北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (5): 10-13,20.doi: 10.13190/j.jbupt.2021-021

• 论文 • 上一篇    下一篇

Dropout回声状态网络的网络流量预测

牟晓惠, 李丽香   

  1. 北京邮电大学 网络空间安全学院, 北京 100876
  • 收稿日期:2021-03-11 出版日期:2021-10-28 发布日期:2021-09-06
  • 通讯作者: 李丽香(1978-),女,教授,博士生导师,E-mail:lixiang@bupt.edu.cn. E-mail:lixiang@bupt.edu.cn
  • 作者简介:牟晓惠(1991-),女,博士生.
  • 基金资助:
    国家重点研发计划项目(2020YFB1805402);国家自然科学基金项目(62032002,61972051)

Network Traffic Prediction of Dropout Echo State Network

MU Xiao-hui, LI Li-xiang   

  1. School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2021-03-11 Online:2021-10-28 Published:2021-09-06

摘要: 提出了一种基于Dropout方法的回声状态网络(ESN).将基于Dropout方法的ESN (Dropout ESN)应用到实际的网络流量预测任务中,设置储备池内神经元以不同的概率停止工作,将经典的ESN和Dropout ESN进行了对比,分析了2种网络对预测性能的影响,将基于Dropout方法的ESN和其他网络的正规化方均根差进行对比分析.仿真结果表明,Dropout ESN对网络流量预测效果更优.

关键词: 机器学习, 回声状态网络, 网络流量预测, Dropout方法

Abstract: An echo state network (ESN) based on Dropout method is proposed. The ESN based on Dropout method (Dropout ESN)is applied to the actual network traffic prediction task, in which the neurons in the reservoir are set to stop working with different probability. Dropout ESN is compared with the classical ESN to analyse the influence of the two networks on the prediction performance. In addition the normalized root mean square error of Dropout ESN and other models are compared and analyzed. Simulation results show that Dropout ESN has better prediction performance on network traffic than other ESN models.

Key words: machine learning, echo state network, network traffic prediction, Dropout method

中图分类号: