On-Device Intelligence for 5G RAN: Knowledge Transfer and Federated Learning enabled UE-Centric Traffic Steering

TL;DR

This paper introduces a novel UE-centric traffic steering framework for 5G RAN that leverages federated learning, knowledge transfer, and model compression to improve service quality and reduce delays and overhead.

Contribution

It proposes a federated learning-based UE-centric traffic steering framework with attention-weighted schemes, model compression, and knowledge transfer for efficient 5G RAN management.

Findings

Achieves 65% lower delay compared to cell-based strategies.

Attains 52% higher throughput over existing UE-centric methods.

Effectively reduces communication overhead and computational burden.

Abstract

Traffic steering (TS) is a promising approach to support various service requirements and enhance transmission reliability by distributing network traffic loads to appropriate base stations (BSs). In conventional cell-centric TS strategies, BSs make TS decisions for all user equipment (UEs) in a centralized manner, which focuses more on the overall performance of the whole cell, disregarding specific requirements of individual UE. The flourishing machine learning technologies and evolving UE-centric 5G network architecture have prompted the emergence of new TS technologies. In this paper, we propose a knowledge transfer and federated learning-enabled UE-centric (KT-FLUC) TS framework for highly dynamic 5G radio access networks (RAN). Specifically, first, we propose an attention-weighted group federated learning scheme. It enables intelligent UEs to make TS decisions autonomously using local models and observations, and a global model is defined to coordinate local TS decisions and share experiences among UEs. Secondly, considering the individual UE's limited computation and energy resources, a growing and pruning-based model compression method is introduced, mitigating the computation burden of UEs and reducing the communication overhead of federated learning. In addition, we propose a Q-value-based knowledge transfer method to initialize newcomer UEs, achieving a jump start for their training efficiency. Finally, the simulations show that our proposed KT-FLUC algorithm can effectively improve the service quality, achieving 65\% and 38\% lower delay and 52% and 57% higher throughput compared with cell-based TS and other UE-centric TS strategies, respectively.