基于休眠模式与注册服务的云架构性能优化问题的研究

doi:10.11959/j.issn.1000-436x.2019202

通信学报 ›› 2019, Vol. 40 ›› Issue (10): 127-136.doi: 10.11959/j.issn.1000-436x.2019202

基于休眠模式与注册服务的云架构性能优化问题的研究

金顺福^1,², 武海星^1,², 霍甜甜^1,², 赵文娟^1,²

¹ 燕山大学信息科学与工程学院，河北秦皇岛 066004
² 河北省计算机虚拟技术与系统集成重点实验室，河北秦皇岛 066004

修回日期:2019-08-25 出版日期:2019-10-25 发布日期:2019-11-07
作者简介:金顺福（1966- ），女，朝鲜族，内蒙古满洲里人，燕山大学教授、博士生导师，主要研究方向为网络资源分配与优化、排队论研究与应用等。|武海星（1993- ），女，河北邯郸人，燕山大学硕士生，主要研究方向为云资源管理与纳什均衡。|霍甜甜（1994- ），女，河北邯郸人，燕山大学硕士生，主要研究方向为排队理论与博弈论的应用研究。|赵文娟（1994- ），女，河北衡水人，燕山大学硕士生，主要研究方向为马尔可夫决策过程与智能优化。
基金资助:
国家自然科学基金资助项目(61872311);国家自然科学基金资助项目(61973261);河北省自然科学基金资助项目(F2017203141)

On the performance optimization for the cloud architecture with sleep-mode and registration service

Shunfu JIN^1,², Haixing WU^1,², Tiantian HUO^1,², Wenjuan ZHAO^1,²

¹ School of Information Science and Engineering,Yanshan University,Qinhuangdao 066004,China
² The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province,Qinhuangdao 066004,China

Revised:2019-08-25 Online:2019-10-25 Published:2019-11-07
Supported by:
The National Natural Science Foundation of China(61872311);The National Natural Science Foundation of China(61973261);The Natural Science Foundation of Hebei Province(F2017203141)

摘要/Abstract

摘要：

兼顾能量节省与匿名用户的服务质量，结合免费云服务与注册云服务，提出了一种基于休眠模式的新型云架构。将免费云服务抽象为第一次服务，注册云服务抽象为第二次服务，休眠抽象为休假，建立了一个带有二次可选服务且部分虚拟机异步多重休假的排队模型。运用矩阵几何解方法求解排队模型的稳态分布，研究了系统节能率与匿名用户平均响应时间等性能指标。综合匿名用户的服务收益与等待服务所消耗的时间成本，建立了收益函数。利用数值结果揭示了匿名用户纳什均衡到达率与社会最优到达率之间的关系。为实现新型云架构下的社会最优提供理论依据。

关键词: 云架构, 注册云服务, 休眠模式, 二次可选服务, 纳什均衡, 社会最优

Abstract:

In order to balance the energy conservation and the service quality for anonymous users,a novel sleep-mode based architecture with the free cloud service and the registration cloud service was proposed.Regarding the free cloud service as the first service,the registration cloud service as the second service and the sleep sate as the vacation,a partial asynchronous multiple vacation queueing model with a second optional service was built.Applying the method of a matrix-geometric solution,the steady-state distribution of the queueing model was derived,and then the energy saving rate of system as well as the average response time of anonymous users were estimated.By considering the benefits from accessing the cloud service and the time cost on waiting for the cloud service,benefit functions were constructed.Numerical results were carried out to reveal the relationship between Nash equilibrium arrival rate and social optimal arrival rate of anonymous users.The proposed cloud architecture provides a theoretical basis for social optimization.

Key words: cloud architecture, registration cloud service, sleep-mode, second optional service, Nash equilibrium, social optimization

中图分类号:

TP393

金顺福, 武海星, 霍甜甜, 赵文娟. 基于休眠模式与注册服务的云架构性能优化问题的研究[J]. 通信学报, 2019, 40(10): 127-136.

Shunfu JIN, Haixing WU, Tiantian HUO, Wenjuan ZHAO. On the performance optimization for the cloud architecture with sleep-mode and registration service[J]. Journal on Communications, 2019, 40(10): 127-136.

图/表 7

图1

表1

图2

图3

图4

图5

表2

参考文献 20

[1]	KALRA S , SOOD S . ECC-based anti-phishing protocol for cloud computing services[J]. International Journal of Security and Networks, 2013,8(3): 130-138.
[2]	王斌, 李伟民, 盛津芳 ,等. TCCL：安全高效的拓展云桌面架构[J]. 通信学报, 2017,38(Z1): 9-18.
	WANG B , LI W M , SHENG J F ,et al. TCCL:secure and efficient development of desktop cloud structure[J]. Journal on Communications, 2017,38(Z1): 9-18.
[3]	赵辉, 丁鸣, 程青松 ,等. SDN与NFV技术在云数据中心的规模应用[J]. 电信科学, 2016,32(1): 144-151.
	ZHAO H , DING M , CHENG Q S ,et al. Application of SDN and NFV technology in the cloud data center[J]. Telecommunications Science, 2016,32(1): 144-151.
[4]	张建标, 朱元曦, 胡俊 ,等. 面向云环境的虚拟机可信迁移方案[J]. 网络与信息安全学报, 2018,4(1): 6-14.
	ZHANG J B , ZHU Y X , HU J ,et al. Scheme of virtual machine trusted migration in cloud environment[J]. Chinese Journal of Network and Information Security, 2018,4(1): 6-14.
[5]	RUAN Z , DONG A . Designing and implementation of a RFID-based VIP customer service information management system[C]// The International Conference on Information Engineering and Applications. 2013: 741-748.
[6]	HUH M , KIM D , KIM E ,et al. Secure virtual personal cloud service based on CCN/VPC[C]// International Conference on Consumer Electronics. IEEE, 2012: 642-643.
[7]	KLIAZOVICH D , BOUVRY P , GRANELLI F ,et al. Energy consumption optimization in cloud data centers[M]. Wiley-IEEE Press. 2015.
[8]	金顺福, 郝闪闪, 王宝帅 . 融合双速率和工作休眠的虚拟机调度策略及参数优化[J]. 通信学报, 2017,38(12): 10-20.
	JIN S F , HAO S S , WANG B S . Virtual machine scheduling strategy based on dual-speed and work vacation mode and its parameter optimization[J]. Journal on Communications, 2017,38(12): 10-20.
[9]	MADAN K . An M/G/1 queue with second optional service[J]. Queueing Systems, 2000,34(1-4): 37-46.
[10]	GHORBANI-MANDOLAKANI M , RAD M . ML and Bayes estimation in a two-phase tandem queue with a second optional service and random feedback[J]. Communications in Statistics-Theory and Methods, 2016,45(9): 2576-2591.
[11]	YANG D Y , CHEN Y H . Computation and optimization of a working breakdown queue with second optional service[J]. Journal of Industrial and Production Engineering, 2018,35(3): 181-188.
[12]	DOSHI B T . Queueing systems with vacations-A survey[J]. Queueing Systems, 1986,1(1): 29-66.
[13]	马晓彤, 金顺福, 刘建平 ,等. 认知无线电网络中的基站节能策略及纳什均衡研究[J]. 通信学报, 2016,37(7): 172-181.
	MA X T , JIN S F , LIU J P ,et al. Study on energy saving strategy and Nash equilibrium of base station in cognitive radio network[J]. Journal on Communications, 2016,37(7): 172-181.
[14]	JAIN A , JAIN M . Multi server machine repair problem with unreliable server and two types of spares under asynchronous vacation policy[J]. International Journal of Mathematics in Operational Research, 2017,10(3): 1-30.
[15]	CHEN Y , CAI L , WEI C M . A discrete-time Geo/G/1 retrial queue with balking customer,second optional service,Bernoulli vacation and general retrial time[C]// The 7th International Conference on Fuzzy Information and Engineering. 2016: 255-266.
[16]	LI X , LI P , HUANG J ,et al. Performance analysis of cloud computing centers serving parallelizable rendering jobs using M/M/c/r queuing systems[C]// IEEE International Conference on Distributed Computing Systems. IEEE , 2017.
[17]	RAJENDRAN V V , SWAMYNATHAN S . Queuing model for improving QoS in cloud service discovery[C]// International Conference on Frontiers in Intelligent Computing:Theory ＆ Applications. 2016.
[18]	LATOUCHE G , RAMASWAMI V , SETHURAMAN J ,et al. Matrix-analytic methods in stochastic models[M]. Springer, 2013.
[19]	GREENBAUM A . Iterative methods for solving linear systems[M]. Society for Industrial and Applied Mathematics, 2001.
[20]	NAOR P . The regulation of queue size by levying tolls[J]. Econometrica, 1969,37(1): 15-24.

参数	设定值
云架构中虚拟机的数量c /个	10
免费服务率μ₁/s^-1	0.5
注册服务率μ₂/s^-1	0.2
单位时间内虚拟机向匿名用户提供免费服务的能量消耗J_a1/mW	5
单位时间内虚拟机向匿名用户提供注册服务的能量消耗J_a2/mW	4
单位时间内虚拟机处于休眠状态的能量消耗J_s /mW	0.5
虚拟机由休眠状态转换到活跃状态所产生的能量消耗J_t/mJ	6

