Adaptive Markov‐based approach for dynamic virtual machine consolidation in cloud data centers with quality‐of‐service constraints. (12th December 2019)

• Record Type: Journal Article
• Authors: Monshizadeh Naeen, Hossein; Zeinali, Esmaeil; Toroghi Haghighat, Abolfazl
• Is Part Of: Software, practice & experience. Volume 50:Number 2(2020)
• Page Start: 161
• Page End: 183
• Publication Date: 2019-12-12
• Subjects: cloud computing -- dynamic consolidation -- energy efficiency -- green information technology -- Markov chains -- virtualization; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2764
• Languages: English
• ISSNs: 0038-0644

Abstract

Summary: Dynamic virtual machine (VM) consolidation is one of the emerging technologies that has been considered for low‐cost computing in cloud data centers. Quality‐of‐service (QoS) assurance is one of the challenging issues in the VM consolidation problem since it is directly affected by the increase of resource utilization due to the consolidations. In this paper, we take advantage of Markov chain models to propose a novel approach for VM consolidation that can be used to explicitly set a desired level of QoS constraint in a data center to ensure the QoS goals while improving system utilization. For this purpose, an energy‐efficient and QoS‐aware best fit decreasing algorithm for VM placement is proposed, which considers QoS objective when determining the location of a migrating VM. This algorithm employs an online transition matrix estimator method to deal with the nonstationary nature of real workload data. We also propose new policies for detecting overloaded and underloaded hosts. The performance of our proposed algorithms is evaluated through simulations. The results show that the proposed VM consolidation algorithms in this paper outperforms the benchmark algorithms in terms of energy consumption, service‐level agreement violations, and other cost factors.