Policy conflict detection in software defined network by using deep learning

Chuanhuang LI; Cheng CHENG; Xiaoyong YUAN; Lijie CEN; Weiming WANG

doi:10.11959/j.issn.1000-0801.2017305

您当前的位置：

首页 >

文章列表页 >

Policy conflict detection in software defined network by using deep learning

Research and Development | 更新时间：2024-06-05

- Policy conflict detection in software defined network by using deep learning
- Telecommunications Science Vol. 33, Issue 11, Pages: 27-36(2017)
- 作者机构：
  
  1. 浙江工商大学信息与电子工程学院，浙江杭州 310018
  2. 美国佛罗里达大学大规模智能系统实验室，美国佛罗里达州盖恩斯维尔 32611
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2017305
  CLC： TP393
- Published Online：2017-11，
  
  Published：20 November 2017
- 稿件说明：
移动端阅览
Chuanhuang LI, Cheng CHENG, Xiaoyong YUAN, et al. Policy conflict detection in software defined network by using deep learning[J]. Telecommunications science, 2017, 33(11): 27-36.
DOI：

Chuanhuang LI, Cheng CHENG, Xiaoyong YUAN, et al. Policy conflict detection in software defined network by using deep learning[J]. Telecommunications science, 2017, 33(11): 27-36. DOI： 10.11959/j.issn.1000-0801.2017305.

摘要

在基于OpenFlow的软件定义网络（SDN）中，应用被部署时，相应的流表策略将被下发到OpenFlow交换机中，不同应用的流表项之间如果产生冲突，将会影响交换机的实际转发行为，进而扰乱特定应用的正确部署以及SDN的安全。随着SDN规模的扩大以及需要部署应用的数量的剧增，交换机中的流表数量呈现爆炸式增长。此时若采用传统的流表冲突检测算法，交换机将会耗费大量的系统计算时间。结合深度学习，首次提出了一种适合SDN中超大规模应用部署的智能流表冲突检测方法。实验结果表明，第一级深度学习模型的AUC达到97.04%，第二级模型的AUC达到99.97%，同时冲突检测时间与流表规模呈现线性增长关系。

Abstract

In OpenFlow-based SDN(software defined network)

applications can be deployed through dispatching the flow polices to the switches by the application orchestrator or controller.Policy conflict between multiple applications will affect the actual forwarding behavior and the security of the SDN.With the expansion of network scale of SDN and the increasement of application number

the number of flow entries will increase explosively.In this case

traditional algorithms of conflict detection will consume huge system resources in computing.An intelligent conflict detection approach based on deep learning was proposed which proved to be efficient in flow entries’ conflict detection.The experimental results show that the AUC (area under the curve) of the first level deep learning model can reach 97.04%

and the AUC of the second level model can reach 99.97%.Meanwhile

the time of conflict detection and the scale of the flow table have a linear growth relationship.

关键词

Keywords

references

韦乐平 . SDN的战略性思考 [J ] . 电信科学 , 2015 , 31 ( 1 ): 7 - 12 .

WEI L P . Strategic Thinking on SDN [J ] . Telecommunications Science , 2015 , 31 ( 1 ): 7 - 12 .

CLOUGHERTY M M , WHITE C A , VISWANATHAN H , et al . SDN在IP网络演进中的作用 [J ] . 电信科学 , 2014 , 30 ( 5 ): 1 - 13 .

CLOUGHERTY M M , WHITE C A , VISWANATHAN H , et al . Role of SDN in IP network evolution [J ] . Telecommunications Science , 2014 , 30 ( 5 ): 1 - 13 .

SPECIFICATION O F S.Version 1.5.1(wire protocol 0x01) [EB ] . 2015 .

VERMA D C . Simplify network administration using policy-based management [J ] . Network IEEE , 2002 , 16 ( 2 ): 20 - 26 .

