Federated learning (FL) has emerged as a pivotal solution for training machine learning models over wireless networks, particularly for Internet of Things (IoT) devices with limited computation resources. Despite its benefits, the efficiency of FL is often restricted by the communication quality between IoT devices and the central server. To address this issue, we introduce an innovative approach by deploying an unmanned aerial vehicle (UAV) as a mobile FL server to enhance the training process of FL. By leveraging the UAV's maneuverability, we establish robust line-of-sight connections with IoT devices, significantly improving communication capacity. To improve the overall training efficiency, we formulate a latency minimization problem by jointly optimizing the bandwidth allocation, computing frequencies, transmit power for both the UAV and IoT devices, and the UAV's trajectory. Then, an efficient alternating optimization algorithm is developed to solve it efficiently. Furthermore, we analyze the convergence and computational complexity of the proposed algorithm. Finally, numerical results demonstrate that our proposed scheme not only outperforms existing benchmark schemes in terms of latency but also achieves training efficiency that closely approximate the ideal scenario.

翻译：联邦学习（FL）已成为在无线网络（特别是计算资源有限的物联网设备上）训练机器学习模型的关键解决方案。尽管具有诸多优势，FL的效率往往受限于物联网设备与中央服务器之间的通信质量。为解决这一问题，我们提出一种创新方法，即部署无人机作为移动FL服务器以增强FL的训练过程。通过利用无人机的机动性，我们与物联网设备建立了稳健的视距连接，显著提升了通信容量。为提高整体训练效率，我们构建了一个延迟最小化问题，通过联合优化带宽分配、计算频率、无人机与物联网设备的发射功率以及无人机的飞行轨迹来实现。随后，我们开发了一种高效的交替优化算法以有效求解该问题。此外，我们分析了所提算法的收敛性与计算复杂度。最终，数值结果表明，我们提出的方案不仅在延迟方面优于现有基准方案，而且达到了接近理想场景的训练效率。