Battery-constrained federated edge learning in UAV-enabled IoT for B5G/6G networks

Abstract

In this paper, we investigate how to optimize the federated edge learning (FEEL) in unmanned aerial vehicle (UAV)-enabled Internet of Things (IoT) for B5G/6G networks. Federated learning is an effective framework to train a shared model between decentralized edge devices and servers without exchanging raw data, which helps protecting data privacy. In UAV-enabled IoT networks, latency and energy consumption are two important metrics limiting the performance of FEEL. Although most of the existing works have studied how to reduce latency and improve energy efficiency, only few of them have investigated the impact of the devices’ limited batteries on FEEL. Motivated by this, we study the battery-constrained FEEL, where the UAVs can adjust their operating CPU-frequencies to prolong battery life and avoid dropping from federated learning training untimely. We optimize the system by jointly allocating the computational resources and wireless bandwidth in time-varying environments based on a deep deterministic policy gradient (DDPG) based strategy, where a linear combination of latency and energy consumption is used to evaluate the system cost. In this end, simulation results are demonstrated to show that the proposed strategy outperforms the conventional ones. In particular, it enables all the devices to complete all rounds of FEEL with limited batteries, and reduce the system cost effectively in the meantime.