Real-time Extended Reality Video Transmission Optimization Based on Frame-priority Scheduling

TL;DR

This paper introduces a frame-priority scheduling scheme using deep reinforcement learning to optimize real-time XR video transmission over 5G, significantly enhancing transmission quality.

Contribution

It presents a novel resource allocation method based on frame-priority scheduling with MS-DQN and CNN, tailored for low-latency, high-data-rate XR video transmission in 5G networks.

Findings

Improves transmission quality by up to 80.2%.

Demonstrates effectiveness of deep reinforcement learning in resource scheduling.

Provides a framework suitable for real-time XR applications.

Abstract

Extended reality (XR) is one of the most important applications of 5G. For real-time XR video transmission in 5G networks, a low latency and high data rate are required. In this paper, we propose a resource allocation scheme based on frame-priority scheduling to meet these requirements. The optimization problem is modelled as a frame-priority-based radio resource scheduling problem to improve transmission quality. We propose a scheduling framework based on multi-step Deep Q-network (MS-DQN) and design a neural network model based on convolutional neural network (CNN). Simulation results show that the scheduling framework based on frame-priority and MS-DQN can improve transmission quality by 49.9%-80.2%.