DCN中基于前馈神经网络的动态多路径负载均衡方法

doi:10.19678/j.issn.1000-3428.0059097

计算机工程 ›› 2021, Vol. 47 ›› Issue (9): 113-119. doi: 10.19678/j.issn.1000-3428.0059097

DCN中基于前馈神经网络的动态多路径负载均衡方法

左攀, 束永安

安徽大学计算机科学与技术学院, 合肥 230601

收稿日期:2020-07-29 修回日期:2020-09-10 发布日期:2020-09-30
作者简介:左攀(1994-),男,硕士研究生,主研方向为软件定义网络;束永安,教授、博士。
基金资助:
安徽省自然科学基金（1408085MF125）。

Dynamic Multi-Path Load Balancing Method Based on Feedforward Neural Network in DCN

ZUO Pan, SHU Yongan

College of Computer Science and Technology, Anhui University, Hefei 230601, China

Received:2020-07-29 Revised:2020-09-10 Published:2020-09-30

摘要/Abstract

摘要： 针对数据中心网络（DCN）中因大象流而引起的网络负载不均衡问题，提出一种基于前馈神经网络的动态多路径负载均衡方法。在拓扑感知和流量信息监控的基础上对大象流进行标记，将收集到的网络流量信息输入前馈神经网络以预估每段链路的负载，并结合优化蚁群算法为大象流寻找最优路径，使大象流根据链路的实时状态完成路径选择。仿真结果表明，该方法能够有效降低网络传输时延，提高链路利用率和网络吞吐量。

关键词: 软件定义网络, 数据中心网络, 负载均衡, 前馈神经网络, 蚁群算法

Abstract: In order to solve the problem of unbalanced network load caused by elephant flows in Data Center Network(DCN), a dynamic multi-path load balancing method based on feedforward neural network(FNN) is proposed.In this method, topological perception and flow information monitoring are carried out first, and the elephant flows are marked.The collected network traffic information is then used as inputs to estimate the load of each link through the FNN.Finally, the optimal paths are found for the elephant flows by combining with the optimized ant colony algorithm, so that the elephant flows complete the paths selection according to the real-time state of the links.Simulation results show that the proposed method can effectively reduce network transmission delay and improve link utilization and network throughput.

Key words: Software Defined Network(SDN), Data Center Network(DCN), load balancing, Feedforward Neural Network(FNN), ant colony algorithm

中图分类号:

TP393

左攀, 束永安. DCN中基于前馈神经网络的动态多路径负载均衡方法[J]. 计算机工程, 2021, 47(9): 113-119.

ZUO Pan, SHU Yongan. Dynamic Multi-Path Load Balancing Method Based on Feedforward Neural Network in DCN[J]. Computer Engineering, 2021, 47(9): 113-119.

https://www.ecice06.com/CN/Y2021/V47/I9/113

图/表 8

20210917190541

20210917190544

20210917190548

20210917190552

20210917190555

20210917190600

20210917190607

20210917190611

参考文献

[1] AL-FUQAHA A, GUIZANI M, MOHAMMADI M, et al.Internet of things:a survey on enabling technologies, protocols, and applications[J].IEEE Communications Surveys & Tutorials, 2015, 17(4):2347-2376.
[2] 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 C K, CUI Y, TANG H Y, et al.State-of-the-Art survey on Software-Defined Networking(SDN)[J].Journal of Software, 2015, 26(1):62-81.(in Chinese)
[3] AL-FARES M, LOUKISSAS A, VAHDAT A.A scalable, commodity data center network architecture[J].ACM SIGCOMM Computer Communication Review, 2009, 38(4):63-74.
[4] GREENBERG A, HAMILTON J R, JAIN N, et al.VL2:a scalable and flexible data center network[J].Communications of the ACM, 2011, 54(3):95-104.
[5] LEE B, KANAGAVELU R, AUNG K M M.An efficient flow cache algorithm with improved fairness in software-defined data center networks[C]//Proceedings of 2013 IEEE International Conference on Cloud Networking.Washington D.C., USA:IEEE Press, 2013:18-24.
[6] LIU F, GUO J, HUANG X, et al.eBA:efficient bandwidth guarantee under traffic variability in datacenters[J].IEEE ACM Transactions on Networking, 2017, 25(1):506-519.
[7] MCKEOWN N, ANDERSON T, BALAKRISHNAN H, et al.OpenFlow:enabling innovation in campus networks[J].ACM SIGCOMM Computer Communication Review, 2008, 38(2):69-74.
[8] DORIGO M, BIRATTARI M, STÜTZLE T.Ant colony optimization[J].IEEE Computational Intelligence Magazine, 2006, 1(4):28-39.
[9] HOPPS C.Analysis of an equal-cost multi-path algorithm:RFC2992[S].[S.l.]:RFC Editor, 2000.
[10] BALLANI H, COSTA P, GKANTSIDIS C, et al.Enabling end-host network functions[C]//Proceedings of 2015 ACM Conference on Special Interest Group on Data Communication.New York, USA:ACM Press, 2015:493-507.
[11] ALFARES M, RADHAKRISHNAN S, RAGHAVAN B, et al.Hedera:dynamic flow scheduling for data center networks[C]//Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation.Berkeley, USA:USENIX, 2010:19.
[12] MAHAPATRA S, YUAN X.Load balancing mechanisms in data center networks[C]//Proceedings of the 7th International Conference and Expo on Emerging Technologies for a Smarter World.Incheon, Korea:CEWIT, 2010:1-5.
[13] HE K, ROZNER E, AGARWAL K, et al.Presto:edge-based load balancing for fast datacenter networks[C]//Proceedings of 2015 ACM Conference on Special Interest Group on Data Communication.New York, USA:ACM Press, 2015:465-478.
[14] CURTIS A R, KIM W H, YALAGANDULA P.Mahout:low-overhead datacenter traffic management using end-host-based elephant detection[C]//Proceedings of IEEE International Conference on Computer Communications.Washington D.C., USA:IEEE Press, 2011:1629-1637.
[15] PAKZAD F, PORTMANN M, TAN W L, et al.Efficient topology discovery in OpenFlow-based software defined networks[J].Computer Communications, 2016, 77:52-61.
[16] BALDI P, VERSHYNIN R.The capacity of feedforward neural networks[J].Neural Networks, 2019, 116:288-311.
[17] CAI G W, FANG Z, CHEN Y F.Estimating the number of hidden nodes of the single-hidden-layer feedforward neural networks[C]//Proceedings of the 15th International Conference on Computational Intelligence and Security.Washington D.C., USA:IEEE Press, 2019:172-176.
[18] 马振.改进蚁群算法及其在TSP中的应用研究[D].青岛:青岛理工大学, 2016. MA Z.Research on the improvement of ant colony algorithm and its application in TSP[D].Qingdao:Qingdao University of Technology, 2016.(in Chinese)
[19] Ryu OpenFlow controller[EB/OL].(2017-09-05)[2020-06-12].http://osrg.github.io/ryu/.
[20] Mininet:an instant virtual network on your laptop(or other PC)[EB/OL].(2018-08-28)[2020-06-12].http://mininet.org/.
[21] 张白, 宋安军.基于Iperf的网络性能测量研究[J].电脑知识与技术, 2009, 36(5):10227-10229. ZHANG B, SONG A J.Iperf-based network performance measurement[J].Computer Knowledge and Technology, 2009, 36(5):10227-10229.(in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容

