杨喜敏,胡明明,唐 菀.动态的 SDN 网络流量模式增量学习算法[J].中南民族大学学报自然科学版,2018,(2):98-103
动态的 SDN 网络流量模式增量学习算法
Dynamical Incremental Learning Algorithm of Traffic Model for Software-Defined Networks
  
DOI:
中文关键词: 软件定义网络  增长型自组织映射  流表统计信息  增量学习
英文关键词: software-defined network  growing self-organizing map  flow table statistics  incremental learning
基金项目:国家自然科学基金资助项目(61103248)
作者单位
杨喜敏,胡明明,唐 菀 中南民族大学 计算机科学学院 武汉 430074 
摘要点击次数: 474
全文下载次数: 345
中文摘要:
      针对基于人工神经网络的流量统计特征学习算法在动态适应性和可扩展性等方面尚显不足.提出了一种基于增长型自组织映射(GSOM) 的增量学习算法,对软件定义网络(SDN) 数据平面交换机的流表统计信息进行持续学习,动态获取网络流量的 GSOM 神经网络模型.基于 DARPA99 数据集的实验结果表明: 所提出的算法能够通过学习确认安全的 SDN 流量,获得稳定、 可塑的流量模式,对异常流量也有较高的敏感度.
英文摘要:
      The learning algorithm based on artificial neural network is still insufficient in dynamic adaptability and expansibility for describing the statistical features of network traffic. In this paper, an incremental learning algorithm is proposed based on growing self-organizing map (GSOM) . It continuously learns the flow-table statistics from the switchers on the data flat, and obtains a dynamic incremental GSOM neural network traffic model for the software-defined network.Experimental results based on the DARPA99 data set show that the proposed algorithm can obtain stable and plastic traffic patterns through incremental learning the traffic which has been confirmed to be secure, and the traffic patterns also perform well in identifying abnormal traffic in software-defined networks
查看全文   查看/发表评论  下载PDF阅读器
关闭