检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:梁栋 燕昺昊 赵博[1,2] LIANG Dong;YAN Binghao;ZHAO Bo(Information Engineering University,Zhengzhou 450001,China;National Digital Switching System Engineering and Technological Research Center,Zhengzhou 450002,China)
机构地区:[1]信息工程大学,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450002
出 处:《信息工程大学学报》2022年第6期754-761,共8页Journal of Information Engineering University
基 金:国家重大科技专项资助项目(2017ZX01030301)。
摘 要:在分布式控制平面中,当主控制器发生故障时,交换机将会被映射到从控制器。如果从控制器分配不合理,有可能会导致从控制器失效,从而造成级联故障。为解决此问题,提出了一种基于冗余从控制器动态映射的控制平面容错性提升机制。首先通过节点重要性找到网络中的热点区域,并部署一定数量的冗余从控制器;随后,从控制器负载均衡、控制器响应时间和交换机重要程度等因素考虑冗余从控制器的动态映射问题,并证明了该问题是NP-hard。仿真结果证明该方法可以有效提升控制平面容错性,应对更多的故障控制器。在多控制器故障下,最大控制器负载率约为其他方案的50%。In the distributed control plane, when the master controller fails, the switches are mapped to the slave controller. If the slave controller is improperly mapped, the slave controller may fail, resulting in cascading faults. To solve this problem, this paper proposes a control plane fault tolerance improvement mechanism based on redundant slave controller dynamic mapping. Firstly, it finds the hot spots in the network through node importance and deploys a certain number of redundant slave controllers. Then, the dynamic mapping of redundant slave controllers is considered from such factors as controller load ratio, controller response time and switch importance, and the problem is proved to be NP-hard. Simulation results show that the proposed method can effectively improve the reliability and fault tolerance performance of the control plane and cope with more fail controllers. In the case of a multi-controller failure, the maximum controller load ratio is at most about 50% of the other solutions.
分 类 号:TP393[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.200