基于深度增强学习的数据中心网络coflow调度机制

doi:10.3969/j.issn.0372-2112.2018.07.011

电子学报 ›› 2018, Vol. 46 ›› Issue (7): 1617-1624.DOI: 10.3969/j.issn.0372-2112.2018.07.011

基于深度增强学习的数据中心网络coflow调度机制

马腾, 胡宇翔, 张校辉

国家数字交换系统工程技术研究中心, 河南郑州 450002

收稿日期:2017-03-17 修回日期:2017-06-13 出版日期:2018-07-25
- 通讯作者:
- 马腾
- 作者简介:
- 胡宇翔,男,1982年生,河南周口人,国家数字交换系统工程技术研究中心副研究员,主要研究方向为网络体系结构;张校辉,男,1979年生,河南洛阳人,国家数字交换系统工程技术研究中心讲师,主要研究方向为网络体系结构、网络安全.
- 基金资助:
- 国家973重点基础研究发展计划 (No.2013CB329104）; 国家863高技术研究发展计划 (No.2013AA013505）

Deep Reinforcement Learning Based Coflow Scheduling in Data Center Networks

MA Teng, HU Yu-xiang, ZHANG Xiao-hui

National Digital Switching System Engineering & Technology Research Center, Zhengzhou, Henan 450002, China

Received:2017-03-17 Revised:2017-06-13 Online:2018-07-25 Published:2018-07-25
- Corresponding author:
- MA Teng
- Supported by:
- National Program on Key Basic Research Project of China (973 Program) (No.2013CB329104); National High-tech R&D Program of China (863 Program) (No.2013AA013505)

摘要/Abstract

摘要： 最小化语义相关流的平均完成时间是数据中心网络流量管理面临的难题之一.受人工智能领域深度增强学习方向的最新研究进展启发，本文提出一种的新的语义相关流调度机制.将带宽约束的语义相关流调度问题转化为连续的学习过程，通过学习以往策略实现最佳调度.引入反向填充和有限复用机制，保证系统的工作保持性和无饥饿性.仿真结果表明，在不同的网络负载下，本文提出的调度机制均使得语义相关流的平均完成时间小于其他调度机制，尤其是网络负载较大时，相比最先进的调度机制，性能提升约50%.

关键词: 数据中心网络, 语义相关流, 流调度

Abstract: Coflow completion time minimization is one of the challenges of traffic management in data center networks.Inspired by the newest research progress in deep reinforcement learning,which is one direction of artificial intelligence,this paper proposes a novel coflow scheduling mechanism.It translates the coflow scheduling problem with bandwidth constraint into a continuous learning process.By learning the previous decisions,the best scheduling is obtained.By introducing back filling and limited multiplexing mechanisms,the system is work-conserving and starvation-free.Simulation results show that,under different network load,compared with other scheduling mechanisms,the average coflow completion time is reduced.Especially when the network load is heavy,the proposed mechanism achieves about 50% performance improvement than the state-of-the-art scheduling mechanism.

Key words: data center network, coflow, flow scheduling

中图分类号:

TP393

马腾, 胡宇翔, 张校辉. 基于深度增强学习的数据中心网络coflow调度机制[J]. 电子学报, 2018, 46(7): 1617-1624.

MA Teng, HU Yu-xiang, ZHANG Xiao-hui . Deep Reinforcement Learning Based Coflow Scheduling in Data Center Networks[J]. Acta Electronica Sinica, 2018, 46(7): 1617-1624.

