Design optimization and ML-based performance prediction of microgrid-hydrogen refueling systems using Gaussian process regression

被引：0

作者：

Elkadeem, Mohamed R. ^{[1
]}

Zayed, Mohamed E. ^{[1
]}

Kotb, Kotb M. ^{[1
]}

Shboul, Bashar ^{[2
]}

AlZahrani, Atif S. ^{[1
,3
]}

Rehman, Shafiqur ^{[1
,4
]}

Abido, Mohammad A. ^{[1
,5
,6
]}

机构：

[1] Interdisciplinary Research Center for Sustainable Energy Systems (IRC-SES), King Fahd University of Petroleum & Minerals (KFUPM), Dhahran

[2] Renewable Energy Engineering Department, Faculty of Engineering, Al Al-Bayt University, Mafraq

[3] Materials Science and Engineering Department, KFUPM, Dhahran

[4] Mechanical Engineering Department, KFUPM, Dhahran

[5] Electrical Engineering Department, KFUPM, Dhahran

[6] SDAIA-KFUPM Joint Research Center for Artificial Intelligence, KFUPM, Dhahran

来源：

International Journal of Hydrogen Energy | 2025年 / 158卷

关键词：

Gaussian process regression; Hydrogen refueling station; Machine learning; Optimization; Renewable energy;

D O I：

10.1016/j.ijhydene.2025.150382

中图分类号：

学科分类号：

摘要：

This paper investigates the synergies of microgrids (MGs) and hydrogen refueling stations (H2RS) for reliable and cost-effective energy supply in arid regions. An optimization model is proposed to determine the optimal capacities of MG-H2RS components, considering real weather conditions and a net-energy metering strategy. The objective is to minimize lifecycle costs while meeting electrical and hydrogen demands. A Gaussian process regression model (GPRM) is developed to create a machine learning-based predictive method that captures the complex, non-linear relationships between input variables (weather conditions, energy consumption) and output variables (energy generation and hydrogen production). Results show that the optimal design reduces lifecycle costs by 15.8 %, cuts fossil fuel consumption by 62.2 %, and reduces carbon emissions by 65.3 %. The GPRM achieves R2 values above 0.99 for key outputs, and the Q-Q regression plots and error distributions show minimal deviation in most performance outputs, confirming the model's stable convergence and strong predictive accuracy. © 2025 Hydrogen Energy Publications LLC

引用

共 48 条

[1]

World energy transitions Outlook 2023: 1.5°C Pathway, World Energy Transitions, 25, (2023)

[2]

Zhen L., Wu J., Yang Z., Ren Y., Li W., Hydrogen refueling station location optimization under uncertainty, Comput Ind Eng, 190, (2024)

[3]

Apostolou D., Xydis G., A literature review on hydrogen refuelling stations and infrastructure. Current status and future prospects, Renew Sustain Energy Rev, 113, (2019)

[4]

Green cost hydrogen reduction electrolysers scaling up to meet the 1.5°C climate goal, (2020)

[5]

Belaid F., Al-Sarihi A., Saudi Arabia energy transition in a post-paris agreement era: an analysis with a multi-level perspective approach, Res Int Bus Finance, 67, (2024)

[6]

Global EV Outlook 2022 - securing supplies for an electric future, Glob EV Outlook, (2022)

[7]

Tian Z., Lv H., Zhou W., Zhang C., He P., Review on equipment configuration and operation process optimization of hydrogen refueling station, Int J Hydrogen Energy, 47, pp. 3033-3053, (2022)

[8]

Genovese M., Fragiacomo P., Hydrogen refueling station: overview of the technological status and research enhancement, J Energy Storage, 61, (2023)

[9]

Okonkwo P.C., Mansir I.B., Barhoumi E.M., Emori W., Radwan A.B., Shakoor R.A., Et al., Utilization of renewable hybrid energy for refueling station in Al-Kharj, Saudi Arabia, Int J Hydrogen Energy, 47, pp. 22273-22284, (2022)

[10]

Ayodele T.R., Mosetlhe T.C., Yusuff A.A., Ntombela M., Optimal design of wind-powered hydrogen refuelling station for some selected cities of South Africa, Int J Hydrogen Energy, 46, pp. 24919-24930, (2021)

← 1 2 3 4 5 →