A Flexible Low-Latency Low-Energy-Consumption Wireless Federated Learning Architecture with UE-to-Network Relay

This paper addresses the difficulty of implementing federated learning (FL) in geographical areas with poor wireless signal coverage, and alleviates the high burden imposed by intensive computation and communication on resource-limited wireless devices. Firstly, we propose a user equipment (UE)-tonetwork relay aided FL (UNR-FL) architecture that facilitates a low-cost and flexible implementation of wireless FL, without densifying network equipment deployment. Secondly, we propose an adaptive network control scheme that jointly optimizes resource allocation, network topology construction, and device scheduling, to achieve low latency and low energy consumption. The second contribution is threefold. 1) For allocating resources, we propose a linear-complexity algorithm which is capable of jointly optimizing the transmission time resource and the computing power. 2) For constructing network topology, we derive the optimal closed-form solution under certain conditions, and propose a tabu search based meta-heuristic algorithm to find feasible solutions under the other conditions. 3) For scheduling devices, we propose a voting-based device scheduling algorithm that is near-optimal. Extensive experimental results demonstrate that the proposed UNR-FL architecture and the adaptive network control scheme are capable of substantially reducing the learning latency and the total energy consumption.