SDN架构下的空间信息网络业务识别技术
|
摘要
针对传统的离线业务流量识别方法消耗时间长、实时性差的问题,通过对空间信息网络管控和网络资源的高效编排,提出一种基于软件定义网络(SDN)架构的空间信息网络业务识别技术。运用OpenFlow协议在线收集业务流量,提取流中前5个数据包作为一条子流,在SDN控制器上实现基于机器学习的在线业务分类,同时给出一种具有噪声过滤功能的协同训练算法Dif-TriTraining。实验结果表明,与传统的Tri-Training算法相比,该算法能够有效提升业务识别的准确率。
Aiming at the problem that the traditional offline business traffic identification method consumes a long time,and has poor real-time performance,through the management and control of spatial information network and the efficient arrangement of network resources,a business identification technology of spatial information network based on Software Defined Network(SDN) architecture is proposed.The OpenFlow protocol is used to collect business traffic online,and extract the first five data packets in the flow as a sub-flow,and implement online business classification based on machine learning on the SDN controller.At the same time,a collaborative training algorithm Dif-TriTraining with noise filtering function is presented.Experimental results show that compared with the traditional Tri-Training algorithm,the algorithm can effectively improve the accuracy of business identification.
Aiming at the problem that the traditional offline business traffic identification method consumes a long time,and has poor real-time performance,through the management and control of spatial information network and the efficient arrangement of network resources,a business identification technology of spatial information network based on Software Defined Network(SDN) architecture is proposed.The OpenFlow protocol is used to collect business traffic online,and extract the first five data packets in the flow as a sub-flow,and implement online business classification based on machine learning on the SDN controller.At the same time,a collaborative training algorithm Dif-TriTraining with noise filtering function is presented.Experimental results show that compared with the traditional Tri-Training algorithm,the algorithm can effectively improve the accuracy of business identification.
引文
[1] YAN J,YUN X,WU Z.Online traffic classification based on co-training method[C]//Proceedings of the 13th International Conference on Parallel and Distributed Computing,Applications and Technologies.Beijing,China:[s.n.],2012:125-136.
[2] SUN M,CHEN J.Research of the traffic characteris-tics for the real time online traffic classification[J].The Journal of China Universities of Posts and Telecommunica-tions,2011,18(3):92-98.
[3] 彭立志.互联网流量识别研究综述[J].济南大学学报(自然科学版),2016,30(2):95-104.
[4] 王丽冲,姚秀娟,闫毅.一种基于OpenFlow的软件定义卫星网络架构设计方案[J].电子设计工程,2016,24(17):85-89.
[5] 杨力,孔志翔,石怀峰.软件定义空间信息网络多控制器动态部署策略[J].计算机工程,2018,44(10):58-63.
[6] NAZARI S,DU P,GERIA M,et al.Software defined naval network for satellite communications[C]//Proceedings of 2016 IEEE Military Communications Conference.Washington D.C.,USA:IEEE Press,2016:124-136.
[7] ELMASRY G,MCCLATCHY D,HiINRICH R,et al.A software defined networking framework for future airborne connectivity[C]//Proceedings of ICNS’17.Herndon,USA:IEEE Press,2017:215-224.
[8] AMARAL P,DINIS J,PINTO P,et al.Machine learning in software defined networks:data collection and traffic classification[C]//Proceedings of the 24th International Conference on Network Protocal.Singapore:[s.n.],2016:321-329.
[9] BERNAILLE L,TEIXEIRA R,AKODKENOU I,et al.Traffic classification on the fly[C]//Proceedings of ACM SIGCOMM’06.New York,USA:ACM Press,2006:158-167.
[10] ESTE A,GRINGOLI F,SALGARELLI L.On the stability of the information carried by traffic flow features at the packet level[J].ACM SIGCOMM Computer Communication Review,2009,39(3):13-18.
[11] 赵树鹏,陈贞翔,彭立志.基于流中前5个包的在线流量分类特征[J].济南大学学报(自然科学版),2012,26(2):156-160.
[12] 刘珍,王若愚,蔡先发,等.互联网流量分类中流量特征研究[J].计算机应用研究,2017,34(1):8-13.
[13] 柏骏,夏靖波,吴吉祥,等.实时网络流量分类研究综述[J].计算机科学,2013,40(9):8-15.
[14] BERNAILLE L,TEIXEIRA R,SALAMATIAN K.Early application identification[C]//Proceedings of CoNEXT’06.New York,USA:ACM Press,2006:147-158.
[15] 彭建芬,周亚建,王枞,等.TCP流量早期识别方法[J].应用科学学报,2011,29(1):73-77.
