Fluctuation-Aware and Predictive Workflow Scheduling in Cost-Effective Infrastructure-as-a-Service Clouds

Fluctuation-Aware and Predictive Workflow Scheduling in Cost-Effective Infrastructure-as-a-Service Clouds
复制标题

经济高效的基础设施即服务云中的波动感知和预测工作流调度

DOI:
10.1109/access.2018.2869827
复制
发表时间:
2018-09
期刊:
IEEE ACCESS 6
影响因子:
--
通讯作者:
朱庆生
朱庆生
中科院分区:
其他
文献类型:
--
作者:
李蔚凌;夏云霓;周孟初;孙晓宁;朱庆生

文献摘要

参考文献

被引文献

相似文献

云计算正在成为执行科学应用程序(如科学工作流程)的越来越受欢迎的平台。与网格和其他传统的高性能计算系统相比,云提供了可定制的基础设施,其中科学工作流可以在执行之前提供所需的资源,并在虚拟机(VM)上设置所需的软件环境。然而,各种挑战,特别是其服务质量预测和优化调度,尚未得到解决。现有的研究主要考虑工作流任务执行的虚拟机具有时不变的,随机的,或有界的性能,并专注于最大限度地减少工作流的执行时间或执行成本,同时满足服务质量的要求。这项工作考虑了时变性能,旨在最大限度地减少部署在云结构即服务云上的工作流的执行成本,同时满足与用户的服务级别协议。我们采用基于时间序列的方法来捕捉动态性能波动,饲料的遗传算法与虚拟机的预测性能,并在运行时生成时间表。基于真实世界的第三方IaaS云和一些著名的科学工作流的案例研究表明,我们提出的方法优于传统方法,特别是那些只考虑时间不变或有限性能的方法。
Cloud computing is becoming an increasingly popular platform for the execution of scientific applications such as scientific workflows. In contrast to grids and other traditional high-performance computing systems, clouds provide a customizable infrastructure where scientific workflows can provision desired resources ahead of the execution and set up a required software environment on virtual machines (VMs). Nevertheless, various challenges, especially its quality-of-service prediction and optimal scheduling, are yet to be addressed. Existing studies mainly consider workflow tasks to be executed with VMs having time-invariant, stochastic, or bounded performance and focus on minimizing workflow execution time or execution cost while meeting the quality-of-service requirements. This work considers time-varying performance and aims at minimizing the execution cost of workflow deployed on Infrastructure-as-a-Service clouds while satisfying Service-Level-Agreements with users. We employ time-series-based approaches to capture dynamic performance fluctuations, feed a genetic algorithm with predicted performance of VMs, and generate schedules at run-time. A case study based on real-world third-party IaaS clouds and some well-known scientific workflows show that our proposed approach outperforms traditional approaches, especially those considering time-invariant or bounded performance only.
支持迁移且容易出错的云的随机建模和性能分析
DOI: 10.1109/tii.2015.2405792
发表时间: 2015-02
期刊: IEEE Trans. Industrial Informatics
影响因子: --
作者:
夏云霓;周孟初;罗辛;庞善臣
通讯作者: 庞善臣
基于时间序列分析的云服务多值协同QoS预测
DOI: 10.1016/j.future.2016.10.012
发表时间: 2017-03
影响因子: 7.5
作者:
Ma Hua;Zhu Haibin;Hu Zhigang;Tang Wensheng;Dong Pingping
通讯作者: Dong Pingping
DOI: 10.1109/jas.2017.7510406
发表时间: 2017-04
期刊: IEEE/CAA Journal of Automatica Sinica
影响因子: --
作者:
Ning Ran;H. Su;Shouguang Wang
通讯作者: Ning Ran;H. Su;Shouguang Wang
DOI: 10.1016/j.jpdc.2011.01.008
发表时间: 2011-06
期刊: J. Parallel Distributed Comput.
影响因子: --
作者:
Eun-Kyu Byun;Yang-Suk Kee;Jin-Soo Kim;E. Deelman;S. Maeng
通讯作者: Eun-Kyu Byun;Yang-Suk Kee;Jin-Soo Kim;E. Deelman;S. Maeng
DOI: 10.1109/tcc.2014.2310737
发表时间: 2014-01
影响因子: 6.5
作者:
R. Ghosh;F. Longo;Flavio Frattini;S. Russo;Kishor S. Trivedi
通讯作者: R. Ghosh;F. Longo;Flavio Frattini;S. Russo;Kishor S. Trivedi