计算机工程 ›› 2020, Vol. 46 ›› Issue (10): 223-230.doi: 10.19678/j.issn.1000-3428.0056436

• 体系结构与软件技术 • 上一篇    下一篇

基于机器学习的SDN网络流量预测与部署策略

刘佳美, 徐巧枝   

  1. 内蒙古师范大学 计算机科学技术学院, 呼和浩特 010022
  • 收稿日期:2019-10-29 修回日期:2019-12-02 发布日期:2019-12-14
  • 作者简介:刘佳美(1994-),女,硕士研究生,主研方向为机器学习、软件定义网络;徐巧枝,副教授。
  • 基金项目:
    内蒙古自治区自然科学基金(2012MS0930);内蒙古自治区高等学校科学研究项目(NJZY18023,NJZY12032)。

Network Traffic Prediction and Deployment Strategy Based on Machine Learning for SDN

LIU Jiamei, XU Qiaozhi   

  1. College of Computer Science and Technology, Inner Mongolia Normal University, Hohhot 010022, China
  • Received:2019-10-29 Revised:2019-12-02 Published:2019-12-14

摘要: 针对由于网络流量的复杂多变而导致的软件定义网络(SDN)架构控制平面的负载不均问题,提出一种基于隐马尔科夫优化的最大熵网络流量预测和控制器预部署PPME模型。根据协议种类对SDN流量进行分类,利用已捕获的历史数据流,采用最大熵算法预测未来数据流的分布,生成控制平面中各类控制器的预部署方案,并加入隐马尔科夫链对预测方案的时效性进行优化。实验结果表明,相比于SVR模型与GBRT模型,该模型具有更高的预测精度,且生成的预部署方案能够适应复杂SDN环境中的动态变化,减少了由于突发事件而导致的负载不均和控制器迁移,缩短了由控制器迁移而产生的网络延迟与响应时间。

关键词: 软件定义网络, 机器学习, 最大熵, 隐马尔科夫, 流量预测, 预部署

Abstract: To address uneven loads in the control plane of Software Defined Network(SDN) architecture caused by the complexity and variability of network traffic,this paper proposes a network traffic prediction and controller pre-deployment PPME model based on hidden Markov optimization with maximum entropy.The model classifies SDN traffic according to the protocol types,and uses the maximum entropy algorithm to predict the distribution of the future data stream based on the captured historical data stream,so as to generate the pre-deployment scheme of various controllers in the control plane.The timeliness of the prediction scheme is optimized by the introduced hidden Markov chain.Experimental results show that compared with SVR model and GBRT model,the proposed model has higher prediction accuracy,and its generated pre-deployment scheme can adapt to the dynamic changes in complex SDN environment.It reduces the load imbalance and controller migration caused by emergencies,and thus reduces the network delay and response time caused by controller migration.

Key words: Software Defined Network(SDN), machine learning, maximum entropy, hidden Markov, traffic prediction, pre-deployment

中图分类号: