Nash equilibrium based replacement of virtual machines for efficient utilization of cloud data centers
- PDF / 509,625 Bytes
- 20 Pages / 439.37 x 666.142 pts Page_size
- 28 Downloads / 194 Views
Nash equilibrium based replacement of virtual machines for efficient utilization of cloud data centers Hammad ur Rehman Qaiser1
· Gao Shu1
Received: 26 October 2019 / Accepted: 7 January 2020 © Springer-Verlag GmbH Austria, part of Springer Nature 2020
Abstract Workload uncertainty has been increased with the integration of the Internet of Things to the computing grid i.e. edge computing and cloud data centers. Therefore, efficient resource utilization in cloud data centers become more challenging. Dynamic consolidation of virtual machines on optimal number of processing machines can increase the efficiency of resource utilization in cloud data centers. This process requires the migration of virtual machines from the under-utilized and over-utilized processing machines to other suitable machines. In this work, the problem of efficient replacement of virtual machines is solved using a game theory based well known technique, Nash Equilibrium (NE). We designed a nash equilibrium based dual on two players, over-load manager and under-load manager, to deduce the dominant strategy profiles for various scenarios during consolidation cycles. Dominant strategy profile is the set of strategies where every player has no incentive in deviation, thus leading to equilibrium position. A virtual machines redeployment algorithm, Nash Equilibrium based Virtual Machines Replacement (NE-VMR), has been proposed on the basis of the dominant strategy profiles for efficient consolidation. Experiment results show that NE-VMR is a more efficient server consolidation technique, saved 30% energy and improved 35% quality of service as compared to baselines. Keywords Virtual machine consolidation · Virtual machine replacement policies · Energy efficient computing · Cloud computing · Efficient resource management system Mathematics Subject Classification 68-02
B 1
Hammad ur Rehman Qaiser [email protected] Wuhan University of Technology, Yujiatou, Wuhan, China
123
H. ur R. Qaiser, G. Shu
1 Introduction Cloud Computing manages a large diversity of heterogeneous services and applications, particularly in the era of 5G. It provides computing resources and services to the organizations, on-demand and pay as you go basis. The enormous size of modern cloud computing infrastructure consumes a huge amount of electricity for cooling, illumination, and data center related operations. It is estimated that the energy cost contributes almost 40% to the total cost of the data center [1]. Apart from high cost due to electricity consumption, the contribution of carbon emission by cloud data centers is almost 2% of the total global emission of CO2 [2]. To alleviate the problem of hefty energy cost and growing carbon footprint of the cloud data center, it has become inevitable to use computing resources more efficiently [3]. It has been observed that the average resource utilization ranges from 10 to 50 percent of the total capacity and a significant amount of computing resources go in waste [4]. Therefore, the utilization rate of active computing resour
Data Loading...
