SDN中基于机器学习的网络流量分类方法研究
|
摘要
由于缺乏网络流量类别信息,目前软件定义网络SDN控制层难以有针对性地对在线视频流量和下载流量进行速率管控。当带宽有限时这会严重影响用户同时观看在线视频和进行下载时的体验。针对此问题,提出一种在SDN中基于机器学习的在线视频流量和下载流量分类方案。该方案选取新的、可以有效区分在线视频流量和下载流量的特征集合。通过测试对比多种机器学习模型的分类效果,在SDN中设计实现了基于随机森林(RandomForest)模型的实时流量分类应用,为在SDN中实现细粒度的网络流量管控、优化QoS等功能奠定了基础。测试结果表明,该方案对SDN中在线视频流量和下载流量的实时分类效果较理想,实时分类平均准确率较高。
Due to the lack of information of network traffic types, it is difficult for the SDN control layer to implement the rate control over online video traffic and download traffic. When the bandwidth is limited, it seriously affects the user experience while watching online video and downloading. Aiming at this problem, we proposed a traffic classification scheme of online video and download based on machine learning in SDN. This scheme selected a new feature set that could effectively distinguish online video traffic and download traffic. Through testing and comparing the classification effects of various machine learning models, we designed and implemented a real-time network traffic classification application based on random forest model in SDN. It laid the foundation for fine-grained network traffic control and optimization of QoS in SDN. The test results show that the scheme has a good real-time classification effect on online video traffic and download traffic in SDN. And the average accuracy of real-time classification is higher.
Due to the lack of information of network traffic types, it is difficult for the SDN control layer to implement the rate control over online video traffic and download traffic. When the bandwidth is limited, it seriously affects the user experience while watching online video and downloading. Aiming at this problem, we proposed a traffic classification scheme of online video and download based on machine learning in SDN. This scheme selected a new feature set that could effectively distinguish online video traffic and download traffic. Through testing and comparing the classification effects of various machine learning models, we designed and implemented a real-time network traffic classification application based on random forest model in SDN. It laid the foundation for fine-grained network traffic control and optimization of QoS in SDN. The test results show that the scheme has a good real-time classification effect on online video traffic and download traffic in SDN. And the average accuracy of real-time classification is higher.
引文
[1] 许晨辉.面向QoS保证的软件定义网络资源管控技术研究[D].南京:南京航空航天大学,2016.
[2] 蔡远俊.基于SDN和OpenFlow的流量分析系统的研究与设计[D].北京:北京邮电大学,2015.
[3] 许廷伟.一种基于SDN的流量管理系统设计与实现[J].电脑知识与技术.2015,11(33):33-36.
[4] 严骏驰.基于SDN的数据中心流量管理研究[D].北京:北京邮电大学,2016.
[5] 房亚明.基于SDN的数据中心网络流量调度技术研究[D].合肥:安徽大学,2017.
[6] 任燕凯.基于SDN的物联网智能流量管理机制的设计与实现[D].北京:北京邮电大学,2016.
[7] 程光,陈玉祥.基于支持向量机的加密流量识别方法[J].东南大学学报(自然科学版),2017,47(4):655-659.
[8] 吴辉.基于模糊K-Means的网络流分类系统研究与实现[D].广州:广东工业大学,2016.
[9] Shafiq M,Yu X,Wang D.Network Traffic Classification Using Machine Learning Algorithms[C]//International Conference on Intelligent and Interactive Systems and Applications,2017:621-627.
[10] Tapaswi S,Gupta A S.Flow-Based P2P Network Traffic Classification Using Machine Learning[C]//International Conference on Cyber-enabled Distributed Computing & Knowledge Discovery.IEEE,2013:402-406.
[11] Bujlow T,Riaz T,Pedersen J M.Classification of HTTP traffic based on C5.0 Machine Learning Algorithm[C]//Proceedings of the 2012 IEEE Symposium on Computers and Communications(ISCC).IEEE,2012:882-887.
[12] 李贺.网络视频业务流的特征选择与识别研究[D].南京:南京邮电大学,2016.
[13] 赵小祥.基于特征选取的网络游戏与视频业务分类研究[D].南京:南京邮电大学,2016.
[2] 蔡远俊.基于SDN和OpenFlow的流量分析系统的研究与设计[D].北京:北京邮电大学,2015.
[3] 许廷伟.一种基于SDN的流量管理系统设计与实现[J].电脑知识与技术.2015,11(33):33-36.
[4] 严骏驰.基于SDN的数据中心流量管理研究[D].北京:北京邮电大学,2016.
[5] 房亚明.基于SDN的数据中心网络流量调度技术研究[D].合肥:安徽大学,2017.
[6] 任燕凯.基于SDN的物联网智能流量管理机制的设计与实现[D].北京:北京邮电大学,2016.
[7] 程光,陈玉祥.基于支持向量机的加密流量识别方法[J].东南大学学报(自然科学版),2017,47(4):655-659.
[8] 吴辉.基于模糊K-Means的网络流分类系统研究与实现[D].广州:广东工业大学,2016.
[9] Shafiq M,Yu X,Wang D.Network Traffic Classification Using Machine Learning Algorithms[C]//International Conference on Intelligent and Interactive Systems and Applications,2017:621-627.
[10] Tapaswi S,Gupta A S.Flow-Based P2P Network Traffic Classification Using Machine Learning[C]//International Conference on Cyber-enabled Distributed Computing & Knowledge Discovery.IEEE,2013:402-406.
[11] Bujlow T,Riaz T,Pedersen J M.Classification of HTTP traffic based on C5.0 Machine Learning Algorithm[C]//Proceedings of the 2012 IEEE Symposium on Computers and Communications(ISCC).IEEE,2012:882-887.
[12] 李贺.网络视频业务流的特征选择与识别研究[D].南京:南京邮电大学,2016.
[13] 赵小祥.基于特征选取的网络游戏与视频业务分类研究[D].南京:南京邮电大学,2016.