Distributed learning on edge devices has attracted increased attention with the advent of federated learning (FL). Notably, edge devices often have limited battery and heterogeneous energy availability, while multiple rounds are required in FL for convergence, intensifying the need for energy efficiency. Energy depletion may hinder the training process and the efficient utilization of the trained model. To solve these problems, this letter considers the integration of energy harvesting (EH) devices into a FL network with multi-channel ALOHA, while proposing a method to ensure both low energy outage probability and successful execution of future tasks. Numerical results demonstrate the effectiveness of this method, particularly in critical setups where the average energy income fails to cover the iteration cost. The method outperforms a norm based solution in terms of convergence time and battery level.

翻译：随着联邦学习（FL）的兴起，边缘设备上的分布式学习引起了广泛关注。值得注意的是，边缘设备通常具有有限的电池容量和异质性能量可用性，而联邦学习需要多轮迭代才能收敛，这加剧了对能效的需求。能量耗尽可能阻碍训练过程及训练模型的有效利用。为解决这些问题，本文考虑将能量采集（EH）设备集成到具有多信道ALOHA的联邦学习网络中，同时提出一种方法，既能确保低能量中断概率，又能保证未来任务的顺利执行。数值结果证明了该方法的有效性，特别是在平均能量收入无法覆盖迭代成本的关键场景下。该方法在收敛时间和电池电量方面优于基于范数的解决方案。