IDEAS home Printed from https://ideas.repec.org/a/eee/renene/v256y2026ipes0960148125017896.html

Hybrid Deep Learning - Driven Modeling and Optimization of Solar Photovoltaic Systems for Green Hydrogen Production with improved Lemurs optimizer

Author

Listed:
  • Kamalakannan, N.
  • Sivasakthi, S.
  • Vinothkumar, M.
  • Karthick, R.

Abstract

Solar-powered water electrolysis can give clear hydrogen for sustainable energy systems. Green hydrogen is such a renewable energy application technology, which can be generated in water electrolysis utilizing renewable energy sources. It slowly became a major support for the diversified, high-quality, and large-scale growth of hydrogen energy in the dual controls of carbon reduction and energy transformation. Photovoltaic (PV) Solar power signifies the lowest and most generally used renewable electricity sources. Hence, it is considered as the energy's prime vector to power green hydrogen performance. The aim is to predict the output of PV solar power previously employing machine learning (ML) at presented weather data to decrease uncertainties concerning the availabilities of solar power at a specified time. In this manuscript, we offer the Hybrid Deep Learning-Driven Modeling and Optimization of Solar Photovoltaic Systems for Green Hydrogen Production (HDLMOSP-GHP) algorithm. The HDLMOSP-GHP technique aims to address challenges in accurately predicting solar energy output and optimizing the water electrolysis process to maximize hydrogen production efficiency. To accomplish that, the HDLMOSP-GHP model contains two stages modeling and optimization. In the first stage, the hybrid deep learning of gated recurrent units‐autoencoder (GRU-AE) model is employed to accurately model the non-linear dynamics of solar PV performance under varying environmental conditions. In the next stage, an improved lemurs optimizer (ILO) algorithm is applied to enable the system to identify optimal operational parameters that maximize hydrogen yield while ensuring system stability and energy efficiency in hydrogen production optimization. To represent the improved performance of the HDLMOSP-GHP method, a broad range of experiments take place and the outcomes are inspected in terms of several measures. The comparison study reported the betterment of the HDLMOSP-GHP approach under various metrics. The experimental analysis proves that the HDLMOSP-GHP method achieves a maximum hydrogen production rate of 1.039 mol/s with a peak output power of 189.13W. In addition, the tracking efficiency of the proposed work is 98.97 %, and power oscillation to 5.76 %.

Suggested Citation

  • Kamalakannan, N. & Sivasakthi, S. & Vinothkumar, M. & Karthick, R., 2026. "Hybrid Deep Learning - Driven Modeling and Optimization of Solar Photovoltaic Systems for Green Hydrogen Production with improved Lemurs optimizer," Renewable Energy, Elsevier, vol. 256(PE).
    • Handle: RePEc:eee:renene:v:256:y:2026:i:pe:s0960148125017896
    DOI: 10.1016/j.renene.2025.124125
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960148125017896
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.renene.2025.124125?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

    for a different version of it.

