Advanced data analytics Framework in Real-time Energy Management of Hydrogen-based Integrated Energy System for Green Transportation
R&D Focus Areas:
Energy systems integration, Mobility
Lead Organisation:
Swinburne University of Technology
Partners:
Not applicable
Status:
Active
Start date:
January 2023
Completion date:
January 2026
Key contacts:
Gordon Chakaodza – Director, Victorian Hydrogen Hub: gchakaodza@swin.edu.au
Victorian Hydrogen Hub (VH2): vichydrogenhub@swin.edu.au
Ali Yavari, Project Primary Supervisor: ayavary@swin.edu.au
Siripond Mullanu, Project Key Researcher: smullanu@swin.edu.au
Funding:
Victorian Government – Victorian Hydrogen Hub
Project total cost:
AUD$120,000
Project summary description:
Hydrogen is a promising technology in Integrated Energy Systems (IES), which enables significant energy transformation. It is changing the way energy is produced, distributed, and consumed towards clean energy, particularly in green transportation. However, the development of Hydrogen-based Integrated Energy Systems (H-IES) remains slow and has not yet achieved widespread adoption, primarily due to several key challenges.
First, the complexity of energy supply integration, which aims for efficient energy management to meet energy needs while considering system constraints and energy sustainability. Second, is the challenge of managing dynamic consumer demand that involves responding to frequently changing consumer needs and the instability of the energy market. Lastly, demand and supply balancing concerns to ensure system reliability and to minimise the risk of energy shortages or wastage.
This project aims to contribute to the field of green transportation through the innovative application of Artificial Intelligence (AI). By applying Advanced Data Analytics (ADA), this research focuses on handling continuous stream data from various energy data sources and enabling autonomous decision-making in real-time energy management within Hydrogen-based Integrated Energy Systems (H-IES).
The project will present real-world use case scenarios that demonstrate the effectiveness of the proposed framework within the context of green transportation.
Related publications and key links:
A. Dolatabadi, H. Abdeltawab, and Y. A.-R. I. Mohamed, “A Novel Model-Free Deep Reinforcement Learning Framework for Energy Management of a PV Integrated Energy Hub,” IEEE Trans. Power Syst., pp. 1–13, 2022, doi: 10.1109/TPWRS.2022.3212938.
A. Dreher et al., “AI agents envisioning the future: Forecast-based operation of renewable energy storage systems using hydrogen with Deep Reinforcement Learning,” Energy Convers. Manag., vol. 258, p. 115401, Apr. 2022, doi: 10.1016/j.enconman.2022.115401.
C. Garrido, L. G. Marín, G. Jiménez-Estévez, F. Lozano, and C. Higuera, “Energy Management System for Microgrids based on Deep Reinforcement Learning,” in 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON), Dec. 2021, pp. 1–7. doi: 10.1109/CHILECON54041.2021.9703072.
X. Wu, S. Qi, Z. Wang, C. Duan, X. Wang, and F. Li, “Optimal scheduling for microgrids with hydrogen fueling stations considering uncertainty using data-driven approach,” Appl. Energy, vol. 253, p. 113568, Nov. 2019, doi: 10.1016/j.apenergy.2019.113568.
Higher degree studies supported:
One PhD student at Swinburne University of Technology is supported by this project.
September 2023