强化学习驱动的MP-QUIC移动流媒体传输优化方法
An Reinforcement-learning driven mobile streaming methodology based on Multipath QUIC
马丁 1王目 1郭鹏 1刘懿晟 1黄子聪1
作者信息
- 1. 北京邮电大学网络与交换技术国家重点实验室，北京 100876
- 折叠
摘要
目前,使用智能手机或其他移动终端来流式传输直播内容变得越来越流行。本文提出了一种基于多路径QUIC（MP-QUIC）的新型强化学习驱动解决方案。通过MPQUIC来充分利用WiFi和蜂窝网络的带宽,最大限度地提高流媒体容量。为了应对移动环境的高动态性,本文结合了部分可靠性和分层编码方案,能够在适应不同的带宽的同时最大限度地减少重传。此外,为了在多个路径上对齐数据传输并优化流媒体比特率,本文将问题建模为随机优化任务,并使用强化学习方法实现其解决方案。大量的实验表明,所提出的方法在比特率、丢包和延迟方面优于最先进的解决方案。Abstract
Currently, applying smartphone or other mobile device to stream the live content becomes increasingly popular. This paper proposes a novel reinforcement learning-driven solution based on multipath QUIC (MP-QUIC). It maximizes streaming capacity by fully utilizing the bandwidth of both WiFi and cellular networks through MPQUIC. To address the high dynamics of mobile environments, it incorporates partial reliability and a layered coding scheme, enabling adaptation to varying bandwidth conditions while minimizing retransmissions. Furthermore, to align data delivery across multiple paths and optimize streaming bitrate, we formulate the problem as a stochastic optimization task and demonstrate its solution using reinforcement learning methods. Extensive experiments demonstrate that the method outperforms state-of-the-art solutions in terms of bitrate, packet loss, and delay. 关键词
计算机科学/强化学习/多路径QUIC/直播/部分可靠性/随机优化Key words
Computer Science/Reinforcement Learning/Multipath QUIC/Live Streaming/Partial Reliability/Stochastic Optimization引用本文复制引用
马丁,王目,郭鹏,刘懿晟,黄子聪.强化学习驱动的MP-QUIC移动流媒体传输优化方法[EB/OL].(2025-05-13)[2025-12-14].http://www.paper.edu.cn/releasepaper/content/202505-41.学科分类
计算技术、计算机技术
评论