搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

一种基于相关分析的局域最小二乘支持向量机小尺度网络流量预测算法

唐舟进 彭涛 王文博

引用本文:
Citation:

一种基于相关分析的局域最小二乘支持向量机小尺度网络流量预测算法

唐舟进, 彭涛, 王文博

A local least square support vector machine prediction algorithm of small scale network traffic based on correlation analysis

Tang Zhou-Jin, Peng Tao, Wang Wen-Bo
PDF
导出引用
  • 本文分析了网络流量数据的特性,针对传统预测算法在预测网络流量时的缺陷提出了一种基于相关分析的相关局域最小二乘支持向量机(LSSVM)预测算法. 算法在对训练数据重构相空间后,利用相关分析同时从距离相关和时间相关的训练样本中选择最优的训练子集,结合自适应参数优化的LSSVM预测模型对小尺度网络流量进行预测. 通过选用实际情况下的网络流量数据对算法进行测试验证,结果显示本文所提算法不仅优于传统的全局预测算法,同时也优于各种改进的局域预测算法. 算法不仅在预测精度上取得大幅的性能提升,同时能够通过留一交叉验证法在预测之前就完成预测模型和训练子集的优化.
    Real-time monitoring and forecasting technology for network traffic has played an important role in network management. Effective network traffic prediction could analyze and solve problems before overload occurs, which significantly improves network availability. In this paper, after the vulnerability of traditional nonlinear prediction method in forecasting modeling is analyzed, the relevant local (RL) forecast which is based on correlation analysis and the parameter optimization method based on pattern search (PS) is introduced. Using the correlation analysis, the optimal training subset is chosen from time-and distance-correlated training samples. On this basis, the prediction model is established by LSSVM. Finally network traffic dataset collected from wired campus networks is studied for our experiments. And the results show that the relevant local LSSVM prediction method whose training set and parameters have been automatically optimized can effectively predict the small scale traffic measurement data, and RL-LSSVM traffic forecasting algorithm exhibits significantly good prediction accuracy for the data set compared with previous algorithm.
    • 基金项目: 国防科技预研项目(批准号:208010201)资助的课题.
    • Funds: Project supported by the Chinese Defence Advance Research Program of Science and Technology, China (Grant No. 208010201).
    [1]

    Man C T, Wong S C, Jian M X, Zhan R G, Peng Z 2009 IEEE Trans. on Int. Trans. Sys. 10 60

    [2]

    Marco L, Matteo B, Paolo F 2013 IEEE Trans. on Int. Trans. Sys. 2 871

    [3]

    Ana M, Rivalino M, Autran M, Paulo R M M, Lucio B A 2011 12th International Conference on Parallel and Distributed Computing, Applications and Technologies Gwangju, Korea, October 20-22, 2011 109

    [4]

    Jun J, Symeon P 2006 Computer Communications 29 1627

    [5]

    Li R, Chen J, Liu Y, Wang Z 2010 The Journal of China Universities of Posts and Telecommunications 17 88

    [6]

    Manoel C, Young S J, Myong K J, Lee D H 2009 Expert Systems with Applications 36 6164

    [7]

    Eleni I V, Matthew G K, John C G 2005 Transportation Research Part C 13 211

    [8]

    Chang H, Lee Y, Yoon B, Baek S 2011 IET Intell. Transo. Syst. 6 292

    [9]

    Tigran T T, Biswajit B, Margaret O M 2012 IEEE Trans. on Int. Trans. Sys. 13 519

    [10]

    Bao R C, Hsiu F T 2009 Expert Systems with Applications 36 6960

    [11]

    Sun H L, Jin Y H, Cui Y D, Cheng S D 2009 Chin. Phys. B 18 4760

    [12]

    Liu X W, Fang X M, Qin Z H, Ye C, Miao X 2011 J. Netw. Syst. Manage 19 427

    [13]

    Bao R C, Hsiu F T 2009 Applied Soft Computing 9 1177

    [14]

    Chen Y H, Yang B, Meng Q F 2012 Applied Soft Computing 12 274

    [15]

    Meng Q F, Chen Y H, Peng Y H 2009 Chin. Phys. B 18 2194

    [16]

    Meng Q F, Chen Y H, Feng Z Q, Wang F L, Chen S S 2013 Acta Phys. Sin. 62 150509 (in Chinese) [孟庆芳, 陈月辉, 冯志全, 王枫林, 陈珊珊 2013 物理学报 62 150509]

    [17]

    Vapnik V N 1999 The Nature of Statistical Learning Theory (2nd Ed.) (New York, Springer)

    [18]

    Sapankevych N I, Sankar R 2009 IEEE Comput. Intell. Mag. 4 24

    [19]

    Wang X D, Ye M Y 2004 Chin. Phys. 13 454

    [20]

    Sun J C, Zhou Y T, Luo J G 2006 Chin. Phys. 15 1208

    [21]

    Liu H, Liu D, Deng L F 2006 Chin. Phys. 15 1196

    [22]

    Tang Z J, Ren F, Peng T, Wang W B 2014 Acta Phys. Sin. 63 050505 (in Chinese) [唐舟进, 任峰, 彭涛, 王文博 2014 物理学报 63 050505]

    [23]

    Farmer J D, Sidorowich J J 1987 Phys. Rev. Lett. 59 845

    [24]

    Jawad N, Keem S Y, Farrukh N, Sieh K T, Syed K A 2011 Applied Soft Computing 11 4774

    [25]

