软件定义网络中一种快速无循环路径迁移策略  

Fast loop-free path migration strategy in software defined network

在线阅读下载全文

作  者:燕昺昊 刘勤让[1,2] 沈剑良[1] 汤先拓 梁栋 YAN Binghao;LIU Qinrang;SHEN Jianliang;TANG Xiantuo;LIANG Dong(Institute of Information Technology,Information Engineering University,Zhengzhou 450001,China;National Digital Switching System Engineering&Technological R&D Center,Zhengzhou 450001,China)

机构地区:[1]信息工程大学信息技术研究所,河南郑州450001 [2]国家数字交换系统工程技术研究中心,河南郑州450001

出  处:《通信学报》2022年第5期24-35,共12页Journal on Communications

基  金:国家科技重大专项基金资助项目(No.2017ZX01030301);工业互联网创新发展工程基金资助项目(No.TC190A446-2)。

摘  要:针对软件定义网络中数据平面转发设备的分布式部署及异步操作导致的路径迁移缓慢及故障等问题,提出了一种快速无循环路径迁移策略。首先,提出了一种基于节点排序的快速循环检测算法。该算法通过对比流的新旧路径上相邻节点的位置差异,可快速判定路径迁移过程中是否存在转发循环以及检测循环发生位置。然后,提出了一种基于节点松弛依赖关系的贪婪更新机制。该机制利用快速循环检测算法发掘出新旧路径上公有交换机之间存在的松弛依赖关系,进而保证了迁移过程每轮更新的交换机数量最大化。仿真实验结果表明,相比于现有迁移方案,所提策略在不同网络状态下均可有效避免迁移循环且获得最佳更新时间开销。Aiming at the problems of slow and faulty path migration caused by distributed deployment and asynchronous operation of data plane forwarding devices in software defined network,a fast loop-free path migration strategy was proposed.First,a fast loop detection algorithm based on node ranking was proposed.By comparing the position differences of adjacent nodes on the old and new paths of the flow,whether there was a forwarding loop in the path migration process and the location detection where the loop occurs could be quickly determined.Then,a greedy update mechanism based on node relaxation dependency was proposed.The fast loop detection algorithm was used to uncover the relaxation dependency between the common switches on the old and new paths,and the number of switches updated in each round of the migration process was ensured to be maximized.Simulation results show that the proposed strategy can effectively avoid migration loops and obtain the optimal update time overhead under different network states compared with existing migration schemes.

关 键 词:软件定义网络 路径迁移 循环避免 松弛依赖 贪婪机制 

分 类 号:TP393[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象