Tuning Self-Similar Traffic to Improve Loss Performance in Small Buffer Routers

被引:0
|
作者
Zang, Yongfei [1 ]
Yan, Jinyao [2 ]
机构
[1] Commun Univ China, Informat Engn Sch, Beijing 100024, Peoples R China
[2] ETH, Comp Engn & Networks Lab, CH-8092 Zurich, Switzerland
来源
PROCEEDINGS OF THE TENTH INTERNATIONAL CONFERENCE ON NETWORKS (ICN 2011) | 2011年
基金
瑞士国家科学基金会;
关键词
buffer size; TCP; self-similarity; traffic smoothing;
D O I
暂无
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
The issue of router buffer sizing is an important research problem and is still open though researchers have debated this for many years. The research method can be classified into two kinds: one is based on queuing theory, the other uses TCP as model. From the point of TCP model, many researchers concluded that buffer size can be significantly reduced. It's desirable that the buffers are so small that fast memory technology and all-optical buffering can be used. But queuing model with self-similar incoming traffic suggested that extremely large buffers are needed to achieve acceptable packet loss rate. In this paper, we will first exam the performance of non-TCP and self-similar traffic with small router buffers, and then address the question how to improve the packet loss rate performance for self-similar traffic. Through a combination of simulation and analysis, we found that packet arrivals' burstiness has a significant influence on loss rate performance. We further point out a simple and effective approach, which smoothes the packet injections to the network, to improve the performance of small buffers at Internet core router for self-similar traffic.
引用
收藏
页码:105 / 108
页数:4
相关论文
共 50 条
  • [21] Performance modelling of generalized processor sharing systems with multiple self-similar traffic flows
    Jin, Xiaolong
    Min, Geyong
    TELECOMMUNICATION SYSTEMS, 2008, 38 (3-4) : 111 - 120
  • [22] Performance modelling of generalized processor sharing systems with multiple self-similar traffic flows
    Xiaolong Jin
    Geyong Min
    Telecommunication Systems, 2008, 38 : 111 - 120
  • [23] Network Self-Similar Traffic Generator with Variable Hurst Parameter
    Savu-Jivanov, Adrian
    Isar, Alexandru
    Stolojescu-Crisan, Cristina
    Gal, Janos
    2020 14TH INTERNATIONAL SYMPOSIUM ON ELECTRONICS AND TELECOMMUNICATIONS (ISETC), 2020, : 359 - 362
  • [24] A new analytic queuing model with self-similar input traffic
    Su, Gongchao
    Lin, Xiaohui
    Wang, Hui
    DCABES 2007 PROCEEDINGS, VOLS I AND II, 2007, : 298 - 300
  • [25] A Simple Estimator of the Hurst Exponent for Self-Similar Traffic Flows
    Millan, G.
    Juan, E. S.
    Jamett, M.
    IEEE LATIN AMERICA TRANSACTIONS, 2014, 12 (08) : 1349 - 1354
  • [26] Hurst Parameter Transition Detection on Self-Similar Network Traffic
    Ledesma, Sergio
    Torres, Miguel
    Avina, Gabriel
    Hernandez, Donato
    Cerda, Gustavo
    WMSCI 2008: 12TH WORLD MULTI-CONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL III, PROCEEDINGS, 2008, : 71 - 76
  • [27] A Combined Forecasting Model for Satellite Network Self-Similar Traffic
    Bie, Yuxia
    Wang, Longzi
    Tian, Ye
    Hu, Zhi
    IEEE ACCESS, 2019, 7 : 152004 - 152013
  • [28] A structure-preserving method of sampling self-similar traffic
    Elbiaze, H
    Cherkaoui, O
    McGibbon, B
    Blais, M
    MASCOTS 2005:13TH IEEE INTERNATIONAL SYMPOSIUM ON MODELING, ANALYSIS, AND SIMULATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS, 2005, : 161 - 168
  • [29] Self-similar characteristic of traffic in current metro area network
    zhang, Guangxing
    xie, Gaogang
    Yang, Jianhua
    Zhang, Dunxing
    Mang, Dafang
    2007 15TH IEEE WORKSHOP ON LOCAL & METROPOLITAN AREA NETWORKS, 2007, : 13 - +
  • [30] The Locality Phenomenon in the Analysis of Self-Similar Network Traffic Flows
    Millan, G.
    Chait, M.
    Lefranc, G.
    2016 IEEE INTERNATIONAL CONFERENCE ON AUTOMATICA (ICA-ACCA), 2016,