云计算虚拟资源的熵优化和动态加权评估模型
作者:
基金项目:

国家自然科学基金(61070092)


Virtual Resource Evaluation Model Based on Entropy Optimized and Dynamic Weighted in Cloud Computing
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [23]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    云资源的动态变化和不确定性给资源管理及任务调度带来了很大的困难.为了准确地掌握资源动态负载和可用能力信息,提出一种基于熵优化和动态加权的资源评估模型,其中,熵优化模型利用最大熵和熵增原理的目标函数及约束条件,筛选出满足用户QoS 和系统最大化的资源,实现最优调度,保障用户QoS.对筛选后的资源再进行动态加权负载评估,对负载过重及长期不可用资源进行迁移、释放等,可减少能耗,实现负载均衡和提高系统利用率.设计了仿真实验,以验证所提评估模型的性能.实验结果表明,熵优化模型对用户QoS 和系统最大化有很好的效果,动态加权负载评估有利于均衡负载,提高系统利用率.该评估模型实现了用户QoS 保障、减少能耗、负载均衡以及提高系统利用率等多目标的优化.

    Abstract:

    The dynamic and uncertainty of cloud resource makes resource allocation and task scheduling more difficult. In order to retrieve accurate resource information about dynamic loads and available capacity, this study proposes a resource evaluation model based on entropy optimization and dynamic weighting. The entropy optimization filters the resources that satisfy user QoS and system maximization by goal function and constraints of maximum entropy and the entropy increase principle, which achieves optimal scheduling and satisfied user QoS. Then the evaluation model evaluates the load of having filtered resources by dynamic weighted algorithm. In order to reduce energy consumption, achieve load balancing and improve system utilization, the study allows the migration or release the resources which overload and unavailable for a long time. Experimental results show the effect of entropy optimization on user QoS and system maximization, and dynamic weighted algorithm benefits load balancing and system utilization. The experimental results prove that the evaluation model achieves multi-objective optimization such as satisfying user QOS, reducing energy assumption, balancing load, improving system utilization and so on.

