This paper proposes a vehicular edge federated learning (VEFL) solution, where an edge server leverages highly mobile connected vehicles' (CVs') onboard central processing units (CPUs) and local datasets to train a global model. Convergence analysis reveals that the VEFL training loss depends on the successful receptions of the CVs' trained models over the intermittent vehicle-to-infrastructure (V2I) wireless links. Owing to high mobility, in the full device participation case (FDPC), the edge server aggregates client model parameters based on a weighted combination according to the CVs' dataset sizes and sojourn periods, while it selects a subset of CVs in the partial device participation case (PDPC). We then devise joint VEFL and radio access technology (RAT) parameters optimization problems under delay, energy and cost constraints to maximize the probability of successful reception of the locally trained models. Considering that the optimization problem is NP-hard, we decompose it into a VEFL parameter optimization sub-problem, given the estimated worst-case sojourn period, delay and energy expense, and an online RAT parameter optimization sub-problem. Finally, extensive simulations are conducted to validate the effectiveness of the proposed solutions with a practical 5G new radio (5G-NR) RAT under a realistic microscopic mobility model.

翻译：本文提出了一种车载边缘联邦学习（VEFL）解决方案，其中边缘服务器利用高移动性互联车辆（CVs）的车载中央处理器（CPU）和本地数据集来训练全局模型。收敛性分析表明，VEFL训练损失取决于间歇性车辆到基础设施（V2I）无线链路上成功接收CVs训练模型的结果。由于高移动性，在全设备参与情况下（FDPC），边缘服务器根据CVs的数据集大小和驻留时间进行加权组合来聚合客户端模型参数，而在部分设备参与情况下（PDPC）则选择CVs子集。随后，我们构建了在延迟、能耗和成本约束下的联合VEFL与无线接入技术（RAT）参数优化问题，以最大化本地训练模型的成功接收概率。考虑到该优化问题属于NP难问题，我们将其分解为：在估计最差驻留时间、延迟和能耗条件下的VEFL参数优化子问题，以及在线RAT参数优化子问题。最后，基于实际的5G新无线电（5G-NR）RAT和微观移动模型进行了大量仿真，验证了所提方案的有效性。