Adaptive Context-Aware Multi-Path Transmission Control for VR/AR Content: A Deep Reinforcement Learning Approach

2024-12-27

AI Summary

To address inflexible path selection, low bandwidth utilization, and high stalling rates in multi-path transmission of VR/AR streaming over dynamic heterogeneous networks, this paper proposes the Adaptive Context-Aware Multi-Path Transmission Control Protocol (ACMPTCP). ACMPTCP innovatively integrates Deep Reinforcement Learning (DRL) into the MPTCP path decision framework for the first time, enabling end-to-end network-state-aware real-time path re-alignment and dynamic bandwidth allocation. By jointly modeling network dynamics and optimizing transmission policies online, ACMPTCP achieves significant performance gains in realistic hybrid network testbeds: end-to-end latency is reduced by 37%, stall rate decreases by 52%, and bandwidth utilization exceeds 91%. These improvements effectively meet the stringent high-bandwidth and ultra-low-latency requirements of immersive VR/AR streaming applications.

Technology Category

• Machine Learning: Hardware-aware ML
• Multiagent Systems: Multiagent Learning
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper introduces the Adaptive Context-Aware Multi-Path Transmission Control Protocol (ACMPTCP), an efficient approach designed to optimize the performance of Multi-Path Transmission Control Protocol (MPTCP) for data-intensive applications such as augmented and virtual reality (AR/VR) streaming. ACMPTCP addresses the limitations of conventional MPTCP by leveraging deep reinforcement learning (DRL) for agile end-to-end path management and optimal bandwidth allocation, facilitating path realignment across diverse network environments.

Problem

• Virtual Reality
• Augmented Reality
• Network Efficiency

Innovation

• ACMPTCP
• Deep Reinforcement Learning
• MPTCP Optimization