    Cai C Z, Fei J F, Wen Y F, Zhu X J, Xiao T T 2009 Acta Phys. Sin. 58 S008 (in Chinese) [蔡从中, 裴军芳, 温玉锋, 朱星键, 肖婷婷 2009 物理学报 58 S008]

    [26]

    Huang T Y 2008 Chinese Journal Of Computers 31 1200 (in Chinese) [黄天云 2008 计算机学报 31 1200]

    [27]

    Ligang Z, Kin K L, Lean Y 2009 Soft Comput. 13 149

  • [1]

    Man C T, Wong S C, Jian M X, Zhan R G, Peng Z 2009 IEEE Trans. on Int. Trans. Sys. 10 60

    [2]

    Marco L, Matteo B, Paolo F 2013 IEEE Trans. on Int. Trans. Sys. 2 871

    [3]

    Ana M, Rivalino M, Autran M, Paulo R M M, Lucio B A 2011 12th International Conference on Parallel and Distributed Computing, Applications and Technologies Gwangju, Korea, October 20-22, 2011 109

    [4]

    Jun J, Symeon P 2006 Computer Communications 29 1627

    [5]

    Li R, Chen J, Liu Y, Wang Z 2010 The Journal of China Universities of Posts and Telecommunications 17 88

    [6]

    Manoel C, Young S J, Myong K J, Lee D H 2009 Expert Systems with Applications 36 6164

    [7]

    Eleni I V, Matthew G K, John C G 2005 Transportation Research Part C 13 211

    [8]

    Chang H, Lee Y, Yoon B, Baek S 2011 IET Intell. Transo. Syst. 6 292

    [9]

    Tigran T T, Biswajit B, Margaret O M 2012 IEEE Trans. on Int. Trans. Sys. 13 519

    [10]

    Bao R C, Hsiu F T 2009 Expert Systems with Applications 36 6960

    [11]

    Sun H L, Jin Y H, Cui Y D, Cheng S D 2009 Chin. Phys. B 18 4760

    [12]

    Liu X W, Fang X M, Qin Z H, Ye C, Miao X 2011 J. Netw. Syst. Manage 19 427

    [13]

    Bao R C, Hsiu F T 2009 Applied Soft Computing 9 1177

    [14]

    Chen Y H, Yang B, Meng Q F 2012 Applied Soft Computing 12 274

    [15]

    Meng Q F, Chen Y H, Peng Y H 2009 Chin. Phys. B 18 2194

    [16]

    Meng Q F, Chen Y H, Feng Z Q, Wang F L, Chen S S 2013 Acta Phys. Sin. 62 150509 (in Chinese) [孟庆芳, 陈月辉, 冯志全, 王枫林, 陈珊珊 2013 物理学报 62 150509]

    [17]

    Vapnik V N 1999 The Nature of Statistical Learning Theory (2nd Ed.) (New York, Springer)

    [18]

    Sapankevych N I, Sankar R 2009 IEEE Comput. Intell. Mag. 4 24

    [19]

    Wang X D, Ye M Y 2004 Chin. Phys. 13 454

    [20]

    Sun J C, Zhou Y T, Luo J G 2006 Chin. Phys. 15 1208

    [21]

    Liu H, Liu D, Deng L F 2006 Chin. Phys. 15 1196

    [22]

    Tang Z J, Ren F, Peng T, Wang W B 2014 Acta Phys. Sin. 63 050505 (in Chinese) [唐舟进, 任峰, 彭涛, 王文博 2014 物理学报 63 050505]

    [23]

    Farmer J D, Sidorowich J J 1987 Phys. Rev. Lett. 59 845

    [24]

    Jawad N, Keem S Y, Farrukh N, Sieh K T, Syed K A 2011 Applied Soft Computing 11 4774

    [25]

    Cai C Z, Fei J F, Wen Y F, Zhu X J, Xiao T T 2009 Acta Phys. Sin. 58 S008 (in Chinese) [蔡从中, 裴军芳, 温玉锋, 朱星键, 肖婷婷 2009 物理学报 58 S008]

    [26]

    Huang T Y 2008 Chinese Journal Of Computers 31 1200 (in Chinese) [黄天云 2008 计算机学报 31 1200]

    [27]

    Ligang Z, Kin K L, Lean Y 2009 Soft Comput. 13 149

计量
  • 文章访问数:  1732
  • PDF下载量:  1103
  • 被引次数: 0
出版历程
  • 收稿日期:  2014-01-15
  • 修回日期:  2014-04-11
  • 刊出日期:  2014-07-05

一种基于相关分析的局域最小二乘支持向量机小尺度网络流量预测算法

  • 1. 北京邮电大学信息与通信工程学院, 北京 100876
    基金项目: 

    国防科技预研项目(批准号:208010201)资助的课题.

摘要: 本文分析了网络流量数据的特性,针对传统预测算法在预测网络流量时的缺陷提出了一种基于相关分析的相关局域最小二乘支持向量机(LSSVM)预测算法. 算法在对训练数据重构相空间后,利用相关分析同时从距离相关和时间相关的训练样本中选择最优的训练子集,结合自适应参数优化的LSSVM预测模型对小尺度网络流量进行预测. 通过选用实际情况下的网络流量数据对算法进行测试验证,结果显示本文所提算法不仅优于传统的全局预测算法,同时也优于各种改进的局域预测算法. 算法不仅在预测精度上取得大幅的性能提升,同时能够通过留一交叉验证法在预测之前就完成预测模型和训练子集的优化.

English Abstract

参考文献 (27)

目录

    /

    返回文章
    返回