You are required to read and agree to the below before accessing a full-text version of an article in the IDE article repository.

The full-text document you are about to access is subject to national and international copyright laws. In most cases (but not necessarily all) the consequence is that personal use is allowed given that the copyright owner is duly acknowledged and respected. All other use (typically) require an explicit permission (often in writing) by the copyright owner.

For the reports in this repository we specifically note that

  • the use of articles under IEEE copyright is governed by the IEEE copyright policy (available at http://www.ieee.org/web/publications/rights/copyrightpolicy.html)
  • the use of articles under ACM copyright is governed by the ACM copyright policy (available at http://www.acm.org/pubs/copyright_policy/)
  • technical reports and other articles issued by M‰lardalen University is free for personal use. For other use, the explicit consent of the authors is required
  • in other cases, please contact the copyright owner for detailed information

By accepting I agree to acknowledge and respect the rights of the copyright owner of the document I am about to access.

If you are in doubt, feel free to contact webmaster@ide.mdh.se

Clustering Cloud Workload Traces to Improve the Performance of Cloud Data Centers

Authors:

Suhad Yousif , Auday Al-Dulaimy

Research group:

Complex Real-Time Embedded Systems

Publication Type:

Conference/Workshop Paper

Venue:

The 25th World Congress on Engineering

Abstract

Cloud computing is the cutting edge model in the IT industry. It offers compute and storage services on demand in a pay-as-you-go manner. Cloud services are delivered by providing an access to shared resources. The resources exist in the physical machines, which are hosted in cloud data centers found globally. For enhanced resource utilization, this paper characterizes and clusters the tasks of Google workload trace based on the resource usage of tasks. According to their resource usage, tasks with similar resource requirements are grouped together. Task clustering aims to help the cloud data center scheduler identify the optimal virtual machine placement strategy. The proposed strategy then seeks to place the virtual machines allocated to the tasks from complemented group or clusters on the same physical machines. Such placement prevents competition for the resources of the same physical machine, which may enhance system performance in the cloud data center. In this paper, two clustering algorithms are applied: k-mean clustering (using the Euclidean and Manhattan methods as the distance measure metrics) and density-based clustering. Applied algorithms implemented with Weka, which is a software that contains a collection of machine learning algorithms to perform the data mining tasks.

Bibtex

@inproceedings{Yousif6134,
author = {Suhad Yousif and Auday Al-Dulaimy},
title = {Clustering Cloud Workload Traces to Improve the Performance of Cloud Data Centers},
volume = {1},
month = {July},
year = {2017},
booktitle = {The 25th World Congress on Engineering},
url = {http://www.es.mdu.se/publications/6134-}
}