Evaluating Transport Protocols on 5G for Mobile Augmented Reality

TL;DR

This study evaluates the performance of various transport protocols like UDP, TCP, MPEG-TS, RTP, and QUIC in supporting Mobile Augmented Reality over 5G, LTE, and WiFi, highlighting protocol efficiency and impact of signal quality.

Contribution

It provides the first comprehensive comparison of transport protocols for MAR on 5G, revealing their performance characteristics and influence of signal quality in real-world settings.

Findings

TCP has the lowest median round-trip-time on 5G.

QUIC performs better on LTE.

Protocol performance is significantly affected by signal quality.

Abstract

Mobile Augmented Reality (MAR) mixes physical environments with user-interactive virtual annotations. Immersive MAR experiences are supported by computation-intensive tasks which rely on offloading mechanisms to ease device workloads. However, this introduces additional network traffic which in turn influences the motion-to-photon latency (a determinant of user-perceived quality of experience). Therefore, a proper transport protocol is crucial to minimise transmission latency and ensure sufficient throughput to support MAR performance. Relatedly, 5G, a potential MAR supporting technology, is widely believed to be smarter, faster, and more efficient than its predecessors. However, the suitability and performance of existing transport protocols in MAR in the 5G context has not been explored. Therefore, we present an evaluation of popular transport protocols, including UDP, TCP, MPEG-TS, RTP, and QUIC, with a MAR system on a real-world 5G testbed. We also compare with their 5G performance with LTE and WiFi. Our evaluation results indicate that TCP has the lowest round-trip-time on 5G, with a median of $15.09\pm0.26$ ms, while QUIC appears to perform better on LTE. Through an additional test with varying signal quality (specifically, degrading secondary synchronisation signal reference signal received quality), we discover that protocol performance appears to be significantly impacted by signal quality.