计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (15): 111-114.DOI: 10.3778/j.issn.1002-8331.2009.15.032

• 网络、通信、安全 • 上一篇    下一篇

城域网出口链路VoIP通话时长的建模与预测

陈楠楠1,袁小坊1,2,王 东1,谢高岗2,黄金钗1   

  1. 1.湖南大学 计算机与通信学院,长沙 410082
    2.中国科学院 计算技术研究所 下一代互联网研究中心,北京 100080
  • 收稿日期:2008-03-26 修回日期:2008-06-02 出版日期:2009-05-21 发布日期:2009-05-21
  • 通讯作者: 陈楠楠

VoIP talk time modeling and prediction on output link of metro area network

CHEN Nan-nan1,YUAN Xiao-fang1,2,WANG Dong1,XIE Gao-gang2,HUANG Jin-chai1   

  1. 1.College of Computer and Communication,Hunan University,Changsha 410082,China
    2.Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100080,China
  • Received:2008-03-26 Revised:2008-06-02 Online:2009-05-21 Published:2009-05-21
  • Contact: CHEN Nan-nan

摘要: 基于IP技术的语音分组传输(VoIP)电话业务目前被广泛部署于全国范围内的城域网。通过对某城域出口链路上实际采集的VoIP综合统计数据,针对有季节变动规律的单因素时间序列,推导建立了ARIMA(2,1,2)×(2,1,2)24季节乘积模型,并以此作为预测的基础,进行了该链路VoIP通话时长的预测。实验表明,模型的预测平均误差为8.38%。应用该模型检测将来超越阀值的可能发生时间,可以预先采取措施,保证VoIP的服务质量。

关键词: 城域网, VoIP通话时长, ARIMA季节乘积模型, 预测, 告警

Abstract: IP-based voice packet transmission(VoIP) telephone services are currently being deployed nationwide in MANs.By using VoIP comprehensive statistical data collected with NetTurbo on an ISP WAN link,this paper establishes a model of multiple seasonal autoregressive integrated moving average(ARIMA) (2,1,2)×(2,1,2) 24,and predicts the VoIP talk time on output link of this MAN.Experimentation shows that the average relative error of the model is 8.38%.And using this model to detect the possible time when the VoIP traffic is beyond the threshold,this paper can pre-take measures to ensure the QoS of VoIP.

Key words: metro area network, VoIP talk time, multiple seasonal ARIMA model, prediction, alert