Approach of Traffic Matrix Estimation in Large-scale IP Backbone Networks

JIANG Ding-de; WANG Xing-wei; GUO Lei; Xu Zheng-zheng; CHEN Zhen-hua

您当前的位置：

首页 >

文章列表页 >

Approach of Traffic Matrix Estimation in Large-scale IP Backbone Networks

更新时间：2025-07-16

- Approach of Traffic Matrix Estimation in Large-scale IP Backbone Networks
- Acta Electronica Sinica Vol. 39, Issue 4, Pages: 763-771(2011)
- 作者机构：
  
  1. 东北大学信息科学与工程学院,辽宁,沈阳,110004
  2. 电子科技大学宽带光纤传输与通信网技术重点实验室,四川,成都,610054
  3. 东北大学信息科学与工程学院辽宁沈阳,110004
  4. 电子科技大学宽带光纤传输与通信网技术重点实验室四川成都,610054
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP393
- Published：2011
- 稿件说明：
移动端阅览
JIANG Ding-de, WANG Xing-wei, GUO Lei, et al. Approach of Traffic Matrix Estimation in Large-scale IP Backbone Networks[J]. Acta Electronica Sinica, 2011, 39(4): 763-771.
DOI：

JIANG Ding-de, WANG Xing-wei, GUO Lei, et al. Approach of Traffic Matrix Estimation in Large-scale IP Backbone Networks[J]. Acta Electronica Sinica, 2011, 39(4): 763-771. DOI：

摘要

流量矩阵估计是当前的热点研究问题

它被网络操作员用来进行负载均衡、路由最优化、流量侦测、网络规划等等.然而

流量矩阵估计本身固有的高度病态特性

使得精确地估计流量矩阵成为具有挑战性的研究课题.本文研究大尺度IP骨干网络的流量矩阵估计;基于RBF(Radial Basis Function)神经网络

提出一种新的估计方法TMRI(Traffic Matrix Recurrence Inference).TMRI利用RBF神经网络强大的建模功能来建模流量矩阵估计问题

将这一问题的病态特性克服于RBF神经网络的训练过程中

从而避免复杂的数学建模过程.并在所建立的估计模型基础上

将流量矩阵估计描述为约束条件下的最优化过程

通过迭代寻优

TMRI能进一步克服这一问题的病态特性.仿真结果表明TMRI能精确地估计流量矩阵和追踪它的动态变化

与以前的方法相比

具有更强的抗噪声性能和显著的性能改善.

Abstract

Traffic matrix estimation is an interesting research problem at present.Network operators use it to conduct load balancing

route optimization

traffic detecting

network dimensioning and so on.However

the highly ill-pose nature of traffic matrix estimation itself makes it being a challenging research subject to estimate accurately traffic matrix.This paper studies traffic matrix estimation in large-scale IP backbone networks.Based on RBF (radial basis function) neural network

a novel estimation method

namely TMRI (traffic matrix recurrence inference)

is proposed.TMRI exploits the powerful modeling ability of RBF neural network to model traffic matrix estimation.The ill-pose nature of this problem will be overcome in the process of training the RBF neural network.Accordingly

the complex process of mathematic modeling can be avoided.Built on this estimation model

traffic matrix estimation is described into the optimal process under the constraints.By seeking the recurrent optimal solution

TMRI can further get rid of the ill-pose nature of this problem.Simulation results show that TMRI can accurately estimate traffic matrix and track its dynamics

and in contrast to previous methods

it holds the stronger robustness to noise and more evident performance improvement.

关键词

Keywords

references

Views

2239

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An Optimal Transformation of Basic Probability Assignment to Probability

Autonomous Learning Path Selection Scheme for Concurrent Multipath Transfer

Study of Dual Linear Programming Neural Networks and Selection of Its Learning Rate

A 2-D Neural Network Model with the Applications

Sibelobe Reduction of Plane Array Using Genetic Algorithm

Related Author

DENG Yong

HAN De-qiang

XU Pei-da

ZHANG Si-dong

YAN Huan

SONG Fei

LIU Chang

BAO Zheng

Related Institution

School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University

Institute of Integrated Automation,Xi’an Jiaotong University

College of Computer and Information Sciences,Southwest University

School of ElectronicInformation and Electrical EngineeringShanghai Jiaotong UniversityShanghai 200240China

Institute of Integrated AutomationXi’an Jiaotong UniversityXi’anShaanxi 710049China

⁰