一种SDN控制节点故障恢复的部署策略

doi:10.6040/j.issn.1671-9352.2.2018.153

《山东大学学报(理学版)》 ›› 2019, Vol. 54 ›› Issue (5): 21-27.doi: 10.6040/j.issn.1671-9352.2.2018.153

一种SDN控制节点故障恢复的部署策略

刘振鹏^1,³(),王文胜¹,贺玉鹏²,孙静薇¹,张彬^3,*()

1. 河北大学电子信息工程学院, 河北保定 071002
2. 河北大学网络空间安全与计算机学院，河北保定 071002
3. 河北大学信息技术中心, 河北保定 071002

收稿日期:2018-09-20 出版日期:2019-05-20 发布日期:2019-05-09
通讯作者: 张彬 E-mail:lzp@hbu.edu.cn;zb@hbu.edu.cn
作者简介:刘振鹏(1966—)，男，博士，教授，硕士生导师，研究方向为网络信息安全、隐私保护、软件定义网络等. E-mail:lzp@hbu.edu.cn
基金资助:
河北省创新能力提升计划项目(179676278D);河北省创新能力提升计划项目(17455309D);教育部云数融合科教创新基金资助项目(2017A20004)

A deployment strategy for fault recovery of SDN control nodes

Zhen-peng LIU^1,³(),Wen-sheng WANG¹,Yu-peng HE²,Jing-wei SUN¹,Bin ZHANG^3,*()

1. School of Electronic Information Engineering, Hebei University, Baoding 071002, Hebei, China
2. School of Cyber Security and Computer, Hebei University, Baoding 071002, Hebei, China
3. Center for Information Technology, Hebei University, Baoding 071002, Hebei, China

Received:2018-09-20 Online:2019-05-20 Published:2019-05-09
Contact: Bin ZHANG E-mail:lzp@hbu.edu.cn;zb@hbu.edu.cn
Supported by:
河北省创新能力提升计划项目(179676278D);河北省创新能力提升计划项目(17455309D);教育部云数融合科教创新基金资助项目(2017A20004)

摘要/Abstract

摘要：

针对广域网中软件定义网络(software defined network, SDN)在运行过程中控制器发生不可恢复的故障的情况,提出一种考虑控制器节点故障的部署方法。首先将网络划分成多个子网络,进而提出采用改进的粒子群优化算法对SDN控制器进行部署,以达到较高的可靠性和较低的时间延迟以及负载较为均衡的目的;在网络运行的过程中,当控制器发生不可恢复的故障时,采用熵权多目标决策法确定由发生故障区域的目标slave控制器,将其升级为master控制器,从而保证网络的正常运行。实验结果表明,相对于采取K-means或贪心算法,使用本方法进行控制器部署,在SDN网络的负载均衡率、链路时间延迟等网络关键指标方面均有所提升,且能以较低的代价降低控制器故障节点对网络正常运行的影响。

关键词: 软件定义网络, 粒子群优化, 熵权多目标决策, 广域网, 控制器部署, 控制节点故障, 网络恢复

Abstract:

Aiming at the situation that the controller has an unrecoverable fault during the operation of the software defined network (SDN) in the WAN, a deployment method considering the fault of the controller node is proposed. Firstly, the network is divided into multiple sub-networks, and then an improved particle swarm optimization algorithm is proposed to deploy the SDN controller in order to achieve higher reliability, lower delay and more balanced load. In the process of network operation, when the controller has an unrecoverable fault, the entropy weight multi-objective decision method is used to determine the target slave controller in the faulty area and upgrade it to the master controller to ensure the normal operation of the network. The experimental results show that compared with the K-means or greedy algorithm, the controller deployment using this method improves the network key indicators such as load balancing rate and link delay of the SDN network, and can reduce decrease the impact of controller failure points on the normal operation of the network at a relatively low costs.

Key words: software defined network, particle swarm optimization, entropy weight multi-objective decision making, wide area network, switch dynamic migration, control node failure, network recovery

中图分类号:

TP393

刘振鹏,王文胜,贺玉鹏,孙静薇,张彬. 一种SDN控制节点故障恢复的部署策略[J]. 《山东大学学报(理学版)》, 2019, 54(5): 21-27.

Zhen-peng LIU,Wen-sheng WANG,Yu-peng HE,Jing-wei SUN,Bin ZHANG. A deployment strategy for fault recovery of SDN control nodes[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2019, 54(5): 21-27.

图/表 5

图1

表1

表2

图2

图3

参考文献 13

1	张朝昆, 崔勇, 唐翯祎, 等. 软件定义网络(SDN)研究进展[J]. 软件学报, 2015, 26 (1): 62- 81.
	ZHANG Chaokun , CUI Yong , TANG Heyi , et al. State-of-the-art survey on software-defined networking (SDN)[J]. Journal of Software, 2015, 26 (1): 62- 81.
2	王丽霞, 曲桦, 赵季红, 等. 软件定义网络中应用二值粒子群优化的控制器部署策略[J]. 西安交通大学学报, 2015, 49 (6): 67- 71.
	WANG Lixia , QU Ye , ZHAO Jihong , et al. A strategy of controller placement in software defined networks using binary particle swarm optimization[J]. Journal of Xi'an Jiaotong University, 2015, 49 (6): 67- 71.
3	伊鹏, 刘邦舟, 王文博, 等. 一种考虑软件定义网络控制节点故障的控制器部署和交换机迁移方法[J]. 电子与信息学报, 2017, 39 (8): 1972- 1978.
	YI Peng , LIU Bangzhou , WANG Wenbo , et al. Controller placement and switch immigration strategy for SDN controller failure[J]. Journal of Electronics & Information Technology, 2017, 39 (8): 1972- 1978.
4	KUANG H, QIU Y, LI R, et al. A hierarchical K-means algorithm for controller placement in SDN-based WAN architecture[C]// International Conference on Measuring Technology and Mechatronics Automation. New York: IEEE, 2018: 263-267.
5	胡涛, 张建辉, 孔维功, 等. SDN中基于双向匹配的多控制器动态部署算法[J]. 通信学报, 2018, 39 (1): 159- 169.
	HU Tao , ZHANG Jianhui , KONG Weigong , et al. Dynamic deployment algorithm for multi-controllers based on bidirectional matching in software defined networking[J]. Journal of Communications, 2018, 39 (1): 159- 169.
6	XIAO Peng, QU Wenyu, QI Heng, et al. The SDN controller placement problem for WAN[C]// IEEE/CIC International Conference on Communications in China. New York: IEEE, 2015: 220-224.
7	陆悠, 奚雪峰, 吴宏杰, 等. 基于拓扑划分的SDN多控制器部署方法[J]. 计算机应用研究, 2017, (11): 3388- 3393. doi: 10.3969/j.issn.1001-3695.2017.11.041
	LU You , XI Xuefeng , WU Hongjie , et al. Multi-controller deployment mechanism for SDN based on topology partitioning[J]. Application Research of Computers, 2017, (11): 3388- 3393. doi: 10.3969/j.issn.1001-3695.2017.11.041
8	刘邦舟, 汪斌强, 王文博, 等. 针对大规模软件定义网络的子域划分及控制器部署方法[J]. 计算机应用, 2016, 36 (12): 3239- 3243. doi: 10.11772/j.issn.1001-9081.2016.12.3239
	LIU Bangzhou , WANG Binqiang , WANG Wenbo , et al. Domain partition and controller placement for large scale software defined network[J]. Journal of Computer Applications, 2016, 36 (12): 3239- 3243. doi: 10.11772/j.issn.1001-9081.2016.12.3239
9	YAO Guang , BI Jun , LI Yuliang , et al. On the capacitated controller placement problem in software defined networks[J]. IEEE Communications Letters, 2014, 18 (8): 1339- 1342. doi: 10.1109/LCOMM.2014.2332341
10	ZHAO Zhipeng , WU Bin . Scalable SDN architecture with distributed placement of controllers for WAN[J]. Concurrency & Computation Practice & Experience, 2017, 29 (16)
11	史久根, 邾伟, 贾坤荥, 等. 软件定义网络中基于负载均衡的多控制器部署算法[J]. 电子与信息学报, 2018, 40 (2): 455- 461.
	SHI Jiugen , ZHU Wei , JIA Kunying , et al. Multi-controller deployment algorithm based on load balance in software defined network[J]. Journal of Electronics & Information Technology, 2018, 40 (2): 455- 461.
12	SHI Yuhui, EBERHART C R. Parameter selection in particle swarm optimization[C]//International Conference on Evolutionary Programming. Berlin: Springer, 1998: 591-600.
13	刘智, 端木京顺, 王强, 等. 基于熵权多目标决策的方案评估方法研究[J]. 数学的实践与认识, 2005, 35 (10): 114- 119. doi: 10.3969/j.issn.1000-0984.2005.10.020
	LIU Zhi , DUANMU Jingshun , WANG Qiang , et al. An evaluation method of scheme based on entropy weight multi-objection decision-making[J]. Mathematics in Practice and Theory, 2005, 35 (10): 114- 119. doi: 10.3969/j.issn.1000-0984.2005.10.020

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

因素	方案1	方案2	…	方案n
交换机到控制器的平均时间延迟的倒数	b₁₁	b₁₂	…	b_1n
控制器的剩余处理能力	b₂₁	b₂₂	…	b_2n
负载均衡率	b₃₁	b₃₂	…	b_3n

因素	交换机到控制器平均时间延迟的倒数	控制器剩余处理能力	负载均衡率
熵(H_i)	H₁	H₂	H₃

[1]	谭韧,殷肖川,焦贤龙,廉哲,陈玉鑫. 一种软件定义APT攻击移动目标防御网络架构[J]. 山东大学学报（理学版）, 2018, 53(1): 38-45.
[2]	马兰,李伟岸,尹天懿. 基于变邻域搜索改进的冲突解脱粒子群算法[J]. 山东大学学报（理学版）, 2017, 52(1): 23-28.
[3]	曲滨鹏, 王智昊. 基于粒子群优化的适应Memetic算法分析[J]. 山东大学学报（理学版）, 2014, 49(08): 118-124.
[4]	万智萍1,吕志民1,2*. 一种自适应物种寻优的无线Mesh网络QoS路由算法[J]. J4, 2013, 48(09): 10-16.
[5]	丁卫平1,2,3,王建东2,段卫华2,施佺1. 一种求解属性约简优化的协同粒子群算法[J]. J4, 2011, 46(5): 97-102.
[6]	裴胜玉，周永权*. 一种基于混沌变异的多目标粒子群优化算法[J]. J4, 2010, 45(7): 18-23.
[7]	李彬1,2,李贻斌1,荣学文1. ELM-RBF神经网络的智能优化策略[J]. J4, 2010, 45(5): 48-51.
[8]	. 微生物批式流加发酵的建模及基于HPSO算法的参数辨识[J]. J4, 2009, 44(7): 71-78.
[9]	吴瑞海董吉文段琪庆. 变尺度混沌粒子群与小波的地基沉降预测应用[J]. J4, 2009, 44(11): 75-78.
[10]	张国英,沙芸,江慧娜 . 基于粒子群优化的快速KNN分类算法[J]. J4, 2006, 41(3): 34-36 .

一种SDN控制节点故障恢复的部署策略

A deployment strategy for fault recovery of SDN control nodes

RichHTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 13

相关文章 10

多维度评价

本文评价

推荐阅读 10