DCN中基于前馈神经网络的动态多路径负载均衡方法

Dynamic Multi-Path Load Balancing Method Based on Feedforward Neural Network in DCN

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	彭世明, 林士飏, 贾硕, 杨苗会. 基于负载预测的多目标优化任务卸载策略[J]. 计算机工程, 2024, 50(1): 206-215.
[2]	刘向举, 赵犇, 方贤进, 徐杨洋. SDN中基于过程优化的动态负载均衡策略[J]. 计算机工程, 2023, 49(8): 137-145.
[3]	赵徐炎, 崔允贺, 钱清, 郭春, 申国伟. 基于虚拟扩展网络的虚拟机及路由路径联合部署[J]. 计算机工程, 2023, 49(8): 154-162.
[4]	付嘉豪, 杨嘉怡, 李爱国. 面向安防系统的高效用语义轨迹模式挖掘[J]. 计算机工程, 2023, 49(6): 62-70.
[5]	陈何雄, 罗宇薇, 韦云凯, 郭威, 杭菲璐, 何映军, 杨宁. 基于联邦学习的SDN异常流量协同检测技术[J]. 计算机工程, 2023, 49(3): 168-176.
[6]	刘宇宸, 唐菀, 杨喜敏, 张艳. 引入区块链的SDN路由一致性检测[J]. 计算机工程, 2023, 49(11): 160-168.
[7]	王奎宇, 宋晓勤, 缪娟娟, 张昕婷, 雷磊. 基于SDN的高性能QoS保障低轨道卫星星间路由算法[J]. 计算机工程, 2022, 48(5): 185-190,199.
[8]	叶和元, 韩俐, 孙士民. SDN中基于蚁群优化的网络测量节点选择算法[J]. 计算机工程, 2022, 48(5): 191-199.
[9]	张然, 高莹雪, 赵钰, 丁元明. 基于Q学习量子蚁群的微纳卫星路由算法[J]. 计算机工程, 2022, 48(3): 162-169,188.
[10]	贺鹏飞, 范鹏飞, 尹千慧, 王中训, 张桐敬, 梁大伟. 基于负载均衡算法的Hyperledger Fabric共识机制研究[J]. 计算机工程, 2022, 48(11): 170-176.
[11]	杜欣欣, 胡晓辉, 赵佳楠. 一种软件定义车载自组织网络的QoS路由算法[J]. 计算机工程, 2022, 48(11): 184-191,200.
[12]	李亚朋, 庞建民, 徐金龙, 聂凯. 一种针对线性循环结构的非线性静态调度策略[J]. 计算机工程, 2022, 48(1): 155-162.
[13]	赵季红, 张文娟, 乔琳琳, 张梦雪. 服务功能链中基于机器学习的QoE评估与预测[J]. 计算机工程, 2022, 48(1): 163-169.
[14]	施凌鹏, 朱征, 周俊松, 李鑫, 李静. 面向微服务架构的云系统负载均衡机制[J]. 计算机工程, 2021, 47(9): 44-50,58.
[15]	徐啸, 顾玲丽, 陈建平, 傅启明, 陆悠. 一种智能多路径路由及子流分配协同算法[J]. 计算机工程, 2021, 47(9): 136-144,152.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

DCN中基于前馈神经网络的动态多路径负载均衡方法

Dynamic Multi-Path Load Balancing Method Based on Feedforward Neural Network in DCN

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献

相关文章 15

编辑推荐

Metrics

本文评价