    参考文献
    [1] Iosup A, Jan M, Sonmez O, Epema DHJ. On the dynamic resource availability in grids. In: Proc. of the 8th IEEE/ACM Int’l Conf.on Grid Computing (Grid 2007). Texas: IEEE Computer Society, 2007. 26-33. [doi: 10.1109/GRID.2007.4354112]
    [2] Khalili O, He J, Olsehanowsky C, Snavely A, Casanova H. Measuring the performance and reliability of production computationalgrids. In: Proc. of the 7th IEEE/ACM Int’l Conf. on Grid Computing (Grid 2006). Barcelona: IEEE Computer Society, 2006.293-300. [doi: 10.1109/ICGRID.2006.311028]
    [3] Xu M, Cui LZ, Wang HY, Bi YB. A multiple QoS constrained scheduling strategy of multiple workflows for cloud computing. In:Proc. of the 2009 IEEE Int’l Symp. on Parallel and Distributed Processing with Applications. 2009. 629-634. [doi: 10.1109/ISPA.2009.95]
    [4] Chen K, Zheng WM. Cloud computing: System instances and current research. Ruan Jian Xue Bao/Journal of Software, 2009,20(5):1337-1345 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/3493.html [doi: 10.3724/SP.J.1001.2013.03493]
    [5] Tian WH, Zhao Y. Cloud Computing: Resource Scheduling Management. Beijing: National Defence Industry Publishing House,2011 (in Chinese).
    [6] Figueiredo R. Adaptive predictor integration for system performance prediction. In: Proc. of the IEEE Int’l Parallel and DistributedProcessing Symp. IEEE Press, 2007. [doi: 10.1109/IPDPS.2007.370277]
    [7] Diaz I, Fernandez G, Martinm M. Integrating the common information model with MDS4. In: Proc. of the 9th IEEE/ACM Int’lConf. on Grid Computing. 2008. [doi: 10.1109/GRID.2008.4662812]
    [8] Iosup A, Sonmez O, Epema D. The characteristics and performance of groups of jobs in grids. Lecture Notes in Computer Science,2007,46(41):382-393. [doi: 10.1007/978-3-540-74466-5_42]
    [9] Dinda PA, O’Hallaron DR. Host load prediction using linear models. Cluster Computing, 2000,3(4):265-280. [doi: 10.1023/A:1019048724544]
    [10] Bucur AID, Epema DHJ. Scheduling policies for processor collocation in multicluster system. IEEE Trans. on Parallel andDistributed Systems, 2007,18(7):958-962. [doi: 10.1109/TPDS.2007.1036]
    [11] Dai YS, Levitin G, Trivedi KS. Performance and reliability of tree-structured grid services considering data dependence and failurecorrelation. IEEE Trans. on Computers, 2007,56(7):925-936. [doi: 10.1109/TC.2007.1018]
    [12] Fu S, Xu CZ. Exploring event correlation for failure prediction in coalitions of clusters. In: Proc. of the 2007 ACM/ IEEE Conf. onSuper Computing (SC 2007). Nevada: IEEE Computer Society, 2007. 41-52. [doi: 10.1145/1362622.1362678]
    [13] He SJ, Guo L, Guo YK, Ghanem M, Han R, Wu C. Elastic application container: A lightweight approach for cloud resourceprovisioning. In: Proc. of the 2012 IEEE 26th Int’l Conf. on Advanced Information Networking and Applications (AINA). IEEE,2012. 15-22. [doi: 10.1109/AINA.2012.74]
    [14] Kuehnhausen M, Frost VS, Minden GJ. Framework for assessing the trustworthiness of cloud resources. In: Proc. of the 2012 IEEEInt’l Multi-Disciplinary Conf. on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA). 2012. 142-145.[doi: 10.1109/CogSIMA.2012.6188367]
    [15] Verma A, Cherkasova L, Campbell RH. Resource provisioning framework for MapReduce jobs with performance goals. LectureNotes in Computer Science, 2011,70(9):165-186. [doi: 10.1007/978-3-642-25821-3_9]
    [16] Katsaros G, Kousiouris G, Gogouvitis SV, Kyriazis D, Menychtas A, varvarigou T. A self-adaptive hierarchical monitoringmechanism for clouds. Journal of Systems and Software, 2012,85(5):1029-1041. [doi: 10.1016/j.jss.2011.11.1043]
    [17] Gong ZH, Gu XH, Wilkes J. PRESS: Predictive elastic resource scaling for cloud systems. In: Proc. of the 2010 Int’l Conf. onNetwork and Service Management (CNSM). 2010. 9-16. [doi: 10.1109/CNSM.2010.5691343]
    [18] Hu ZJ. The resource availability evaluation in service grid environment for QoS [Ph.D. Thesis]. Changsha: Central SouthUniversity, 2010 (in Chinese with English abstract).
    [19] Iosup A, Jan M, Sonmez OO, Epema DHJ. The characteristics and the performance of groups of jobs in grids. Lecture Notes onComputer Science, 2007,4641(8):382-393. [doi: 10.1007/978-3-540-74466-5_42]
    [20] Ebrahimi N, Maasoumi E, Soofi ES. Ordering univariate distributions by entropy and variance. Journal of Econometrics, 1999,90(2):317-336. [doi: 10.1016/S0304-4076(98)00046-3]
    [21] Tao M, Dong SB, Zhang L. A multi-strategy collaborative prediction model for the runtime of online tasks in computing cluster/grid. Cluster Computing, 2011,14(2):199-210. [doi: 10.1007/s10586-010-0145-4]
    [22] Buyya R, Murshed M. Gridsim: A toolkit for the modeling and simulation of distributed resource management and scheduling forgrid computing. Concurrency and Computation: Practice and Experience, 2002,14(12):1175-1220.
    [23] Azougagh D, Yu JL, Kim JS, Maeng SR. Resource co-allocation: A complementary technique that enhances performance in gridcomputing environment. In: Proc. of the 1lth Int’l Conf. on Parallel and Distributed System (ICPADS 2005). Fukuoka: IEEEComputer Society, 2005. 36-42. [doi: 10.1109/ICPADS.2005.253]
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

左利云,曹志波,董守斌.云计算虚拟资源的熵优化和动态加权评估模型.软件学报,2013,24(8):1937-1946

复制
分享
文章指标
  • 点击次数:4029
  • 下载次数: 7056
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2012-06-19
  • 最后修改日期:2012-12-27
  • 在线发布日期: 2013-07-26
文章二维码
您是第19862253位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号