基于多节点故障恢复的虚拟网络映射算法  被引量:6

Virtual network embedding algorithm based on multiple node failures recovery

在线阅读下载全文

作  者:朱国晖 刘秀霞 张茵 陈刚[2] ZHU Guo-hui;LIU Xiu-xia;ZHANG Yin;CHEN Gang(School of Communications and Information Engineering,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;China United Network Communication Limited Corporation Dongying Branch,Dongying 257000,China)

机构地区:[1]西安邮电大学通信与信息工程学院,陕西西安710121 [2]中国联合网络通信有限公司东营市分公司,山东东营257000

出  处:《计算机工程与设计》2020年第12期3313-3319,共7页Computer Engineering and Design

摘  要:为保障虚拟网络映射成功,大量研究者提出许多虚拟网络映射算法,但在这些算法中,一部分忽略了物理网络发生故障的情况,另一部分只考虑了单个物理节点发生故障。为此,针对在物理网络出现多个节点故障问题,提出一种基于多节点故障恢复的虚拟网络映射算法。将物理网络资源按比例分为主、备用资源,在虚拟请求到达之前,每个物理节点都会通过广度优先搜索算法创建节点候选集合;当发生多节点故障时,采用提出的节点选择策略找到最佳候选节点;依据所提目标函数对受影响的虚拟节点逐一进行重映射。仿真结果表明,该算法具有最佳的长期业务利润,提高了虚拟网络恢复率,缩短了故障恢复时延。To ensure the success of virtual network embedding,a large number of researchers have proposed many virtual network embedding algorithms.However,for these algorithms,some of them ignore the failure of the physical network,the others only consider the failure of a single physical node.Therefore,a virtual network embedding algorithm based on multiple node failures recovery was proposed for the problem of multiple node failures in physical networks.The physical network resources were divided into main and standby resources.Before the virtual request arrived,each physical node created a set of candidate nodes using the breadth-first search algorithm.When multiple physical nodes failed at the same time,the node selection proposed was adopted.The best candidate node was found and the affected virtual nodes were remapped one by one according to the proposed objective function.Simulation results show that the algorithm not only has the best long-term business profit,but also greatly enhances the virtual network recovery rate and shortens the fault recovery delay.

关 键 词:网络虚拟化 节点恢复度因子 生存性虚拟网络映射 虚拟网络重映射 多节点故障 

分 类 号:TP393.1[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