Low Earth Orbit (LEO) mega-constellations extend the cloud-to-edge continuum into space, enabling satellite edge computing. However, Federated Learning (FL) in this environment is fundamentally energy-constrained due to dynamic inter-satellite connectivity, heterogeneous onboard computing hardware, and strict power budgets. We propose CroSatFL, a sustainable on-orbit hierarchical FL framework that reduces end-to-end energy across computation and communication while maintaining strong training performance under realistic LEO dynamics. CroSatFL keeps the ground station (GS) off the iterative loop by performing all local training and intermediate aggregations on orbit, requiring only two GS communication phases: one for initialization and one for final model collection. This sharply reduces repeated use of bandwidth-limited and energy-expensive GS links and shifts iterative exchanges to laser inter-satellite links (LISLs). CroSatFL integrates three energy-aware mechanisms: StarMask forms LISL-feasible clusters that align data volume with heterogeneous CPU/GPU capability, Skip-One mitigates transient stragglers by skipping at most one slow client per cluster to lower round energy and latency while preserving long-term fairness, and random-k cross-aggregation enables lightweight topology-aware cross-cluster mixing without extending round duration. Using an end-to-end energy model with a realistic Walker-Delta constellation, we show that CroSatFL reduces GS communication count by over two orders of magnitude and GS transmission energy by about 6x relative to GS-centric and on-orbit baselines, while achieving competitive accuracy and faster convergence.

翻译：低地球轨道（LEO）巨型星座将云-边缘连续体延伸至太空，从而实现了卫星边缘计算。然而，由于动态的星间连接、异构的机载计算硬件以及严格的功率预算，该环境中的联邦学习（FL）从根本上受到能量约束。我们提出CroSatFL，这是一种可持续的在轨分层联邦学习框架，在现实LEO动态条件下，通过减少计算和通信的全链路能耗，同时保持强大的训练性能。CroSatFL将地面站（GS）排除在迭代循环之外，所有本地训练和中间聚合均在轨道上完成，仅需两个GS通信阶段：一个用于初始化，一个用于最终模型收集。这极大地减少了带宽有限且能耗高昂的地面站链路的重复使用，并将迭代交互转移至激光星间链路（LISL）。CroSatFL集成了三种能量感知机制：StarMask形成LISL可行的集群，将数据量与异构的CPU/GPU能力对齐；Skip-One通过每个集群最多跳过一名慢客户端来缓解瞬时掉队者，从而降低单轮能量和延迟，同时保持长期公平性；Random-k跨聚合则能在不延长轮次持续时间的情况下，实现轻量级的拓扑感知跨集群混合。通过使用真实的Walker-Delta星座建立全链路能量模型，我们证明，相对于以地面站为中心和在轨的基线方法，CroSatFL将GS通信次数减少了两个数量级以上，并将GS传输能量降低了约6倍，同时实现了具有竞争力的精度和更快的收敛速度。