Online Slice Reconfiguration for End-to-End QoE in 6G Applications

TL;DR

This paper presents an online learning-based slice reconfiguration algorithm for 6G networks that optimizes end-to-end QoE by adapting to stochastic resource demands, outperforming existing methods especially during traffic bursts.

Contribution

The work introduces a gradient-based online slice reconfiguration algorithm that learns the QoE-resource relationship and manages slices effectively in dynamic, resource-constrained environments.

Findings

Achieves high accuracy in meeting QoE requirements.

Improves performance by approximately 98% during bursty traffic.

Ensures low end-to-end delay violations for lower priority slices.

Abstract

End-to-end (E2E) quality of experience (QoE) for 6G applications depends on the synchronous allocation of networking and computing resources, also known as slicing. However, the relationship between the resources and the E2E QoE outcomes is typically stochastic and non-stationary. Existing works consider known resource demands for slicing and formulate optimization problems for slice reconfiguration. In this work, we create and manage slices by learning the relationship between E2E QoE and resources. We develop a gradient-based online slice reconfiguration algorithm (OSRA) to reconfigure and manage slices in resource-constrained scenarios for radio access networks (RAN). We observe that our methodology meets the QoE requirements with high accuracy compared to existing approaches. It improves upon the existing approaches by approximately 98\% for bursty traffic variations. Our algorithm has fast convergence and achieves low E2E delay violations for lower priority slices.