Integrating machine learning and IoT in hydrogen production, storage, and distribution for a decarbonized transport future
Bekmyrza K.Z. Kuterbekov K.A. Kabyshev A.M. Kubenova M.M. Baratova A.A. Aidarbekov N. Vinceslas F.F.C.
2025Oxford University Press
International Journal of Low-Carbon Technologies
2025#201554 - 1570 pp.
This study integrates reinforcement learning (RL) optimization and internet of things (IoT) monitoring within a MATLAB/Simulink simulation framework for hydrogen infrastructure. IoT sensors provide real-time data, enabling dynamic adjustments, while RL optimizes hydrogen logistics, reducing costs and emissions. This approach enhances predictive accuracy beyond conventional models, offering a scalable solution for sustainability. IoT sensors improve model precision, identifying underground storage as the most economical. Renewable energy integration lowered emissions by 97.8% (from 9.00 to 0.20 kg CO2-eq/kg H) and reduced hydrogen costs by 40% (from US$5.50 to US$3.30/kg), while RL optimization achieved US$15 000 in cost savings and a 30% emissions reduction.
hydrogen infrastructure , internet of things (IoT) , machine learning , simulation-based modeling , sustainable energy systems
Text of the article Перейти на текст статьи
Caspian University of Technology and Engineering Named after Sh. Yessenov, Aktau, 130000, Kazakhstan
Institute of Physical and Technical Sciences, L.N. Gumilyov Eurasian National University, Astana, 010008, Kazakhstan
Department of Renewable Energy Technology, College of Technology, University of Bamenda, P.O Box 39, Cameroon
Caspian University of Technology and Engineering Named after Sh. Yessenov
Institute of Physical and Technical Sciences
Department of Renewable Energy Technology
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026