CARGO: Carbon-Aware Gossip Orchestration in Smart Shipping

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 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. We evaluate CARGO under a predictive-maintenance scenario using operational bulk-carrier engine data and a trace-driven maritime communication protocol that captures client dropout, partial participation, packet loss, and multiple connectivity regimes, derived from mobility-aware vessel interactions. 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. Overall, the conducted performance evaluation demonstrates that CARGO is a feasible and practical solution for reliable and resource-conscious maritime AI deployment.

Figures (6)

• Figure 1: CARGO control plane. The CARGO Orchestrator combines utility, carbon, and fairness signals to compute per-node scores $\{g_i(t)\}_{i\in\Omega_t}$ over the available set. These scores drive the Participation Scheduler, while the Topology Scheduler, Carbon-Aware Compressor, and Gossip Mixer determine the activated graph $E_t$, compression policy $\mathcal{C}_t$, and mixing matrix $W_t$, respectively. The controller output at round $t$ is the decision bundle $\mathcal{D}_t=(A_t,E_t,W_t,\mathcal{C}_t,r_t)$, where $r_t$ denotes the resynchronization flag.
• Figure 2: Round-level scheduling view. Starting from the available-node set $\Omega_t$ and the candidate edge set $E_t^{\mathrm{cand}}$ induced by the current topology snapshot, CARGO first selects the active-node set $A_t\subseteq\Omega_t$ and then activates a degree-bounded communication subgraph $E_t\subseteq E_t^{\mathrm{cand}}$.
• Figure 3: Visualization of maritime gossip topologies across three regimes: (A) Well-connected, (B) mid, and (C) fragmented.
• Figure 4: Model fidelity and optimization behavior. (A) Predictive performance ($R^2$) versus cumulative compute energy, reported as median with IQR range across seeds/methods. The curve summarizes how quickly each approach reaches the high-$R^2$ plateau per unit energy. (B) Training and evaluation loss trajectories (median $\pm$ IQR) as a function of cumulative local updates, illustrating stable convergence without late-stage divergence. (C) Example time-series segment (median $\pm$ IQR) comparing normalized ground truth and predictions, showing that the learned model tracks temporal dynamics and preserves trend changes under uncertainty.
• Figure 5: Packet-loss robustness across connectivity regimes. Performance and resource profiles under increasing packet-loss probability $p \in \{0,0.05,0.1,0.2\}$ for three topology regimes: fragmented, mid, and well-connected. Top row: final RMSE ($\times 10^{-3}$); middle row: total carbon footprint (g); bottom row: total energy consumption (J). Error bars indicate variability across seeds. The regimes correspond to distinct encounter opportunities derived from the spatiotemporal contact construction (larger communication radius increases connectivity, while coarser temporal binning reduces effective contacts), enabling a controlled evaluation of learning stability and efficiency as network reliability degrades.