基于分形网络（FractalNet）的异构联邦学习用于卫星巨型星座的轨道边缘智能：野火案例研究

中文摘要 AI 辅助

卫星巨型星座正逐渐成为大规模感知、通信与计算架构，但其学习架构仍在很大程度上沿用地面联邦学习和以地面为中心的任务操作模式，并不适用于在尺寸、重量、功率与成本（SWAP-C）、辐射耐受性、链路可用性及传播延迟方面存在数个数量级差异的卫星。我们提出一种基于分形网络（FractalNet）架构的异构联邦学习方法，用于轨道边缘智能。我们将接触窗口约束下的深度异构联邦优化形式化，并引入分布式路径调度器，该调度器根据SWAP-C约束、预测的星间接触情况及训练统计数据分配模型深度。为减少消息开销与能耗，每一层级定期聚合更新而非在每次接触机会时聚合，且一个三层智能体控制平面管控空间内调度、异常升级及基于策略的自主操作。作为案例研究，我们将该框架应用于野火检测，其中每个轨道层自然学习到不同的态势感知语义层级：低地球轨道（LEO）获取像素级热异常，中地球轨道（MEO）获取区域火线动态，地球静止轨道或高地球轨道（GEO/HEO）获取更大范围的风险传播。在模拟巨型星座上开展的实验从收敛性、通信效率、能耗适配、调度聚合节省、鲁棒性及延迟等方面验证了该方法的有效性。

英文摘要

Satellite mega-constellations are emerging as large-scale sensing, communication, and computation fabrics, yet their learning architectures remain largely inherited from terrestrial federated learning and ground-centric mission operations--- ill-suited to satellites that differ by orders of magnitude in Size, Weight, Power, and Cost (SWAP-C), radiation tolerance, link availability, and propagation delay. We propose a heterogeneous federated learning method based on the FractalNet architecture for orbital edge intelligence. We formalize contact-window-constrained, depth-heterogeneous federated optimization and introduce a distributed path scheduler that assigns model depth as a function of SWAP-C constraints, predicted inter-satellite contacts, and training statistics. To reduce message overhead and energy consumption, each tier pools updates periodically rather than at every contact opportunity, and a three-tier agentic control plane governs in-space scheduling, anomaly escalation, and policy-governed autonomy. As a case study, we apply the framework to wildfire detection, where each orbital shell naturally learns a different semantic level of situational awareness: pixel-scale thermal anomalies at low Earth orbit (LEO), regional fire-front dynamics at medium Earth orbit (MEO), and larger-scale risk propagation at geostationary or high Earth orbit (GEO/HEO). Experiments on simulated mega-constellations validate the approach across convergence, communication efficiency, energy adaptation, scheduled-pooling savings, robustness, and latency.

发表机构

• School of Computing（计算机学院）
• Southern Illinois University（南伊利诺伊大学）

机构由 AI 辅助整理，请以论文原文为准。