作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (24): 262-265. doi: 10.3969/j.issn.1000-3428.2012.24.062

• 开发研究与设计技术 • 上一篇    下一篇

基于核密度估计的可变码率视频流量预测算法

吴俊琦1,倪 宏1,2,李 俊1   

  1. (1. 中国科学技术大学自动化系,合肥 230027;2. 中国科学院声学研究所国家网络新媒体工程技术研究中心,北京 100180)
  • 收稿日期:2012-03-29 修回日期:2012-04-26 出版日期:2012-12-20 发布日期:2012-12-18
  • 作者简介:吴俊琦(1986-),男,硕士研究生,主研方向:网络传播与控制;倪 宏,研究员、博士生导师;李 俊,副教授
  • 基金资助:
    中央高校基本科研业务费专项基金资助项目(Wk2100100006)

Prediction Algorithm for VBR Video Traffic Based on Kernel Density Estimation

WU Jun-qi 1, NI Hong 1,2, LI Jun 1   

  1. (1. Department of Automation, University of Science and Technology of China, Hefei 230027, China; 2. National Network New Media Engineering & Technology Research Center, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100180, China)
  • Received:2012-03-29 Revised:2012-04-26 Online:2012-12-20 Published:2012-12-18

摘要: 为解决实时可变码率(VBR)视频在传输中难以准确预测流量的问题,提出一种变带宽核密度估计算法。该算法以核密度估计算法为基础,针对VBR视频的场景切换特性动态改变各样本点的带宽,加快算法收敛速度。仿真结果表明,与变步长归一化最小均方法相比,该算法能够减少10%左右的预测误差,保证流量预测具有较高的预测精度。

关键词: 动态带宽分配, 可变码率, MPEG-4视频, 实时预测, 变带宽核密度估计

Abstract: In order to reduce the difficulty of predicting the real-time Variable Bit Rate(VBR) video traffic, this paper proposes a novel algorithm called VBKDE(Variable Bandwidth Kernel Density Estimation). The algorithm is based on kernel density estimation. It dynamically updates the bandwidth of every sample when the scene change happens so as to accelerate the convergence. Simulation results show that, compared with variable step size normalized least mean square, the algorithm can reduce prediction errors by 10%.

Key words: dynamic bandwidth allocation, Variable Bit Rate(VBR), MPEG-4 video, real-time prediction, Variable Bandwidth Kernel Density Estimation(VBKDE)

中图分类号: