A Multi-objective Optimization Model for Virtual Machine Mapping in Cloud Data Centres

Publication Type:
Conference Proceeding
Citation:
2016 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2016, 2016, pp. 1259 - 1265
Issue Date:
2016-11-07
Metrics:
Full metadata record
Files in This Item:
Filename Description Size
0782EF99-AD08-49B8-9148-36E319FDA9D0.pdfAccepted Manuscript version735.32 kB
Adobe PDF
© 2016 IEEE. Modern cloud computing environments exploit virtualization for efficient resource management to reduce computational cost and energy budget. Virtual machine (VM) migration is a technique that enables flexible resource allocation and increases the computation power and communication capability within cloud data centers. VM migration helps cloud providers to successfully achieve various resource management objectives such as load balancing, power management, fault tolerance, and system maintenance. However, the VM migration process can affect the performance of applications unless it is supported by smart optimization methods. This paper presents a multi-objective optimization model to address this issue. The objectives are to minimize power consumption, maximize resource utilization (or minimize idle resources), and minimize VM transfer time. Fuzzy particle swarm optimization (PSO), which improves the efficiency of conventional PSO by using fuzzy logic systems, is relied upon to solve the optimization problem. The model is implemented in a cloud simulator to investigate its performance, and the results verify the performance improvement of the proposed model.
Please use this identifier to cite or link to this item: