CARGO: Carbon-Aware Gossip Orchestration in Smart Shipping
Summary: arXiv:2603.27857v1 Announce Type: new
Abstract: Smart shipping operations increasingly depend on collaborative AI, yet the underlying data are generated across vessels with uneven connectivity, limited backhaul, and clear commercial sensitivity. In such settings, server-coordinated Federated Learning (FL) remains a weak systems assumption, depending on a reachable aggregation point and repeated wide-area synchronization, both of which are difficult to guarantee in maritime networks. A serverless gossip approach therefore represents a more natural approach, but existing methods still treat communication mainly as an optimization bottleneck, rather than as a resource that must be managed jointly with carbon cost, reliability, and long-term participation balance.
In this context, this paper presents CARGO, a carbon-aware gossip orchestration framework for smart shipping. CARGO separates learning into a control and a data plane. The data plane performs local optimization with compressed gossip exchange, while the control plane decides, at each round, which vessels should participate, which communication edges should be activated, how aggressively updates should be compressed, and when recovery actions should be triggered.
Key Features of CARGO
- Separation of Control and Data Plane: This design allows for optimized local computations and efficient communication strategies.
- Compressed Gossip Exchange: By compressing communications, CARGO reduces bandwidth usage while maintaining effective data sharing.
- Adaptive Participation: The control plane dynamically decides which vessels participate in each communication round, enhancing flexibility and resource management.
- Resilience Mechanisms: CARGO includes recovery actions to manage client dropout and ensure reliable operations even in adverse conditions.
Performance Evaluation
We evaluate CARGO under a predictive-maintenance scenario using operational bulk-carrier engine data and a trace-driven maritime communication protocol. This protocol effectively captures:
- Client dropout
- Partial participation of vessels
- Packet loss
- Multiple connectivity regimes
These scenarios are derived from mobility-aware vessel interactions that reflect real maritime environments. Across the tested stress settings, CARGO consistently remains in the high-accuracy regime while reducing carbon footprint and communication overheads, compared to accuracy-competitive decentralized baselines.
Conclusion
The conducted performance evaluation demonstrates that CARGO is a feasible and practical solution for reliable and resource-conscious maritime AI deployment. By managing communication as a resource and incorporating carbon awareness, CARGO sets a new standard for smart shipping operations, paving the way for more sustainable and efficient maritime logistics.