Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Quality of Experience Optimization for Real-time XR Video Transmission with Energy Constraints

Guangjin Pan, Shugong Xu, Shunqing Zhang, Xiaojing Chen, Yanzan Sun

TL;DR

This work addresses real-time XR video transmission over wireless networks under long-term energy constraints by introducing a frame-by-frame QoE model and formulating a QoE-maximization problem. It combines Lyapunov optimization to convert the long-horizon problem into a per-frame objective and an LSTM-DQN-based bitrate controller, with an analytical solution for the channel allocation subproblem. The approach yields QoE improvements up to $0.46$ in simulations and $0.42$ in real-system traces, while also reducing bitrate variations and maintaining high frame transmission success rates. The results demonstrate energy-aware, low-latency XR streaming viability in 5G/6G-like networks and offer a practical framework for adaptive bitrate and wireless resource management in XR deployments.

Abstract

Extended Reality (XR) is an important service in the 5G network and in future 6G networks. In contrast to traditional video on demand services, real-time XR video is transmitted frame-by-frame, requiring low latency and being highly sensitive to network fluctuations. In this paper, we model the quality of experience (QoE) for real-time XR video transmission on a frame-by-frame basis. Based on the proposed QoE model, we formulate an optimization problem that maximizes QoE with constraints on wireless resources and long-term energy consumption. We utilize Lyapunov optimization to transform the original problem into a single-frame optimization problem and then allocate wireless subchannels. We propose an adaptive XR video bitrate algorithm that employs a Long Short Term Memory (LSTM) based Deep Q-Network (DQN) algorithm for video bitrate selection. Through numerical results, we show that our proposed algorithm outperforms the baseline algorithms, with the average QoE improvements of 0.04 to 0.46. Specifically, compared to baseline algorithms, the proposed algorithm reduces average video quality variations by 29% to 50% and improves the frame transmission success rate by 5% to 48%.

Quality of Experience Optimization for Real-time XR Video Transmission with Energy Constraints

TL;DR

This work addresses real-time XR video transmission over wireless networks under long-term energy constraints by introducing a frame-by-frame QoE model and formulating a QoE-maximization problem. It combines Lyapunov optimization to convert the long-horizon problem into a per-frame objective and an LSTM-DQN-based bitrate controller, with an analytical solution for the channel allocation subproblem. The approach yields QoE improvements up to in simulations and in real-system traces, while also reducing bitrate variations and maintaining high frame transmission success rates. The results demonstrate energy-aware, low-latency XR streaming viability in 5G/6G-like networks and offer a practical framework for adaptive bitrate and wireless resource management in XR deployments.

Abstract

Extended Reality (XR) is an important service in the 5G network and in future 6G networks. In contrast to traditional video on demand services, real-time XR video is transmitted frame-by-frame, requiring low latency and being highly sensitive to network fluctuations. In this paper, we model the quality of experience (QoE) for real-time XR video transmission on a frame-by-frame basis. Based on the proposed QoE model, we formulate an optimization problem that maximizes QoE with constraints on wireless resources and long-term energy consumption. We utilize Lyapunov optimization to transform the original problem into a single-frame optimization problem and then allocate wireless subchannels. We propose an adaptive XR video bitrate algorithm that employs a Long Short Term Memory (LSTM) based Deep Q-Network (DQN) algorithm for video bitrate selection. Through numerical results, we show that our proposed algorithm outperforms the baseline algorithms, with the average QoE improvements of 0.04 to 0.46. Specifically, compared to baseline algorithms, the proposed algorithm reduces average video quality variations by 29% to 50% and improves the frame transmission success rate by 5% to 48%.
Paper Structure (17 sections, 16 equations, 5 figures, 1 table)

This paper contains 17 sections, 16 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. System model
  3. Transmission Model
  4. Real-time XR Video Streaming and QoE Model
  5. Problem Formulation
  6. Lyapunov-guided DQN algorithm
  7. Problem Transformation via Lyapunov Optimization
  8. Solution for Channel Allocation Subproblem
  9. Solution for Adaptive Video Streaming
  10. State
  11. Action
  12. Reward
  13. Numerical Results
  14. Selection of Observation Window Size
  15. Performance Comparison
  16. ...and 2 more sections

Figures (5)

  • Figure 1: System architecture for adaptive real-time XR video streaming.
  • Figure 2: Comparison of the average QoE under different observation window sizes.
  • Figure 3: Comparison of average QoE, average quality, average quality variation, and frame transmission success rate between different algorithms in a simulation environment.
  • Figure 4: Comparison of average QoE, average quality, average quality variation, and frame transmission success rate between different algorithms in the real system environment. The data traces are collected from the OAI system.
  • Figure 5: Average QoE of our proposed algorithm under different energy constraints and subchannel constraints.