东北大学学报:自然科学版 ›› 2018, Vol. 39 ›› Issue (3): 311-315.DOI: 10.12068/j.issn.1005-3026.2018.03.002

• 信息与控制 • 上一篇    下一篇

基于改进黑洞算法优化ESN的网络流量短期预测

韩莹1,2, 井元伟1, 金建宇3, 李琨2   

  1. (1. 东北大学 信息科学与工程学院, 辽宁 沈阳110819; 2. 渤海大学 工学院, 辽宁 锦州121013; 3. 东北大学 国防教育学院, 辽宁 沈阳110819)
  • 收稿日期:2016-10-21 修回日期:2016-10-21 出版日期:2018-03-15 发布日期:2018-03-09
  • 通讯作者: 韩莹
  • 作者简介:冯明杰(1971-), 男, 河南禹州人, 东北大学副教授; 王恩刚(1962-), 男, 辽宁沈阳人, 东北大学教授,博士生导师.韩莹(1982-),女,辽宁锦州人,东北大学博士研究生; 井元伟(1956-),男,辽宁沈阳人,东北大学教授,博士生导师.
  • 基金资助:
    国家自然科学基金资助项目(51171041).国家自然科学基金资助项目(61773108, 61403040).

Network Traffic Short-Term Prediction Based on Echo State Network Optimized by Improved Black Hole Algorithm

HAN Ying1,2, JING Yuan-wei1, JIN Jian-yu3, LI Kun2   

  1. 1. School of Information Science & Engineering, Northeastern University, Shenyang 110819, China; 2. College of Engineering, Bohai University, Jinzhou 121013, China; 3. School of National Defense Education, Northeastern University, Shenyang 110819, China.
  • Received:2016-10-21 Revised:2016-10-21 Online:2018-03-15 Published:2018-03-09
  • Contact: JING Yuan-wei
  • About author:-
  • Supported by:
    -

摘要: 网络流量数据序列具有混沌特性.相空间重构后,采用一种改进黑洞算法优化回声状态网络的非线性模型对网络流量进行预测.改进黑洞算法是在现有工作的基础上提出一种新的新解生成机制,可以提高算法的收敛速度和精度;相比于遗传算法、和声搜索算法等其他优化算法,所提出的改进黑洞算法不依赖自身相关参数的准确设定;将其应用于回声状态网络4个重要参数的优化选取,使得预测模型具有较好的预测稳定性.通过Mackey-Glass混沌时间序列和网络流量公共数据集的仿真实验,结果表明所提出的方法具有较好的预测性能.

关键词: 网络流量, 混沌时间序列, 回声状态网络, 黑洞算法, 预测

Abstract: The network traffic data series has chaos characteristics. After phase space reconstruction, a nonlinear prediction model based on echo state network (ESN) optimized by improved black hole (BH) was used to predict network traffic. The improved BH algorithm is a new mechanism for new-solution generation based on current works, which can increase the algorithms convergence speed and precision. Compared with other optimization algorithms, such as genetic algorithm (GA), harmony search (HS) algorithm, etc, the proposed improved BH algorithm is not affected by the accuracy of the setting for some parameters of itself. It is used to optimally select four key parameters of the ESN model, which has better prediction stability. Simulation experiments of Mackey-Glass chaos time series and public network traffic data set show that the proposed method has better prediction ability.

Key words: network traffic, chaos time series, echo state network(ESN), black hole algorithm, prediction

中图分类号: