Enabling green computing in cloud environments: network virtualization approach toward 5G support

Verma, JK ORCID logoORCID: https://orcid.org/0000-0003-4103-4218, Kumar, S, Kaiwartya, O ORCID logoORCID: https://orcid.org/0000-0001-9669-8244, Cao, Y, Lloret, J ORCID logoORCID: https://orcid.org/0000-0002-0862-0533, Katti, CP and Kharel, R, 2018. Enabling green computing in cloud environments: network virtualization approach toward 5G support. Transactions on Emerging Telecommunications Technologies: e3434. ISSN 2161-3915

[thumbnail of 11697_Kaiwartya.pdf]
Preview
Text
11697_Kaiwartya.pdf - Post-print

Download (1MB) | Preview

Abstract

Virtualization technology has revolutionized the mobile network and widely used in fifth-generation innovation. It is a way of computing that allows dynamic leasing of server capabilities in the form of services like Software as a Service (SaaS), Platform as a Service (PaaS), and Infrastructure as a Service (IaaS). The proliferation of these services among the users led to the establishment of large-scale cloud data centers that consume an enormous amount of electrical energy and results into high metered bill cost and carbon footprint. In this paper, we propose three heuristic models, namely, median migration time, smallest void detection, and maximum fill technique, that can reduce energy consumption with minimal variation in service-level agreements negotiated. Specifically, we derive the cost of running cloud data center, cost optimization problem, and resource utilization optimization problem. Power consumption model is developed for cloud computing environment focusing on linear relationship between power consumption and resource utilization. A virtual machine (VM) migration technique is considered, focusing on synchronization-oriented shorter stop-and-copy phase. The complete operational steps as algorithms are developed for energy-aware heuristic models including median migration time, smallest void detection, and maximum fill technique. To evaluate the proposed heuristic models, we conduct experimentations using PlanetLab server data often in ten days and synthetic workload data collected randomly from the similar number of VMs employed in PlanetLab servers. Through evaluation process, we deduce that the proposed approaches can significantly reduce the energy consumption, total VM migration, and host shutdown while maintaining high system performance.

Item Type: Journal article
Publication Title: Transactions on Emerging Telecommunications Technologies
Creators: Verma, J.K., Kumar, S., Kaiwartya, O., Cao, Y., Lloret, J., Katti, C.P. and Kharel, R.
Publisher: Wiley-Blackwell
Date: 29 May 2018
ISSN: 2161-3915
Identifiers:
Number
Type
10.1002/ett.3434
DOI
Divisions: Schools > School of Science and Technology
Record created by: Jonathan Gallacher
Date Added: 06 Aug 2018 08:32
Last Modified: 29 May 2019 03:00
URI: https://irep.ntu.ac.uk/id/eprint/34244

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year