Real-Time Energy Management Optimization for Renewable Energy Ships

As concern for greenhouse gas emissions grows, the shipping industry is gradually transitioning from traditional diesel-driven vessels to renewable energy ships, which utilize zero-carbon power sources such as photovoltaic (PV) power generation. However, the uncertainty associated with onboard PV generation has become a significant obstacle to effective energy management on these alternative energy ships. Researchers from Shanghai Jiao Tong University have proposed a real-time energy management optimization method based on reinforcement learning, tailored to handle PV uncertainty and dynamic load variations during navigation.

Key Takeaways:

• The proposed algorithm optimizes the energy flow between the onboard diesel generator and the energy storage system in real-time, aiming to minimize fuel consumption and enhance operational stability.
• Real-world shipboard microgrid data is utilized to perform case studies, demonstrating the effectiveness of the proposed approach.
• The method effectively stabilizes the state of charge within a safe operational range of [0.2, 0.8], which is helpful for energy storage lifespan.
• The proposed approach has the potential to reduce fuel consumption by up to 90.32% and 94.57% compared to scenarios without PV systems and traditional robust optimization methods, respectively.
• The research utilizes a reinforcement learning-based method, specifically tailored to address the uncertainty associated with onboard PV generation.
• The proposed algorithm optimizes the energy flow between the diesel generator and the energy storage system in real-time, considering both PV uncertainty and dynamic load variations.

Statistics:

• The proposed approach reduces fuel consumption by up to 90.32% and 94.57% compared to scenarios without PV systems and traditional robust optimization methods, respectively.
• The method effectively stabilizes the state of charge within a safe operational range of [0.2, 0.8].
• Real-world shipboard microgrid data is utilized to perform case studies.

Sources:

• A Reinforcement Learning Based Real-time Energy Management Method for Mobile Microgrid Considering Photovoltaic Uncertainty. International Journal of Electrical Power & Energy Systems, 2025;170.
• NewsRx. Study Findings from Shanghai Jiao Tong University Broaden Understanding of Electrical Power and Energy Systems (A Reinforcement Learning Based Real-time Energy Management Method for Mobile Microgrid Considering Photovoltaic Uncertainty). Energy Weekly News. September 5, 2025; p 975.