We propose a federated learning (FL) in stratosphere (FLSTRA) system, where a high altitude platform station (HAPS) facilitates a large number of terrestrial clients to collaboratively learn a global model without sharing the training data. FLSTRA overcomes the challenges faced by FL in terrestrial networks, such as slow convergence and high communication delay due to limited client participation and multi-hop communications. HAPS leverages its altitude and size to allow the participation of more clients with line-of-sight (LOS) links and the placement of a powerful server. However, handling many clients at once introduces computing and transmission delays. Thus, we aim to obtain a delay-accuracy trade-off for FLSTRA. Specifically, we first develop a joint client selection and resource allocation algorithm for uplink and downlink to minimize the FL delay subject to the energy and quality-of-service (QoS) constraints. Second, we propose a communication and computation resource-aware (CCRA-FL) algorithm to achieve the target FL accuracy while deriving an upper bound for its convergence rate. The formulated problem is non-convex; thus, we propose an iterative algorithm to solve it. Simulation results demonstrate the effectiveness of the proposed FLSTRA system, compared to terrestrial benchmarks, in terms of FL delay and accuracy.

翻译：我们提出了一种平流层联邦学习系统（FLSTRA），其中高空平台站（HAPS）能够促进大量地面客户端在不共享训练数据的情况下协作学习全局模型。FLSTRA克服了地面网络中联邦学习面临的挑战，例如因客户端参与受限和多跳通信导致的收敛缓慢和高通信延迟。HAPS利用其高度和尺寸优势，允许更多客户端通过视距（LOS）链路参与，并部署强大的服务器。然而，同时处理大量客户会引入计算和传输延迟。因此，我们旨在为FLSTRA获得延迟-精度权衡。具体而言，我们首先开发了一种联合上行和下行链路的客户端选择与资源分配算法，以在能量和服务质量（QoS）约束下最小化FL延迟。其次，我们提出了一种通信与计算资源感知（CCRA-FL）算法，在推导其收敛速率上界的同时，实现目标FL精度。所构建的问题是非凸的，因此我们提出了一种迭代算法来求解。仿真结果表明，与地面基准方法相比，所提出的FLSTRA系统在FL延迟和精度方面具有有效性。