper Graa & Haglind, Fredrik, 2017. "A review of solar energy based heat and power generation systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 67(C), pages 1047-1064.
    8. Huang, Xiaoqiao & Li, Qiong & Tai, Yonghang & Chen, Zaiqing & Zhang, Jun & Shi, Junsheng & Gao, Bixuan & Liu, Wuming, 2021. "Hybrid deep neural model for hourly solar irradiance forecasting," Renewable Energy, Elsevier, vol. 171(C), pages 1041-1060.
    9. Rajesh, R. & Carolin Mabel, M., 2015. "A comprehensive review of photovoltaic systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 51(C), pages 231-248.
    10. Narvaez, Gabriel & Giraldo, Luis Felipe & Bressan, Michael & Pantoja, Andres, 2021. "Machine learning for site-adaptation and solar radiation forecasting," Renewable Energy, Elsevier, vol. 167(C), pages 333-342.
    11. Paulescu, Marius & Paulescu, Eugenia, 2019. "Short-term forecasting of solar irradiance," Renewable Energy, Elsevier, vol. 143(C), pages 985-994.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Rodríguez, Fermín & Martín, Fernando & Fontán, Luis & Galarza, Ainhoa, 2021. "Ensemble of machine learning and spatiotemporal parameters to forecast very short-term solar irradiation to compute photovoltaic generators’ output power," Energy, Elsevier, vol. 229(C).
    2. Acikgoz, Hakan, 2022. "A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting," Applied Energy, Elsevier, vol. 305(C).
    3. Hartmann, Bálint, 2020. "Comparing various solar irradiance categorization methods – A critique on robustness," Renewable Energy, Elsevier, vol. 154(C), pages 661-671.
    4. Mohammad Mahdi Forootan & Iman Larki & Rahim Zahedi & Abolfazl Ahmadi, 2022. "Machine Learning and Deep Learning in Energy Systems: A Review," Sustainability, MDPI, vol. 14(8), pages 1-49, April.
    5. Bashir, Tasarruf & Wang, Huifang & Tahir, Mustafa & Zhang, Yixiang, 2025. "Wind and solar power forecasting based on hybrid CNN-ABiLSTM, CNN-transformer-MLP models," Renewable Energy, Elsevier, vol. 239(C).
    6. Azizi, Narjes & Yaghoubirad, Maryam & Farajollahi, Meisam & Ahmadi, Abolfzl, 2023. "Deep learning based long-term global solar irradiance and temperature forecasting using time series with multi-step multivariate output," Renewable Energy, Elsevier, vol. 206(C), pages 135-147.
    7. Puah, Boon Keat & Chong, Lee Wai & Wong, Yee Wan & Begam, K.M. & Khan, Nafizah & Juman, Mohammed Ayoub & Rajkumar, Rajprasad Kumar, 2021. "A regression unsupervised incremental learning algorithm for solar irradiance prediction," Renewable Energy, Elsevier, vol. 164(C), pages 908-925.
    8. Mehmood, Faiza & Ghani, Muhammad Usman & Asim, Muhammad Nabeel & Shahzadi, Rehab & Mehmood, Aamir & Mahmood, Waqar, 2021. "MPF-Net: A computational multi-regional solar power forecasting framework," Renewable and Sustainable Energy Reviews, Elsevier, vol. 151(C).
    9. Belgasim, Basim & Aldali, Yasser & Abdunnabi, Mohammad J.R. & Hashem, Gamal & Hossin, Khaled, 2018. "The potential of concentrating solar power (CSP) for electricity generation in Libya," Renewable and Sustainable Energy Reviews, Elsevier, vol. 90(C), pages 1-15.
    10. Hoyos-Gómez, Laura S. & Ruiz-Muñoz, Jose F. & Ruiz-Mendoza, Belizza J., 2022. "Short-term forecasting of global solar irradiance in tropical environments with incomplete data," Applied Energy, Elsevier, vol. 307(C).
    11. N. Yogambal Jayalakshmi & R. Shankar & Umashankar Subramaniam & I. Baranilingesan & Alagar Karthick & Balasubramaniam Stalin & Robbi Rahim & Aritra Ghosh, 2021. "Novel Multi-Time Scale Deep Learning Algorithm for Solar Irradiance Forecasting," Energies, MDPI, vol. 14(9), pages 1-23, April.
    12. DeLovato, Nicolas & Sundarnath, Kavin & Cvijovic, Lazar & Kota, Krishna & Kuravi, Sarada, 2019. "A review of heat recovery applications for solar and geothermal power plants," Renewable and Sustainable Energy Reviews, Elsevier, vol. 114(C), pages 1-1.
    13. Oyekale, Joseph & Petrollese, Mario & Cau, Giorgio, 2020. "Modified auxiliary exergy costing in advanced exergoeconomic analysis applied to a hybrid solar-biomass organic Rankine cycle plant," Applied Energy, Elsevier, vol. 268(C).
    14. Frank, Johannes, 2023. "Forecasting realized volatility in turbulent times using temporal fusion transformers," FAU Discussion Papers in Economics 03/2023, Friedrich-Alexander University Erlangen-Nuremberg, Institute for Economics.
    15. Liao, Zhouyi & Coimbra, Carlos F.M., 2024. "Hybrid solar irradiance nowcasting and forecasting with the SCOPE method and convolutional neural networks," Renewable Energy, Elsevier, vol. 232(C).
    16. Tiantian Tu, 2025. "Bridging Short- and Long-Term Dependencies: A CNN-Transformer Hybrid for Financial Time Series Forecasting," Papers 2504.19309, arXiv.org.
    17. Fernando Venâncio Mucomole & Carlos Augusto Santos Silva & Lourenço Lázaro Magaia, 2025. "Parametric Forecast of Solar Energy over Time by Applying Machine Learning Techniques: Systematic Review," Energies, MDPI, vol. 18(6), pages 1-51, March.
    18. Baharoon, Dhyia Aidroos & Rahman, Hasimah Abdul & Fadhl, Saeed Obaid, 2016. "Publics׳ knowledge, attitudes and behavioral toward the use of solar energy in Yemen power sector," Renewable and Sustainable Energy Reviews, Elsevier, vol. 60(C), pages 498-515.
    19. Yanara Tranamil-Maripe & José M. Cardemil & Rodrigo Escobar & Diego Morata & Cristóbal Sarmiento-Laurel, 2022. "Assessing the Hybridization of an Existing Geothermal Plant by Coupling a CSP System for Increasing Power Generation," Energies, MDPI, vol. 15(6), pages 1-28, March.
    20. Rômulo de Oliveira Azevêdo & Paulo Rotela Junior & Luiz Célio Souza Rocha & Gianfranco Chicco & Giancarlo Aquila & Rogério Santana Peruchi, 2020. "Identification and Analysis of Impact Factors on the Economic Feasibility of Photovoltaic Energy Investments," Sustainability, MDPI, vol. 12(17), pages 1-40, September.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:renene:v:238:y:2025:i:c:s0960148124020238. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/renewable-energy .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.