[16] MOORE A W,ZUEV D.Internet traffic classification using Bayesian analysis techniques[C]//Proceedings of International Conference on Measurement and Modeling of Computer Systems.Alberta,Canada:[s.n.],2005:50-60.
[17] WEI L,ABDIN K,DANN R,et al.Approaching real-time network traffic classification[D].London,UK:London University,2006.
[18] 张剑,钱宗珏,寿国础,等.在线聚类的网络流量识别[J].北京邮电大学学报,2011,34(1):103-106.
[19] 郭翔宇,王魏.一种改进的协同训练算法:Compatible Co-training[J].南京大学学报(自然科学版),2016,52(4):662-671.
[20] ZHOU Z H,LI M.Tri-Training:exploiting unlabeled data using three classifiers[J].IEEE Transactions on Knowledge and Data Engineering,2005,17(11):1259-1541.
[21] 徐鹏,林森.基于C4.5决策树的流量分类方法[J].软件学报,2009,20(10):2692-2704.
[2] SUN M,CHEN J.Research of the traffic characteris-tics for the real time online traffic classification[J].The Journal of China Universities of Posts and Telecommunica-tions,2011,18(3):92-98.
[3] 彭立志.互联网流量识别研究综述[J].济南大学学报(自然科学版),2016,30(2):95-104.
[4] 王丽冲,姚秀娟,闫毅.一种基于OpenFlow的软件定义卫星网络架构设计方案[J].电子设计工程,2016,24(17):85-89.
[5] 杨力,孔志翔,石怀峰.软件定义空间信息网络多控制器动态部署策略[J].计算机工程,2018,44(10):58-63.
[6] NAZARI S,DU P,GERIA M,et al.Software defined naval network for satellite communications[C]//Proceedings of 2016 IEEE Military Communications Conference.Washington D.C.,USA:IEEE Press,2016:124-136.
[7] ELMASRY G,MCCLATCHY D,HiINRICH R,et al.A software defined networking framework for future airborne connectivity[C]//Proceedings of ICNS’17.Herndon,USA:IEEE Press,2017:215-224.
[8] AMARAL P,DINIS J,PINTO P,et al.Machine learning in software defined networks:data collection and traffic classification[C]//Proceedings of the 24th International Conference on Network Protocal.Singapore:[s.n.],2016:321-329.
[9] BERNAILLE L,TEIXEIRA R,AKODKENOU I,et al.Traffic classification on the fly[C]//Proceedings of ACM SIGCOMM’06.New York,USA:ACM Press,2006:158-167.
[10] ESTE A,GRINGOLI F,SALGARELLI L.On the stability of the information carried by traffic flow features at the packet level[J].ACM SIGCOMM Computer Communication Review,2009,39(3):13-18.
[11] 赵树鹏,陈贞翔,彭立志.基于流中前5个包的在线流量分类特征[J].济南大学学报(自然科学版),2012,26(2):156-160.
[12] 刘珍,王若愚,蔡先发,等.互联网流量分类中流量特征研究[J].计算机应用研究,2017,34(1):8-13.
[13] 柏骏,夏靖波,吴吉祥,等.实时网络流量分类研究综述[J].计算机科学,2013,40(9):8-15.
[14] BERNAILLE L,TEIXEIRA R,SALAMATIAN K.Early application identification[C]//Proceedings of CoNEXT’06.New York,USA:ACM Press,2006:147-158.
[15] 彭建芬,周亚建,王枞,等.TCP流量早期识别方法[J].应用科学学报,2011,29(1):73-77.
[16] MOORE A W,ZUEV D.Internet traffic classification using Bayesian analysis techniques[C]//Proceedings of International Conference on Measurement and Modeling of Computer Systems.Alberta,Canada:[s.n.],2005:50-60.
[17] WEI L,ABDIN K,DANN R,et al.Approaching real-time network traffic classification[D].London,UK:London University,2006.
[18] 张剑,钱宗珏,寿国础,等.在线聚类的网络流量识别[J].北京邮电大学学报,2011,34(1):103-106.
[19] 郭翔宇,王魏.一种改进的协同训练算法:Compatible Co-training[J].南京大学学报(自然科学版),2016,52(4):662-671.
[20] ZHOU Z H,LI M.Tri-Training:exploiting unlabeled data using three classifiers[J].IEEE Transactions on Knowledge and Data Engineering,2005,17(11):1259-1541.
[21] 徐鹏,林森.基于C4.5决策树的流量分类方法[J].软件学报,2009,20(10):2692-2704.