阈值d	注册概率q	休眠参数θ	纳什均衡到达率λ_e	社会最优到达率λ^*	阈值d	注册概率q	休眠参数θ	纳什均衡到达率λ_e	社会最优到达率λ^*
1	0.1	0.1	3.300 5	1.536 6	5	0.5	0.1	1.922 6	1.203 1
1	0.1	0.2	3.569 3	2.360 6	5	0.5	0.2	1.989 9	1.357 4
1	0.1	0.3	3.626 1	2.591 4	5	0.5	0.3	2.006 7	1.449 0
1	0.1	0.4	3.650 0	2.696 7	5	0.5	0.4	2.012 4	1.472 2
1	0.1	0.5	3.665 0	2.759 0	5	0.5	0.5	2.016 1	1.501 4
1	0.1	0.6	3.675 4	2.805 6	5	0.5	0.6	2.018 6	1.511 1
1	0.1	0.7	3.683 0	2.850 4	5	0.5	0.7	2.020 5	1.543 6
1	0.1	0.8	3.688 8	2.866 5	5	0.5	0.8	2.022 0	1.548 5
1	0.1	0.9	3.693 5	2.888 1	5	0.5	0.9	2.023 2	1.551 3
3	0.3	0.1	2.402 7	1.267 5	7	0.7	0.1	1.621 7	1.162 6
3	0.3	0.2	2.533 0	1.638 3	7	0.7	0.2	1.640 0	1.240 8
3	0.3	0.3	2.568 1	1.806 2	7	0.7	0.3	1.647 4	1.259 8
3	0.3	0.4	2.587 1	1.870 4	7	0.7	0.4	1.651 6	1.262 0
3	0.3	0.5	2.599 2	1.928 0	7	0.7	0.5	1.654 3	1.289 7
3	0.3	0.6	2.603 3	1.965 4	7	0.7	0.6	1.656 3	1.291 7
3	0.3	0.7	2.606 0	1.951 8	7	0.7	0.7	1.657 7	1.292 4
3	0.3	0.8	2.608 0	1.986 7	7	0.7	0.8	1.658 8	1.304 2
3	0.3	0.9	2.609 6	2.009 7	7	0.7	0.9	1.659 7	1.309 4

基于休眠模式与注册服务的云架构性能优化问题的研究

On the performance optimization for the cloud architecture with sleep-mode and registration service

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 20

相关文章 15

Metrics

推荐阅读 0

[1]	范伟, 彭诚, 朱大立, 王雨晴. 移动边缘计算网络下基于静态贝叶斯博弈的入侵响应策略研究[J]. 通信学报, 2023, 44(2): 70-81.
[2]	张红斌, 尹彦, 赵冬梅, 刘滨. 基于威胁情报的网络安全态势感知模型[J]. 通信学报, 2021, 42(6): 182-194.
[3]	张红旗,杨峻楠,张传富. 基于不完全信息随机博弈与Q-learning的防御决策方法[J]. 通信学报, 2018, 39(8): 56-68.
[4]	单芳芳,李晖,朱辉. 基于博弈论的社交网络转发控制机制[J]. 通信学报, 2018, 39(3): 172-180.
[5]	刘建平,金顺福,王宝帅. 基于排队模型的混合overlay/underlay频谱共享优化策略研究[J]. 通信学报, 2017, 38(9): 55-64.
[6]	贾亚男,岳殿武. 认知小蜂窝网络中基于能效的下行资源分配算法[J]. 通信学报, 2016, 37(4): 116-127.
[7]	王洁,蔡永泉,田有亮. 基于博弈论的门限签名体制分析与构造[J]. 通信学报, 2015, 36(5): 148-155.
[8]	魏淑芝,朱琦. 基于网络选择的视频通信带宽博弈算法[J]. 通信学报, 2015, 36(2): 212-220.
[9]	谭雪松，林超，郭伟. 基于合作形成的认知无线网络频谱共享策略[J]. 通信学报, 2014, 35(3): 7-68.
[10]	谭雪松,林超,郭伟. 基于合作形成的认知无线网络频谱共享策略[J]. 通信学报, 2014, 35(3): 58-58.
[11]	张士兵,张国栋,包志华. 认知无线网络中基于代理的动态频谱交易算法[J]. 通信学报, 2013, 34(3): 119-125.
[12]	李方伟，唐永川，朱江. 未知环境中基于图型博弈和Multi-Q学习的动态信道选择算法[J]. 通信学报, 2013, 34(11): 1-7.
[13]	李方伟,唐永川,朱江. 未知环境中基于图型博弈和multi-Q学习的动态信道选择算法[J]. 通信学报, 2013, 34(11): 1-7.
[14]	姜永,陈山枝,胡博. 异构无线网络中基于Stackelberg博弈的分布式定价和资源分配算法[J]. 通信学报, 2013, 34(1): 61-68.
[15]	赵军辉,杨涛,张雪雪. 基于认知无线电的新型非合作功率控制博弈算法[J]. 通信学报, 2012, 33(Z2): 97-103.