因特网流量矩阵的流形结构

钱叶魁; 陈鸣

doi:10.3724/SP.J.1146.2010.00130

因特网流量矩阵的流形结构

doi: 10.3724/SP.J.1146.2010.00130

钱叶魁^{①② 陈鸣,},
陈鸣

基金项目:

国家自然科学基金重大研究计划(90304016)，国家863计划项目(2007AA01Z418)和江苏省自然科学基金(BK2009058)资助课题

计量
- 文章访问数: 3687
- HTML全文浏览量: 94
- PDF下载量: 1075
- 被引次数: 0
出版历程
- 收稿日期: 2010-02-02
- 修回日期: 2010-06-14
- 刊出日期: 2010-12-19

On the Manifold Structure of Internet Traffic Matrix

Qian Ye-Kui^{①② 陈鸣
,},
Chen Ming

摘要

摘要: 当前，流量矩阵已经被广泛应用于异常检测、流量预测、流量工程等领域，但是现有研究仅仅发现流量矩阵存在线性结构。为了寻找流量矩阵中可能存在的非线性结构，构建流量矩阵模型并从实际因特网骨干网Abilene中采集流量矩阵数据集，应用经典的流形学习算法进行实测数据分析，发现这些高维(81维或121维)的流量矩阵数据集实际上是嵌入的固有维度为5维的低维流形，且其受采样密度和噪声数据等各种因素的影响呈现出不同的结构。
- 网络流量分析 /
- 流量矩阵 /
- 流形学习 /
- 非线性降维 /
- 流形结构
Abstract: Currently, traffic matrices have been applied to anomaly detection, traffic forecasting and traffic engineering widely, but existing researches only find the linear structure of traffic matrix. In order to search the nonlinear structure of traffic matrix, a traffic matrix model is constructed and traffic matrix datasets are collected from real Internet backbone Abilene. Using classical manifold learning algorithms, based on measurement data from Abilene find that these traffic matrix datasets with high dimensionality (81 or 121 dimensions) have a intrinsic dimensionality of 5 and have all kinds of manifold structures in low-dimension embedding space, influenced by sampling density and noise data.
- Network traffic analysis /
- Traffic matrix /
- Manifold learning /
- Nonlinear dimensionality reduction /
- Manifold structure

HTML全文

参考文献(1)

Leland W, Taqqu M, and Weland W, et al.. On the self-similar nature of ethernet traffic (Extended version)[J].IEEE/ACM Transactions on Networking.1994, 2(3):1-15[2]Paxson V and Floyd S. Wide-area traffic: the failure of poisson modeling[J].IEEE/ACM Transactions on Networking.1995, 3(2):226-244[3]Uhlig S, Quoitin B, and Lepropre J, et al.. Providing public intradomain traffic matrices to the research community. ACM SIGCOMM Computer Communication Review, 2006, 36(3): 156-167.[4]Lakhina A, Crovella M, and Diot C. Diagnosing network-wide traffic anomalies. SIGCOMM, Portland, Oregon, USA, 2004: 224-235.[5]Rubinstein B I P, Nelson B, and Huang L. Stealthy Poisoning Attacks on PCA-based Anomaly Detectors. SIGMETRICS, 2009: 168-179.Rubinstein B I P, Nelson B, and Huang L, et al.. Compromising PCA-based anomaly detectors for network- wide traffic. Technical Report UCB/EECS-2008-73, 2009.[6]Vardi V. Network tomography: estimating source-destination traffic intensities from link data[J].Journal of the American Statistical Association.1996, 91(6):365-377[7]Lakhina A, papagiannaki K, and Crovella M, et al.. Structural analysis of network traffic flows. SIGMETRICS, New York, NY, USA, 2004: 345-356.[8]Zhang Y, Roughan M, and Willinger W, et al.. Spatio- temporal compressive sensing and Internet traffic matrices. SIGCOMM, Barcelona, Spain, 2009: 110-121.[9]Xu K, Zhang Z L, and Bhattacharyya S. Internet traffic behavior profiling for network security monitoring[J].IEEE/ACM Transactions on Networking.2008, 16(4):1241-1252[10]Tenenbaum J B, Silva V D, and Langford J C. A global geometric framework for nonlinear dimensionality reduction[J].Science.2000, 290(12):2319-2323[11]Roweis S T and Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J].Science.2000, 290(12):2323-2325[12]Gerber S, Tasdizen T, and Joshi S, et al.. On the manifold structure of the space of brain images. MICCAI, USA, 2009: 263-268.[13]邵超, 黄厚宽, 赵连伟. 一种更具拓扑稳定性的ISOMAP算法. 软件学报, 2007, 18(3): 869-877.[14]文贵华, 陆庭辉, 江丽君. 基于相对流形的局部线性嵌入. 软件学报, 2009, 20(6): 2376-2386.

施引文献

资源附件(0)

访问统计