北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (5): 115-120.

• 研究报告 • 上一篇    下一篇

一种基于无线网络场景的自适应比特率算法模型

陈峻磊,刘凯俊,董辰,周虹媛   

  1. 北京邮电大学 信息与通信工程学院
  • 收稿日期:2021-10-05 修回日期:2021-11-27 出版日期:2022-10-28 发布日期:2022-11-01
  • 通讯作者: 董辰 E-mail:dongchen@bupt.edu.cn
  • 基金资助:
    北京邮电大学基本科研业务费

An Adaptive Bit Rate Algorithm Model Based on Wireless Network

CHEN Chunlei, LIU Kaijun, DONG Chen, ZHOU Hongyuan #br#   

  • Received:2021-10-05 Revised:2021-11-27 Online:2022-10-28 Published:2022-11-01

摘要: 为了适应剧烈变化的网络波动与长尾问题,提出了基于深度学习的自适应比特率算法模型,该算法以视频码率码率切换频率视频暂停时间为优化对象,可以更加适应网络波动随机性与对比模型相比,所提模型在无线网络的大尺度波动的场景下具有更优越的性能在最差的网络条件下,对比模型造成视频播放卡顿的概率高达16% ,而所提模型的卡顿概率仅为 1% ,且平均体验质量指标比对比模型高了 30% 。

关键词: 强化学习, 无线网络, 自适应比特率

Abstract: To solve the problem of drastically changing network fluctuation and long tail, an adaptive bit rate algorithm model based on deep learning is proposed. The algorithm optimizes video bit rate, bit rate switching frequency, and video pause time, and it is robust to the randomness of network fluctuations. Compared with other models, the proposed model has better performance in the scenario of drastic fluctuations in wireless networks. Under the worst network conditions, the comparison model causes video playback lag with a probability as high as 16% , while the proposed model has a lag probability of only 1% , and the average quality of experience index is 30% higher than that of the comparative model.

Key words: reinforcement learning, mobile wireless network, adaptive bit rate

中图分类号: