Joint Communication Scheduling and Resource Allocation for Distributed Edge Learning: Seamless Integration in Next-Generation Wireless Networks

TL;DR

This paper proposes a time-dependent joint communication scheduling and resource allocation framework for distributed edge learning in 6G networks, addressing inefficiencies of traditional rigid resource allocation methods.

Contribution

It introduces a novel timeslot-wise optimization approach for edge learning resource management, considering realistic system heterogeneity and coexistence with high-bandwidth traffic.

Findings

The proposed framework reduces learning time within a communication round.

Simulation results validate the efficiency of the joint scheduling and resource allocation.

The method outperforms traditional rigid resource allocation approaches.

Abstract

Distributed edge learning (DL) is considered a cornerstone of intelligence enablers, since it allows for collaborative training without the necessity for local clients to share raw data with other parties, thereby preserving privacy and security. Integrating DL into the 6G networks requires a coexistence design with existing services such as high-bandwidth (HB) traffic like eMBB. Current designs in the literature mainly focus on communication round-wise designs that assume a rigid resource allocation throughout each communication round (CR). However, rigid resource allocation within a CR is a highly inefficient and inaccurate representation of the system's realistic behavior, especially when CR duration far exceeds the channel coherence time due to large model size or limited resources. This is due to the heterogeneous nature of the system, as clients inherently may need to access the network at different time instants. This work zooms into one arbitrary CR, and demonstrates the importance of considering a time-dependent design for sharing the resource pool with HB traffic. We first formulate a timeslot-wise optimization problem to minimize the consumed time by DL within the CR while constrained by a DL energy budget. Due to its intractability, a session-based optimization problem is formulated assuming a CR lasts less than a large-scale coherence time. Some scheduling properties of such multi-server joint communication scheduling and resource allocation framework have been established. An iterative algorithm has been designed to solve such non-convex and non-block-separable-constrained problems. Simulation results confirm the importance of the efficient and accurate integration design proposed in this work.