Dropout回声状态网络的网络流量预测

doi:10.13190/j.jbupt.2021-021

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

Dropout回声状态网络的网络流量预测

牟晓惠, 李丽香

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

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/Abstract

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:

TP183

牟晓惠, 李丽香. Dropout回声状态网络的网络流量预测[J]. 北京邮电大学学报, 2021, 44(5): 10-13,20.

MU Xiao-hui, LI Li-xiang. Network Traffic Prediction of Dropout Echo State Network[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(5): 10-13,20.

参考文献

[1] 王瑞雪. 基于机器学习方法的网络流量感知与预测研究[D]. 无锡:江南大学, 2013:2-16.
[2] Zhou Dingding, Chen Songlin, Dong Shi. Network traffic prediction based on ARFIMA model[J]. International Journal of Computer Science Issues, 2012, 9(6):84-87.
[3] Gao Feng. Network traffic prediction based on neural network[C]//2015 International Conference on Intelligent Transportation, Big Data and Smart City. Halong Bay:IEEE, 2016:527-530.
[4] Hu Shenmin, Xu Weisheng, Wang Zhongjie, et al. Network traffic modeling and prediction based on fractional differencing and fuzzy-AR[J]. Computer Engineering and Applications, 2006, 42(19):104-107.
[5] Periyanayagi S, Sumathy V. S-ARMA model for network traffic predicition in wireless sensor networks[J]. Journal of Theoretical and Applied Information Technology, 2014, 60(3):524-530.
[6] Wang Jin. A process level network traffic prediction algorithm based on ARIMA model in smart substation[C]//2013 IEEE International Conference on Signal Processing, Communication and Computing (ICSPCC 2013). Kunming:IEEE, 2013:1-5.
[7] Marquez P, Pinos D, Juan I O. Performance comparison in network traffic prediction for polynomial regression to P1P versus ARIMA and MWM[C]//2018 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus). Moscow:IEEE, 2018:77-82.
[8] Wei Yongtao, Wang Jinkuan, Wang Cuirong. Network traffic prediction based on wavelet transform and season ARIMA model[C]//International Symposium on Neural Networks. Berlin:Springer, 2011:152-159.
[9] Dethe C G, Wakde D G. On the prediction of packet process in network traffic using FARIMA time-series model[J]. Journal of the Indian Institute of Science, 2004, 84310(2):31-39.
[10] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6):84-90.
[11] Strauss T, Wustlich W, Labahn R. Design strategies for weight matrices of echo statenetworks[J]. Neural Computation, 2012, 24(12):3246-3276.
[12] Bianchi F M, Livi L, Alippi C. Investigating echo-state networks dynamics by means of recurrence analysis[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(2):427-439.
[13] Ozturk M C, Xu D, Príncipe J C. Analysis and design of echo state networks[J]. Neural Computation, 2007, 19(1):111-138.
[14] Deng Zhidong, Zhang Yi. Collective behavior of a small-world recurrent neural system with scale-free distribution[J]. IEEE Transactions on Neural Networks, 2007, 18(5):1364-1375.
[15] Jaeger H, Haas H. Harnessing nonlinearity:predicting chaotic systems and saving energy in wireless communication[J]. Science, 2004, 304(5667):78-80.
[16] British Academic Backbone Network. Internet traffic time series datasets[2021-02-21]. http://www3.dsi.nminho.pt/pcortez/series/.
[17] 吴佳东. 基于回声状态网络的网络流量预测研究[D]. 兰州:兰州大学, 2016:37.

Dropout回声状态网络的网络流量预测

Network Traffic Prediction of Dropout Echo State Network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	常霄, 黄智濒, 禹旻, 杨武兵. 一种适用于航天大数据的深度决策树算法[J]. 北京邮电大学学报, 2023, 46(3): 1-6.
[2]	欧阳莫微, 康桂霞, 王开亮, 王亚明. 一种放射组学分析的海马硬化自动诊断方法[J]. 北京邮电大学学报, 2022, 45(4): 51-57.
[3]	晁浩, 马庆敏, 刘永利. 利用卷积回声状态网络实现脑电情感识别[J]. 北京邮电大学学报, 2022, 45(2): 36-43.
[4]	汤永利, 李星宇, 赵宗渠, 李运峰. 面向Android支付破解应用的检测方法[J]. 北京邮电大学学报, 2021, 44(4): 95-101.
[5]	彭雨荷, 陈翔, 陈双武, 杨坚. 基于迁移学习的跨域异常流量检测[J]. 北京邮电大学学报, 2021, 44(2): 33-39.
[6]	吕兴凤, 李金宝. 一种利用随机森林方法检测睡眠呼吸暂停的研究[J]. 北京邮电大学学报, 2020, 43(5): 64-70.
[7]	张德干, 陈露, 陈晨, 张婷, 崔玉亚. 一种面向边缘计算节点能量优化的QoS约束路由算法[J]. 北京邮电大学学报, 2020, 43(4): 101-105.
[8]	周怡琳, 杨璐, 鲁文睿. 尘土颗粒影响下电路板电化学迁移失效寿命建模探索[J]. 北京邮电大学学报, 2020, 43(3): 11-18,31.
[9]	张国栋, 应欢, 杨寿国, 石志强, 李霁远. 嵌入式固件脆弱哈希函数自动识别与破解方法[J]. 北京邮电大学学报, 2020, 43(1): 46-53.
[10]	余凯祥, 陈振豪, 张四海. 一种多变量制造过程中的关键变量检测算法[J]. 北京邮电大学学报, 2019, 42(6): 98-104.
[11]	孟浩, 霍如, 郭倩影, 黄韬, 刘韵洁. 基于机器学习的MEC随机任务迁移算法[J]. 北京邮电大学学报, 2019, 42(2): 25-30.
[12]	赵季红, 王明欣, 曲桦, 谢志勇, 刘熙. 一种基于自适应KLMS的卫星网络流量预测算法[J]. 北京邮电大学学报, 2018, 41(3): 51-55.
[13]	崔鸿雁, 徐帅, 张利锋, Roy E. Welsch, Berthold K. P. Horn. 机器学习中的特征选择方法研究及展望[J]. 北京邮电大学学报, 2018, 41(1): 1-12.
[14]	董枫, 刘天铭, 徐国爱, 郭燕慧, 李承泽. 面向Android二进制代码的缺陷预测方法[J]. 北京邮电大学学报, 2018, 41(1): 13-23.
[15]	孙韩林，金跃辉，崔毅东，程时端. 粗粒度网络流量的灰色模型预测[J]. 北京邮电大学学报, 2010, 33(1): 7-11.