基于WP-MLP神经网络的VoIP自适应抖动缓冲算法  

VoIP Adaptive Jitter Buffer Algorithm Based on WP-MLP Neural Network

作　　者：李云峰 LI Yun-feng(Civil Aviation Air Traffic Management Bureau of Ning Xia Branch,Yinchuan 750001,China)

机构地区：[1]中国民用航空西北地区空中交通管理局宁夏分局,宁夏银川750001

出　　处：《中国电子科学研究院学报》2024年第6期546-551,共6页Journal of China Academy of Electronics and Information Technology

摘　　要：为解决抖动缓冲区播放延时和丢包之间的矛盾,实现缓冲区的动态调整使延时和丢包达到最优的平衡,提出一种基于WP-MLP神经网络的自适应抖动缓冲算法。首先,对抖动缓冲区的基本原理进行了分析并给出了丢包率与缓冲延时之间的函数关系;其次,提出了WP-MLP神经网络抖动缓冲算法的网络模型并对算法流程进行了分析;最后,通过VoIP网络仿真进行建模对比几种常用抖动缓冲算法,结果表明,本文所提算法能够在播放延时和丢包率之间保持更好的平衡,对缓冲区大小的动态调节表现出更优异的性能。In order to solve the contradiction between the playout delay and packet loss of the jitter buffer,and realize the dynamic adjustment of the buffer to achieve the optimal balance between delay and packet loss,an adaptive jitter buffer based on WP-MLP neural network algorithm is proposed.First,the basic princi-ple of the jitter buffer is analyzed and the functional relationship between the packet loss rate and the buffer delay is given;second,the network model of the WP-MLP neural network jitter buffer algorithm is proposed and the algorithm flow is analysis;Finally,modeling and comparing several commonly used jitter buffer algo-rithms through VoIP network simulation,the results show that the algorithm proposed in this paper can main-tain a better balance between playout delay and packet loss rate,and dynamic adjustment of buffer size shows better performance.

关 键 词：神经网络 播出延迟 小波包 VOIP 多层感知器 自适应抖动缓冲 

分 类 号：TN919.5[电子电信—通信与信息系统]