| IP骨干网络流量矩阵估计算法研究 |
| |
| 引用本文： | 蒋定德,胡光岷,倪海转. IP骨干网络流量矩阵估计算法研究[J]. 电子科技大学学报(自然科学版), 2010, 39(3): 420-424. DOI: 10.3969/j.issn.1001-0548.2010.03.021 |
| |
| 作者姓名： | 蒋定德 胡光岷 倪海转 |
| |
| 作者单位： | 东北大学信息科学与工程学院,沈阳,110004;电子科技大学宽带光纤传输与通信网技术重点实验室,成都,610054;电子科技大学宽带光纤传输与通信网技术重点实验室,成都,610054;东北大学信息科学与工程学院,沈阳,110004 |
| |
| 基金项目： | 中央高校基本科研业务费专项资金项目 |
| |
| 摘 要： | 流量矩阵估计的高度病态特性，使得要精确地估计流量矩阵变得非常困难，如何克服这一问题的病态特性是当前面临的主要挑战。该文研究大尺度IP骨干网络流量矩阵估计问题，并利用BP神经网络的强大建模功能来捕捉流量矩阵的特征，通过将流量矩阵估计描述成约束条件下的最优化过程，能成功地克服这一问题的病态特性。仿真结果表明基于BP神经网络的估计算法具有明显的性能改善。
|
| 关 键 词： | 病态问题 网络流量 神经网络 流量矩阵估计 |
| 收稿时间： | 2008-11-06 |
Algorithm of Traffic Matrix Estimation in IP Backbone Networks |
| |
| JIANG Ding-de,HU Guang-min,NI Hai-zhuan. Algorithm of Traffic Matrix Estimation in IP Backbone Networks[J]. Journal of University of Electronic Science and Technology of China, 2010, 39(3): 420-424. DOI: 10.3969/j.issn.1001-0548.2010.03.021 |
| |
| Authors: | JIANG Ding-de HU Guang-min NI Hai-zhuan |
| |
| Affiliation: | 1.College of Information Science and Engineering,Northeastern University Shenyang 110004;2.Key Laboratory of Broadband Optical Fiber Transmission and Communication Networks,University of Electronic Science and Technology of China,Chengdu 610054 |
| |
| Abstract: | Traffic matrix estimation is significantly difficult because it is a highly ill-posed problem. How to overcome the ill-posed nature of this problem is the main challenge faced at present. This paper studies the large-scale IP (Internet Protocol) traffic matrix estimation and uses backpropagation neural network to capture the characteristics of traffic matrix. By describing traffic matrix estimation into an optimal process under the constraints, ill-posed nature of this problem can successfully be avoided. Simulation results show that the estimation algorithm based on backpropagation neural network brings the evident performance improvement. |
| |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《电子科技大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《电子科技大学学报(自然科学版)》下载全文 |
