[1]吴桦,丁伟.基于奇异谱方法的网络行为分析[J].东南大学学报(自然科学版),2002,32(6):889-894.[doi:10.3969/j.issn.1001-0505.2002.06.014]
 Wu Hua,Ding Wei.Study of network behavior based on singular-spectrum analysis[J].Journal of Southeast University (Natural Science Edition),2002,32(6):889-894.[doi:10.3969/j.issn.1001-0505.2002.06.014]
点击复制

基于奇异谱方法的网络行为分析()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
32
期数:
2002年第6期
页码:
889-894
栏目:
计算机科学与工程
出版日期:
2002-11-20

文章信息/Info

Title:
Study of network behavior based on singular-spectrum analysis
作者:
吴桦 丁伟
东南大学计算机科学与工程系,南京 210096
Author(s):
Wu Hua Ding Wei
Department of Computer Science and Engineering, Southeast University, Nanjing 210096, China
关键词:
网络测量 网络行为 性能分析 奇异谱分析
Keywords:
network measurement network behavior performance analysis singular-spectrum analysis
分类号:
TP393.07
DOI:
10.3969/j.issn.1001-0505.2002.06.014
摘要:
运用数字信号处理中的奇异谱分析方法,讨论了如何提取网络流量的周期和趋势特征,并结合最大熵谱方法对吞吐量趋势做出预测.将该方法运用于中国教育和科研网CERNET华东(北)地区网的主干网,分析了若干天的网络流量行为特征,分析结果与使用情况相吻合.对主干的流量进行了预测,并将预测结果与实际情况做了比较.定义了评价预测准确性的公式,将预测的准确性与国际上具有代表性的成果进行多方面的比较,结果说明该方法准确性较好.
Abstract:
A method borrowed from digital signal processing is applied to identify and retrieve low-frequency variability and trend components from history metrics. Combined with maximum entropy method, predictions of network throughput can be made. This arithmetic was applied to the backbone throughput of China Education and Research Network Eastern China(North)Regional network, and the results were consistent with the practice. Predictions of the backbone throughput were made and the results were compared with the practice. A function which can evaluate the veracity of prediction results is defined, the veracity of this arithmetic is compared with the results of other international research communities. It is shown that this arithmetic has a better veracity.

参考文献/References:

[1] Wolski Rich.Forecasting network performance to support dynamic scheduling using the network weather service [DB/OL].http://citeseer.nj.nec.com/wolski98dynamically.html.1998-01-07/2002-10-10.
[2] Basu S,Mukherjee A.Time series models for internet traffic[A].In: Proc IEEE INFOCOM’96[C].San Francisco,CA,1996,2.611-620.
[3] Groschwitz N,Polyzos G.A time series model of long-term traffic on the NSFnet backbone[A].In:Proceedings of the IEEE International Conference on Communications(ICC’94)[C].New Orleans,LA,1994.1400-1404.
[4] 徐科,徐金梧,班晓娟.基于小波分解的某些非平稳时间序列预测方法[J].电子学报,2001,29(4):566-568.
  Xu Ke,Xu Jinwu,Ban Xiaojuan.Forecasting of some non-stationary time series based on wavelet decomposition[J].Acat Electronica Sinica,2001,29(4):566-568.(in Chinese)
[5] Vautard.SSA:a toolkit for noisy chaotic signals[J]. Physica D,1992,58:95-126.
[6] Burg J P.Maximum entropy spectral analysis[A].In:Childers D G,ed.Modern spectral Analysis[C].New York:IEEE Press,1978.34-41.
[7] Wolski Rich.Dynamically forecasting network performance using the network weather service[J].Journal of Cluster Computing,1998,1:119-132.

相似文献/References:

[1]王婷,宋俊德,宋美娜.一种基于关联规则挖掘的IP定位方法[J].东南大学学报(自然科学版),2015,45(4):657.[doi:10.3969/j.issn.1001-0505.2015.04.008]
 Wang Ting,Song Junde,Song Meina.Method for IP geolocation based on association rule mining[J].Journal of Southeast University (Natural Science Edition),2015,45(6):657.[doi:10.3969/j.issn.1001-0505.2015.04.008]

备注/Memo

备注/Memo:
基金项目: 国家863资助项目(2001AA112060)、国家自然科学基金重点课题资助项目(90104031).
作者简介: 吴桦(1973—),女,硕士,助教; 丁伟(联系人),女,博士,教授.
更新日期/Last Update: 2002-11-20