参考文献

[1] DEAN J,GHEMAWAT S.Map Reduce:simplified data processing on large clusters[J].Communications of the ACM,2008,51(1):107-113.
[2] ZAHARIA M,CHOWDHURY M,FRANKLIN M J,et al.Spark:cluster computing with working sets[J].HotCloud,2010,10(10-10):95.
[3] ISARD M,BUDIU M,YU Y,et al.Dryad:distributed data-parallel programs from sequential building blocks[A].Proceedings of ACM EuroSys[C].Lisboa:ACM,2007.59-72.
[4] CHOWDHURY M,ZAHARIA M,MA J,et al.Managing data transfers in computer clusters with orchestra[J].ACM Special Interest Group on Data Communication,2011,41(4):98-109.
[5] CHOWDHURY M,STOICA I.Coflow:A networking abstraction for cluster applications[A].Proceedings of ACM HotNets[C].Redmond:ACM,2012.31-36.
[6] SILVER D,HUANG A,MADDISON C,et al.Mastering the game of Go with deep neural networks and tree search[J].Nature,2016,529(7587):484-489.
[7] 赵冬斌,邵坤,朱圆恒,等.深度强化学习综述:兼论计算机围棋的发展[J].控制理论与应用,2016,33(6):701-717. ZHAO Dong-bin,SHAO Kun,ZHU Yuan-heng,et al.Review of deep reinforcement learning and discussions on the development of computer Go[J].Control Theory & Applications,2016,33(6):701-717.(in Chinese)
[8] MNIH V,KAVUKCUOGLU K,SILVER D,et al.Human-level control through deep reinforcement learning[J].Nature,2015,518(7540):529-533.
[9] MAO H,ALIZADEH M,MENACHE I,et al.Resource management with deep reinforcement learning[A].Proceedings of the ACM HotNets[C].Atlanta:ACM,2016.50-56.
[10] WILSON C,BALLANI H,KARAGIANNIS T,et al.Better never than late:meeting deadlines in datacenter networks[J].ACM Special Interest Group on Data Communication,2011,41(4):50-61.
[11] HONG C,CAESAR M,GODFREY P B,et al.Finishing flows quickly with preemptive scheduling[J].ACM Special Interest Group on Data Communication,2012,42(4):127-138.
[12] ALIZADEH M,YANG S,SHARIF M,et al.Pfabric:Minimal near-optimal datacenter transport[A].ACM SIGCOMM Computer Communication Review[C].Hong Kong:ACM,2013.435-446.
[13] CHOWDHURY M,ZHONG Y,STOICA I.Efficient coflow scheduling with varys[A].Proceedings of ACM SIGCOMM[C].Chicago:ACM,2014.443-454.
[14] DOGAR F R,KARAGIANNIS T,BALLANI H,et al.Decentralized task-aware scheduling for data center networks[A].Proceedings of the ACM SIGCOMM Computer Communication Review[C].Chicago:ACM,2014.431-442.
[15] ZHAO Y,CHEN K,BAI W,et al.Rapier:Integrating routing and scheduling for coflow-aware data center networks[A].Proceedings of IEEE INFOCOM[C].Hong Kong:IEEE,2015.424-432.
[16] MC KEOWN N,ANDERSON T,BALAKRISHNAN H,et al.OpenFlow:enabling innovation in campus networks[J].ACM SIGCOMM Computer Communication Review,2008,38(2):69-74.
[17] JEYAKUMAR V,ALIZADEH M,MAZIèRES D,et al.EyeQ:Practical network performance isolation at the edge[A].Proceedings of NSDI[C].Lombard:USENIX,2013.297-312.
[18] SUTTON R S,BARTO A G.Reinforcement Learning:An Introduction[M].Cambridge:MIT Press,1998.
[19] HAGAN M T,DEMUTH H B,BEALE M H,et al.Neural Network Design[M].USA:PWS Publishing Company Boston,1996.
[20] SUTTON R S,MCALLESTER D A,SINGH S P,et al.Policy gradient methods for reinforcement learning with function approximation[A].Proceedings of NIPS[C].Denver:NIPS,2000.1057-1063.
[21] SCHULMAN J,LEVINE S,ABBEEL P,et al.Trust region policy optimization[A].Proceedings of ICML[C].Lille:IMLS,2015.1889-1897.
[22] JIANG J,MA S,LI B,et al.Adia:achieving high link utilization with coflow-aware scheduling in data center networks[J].IEEE Transactions on Cloud Computing,2016,99(11):1-10.
[23] MA S,JIANG J,LI B,et al.Chronos:meeting coflow deadlines in data center networks[A].Proceedings of the IEEE International Conference on Communications (ICC)[C].Kuala Lumpur:IEEE,2016.1-6.

基于深度增强学习的数据中心网络coflow调度机制

Deep Reinforcement Learning Based Coflow Scheduling in Data Center Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

[1]	崔子熙, 胡宇翔, 兰巨龙, 王雨. 基于流分类的数据中心网络负载均衡机制[J]. 电子学报, 2021, 49(3): 559-565.
[2]	罗智勇, 朱梓豪, 谢志强, 孙广路. 面向云计算的花朵差分授粉工作流多目标优化算法研究[J]. 电子学报, 2021, 49(3): 470-476.
[3]	臧韦菲, 兰巨龙, 胡宇翔. 基于松弛时间与累计发送量的数据中心网络混合流调度机制[J]. 电子学报, 2019, 47(10): 2061-2068.
[4]	林智华, 高文, 吴春明, 李勇燕. 基于离散粒子群算法的数据中心网络流量调度研究[J]. 电子学报, 2016, 44(9): 2197-2202.
[5]	宣恒农, 张润驰, 左苗, 刘田田. 面向数据中心网络的分层式故障诊断算法[J]. 电子学报, 2014, 42(12): 2536-2542.
[6]	商云飞, 徐明伟, 李丹. 互联网路由设备与协议节能研究综述[J]. 电子学报, 2012, 40(11): 2290-2297.