A study on the dynamic optimization strategy of energy routers in zero-carbon ports based on digital twin technology
Shun Li, Xingda Fan, Zhaoyu Qi
Abstract
The global maritime industry faces urgent demands for carbon neutrality while maintaining efficiency. Ports, as critical logistics nodes, need innovative solutions for zero-carbon energy. This study proposes a dynamic optimization framework for energy routers in zero-carbon ports, leveraging digital twins to address renewable integration, real-time coordination, and carbon accountability. By synergistically integrating physics-informed modeling, federated learning, and hybrid quantum–classical optimization, the framework achieves synchronized multi-timescale energy control. A Tianjin Port case study showed 92.4% renewable utilization, 42.8% lower carbon intensity, and 29% reduced costs. Resilience was validated under extreme weather, maintaining 94.7% capacity in typhoons. Innovations include blockchain-audited carbon tracking and adversarial reinforcement learning for cybersecurity. This study bridges the gaps in temporal-spatial decoupling and multi-stakeholder coordination, offering a replicable port decarbonization blueprint aligned with IMO 2050. Challenges like sensor dependency and embodied carbon highlight future research in edge AI and circular economy.