Efficient and Fair Bandwidth Scheduling in Cloud Environments

Khaleel, Mustafa and Zhu, Mengxia (2018) Efficient and Fair Bandwidth Scheduling in Cloud Environments. ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY, 6 (2). pp. 20-26. ISSN 2410-9355

[img] Text (PDF file)
ARO.10441- Vol6.No2.2018.ISSUE11-PP20-26.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)
Official URL: http://dx.doi.org/10.14500/aro.10441


Hundreds of thousands of servers from data centers are operated to provide users with pay-as-yougo infrastructure as a service, platform as a service, and software as a service. Many different types of virtual machine (VM) instances hosted on these servers oftentimes need to efficiently communicate with data movement under current bandwidth capacity. This motivates providers to seek for a bandwidth scheduler to satisfy objectives, namely assuring the minimum bandwidth per VM for the guaranteed deadline and eliminating network congestion as much as possible. Based on some rigorous mathematical models, we formulated a cloud-based bandwidth scheduling algorithm which enables dynamic and fair bandwidth management by categorizing the total bandwidth into several categories and adjusting the allocated bandwidth limit per VM for both upstream and downstream traffics in real time. The simulation showed that paradigm was able to utilize the total assigned bandwidth more efficiently compared to algorithms such as bandwidth efficiency persistence proportional sharing (PPS), PPS, and PS at the network level.

Item Type: Article
Uncontrolled Keywords: Cloud Infrastructure, Cloud Scheduler, Pay-as-you-go, Makespan
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Aro-The Scientific Journal of Koya University > VOL 6, NO 2 (2018)
Depositing User: Dr Salah Ismaeel Yahya
Date Deposited: 17 Feb 2019 19:39
Last Modified: 17 Feb 2019 19:39
URI: http://eprints.koyauniversity.org/id/eprint/177

Actions (login required)

View Item View Item