Dynamic Resource Management for Cloud Spot Markets

IEEE Access

卷:8

Anjali Agarwal¹  Yan Liu¹  Mustafa Daraghmeh¹  Sadeq Younis¹  Fadi Alzhouri²  Suhib Bani Melhem³ 

[1] Department of Electrical and Computer Engineering, Concordia University, Montreal, QC, Canada;

[2] Department of Electrical and Computer Engineering, University of Ottawa, Ottawa, ON, Canada;

[3] Department of Electrical and Computer Engineering, York University, Toronto, ON, Canada;

关键词: Resource management;    resource allocation;    dynamic allocation;    cloud;    IaaS;    spot market;   

DOI  :  10.1109/ACCESS.2020.3007469

来源: DOAJ

【 摘 要 】

Resource management for cloud computing environments that are characterized by many layers emerges as a critical task for cloud computing providers. Such providers are compelled by the demands and strategies of stochastic customers to adopt dynamic resource management for the top-bottom scaling of the cloud resources on the basis of variable needs. Resource management in the infrastructure as a service layer relies on virtual machine (VM) characteristics, such as estimated VM classes. Given that a cloud provider offers a variety of VM classes that differ as regards the size of computing resources (e.g., central processing unit, memory, and input/output devices), optimizing cloud resources to maximize cloud revenue is a challenging dilemma. More specifically, the dynamic management of resources in cloud spot markets is confronted with various severe obstacles. In consideration of these issues, this study investigated a dynamic resource management model for cloud spot markets and put forward an efficient model that manages spare resources for the purpose of expanding cloud revenue. The model estimates the available spare capacity of a spot market, evaluates the maximum expected revenue of stagnant VMs on the basis estimated cumulative capacity, and locates the optimum VM combinations that bear complementary workloads and capacities and can coexist in a certain host. Our model also improves the understanding of cloud resource scaling and generates inferences that can be adopted in managing cloud resources for all layers as well as Reserved and On-Demand markets.

【 授权许可】

Unknown