一种SDN中基于熵值计算的异常流量检测方法

发布时间：2018-07-06 15:24

本文选题：软件定义网络 + 安全中心　；参考：《电信科学》2015年09期

【摘要】：软件定义网络(software defined networking,SDN)是一种新型网络创新架构,其分离了控制平面与转发平面,使得网络管理更为灵活。借助SDN控制与转发分离的思想,在SDN基础上引入一个集中式安全中心,在数据平面设备上采集数据,用于对网络流量进行分析,通过熵值计算和分类算法判断异常流量行为。对于检测到的网络异常情况,安全中心通过与SDN控制器的接口通告SDN控制器上的安全处理模块,进行流表策略的下发,进而缓解网络异常行为。通过本系统可以在不影响SDN控制器性能的情况下,快速检测网络中的异常行为,并通过SDN下发流表策略对恶意攻击用户进行限制,同时对SDN控制器进行保护。
[Abstract]:Software defined Network networking (software defined) is a new network innovation architecture, which separates the control plane from the forwarding plane and makes the network management more flexible. With the idea of separating SDN control from forwarding, a centralized security center is introduced on the basis of SDN to collect data on data plane equipment, which can be used to analyze the network traffic. The abnormal traffic behavior is judged by entropy calculation and classification algorithm. For the detected network anomaly, the security center notifies the security processing module on the SDN controller through the interface with the SDN controller, and emits the stream table policy to alleviate the abnormal behavior of the network. The system can quickly detect the abnormal behavior in the network without affecting the performance of the SDN controller, restrict the malicious attack users by SDN downflow table strategy, and protect the SDN controller at the same time.
【作者单位】：北京交通大学电子信息工程学院;
【基金】：国家科技重大专项基金资助项目(No.2013ZX03006002) 基本科研业务费资助项目(No.2015YJS028) 国家高技术研究发展计划(“863”计划)基金资助项目(No.2015AA015702)~~
【分类号】：TP393.06

【参考文献】