article · Frontiers in Energy Research
Solar-powered water electrolysis provides clean fuel, but effective system planning requires reliable forecasting of solar energy generation. A hybrid forecasting framework combines the Al-Biruni Earth Radius metaheuristic search algorithm and Particle Swarm Optimisation to dynamically tune the hyperparameters of a recurrent neural network. Using four months of weather station records from Hawaii, the model simulates seasonal solar output to estimate hydrogen production. Statistical evaluations, including Wilcoxon rank-sum and analysis of variance tests, confirm the accuracy, resilience, and computational economy of the approach relative to alternative methods. When applied to time-series data, the hybrid model predicted an average seasonal yield of 0.622 kilograms of hydrogen per day. These forecasting capabilities offer a valuable computational tool to improve the design, operational scheduling, and overall efficiency of solar-driven green hydrogen generation facilities.
Renewable hydrogen offers a path to decarbonise energy networks, yet solar energy fluctuations make facility planning and daily operation challenging. Accurate forecasting helps operators anticipate energy yields, size equipment correctly, and balance production schedules. By delivering computationally efficient and statistically robust predictions, this approach supports the wider integration of solar-driven electrolysis into sustainable energy infrastructure.
The method targets operators and engineers designing or managing solar-powered water electrolysis plants. Potential applications include software for production planning, grid integration, and dynamic operational scheduling. Based on simulated forecasts using historical weather station data, the technology sits at an applied research stage and requires further testing on operating physical electrolysis systems before full commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Solar-powered water electrolysis can produce clean hydrogen for sustainable energy systems. Accurate solar energy generation forecasts are necessary for system operation and planning. Al-Biruni Earth Radius (BER) and Particle Swarm Optimization (PSO) are used in this paper to ensemble forecast solar hydrogen generation. The suggested method optimizes the dynamic hyperparameters of the deep learning model of recurrent neural network (RNN) using the BER metaheuristic search optimization algorithm and PSO algorithm. We used data from the HI-SEAS weather station in Hawaii for 4 months (September through December 2016). We will forecast the level of solar energy production next season in our simulations and compare our results to those of other forecasting approaches. Regarding accuracy, resilience, and computational economy, the results show that the BER-PSO-RNN algorithm has great potential as a useful tool for ensemble forecasting of solar hydrogen generation, which has important ramifications for the planning and execution of such systems. The accuracy of the proposed algorithm is confirmed by two statistical analysis tests, such as Wilcoxon’s rank-sum and one-way analysis of variance (ANOVA). With the use of the proposed BER-PSO-RNN algorithm that excels in processing and forecasting time-series data, we discovered that with the proposed algorithm, the Solar System could produce, on average, 0.622 kg/day of hydrogen during the season in comparison with other algorithms.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3389/fenrg.2023.1221006
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
