当前位置: X-MOL 学术J. Netw. Syst. Manag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Meta-heuristic Approaches for Effective Scheduling in Infrastructure as a Service Cloud: A Systematic Review
Journal of Network and Systems Management ( IF 4.1 ) Pub Date : 2021-01-20 , DOI: 10.1007/s10922-020-09577-2
J. Kok Konjaang , Lina Xu

Cloud computing involves a large number of shared virtual servers that are accessible from both public and private networks. It has provided scalable and multitenant computing approaches for Infrastructure as a Service, Software as a Service, and Platform as a Service to cloud users on pay-per-use bases. Over the past decades, researchers from different domains such as astronomy, physics, earth science, and bioinformatics have used scientific workflow applications to model many real-world problems in both paralleled and distributed computing environments. However, achieving efficient workflow scheduling is challenging. This is due to the large size of the task set that each workflow application generates. The complex dependencies between these workflows make it difficult to find an optimal solution to workflow scheduling problems within polynomial time. This paper analyzed workflows scheduling problems in cloud and grid computing environment through providing a comprehensive survey based on the state-of-the-art meta-heuristic algorithms. We analyzed the literature from four perspectives, including (i) existing meta-heuristics, (ii) scheduling efficiency, system performance, and execution budget, (iii) scheduling environment and (iv) quality of service performance metrics. Also, we have presented the research gaps and provided future directions for future investigation.

中文翻译:

在基础设施即服务云中进行有效调度的元启发式方法:系统回顾

云计算涉及大量共享虚拟服务器,可从公共和私有网络访问。它为基础设施即服务、软件即服务和平台即服务提供了可扩展和多租户的计算方法,以按使用付费的方式为云用户提供服务。在过去的几十年里,来自天文学、物理学、地球科学和生物信息学等不同领域的研究人员使用科学工作流应用程序对并行和分布式计算环境中的许多现实问题进行建模。然而,实现高效的工作流调度具有挑战性。这是因为每个工作流应用程序生成的任务集都很大。这些工作流之间复杂的依赖关系使得很难在多项式时间内找到工作流调度问题的最佳解决方案。本文通过提供基于最先进元启发式算法的综合调查,分析了云和网格计算环境中的工作流调度问题。我们从四个角度分析了文献,包括 (i) 现有的元启发式,(ii) 调度效率、系统性能和执行预算,(iii) 调度环境和 (iv) 服务质量性能指标。此外,我们还提出了研究空白并为未来的调查提供了未来的方向。本文通过提供基于最先进元启发式算法的综合调查,分析了云和网格计算环境中的工作流调度问题。我们从四个角度分析了文献,包括 (i) 现有的元启发式,(ii) 调度效率、系统性能和执行预算,(iii) 调度环境和 (iv) 服务质量性能指标。此外,我们还提出了研究空白并为未来的调查提供了未来的方向。本文通过提供基于最先进元启发式算法的综合调查,分析了云和网格计算环境中的工作流调度问题。我们从四个角度分析了文献,包括 (i) 现有的元启发式,(ii) 调度效率、系统性能和执行预算,(iii) 调度环境和 (iv) 服务质量性能指标。此外,我们还提出了研究空白并为未来的调查提供了未来的方向。
更新日期:2021-01-20
down
wechat
bug