一种基于机器学习的虚拟机放置方法

doi:10.19678/j.issn.1000-3428.0052354

计算机工程 ›› 2019, Vol. 45 ›› Issue (5): 135-142. doi: 10.19678/j.issn.1000-3428.0052354

所属专题：机器学习；

一种基于机器学习的虚拟机放置方法

郭良敏^a,b,高俊杰^a,b,胡桂银^a,b

安徽师范大学 a.计算机与信息学院; b.网络与信息安全安徽省重点实验室,安徽芜湖 241003

收稿日期:2018-08-10 出版日期:2019-05-15 发布日期:2019-05-15
作者简介:郭良敏(1980—),女,副教授、博士,主研方向为云计算、服务推荐、信息安全;高俊杰,学士;胡桂银,讲师、硕士。
基金资助:
安徽省自然科学基金(1908085MF190,1508085QF133,1808085MF172)。

A Method for Virtual Machine Placement Based on Machine Learning

GUO Liangmin^a,b,GAO Junjie^a,b,HU Guiyin^a,b

a.School of Computer and Information; b.Anhui Provincial Key Laboratory of Network and Information Security,Anhui Normal University,Wuhu,Anhui 241003,China

Received:2018-08-10 Online:2019-05-15 Published:2019-05-15

摘要/Abstract

摘要：

为改善云数据中心的能耗、负载均衡性和服务等级协议(SLA)违背率,对虚拟机放置策略进行优化。基于IaaS环境,提出一种基于机器学习的虚拟机迁移调整方法。根据资源消耗的互补性和不均衡性对虚拟机进行预放置,使用深度神经网络预测物理机负载等级,并利用深度Q网络调整物理机数量。实验结果表明,该方法能够有效均衡负载分布,降低能源开销和SLA违背率。

关键词: 虚拟机放置, 机器学习, 能耗, 负载均衡, 服务等级协议

Abstract:

In order to improve energy consumption,load balance,and Service Level Agreement(SLA) violation rate of cloud data centers,it is necessary to optimize virtual machine placement strategy.Therefore,based on the IaaS environment,a virtual machine migration adjustment method based on machine learning is proposed.The virtual machine is pre-placed according to the complementarity and imbalance of resource consumption,the deep neural network is used to predict the physical machine load level,and the Deep Q Network(DQN) is used to adjust the number of physical machines.Experimental results show that this method can effectively balance load distribution,reduce energy cost and SLA violation rate.

Key words: virtual machine placement, machine learning, energy consumption, load balance, Service Level Agreement(SLA)

中图分类号:

TP399

郭良敏,高俊杰,胡桂银. 一种基于机器学习的虚拟机放置方法[J]. 计算机工程, 2019, 45(5): 135-142.

GUO Liangmin,GAO Junjie,HU Guiyin. A Method for Virtual Machine Placement Based on Machine Learning[J]. Computer Engineering, 2019, 45(5): 135-142.

