针对设备端口链路的LSTM网络流量预测与链路拥塞方案

doi:10.11959/j.issn.2096-109x.2019066

网络与信息安全学报 ›› 2019, Vol. 5 ›› Issue (6): 50-57.doi: 10.11959/j.issn.2096-109x.2019066

针对设备端口链路的LSTM网络流量预测与链路拥塞方案

黄伟,刘存才,祁思博()

中国电子科技集团公司第五十四研究所，河北石家庄050081

修回日期:2019-02-20 出版日期:2019-12-15 发布日期:2019-12-14
作者简介:黄伟（1978- ），男，河北保定人，中国电子科技集团公司第五十四研究所高级工程师，主要研究方向为通信系统总体技术、通信系统与网络仿真|刘存才（1965- ），男，河北石家庄人，中国电子科技集团公司第五十四研究所高级工程师，主要研究方向为通信网仿真和通信网可靠性研究|祁思博（1991-），男，河北石家庄人，中国电子科技集团公司第五十四研究所工程师，主要研究方向为通信网仿真和软件定义网络
基金资助:
国防科技重点实验室基金资助项目(614210401050217)

LSTM network traffic prediction and link congestion warning scheme for single port and single link

Wei HUANG,Cuncai LIU,Sibo QI()

The 54th Research Institute of China Electronic Technology Group Corporation,Shijiazhuang 050081,China

Revised:2019-02-20 Online:2019-12-15 Published:2019-12-14
Supported by:
The National Defence Science and Technology Key Laboratories Foundation of China(614210401050217)

摘要/Abstract

摘要：

针对设备端口链路流量，提出两种基于长短期记忆网络的预测模型。第一种针对在大时间粒度下平稳变化的流量；第二种则针对在小时间粒度下波动剧烈的非平稳流量。通过选用不同的数据划分方式与模型训练方法，构建两种具有不同网络结构的流量预测模型。实验结果表明，前者在处理平稳变化的流量时能够达到极高的预测精度，后者在处理非平稳流量时具有明显优于SVR模型、BP神经网络模型的预测效果。在第二种预测模型的基础上，提出了参数可调的链路拥塞预警方案，实验证明该方案具有一定的可行性。

关键词: 长短期记忆网络, 机器学习, 网络流量预测, 非平稳流量预测, 时间序列预测

Abstract:

To predict the traffic at single port and single link,two network traffic prediction models based on long short-term memory neural network were proposed.The first model is for the traffic which changes smoothly at large time granularity.The second model is for the nonstationary traffic which fluctuates violently at small time granularity.By selecting different methods of splitting data and training models,two traffic prediction models with different neural network structures were constructed.The experimental results show that the former can achieve a very high accuracy when predicting smoothly changed traffic,the latter has a significantly better prediction effect than the support vector regression model and the back propagation neural network model when dealing with nonstationary traffic.Based on the second model,a link congestion warning scheme with variable parameters was proposed.The scheme is proved to be practicable by experiments.

Key words: long short-term memory (LSTM), machine learning, network traffic prediction, nonstationary traffic prediction, time series prediction

中图分类号:

TP393

黄伟,刘存才,祁思博. 针对设备端口链路的LSTM网络流量预测与链路拥塞方案[J]. 网络与信息安全学报, 2019, 5(6): 50-57.

Wei HUANG,Cuncai LIU,Sibo QI. LSTM network traffic prediction and link congestion warning scheme for single port and single link[J]. Chinese Journal of Network and Information Security, 2019, 5(6): 50-57.

图/表 9

图1

图2

表1

图3

表2

表3

图4

图5

图6

参考文献 20

[1]	YU F , LIU W , GAO C ,et al. Network situation prediction based on optimized SVR model[C]// International Conference on Mechatronic Sciences. 2014: 2414-2419.
[2]	LIANG Y , QIU L , . L Network Traffic Prediction based on SVR improved by chaos theory and ant colony optimization[J]. International Journal of Future Generation Communication ＆ Networking, 2015,8: 484-488.
[3]	LIU ， J HUANG . Y L Nonlinear network traffic prediction based on BP neural network[J]. Journal of Computer Applications, 2007,27(7): 1770-1772.
[4]	ZHU L , QIN L , XUE K Y ,et al. A novel bp neural network model for traffic prediction of next generation network[C]// International Conference on Natural Computation. 2009(1): 32-38.
[5]	WANG X , ZHANG C ZHANG S . Modified Elman neural network and its application to network traffic prediction[C]// IEEE International Conference on Cloud Computing ＆ Intelligent Systems. 2012: 629-633.
[6]	GAO F , . Network traffic prediction based on neural network[C]// .International Conference on Intelligent Transportation. 2016: 527-530.
[7]	WANG J S .Modeling and prediction for network traffic based on elman neural network[J]. Computer Engineering, 2009,35(9): 190-191.
[8]	MA X TAO , Z WANG , Y H Yu ,et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C, 2015,54: 187-197.
[9]	CHEN S Y , CHOU W Y , . Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach[C]// International IEEE Conference on Intelligent Transportation Systems. 2012: 1821-1826.
[10]	ARDALANI-FARSA M ZOLFAGHARI . S Chaotic time series prediction with residual analysis method using hybrid Elman–NARX neural networks[J]. Neurocomputing, 2010,73(13-15): 2540-2553.
[11]	CHANDRA R ZHANG ， . M Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction[J]. Neurocomputing, 2012,86(12): 116-123.
[12]	ZHANG , K CHAI , Y FU . X A A network traffic prediction model based on recurrent wavelet neural network[C]// International Conference on Computer Science ＆ Network Technology. 2013: 1630-1633.
[13]	HOCHREITER S , SCHMIDHUBER J . Long short-termmemory[M]. Springer Berlin Heidelberg, 2019,9(8): 1735-1780.
[14]	TIAN , Y PAN , . L predicting short-term traffic flow by long short-term memory recurrent neural network[C]// IEEE International Conference on Smart City/Socialcom/Sustaincom. 2015: 153-158.
[15]	DUAN , Y LV , Y WANG . F Y Travel time prediction with LSTM neural network[C]// IEEE International Conference on Intelligent Transportation Systems. 2016: 1053-1058.
[16]	FU , R ZHANG , Z LI . L Using LSTM and GRU neural network methods for traffic flow prediction[C]// Chinese Association of Automation. 2017: 324-328.
[17]	SHAO , H SOONG , . B H Traffic flow prediction with long short-term memory networks (LSTMs)[C]// Region 10 Conference. 2017: 2986-2989.
[18]	XUE ， Z XUE . Y Multi long-short term memory models for short term traffic flow prediction[J]. IEICE Transactions on Information and Systems, 2018,101(12): 3272-3275.
[19]	LEE , Y J MIN , . O Long short-term memory recurrent neural network for urban traffic prediction:a case study of seoul[C]// IEEE Conference on Intelligent Transportation Systems. 2018: 1279-1284.
[20]	ZHUO , Q LI , Q HAN , Y et al . Long short-term memory neural network for network traffic prediction[C]// 12th International Conference on Intelligent Systems and Knowledge Engineering. 2018: 1-6.

