Comparative analysis of the prototype and the simulator of a new load balancing algorithm for heterogeneous computing environments
by R.F. De Mello, L.C. Trevelin, M.S. V. De Paiva, Laurence Tianruo Yang
International Journal of High Performance Computing and Networking (IJHPCN), Vol. 1, No. 1/2/3, 2004

Abstract: The availability of low cost hardware has increased the development of distributed systems. The allocation of resources in these systems may be optimised through the use of a load balancing algorithm. The load balancing algorithms are responsible for the homogeneous distribution of the occupation in the environment, with the aim of obtaining gains on the final performance. This paper presents and analyses a new load balancing algorithm that is based on a logical computer tree hierarchy. The analysis is made using results obtained by a simulator and a prototype of this algorithm. The algorithm simulations show a significant performance gain by lowering the response times and the number of messages that pass through the communication system to perform the load balancing operations. After good results were obtained by the simulations, a prototype was built and validated such results.

Online publication date: Fri, 05-Aug-2005

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of High Performance Computing and Networking (IJHPCN):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com