    References listed on IDEAS

    as
    1. Arturs Nikulins & Kaspars Sudars & Edgars Edelmers & Ivars Namatevs & Kaspars Ozols & Vitalijs Komasilovs & Aleksejs Zacepins & Armands Kviesis & Andreas Reinhardt, 2024. "Deep Learning for Wind and Solar Energy Forecasting in Hydrogen Production," Energies, MDPI, vol. 17(5), pages 1-12, February.
    2. Shi, Tao & Xu, Chang & Dong, Wenhao & Zhou, Hangyu & Bokhari, Awais & Klemeš, Jiří Jaromír & Han, Ning, 2023. "Research on energy management of hydrogen electric coupling system based on deep reinforcement learning," Energy, Elsevier, vol. 282(C).
    3. Balali, Adel & Asadabadi, Mohammad Javad Raji & Mehrenjani, Javad Rezazadeh & Gharehghani, Ayat & Moghimi, Mahdi, 2023. "Development and neural network optimization of a renewable-based system for hydrogen production and desalination," Renewable Energy, Elsevier, vol. 218(C).
    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. Baseer, Mohammad Abdul & Kumar, Prashant & Nascimento, Erick Giovani Sperandio, 2025. "Advancements in hydrogen production through the integration of renewable energy sources with AI techniques: A comprehensive literature review," Applied Energy, Elsevier, vol. 383(C).
    2. Zhang, Tianhao & Dong, Zhe & Huang, Xiaojin, 2024. "Multi-objective optimization of thermal power and outlet steam temperature for a nuclear steam supply system with deep reinforcement learning," Energy, Elsevier, vol. 286(C).
    3. Nasir, M. & Bansal, R.C. & Saloumi, M., 2025. "Reinforcement learning algorithms in AC, DC, and hybrid microgrids applications: A comprehensive review," Applied Energy, Elsevier, vol. 401(PC).
    4. Balali, Adel & Raji Asadabadi, Mohammad Javad & Lotfollahi, Amirhosein & Moghimi, Mahdi, 2025. "Machine learning-based optimization of a waste-to-energy power plant with CAES for peak load management: Feasibility and a case study in Tehran," Energy, Elsevier, vol. 335(C).
    5. Feng, Jianbing & Ren, Zhouyang & Li, Wenyuan, 2025. "A robust safe reinforcement learning-based operation method for hybrid electric-hydrogen energy system risk-based dispatch considering dynamic efficiency characteristics of electrolysers," Renewable Energy, Elsevier, vol. 254(C).
    6. Wang, Zhe & Cao, Menglong & Tang, Haobo & Ji, Yulong & Han, Fenghui, 2024. "A global heat flow topology for revealing the synergistic effects of heat transfer and thermal power conversion in large scale systems: Methodology and case study," Energy, Elsevier, vol. 290(C).
    7. Yang, Zhixue & Ren, Zhouyang & Li, Hui & Sun, Zhiyuan & Feng, Jianbing & Xia, Weiyi, 2024. "A multi-stage stochastic dispatching method for electricity‑hydrogen integrated energy systems driven by model and data," Applied Energy, Elsevier, vol. 371(C).
    8. Huang, Yu & Li, Sijun & Zhang, Peng & Wang, Dongfeng & Lan, Jianjiang & Lee, Kwang Y. & Zhang, Qiliang, 2024. "Parameter adaptive stochastic model predictive control for wind–solar–hydrogen coupled power system," Renewable Energy, Elsevier, vol. 237(PA).
    9. Chen, Jinzhou & He, Hongwen & Wang, Ya-Xiong & Quan, Shengwei & Zhang, Zhendong & Wei, Zhongbao & Han, Ruoyan, 2024. "Research on energy management strategy for fuel cell hybrid electric vehicles based on improved dynamic programming and air supply optimization," Energy, Elsevier, vol. 300(C).
    10. Chen, Qi & Kuang, Zhonghong & Liu, Xiaohua & Zhang, Tao, 2024. "Application-oriented assessment of grid-connected PV-battery system with deep reinforcement learning in buildings considering electricity price dynamics," Applied Energy, Elsevier, vol. 364(C).
    11. Wang, Hao & Hu, Enyi & Zhu, Bin & Yang, Fan & Lund, Peter, 2025. "H2 treatment benefit stable operation for ceramic fuel cells with NFMNa electrolyte at lower temperature," Renewable Energy, Elsevier, vol. 239(C).
    12. Bozzolo Lueckel, Fabio B. & Monaghan, Rory F.D. & Lynch, Muireann Á., 2025. "Hydrogen supply chain modelling at energy system scale: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 210(C).
    13. Liu, Meng & Bu, Siqi & Zhu, Ziqing & Zhou, Bin, 2026. "Adaptive home energy management based on PI-DRA-PPO for integrated electricity, hydrogen, and heat storage systems," Applied Energy, Elsevier, vol. 407(C).
    14. Dariusz Bradło & Witold Żukowski & Jan Porzuczek & Małgorzata Olek & Gabriela Berkowicz-Płatek, 2025. "Towards Net Zero in Poland: A Novel Approach to Power Grid Balance with Centralized Hydrogen Production Units," Energies, MDPI, vol. 18(7), pages 1-24, March.
    15. Ling Miao & Ning Zhou & Jianwei Ma & Hao Liu & Jian Zhao & Xiaozhao Wei & Jingyuan Yin, 2025. "Current Status, Challenges and Future Perspectives of Operation Optimization, Power Prediction and Virtual Synchronous Generator of Microgrids: A Comprehensive Review," Energies, MDPI, vol. 18(13), pages 1-41, July.
    16. Moiz Ahmad & Muhammad Babar Ramzan & Muhammad Omair & Muhammad Salman Habib, 2024. "Integrating Risk-Averse and Constrained Reinforcement Learning for Robust Decision-Making in High-Stakes Scenarios," Mathematics, MDPI, vol. 12(13), pages 1-32, June.
    17. Chen, Heng & Salih, Sinan Q. & Almadhor, Ahmad & Khan, Mohammad Nadeem & Al Barakeh, Zaher & Ghandour, Raymond & Alturise, Fahad & Alkhalaf, Salem & Elhosiny Ali, H. & Albalawi, Hind, 2025. "Leveraging multi-effect energy utilization in a biomass-based system for H2 production and urban energy needs: 4E analysis and ANN-based grey wolf optimization," Energy, Elsevier, vol. 333(C).
    18. Zhong, Shangpeng & Wang, Xiaoming & Wu, Hongbin & He, Ye & Xu, Bin & Ding, Ming, 2024. "Energy hub management for integrated energy systems: A multi-objective optimization control strategy based on distributed output and energy conversion characteristics," Energy, Elsevier, vol. 306(C).
    19. Li, Ruiqi & Ren, Hongbo & Wu, Qiong & Li, Qifen & Gao, Weijun, 2024. "Cooperative economic dispatch of EV-HV coupled electric-hydrogen integrated energy system considering V2G response and carbon trading," Renewable Energy, Elsevier, vol. 227(C).
    20. Du, Yida & Li, Xiangguang & Liang, Yan & Tan, Zhongfu, 2024. "Two-stage multi-objective distributionally robust optimization of the electricity-hydrogen coupling system under multiple markets," Energy, Elsevier, vol. 303(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    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:256:y:2026:i:pe:s0960148125017896. 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.