模型	Accurate Rate	Unbelievable Rate
SVR	0.913 8	0
BP	0.931	0
LSTM	0.965 5	0.017 2

模型	Accurate Rate	Unbelievable Rate
SVR	0.783 1	0.012
BP	0.819 3	0.024 1
LSTM	0.831 3	0.024 1
LSTM-modified	0.903 6	0.012

模型	Accurate Rate	Unbelievable Rate
SVR	0.494	0.192 8
BP	0.759	0.048 2
LSTM	0.771 1	0.048 2
LSTM-modified	0.722 9	0.060 2

针对设备端口链路的LSTM网络流量预测与链路拥塞方案

LSTM network traffic prediction and link congestion warning scheme for single port and single link

在线阅读

pdf下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 20

相关文章 15

Metrics

推荐阅读 0

[1]	夏锐琪, 李曼曼, 陈少真. 基于机器学习的分组密码结构识别[J]. 网络与信息安全学报, 2023, 9(3): 79-89.
[2]	韦南, 殷丽华, 宁洪, 方滨兴. 本科“机器学习”课程教学改革初探[J]. 网络与信息安全学报, 2022, 8(4): 182-189.
[3]	黄诚, 孙明旭, 段仁语, 吴苏晟, 陈斌. 面向项目版本差异性的漏洞识别技术研究[J]. 网络与信息安全学报, 2022, 8(1): 52-62.
[4]	张颖君,刘尚奇,杨牧,张海霞,黄克振. 基于日志的异常检测技术综述[J]. 网络与信息安全学报, 2020, 6(6): 1-12.
[5]	付溪,李晖,赵兴文. 网络钓鱼识别研究综述[J]. 网络与信息安全学报, 2020, 6(5): 1-10.
[6]	孙旸,曹春杰,赖俊晓,于天娇. 基于LSTM-KF模型的无人机抗GPS欺骗方法[J]. 网络与信息安全学报, 2020, 6(5): 80-88.
[7]	何康,祝跃飞,刘龙,芦斌,刘彬. 敌对攻击环境下基于移动目标防御的算法稳健性增强方法[J]. 网络与信息安全学报, 2020, 6(4): 67-76.
[8]	袁福祥,刘粉林,刘翀,刘琰,罗向阳. MLAR：面向IP定位的大规模网络别名解析[J]. 网络与信息安全学报, 2020, 6(4): 77-94.
[9]	骆子铭,许书彬,刘晓东. 基于机器学习的TLS恶意加密流量检测方案[J]. 网络与信息安全学报, 2020, 6(1): 77-83.
[10]	张晓斌, 陈福才, 黄瑞阳. 基于CNN和双向LSTM融合的实体关系抽取[J]. 网络与信息安全学报, 2018, 4(9): 44-51.
[11]	宋蕾, 马春光, 段广晗. 机器学习安全及隐私保护研究进展[J]. 网络与信息安全学报, 2018, 4(8): 1-11.
[12]	明拓思宇, 陈鸿昶. 文本摘要研究进展与趋势[J]. 网络与信息安全学报, 2018, 4(6): 1-10.
[13]	王正琦,冯晓兵,张驰. 基于两层分类器的恶意网页快速检测系统研究[J]. 网络与信息安全学报, 2017, 3(8): 44-60.
[14]	张茜,延志伟,李洪涛,耿光刚. 网络钓鱼欺诈检测技术研究[J]. 网络与信息安全学报, 2017, 3(7): 7-24.
[15]	张东,张尧,刘刚,宋桂香. 基于机器学习算法的主机恶意代码检测技术研究[J]. 网络与信息安全学报, 2017, 3(7): 25-32.