A Fuzzy Logic Based Approach in Choosing the Appropriate Physical Machines for Live Virtual Machines Migration in Cloud Computing

S.R. Hosseini, S. Adabi, R. Tavoli

Abstract


Migration of Virtual Machine (VM) has become a critical issue in modern data centers that are working based on virtualization. Among VM Migration challenges, choosing an appropriate Physical Machine (PM) is an important issue. To choose a place for VM several parameters, such as physical topology, migration duration, power consumption, service continuity, and price must be considered. Finding a near optimal place for VM migration that trades-off between some or all of these features is a challenging problem. In this paper, we propose three aspects for ranking potential destination PMs to find the most appropriate PM as VM host. In the first aspect, PMs are ranked in terms of servicing condition using Fuzzy logic technique according to three parameters: workload, performance efficiency and availability. In the second aspect, PMs are ranked in terms of power consuming condition using Fuzzy logic technique according to power, temperature efficiency and power efficiency metrics. In the third aspect, the output of two fuzzy logic engines with communication cost metric is used as the third fuzzy logic engine inputs that rank PMs. The proposed technique has been compared with AppAware algorithm in terms of communication cost and performance efficiency. Experimental results demonstrate that the proposed technique has appropriate improvement in these metrics and outperforms AppAware algorithm

Keywords


Fuzzy Logic; Network topology; Performance evaluation; Servers.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ISSN: 2180-1843

eISSN: 2289-8131