LOPES A B B , LIMA DE C G A , FERNANDEZ M P . Flow-based conflict detection in OpenFlow networks using first-order logic [C ] // 2014 IEEE Symposium on Computers and Communication (ISCC),April 27-May 2,2014,Toronto,Japan . New Jersey:IEEE Press , 2014 : 1 - 6 .

BATISTA B L A , DE CAMPOS G A L , FERNANDEZ M P . A proposal of policy based OpenFlow network management [C ] // 2013 20th International Conference on Telecommunications (ICT),Aug 14-16,2013,Guilin,China . New Jersey:IEEE Press , 2013 : 1 - 5 .

NATARAJAN S , HUANG X , WOLF T . Efficient conflict detection in flow-based virtualized networks [C ] // 2012 International Conference on Computing,Networking and Communications (ICNC),Oct 8-10,2012,Maui,Hawaii . New Jersey:IEEE Press , 2012 : 690 - 696 .

LO C C , WU P Y , KUO Y H . Flow entry conflict detection scheme for software-defined network [C ] // 2015 International Telecommunication Networks and Applications Conference(ITNAC),November 18,2015,Sydney,Australia . New Jersey:IEEE Press , 2015 : 220 - 225 .

PORRAS P , SHIN S , YEGNESWARAN V , et al . A security enforcement kernel for OpenFlow networks [C ] // The First Workshop on Hot Topics in Software Defined Networks,August 13,2012,Helsinki,Finland . New York:ACM Press , 2012 : 121 - 126 .

HU H , HAN W , AHN G J , et al . FLOWGUARD:building robust firewalls for software-defined networks [C ] // The Third Workshop on Hot Topics in Software Defined Networking,August 22,2014,Chicago,Illinois,USA . New York:ACM Press , 2014 : 97 - 102 .

KHURSHID A , ZOU X , ZHOU W , et al . VerIFlow:verifying network-wide invariants in real time [C ] // 10th USENIX Symposium on Networked Systems Design and Implementation (NSDI 13),Apr 3-5,2013 , Lombard,IL,USA .[S.l.:s.n. ] 2013 : 15 - 27 .

BASILE C , CANAVESE D , LIOY A , et al . Inter‐function anomaly analysis for correct SDN/NFV deployment [J ] . International Journal of Network Management , 2016 , 26 ( 1 ): 25 - 43 .

WANG P , HUANG L , XU H , et al . Rule anomalies detecting and resolving for software defined networks [C ] // 2015 IEEE Global Communications Conference (GLOBECOM),Dec 6-10,2015,San Diego,USA . New Jersey:IEEE Press , 2015 : 1 - 6 .

王娟 , 王江 , 焦虹阳 , 等 . 一种基于OpenFlow的SDN访问控制策略实时冲突检测与解决办法 [J ] . 计算机学报 , 2015 , 38 ( 4 ): 872 - 883 .

WANG J , WANG J , JIAO H Y , et al . A method of OpenFlow-based real-time conflict detection and resolution for SDN access control policies [J ] . Chinese Journal of Computers , 2015 , 38 ( 4 ): 872 - 883 .

LIAW A , WIENER M . Classification and regression by randomForest [J ] . R News , 2002 , 2 ( 3 ): 18 - 22 .

Views

1100

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research and application of traffic engineering algorithm based on deep learning

SDN Technology and Industry Analysis and Strategy Recommendations for Telecom Operator

GMTBLC: a deep learning-based bi-modal network traffic classification method

Research on antenna dip angle recognition method based on improved YOLOv5

Mixed signal modulation recognition method based on temporal depth residual shrinkage network

Related Author

Daoyun HU

Jin QI

Qianchun LU

Feng LI

Hongqiang FANG

Yongbing Fan

Zhilan Huang

WEI Debin

Related Institution

University of Science and Technology of China

State Key Laboratory of Mobile Network and Mobile Multimedia Technology

School of Information Engineering, Dalian University

China Mobile Group Design Institute Co., Ltd.

China Mobile Group Co., Ltd.

⁰