Abstract
In this paper, we develop a model for the competitive relationship between cloud service providers and cloud brokers during the virtual machine (VM) placement. The model adopts the idea of a strategy game, in which the cloud service provider and all VMs are participants. First, we define the strategy for the participants in the strategy game model according to the difference between the number of physical resources provided by the provider, and that requested for the VMs by the brokers. Next, payment values between the providers and brokers are obtained from each strategy in the game matrix, which corresponds to the strategy set of VM placement. In addition, the Nash equilibrium solution of the current strategy game demonstrates the trade-off between reducing energy consumption and guaranteeing QoS. On the basis of this, the optimal VM placement scheme is obtained, and the ongoing VM consolidation is examined. Finally, a strategy-game-based VM consolidation (SG-VMC) method is proposed. The extensive experimental results show that the proposed SG-VMC method can significantly reduce energy consumption while guaranteeing QoS.
Highlights
In cloud data centers, after the cloud rental users and cloud service provider sign a service-level agreement (SLA), the cloud consumer has the right to a high quality of service (QoS) that satisfies the specified service level at all times
The purpose of virtual machine (VM) consolidation is to achieve an optimum balance between the profit of the cloud service provider and the QoS enjoyed by the cloud rental user
The broker is directly associated with all computing tasks in data centers, whose game purpose is to achieve the optimal QoS for all tasks, i.e., to ensure that when all VMs are executing tasks, there are sufficient physical resources to allow for stochastic requested resources from VMs
Summary
After the cloud rental users and cloud service provider sign a service-level agreement (SLA), the cloud consumer has the right to a high quality of service (QoS) that satisfies the specified service level at all times. In order to simultaneously improve energy efficiency and guarantee QoS during VM consolidation, a strategy-game-based VM placement (SGVMP) scheme and algorithm is proposed in this paper. This pair of contradictions competes for the idle resources of PMs in data centers, which coincides with the concept of a strategy game (SG) of game theory On this basis, a competition model is developed to describe the VM placement scheme of deploying the virtual machine set V = {v1, v2, · · · , vm} to the host set H = {h1, h2, · · · hn}. The broker is directly associated with all computing tasks in data centers, whose game purpose is to achieve the optimal QoS for all tasks, i.e., to ensure that when all VMs are executing tasks, there are sufficient physical resources to allow for stochastic requested resources from VMs. Second, the probable behaviors of the participants, including those of provider and broker during VM placement, are analyzed to define the corresponding operation set. Based on the solution for the game model, the VM placement scheme that optimizes and balances the energy consumption and QoS is successfully obtained
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
