Temporal Characterization of XR Traffic with Application to Predictive Network Slicing

TL;DR

This paper analyzes XR traffic patterns to improve network slicing by proposing prediction models for frame sizes, addressing the unpredictability caused by fluctuations even in CBR encoding, based on real-world data.

Contribution

It provides the first detailed temporal characterization of XR streams with CBR encoding and introduces effective prediction models applicable across various contents and traces.

Findings

Significant frame size fluctuations occur even with CBR mode.

Proposed models achieve consistent prediction performance across different traces.

Trade-off identified between network efficiency and XR QoS.

Abstract

Over the past few years, eXtended Reality (XR) has attracted increasing interest thanks to its extensive industrial and commercial applications, and its popularity is expected to rise exponentially over the next decade. However, the stringent Quality of Service (QoS) constraints imposed by XR's interactive nature require Network Slicing (NS) solutions to support its use over wireless connections: in this context, quasi-Constant Bit Rate (CBR) encoding is a promising solution, as it can increase the predictability of the stream, making the network resource allocation easier. However, traffic characterization of XR streams is still a largely unexplored subject, particularly with this encoding. In this work, we characterize XR streams from more than 4 hours of traces captured in a real setup, analyzing their temporal correlation and proposing two prediction models for future frame size. Our results show that even the state-of-the-art H.264 CBR mode can have significant frame size fluctuations, which can impact the NS optimization. Our proposed prediction models can be applied to different traces, and even to different contents, achieving very similar performance. We also show the trade-off between network resource efficiency and XR QoS in a simple NS use case.