http://www.ecice06.com/CN/Y2019/V45/I5/135

参考文献

［1］ZHANG Xiaojing,LINDBERG T,XIONG N,et al.Cooling energy consumption investigation of data center it room with vertical placed server［J］.Energy Procedia,2017,105:2047-2052.
［2］KUSIC D,KEPHART J O,HANSON J E,et al.Power and performance management of virtualized computing environments via lookahead control［J］.Cluster Computing,2009,12(1):1-15.
［3］ZHENG Qinghua,LI Rui,LI Xiuqi,et al.A multi-objective biogeography-based optimization for virtual machine placement［C］//Proceedings of the 15th IEEE/ACM International Symposium on Cluster,Cloud and Grid Computing.Washington D.C.,USA:IEEE Press,2015:687-696.
［4］JIANG Dailin,HUANG Peijie,LIN Piyuan,et al.Energy efficient VM placement heuristic algorithms comparison for cloud with multidimensional resources［C］//Proceedings of International Conference on Information Computing and Applications.Berlin,Germany:Springer,2012:413-420.
［5］LI Rui,ZHENG Qinghua,LI Xiuqi,et al.A novel multi-objective optimization scheme for rebalancing virtual machine placement［C］//Proceedings of the 9th IEEE International Conference on Cloud Computing.Washington D.C.,USA:IEEE Press,2016:710-717.
［6］AHVAR E,AHVAR S,MANN Z A,et al.CACEV:a cost and carbon emission-efficient virtual machine placement method for green distributed clouds［C］//Proceedings of IEEE International Conference on Services Computing.Washington D.C.,USA:IEEE Press,2016:275-282.
［7］FELLER E,RILLING L,MORIN C.Energy-aware ant colony based workload placement in clouds［C］//Proceedings of the 12th International Conference on Grid Computing.Washington D.C.,USA:IEEE Computer Society,2011:26-33.
［8］TSAIM H,CHOU J,CHEN J.Prevent VM migration in virtualized clusters via deadline driven placement policy［C］//Proceedings of IEEE International Conference on Cloud Computing Technology and Science.Washington D.C.,USA:IEEE Computer Society,2013:599-606.
［9］徐思尧,林伟伟,王子骏.基于负载高峰特征的虚拟机放置算法［J］.软件学报,2016,27(7):1876-1887.
［10］BOBROFF N,KOCHUT A,BEATY K.Dynamic placement of virtual machines for managing SLA violations［C］//Proceedings of the 10th IFIP/IEEE International Symposium on Integrated Network Management.Washington D.C.,USA:IEEE Press,2007:119-128.
［11］BUYYA R,GARG S K,CALHEIROS R N.SLA-oriented resource provisioning for cloud computing:challenges,architecture,and solutions［C］//Proceedings of International Conference on Cloud and Service Computing.Washington D.C.,USA:IEEE Computer Society,2011:1-10.
［12］VERMA M,GANGADHARAN G R,NARENDRA N C,et al.Dynamic resource demand prediction and allocation in multi-tenant service clouds［J］.Concurrency and Computation:Practice and Experience,2016,28(17):4429-4442.
［13］HUANG Wei,LI Xin,QIAN Zhuzhong.An energy efficient virtual machine placement algorithm with balanced resource utilization［C］//Proceedings of the 7th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing.Washington D.C.,USA:IEEE Press,2013:313-319.
［14］FARAHNAKIAN F,LILJEBERG P,PLOSILA J.Energy-efficient virtual machines consolidation in cloud data centers using reinforcement learning［C］//Proceedings of the 22nd Euromicro International Conference on Parallel,Distributed,and Network-Based Processing.Washington D.C.,USA:IEEE Computer Society,2014:500-507.
［15］GHOBAEI-ARANI M,RAHMANIAN A A,SHAMSI M,et al.A learning-based approach for virtual machine placement in cloud data centers［EB/OL］.［2018-07-02］.https://onlinelibrary.wiley.com/doi/full/10.1002/dac.3537.
［16］RANJBARI M,AKBARI TORKESTANI J.A learning automata-based algorithm for energy and SLA efficient consolidation of virtual machines in cloud data centers［J］.Journal of Parallel and Distributed Computing,2017,113:55-62.
［17］BELOGLAZOV A,BUYYA R.Optimal online deterministic algorithms and adaptive heuristics for energy and performance efficient dynamic consolidation of virtual machines in cloud data centers［J］.Concurrency and Computation:Practice and Experience,2012,24(13):1397-1420.
［18］ZHU Qian,ZHU Jiedan,AGRAWAL G.Power-aware consolidation of scientific workflows in virtualized environments［C］//Proceedings of ACM/IEEE International Conference for High Performance Computing,Networking,Storage and Analysis.Washington D.C.,USA:IEEE Computer Society,2010:1-12.
［19］MENG Xiaoqiao,ISCI C,KEPHART J,et al.Efficient resource provisioning in compute clouds via VM multiplexing［C］//Proceeding of the 7th International Conference on Autonomic Computing.New York,USA:ACM Press,2010:11-20.
［20］NG A Y.Shaping and policy search in reinforcement learning［D］.Berkeley,USA:University of California,2003.
［21］MNIH V,KAVUKCUOGLU K,SILVER D,et al.Playing atari with deep reinforcement learning［EB/OL］.［2018-07-02］.https://arxiv.org/pdf/1312.5602v1.pdf.
［22］SCHAUL T,QUAN J,ANTONOGLOU I,et al.Prioritized experience replay ［EB/OL］.［2018-07-02］.https://arxiv.org/pdf/1511.05952.pdf.
［23］DUCHI J,HAZAN E,SINGER Y.Adaptive subgradient methods for online learning and stochastic optimization［J］.The Journal of Machine Learning Research,2011,12:2121-2159.

[1]	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.
[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]	李强, 仪晋辉, 杜婷婷, 王胜春. 移动边缘计算中基于A3C的依赖任务卸载与资源分配[J]. 计算机工程, 2023, 49(6): 42-52.
[4]	陈治旭, 靳雁霞, 芦烨, 杨晶, 刘亚变, 史志儒. 基于子图卷积神经网络的多精度服装建模方法[J]. 计算机工程, 2023, 49(4): 174-181.
[5]	刘金硕, 詹岱依, 邓娟, 王丽娜. 基于深度神经网络和联邦学习的网络入侵检测[J]. 计算机工程, 2023, 49(1): 15-21,30.
[6]	葛昕, 邹福泰, 郭万达, 谭越, 李林森. 社交僵尸网络发展综述[J]. 计算机工程, 2022, 48(8): 12-24.
[7]	俞莎莎, 牛保宁. 基于交易不可信度的比特币非法交易检测[J]. 计算机工程, 2022, 48(8): 166-172.
[8]	金海波, 赵欣越. 共形预测框架下的高可靠入侵检测算法[J]. 计算机工程, 2022, 48(7): 130-140.
[9]	钱龙, 赵静, 韩京宇, 毛毅. 基于标签相关性的K近邻多标签学习[J]. 计算机工程, 2022, 48(6): 73-78,88.
[10]	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.
[11]	李莉, 任振康, 石可欣. 代价敏感的Boosting软件缺陷预测方法[J]. 计算机工程, 2022, 48(3): 175-180.
[12]	刘鹏, 叶润, 闫斌, 谢茜, 刘睿. 一种深度回声状态网络的输入尺度自适应算法[J]. 计算机工程, 2022, 48(2): 92-98,105.
[13]	雷恒林, 古兰拜尔·吐尔洪, 买日旦·吾守尔, 曾琪. 基于Hellinger距离与词向量的终身机器学习主题模型[J]. 计算机工程, 2022, 48(11): 89-95.
[14]	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.
[15]	陈良臣, 傅德印. 面向小样本数据的机器学习方法研究综述[J]. 计算机工程, 2022, 48(11): 1-13.

选择文件类型/文献管理软件名称

选择包含的内容

一种基于机器学习的虚拟机放置方法

A Method for Virtual Machine Placement Based on Machine Learning

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

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

一种基于机器学习的虚拟机放置方法

A Method for Virtual Machine Placement Based on Machine Learning

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价