In the heart of Morocco, a groundbreaking study is harnessing the power of artificial intelligence to revolutionize green hydrogen production. Hanane Ait Lahoussine Ouali, a researcher at the African Sustainable Agriculture Research Institute (ASARI) within Mohammed VI Polytechnic University, has developed a sophisticated model that could significantly impact the energy sector.
Ouali’s research, published in the journal ‘Cleaner Engineering and Technology’ (translated from French), focuses on using a feed-forward back-propagation network (FFBPN) to predict hydrogen production through electrolysis powered by concentrated solar power plants. Specifically, the study examines a Dish/Stirling system, a technology that converts solar energy into electrical energy using a mirror dish and a Stirling engine.
The model evaluates the impact of various input parameters, including direct normal irradiation (DNI) at different geographical locations, on hydrogen production. “By leveraging machine learning, we can optimize the placement and efficiency of these solar-powered electrolysis systems,” Ouali explains. The study trained the FFBPN model using different algorithms to identify the most effective approach for predicting green hydrogen production.
The findings are promising. Among the locations examined in eastern Morocco, Figuig and Bouarfa cities emerged as the most suitable for implementing the proposed system, yielding the highest annual net electric energy output. The system allowed the production of over 1462 tons/yr of green hydrogen, supported by a total installed capacity of 50 MWe.
The research also revealed that the Levenberg-Marquardt (LM) algorithm, using 33 neurons, outperformed other algorithms, exhibiting the lowest errors and the highest R2 value during both training and testing. “This model stands as a pioneering and effective tool to predict green hydrogen production from the Dish/Stirling system,” Ouali states.
The implications for the energy sector are substantial. As the world shifts towards cleaner energy sources, the ability to accurately predict and optimize hydrogen production can drive significant commercial impacts. “This research can help energy companies make informed decisions about where to invest in solar-powered hydrogen production facilities,” Ouali notes.
Moreover, the study highlights the potential of machine learning in enhancing the efficiency and sustainability of renewable energy technologies. As Ouali puts it, “The integration of AI in renewable energy systems is not just a trend; it’s a necessity for a sustainable future.”
This research paves the way for future developments in the field, offering a blueprint for how AI can be used to optimize renewable energy production. As the world continues to grapple with climate change, such innovations are crucial in transitioning to a greener, more sustainable energy landscape. The study, published in ‘Cleaner Engineering and Technology’, serves as a testament to the power of AI in driving forward the renewable energy sector.