We propose a federated learning (FL) in stratosphere (FLSTRA) system, where a high altitude platform station (HAPS) felicitates 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（FLSTRA）系统，其中高空平台站（HAPS）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，例如因有限客户端参与和多跳通信导致的收敛速度慢和高通信延迟。HAPS 利用其高度和尺寸优势，允许通过视距（LoS）链路接入更多客户端，并部署强大服务器。然而，同时处理大量客户端会引入计算和传输延迟。因此，我们旨在实现 FLSTRA 的延迟-准确率权衡。具体而言，我们首先开发了联合客户端选择与上下行资源分配算法，以在能量和服务质量（QoS）约束下最小化联邦学习延迟。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联邦学习准确率。所构建的问题是非凸的，因此我们提出了一种迭代算法进行求解。仿真结果表明，与地面基准方案相比，所提出的 FLSTRA 系统在联邦学习延迟和准确率方面具有有效性。