Abu-Rahmeh, O (2009) A statistical mechanics approach for an effective, scalable, and reliable distributed load balancing scheme for grid networks. Doctoral thesis, Liverpool John Moores University.

Preview

Text 502748.pdf - Published Version Download (16MB) | Preview

Abstract

The advances in computer and networking technologies over the past decades produced new type of collaborative computing environment called Grid Networks. Grid network is a parallel and distributed computing network system that possesses the ability to achieve a higher computing throughput by taking advantage of many computing resources available in the network. To achieve a scalable and reliable Grid network system, the workload needs to be efficiently distributed among the resources accessible on the network. A novel distributed algorithm based on statistical mechanics that provides an efficient load-balancing paradigm without any centralised monitoring is proposed here. The resulting load-balancer would be integrated into Grid network to increase its efficiency and resources utilisation. This distributed and scalable load-balancing framework is conducted using the biased random sampling (BRS) algorithm. In this thesis, a novel statistical mechanics approach that gives a distributed loadbalancing scheme by generating almost regular networks is proposed. The generated network system is self-organised and depends only on local information for load distribution and resource discovery. The in-degree of each node refers to its free resources, and job assignment and resource updating processes required for load balancing are accomplished by using random sampling (RS). An analytical solution for the stationary degree distributions has been derived that confirms that the edge distribution of the proposed network system is compatible with ER random networks. Therefore, the generated network system can provide an effective loadbalancing paradigm for the distributed resources accessible on large-scale network 1 systems. Furthermore, it has been demonstrated that introducing a geographic awareness factor in the random walk sampling can reduce the effects of communication latency in the Grid network environment. Theoretical and simulation results prove that the proposed BRS load-balancing scheme provides an effective, scalable, and reliable distributed load-balancing scheme for the distributed resources available on Grid networks.

Item Type:	Thesis (Doctoral)
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General)
Divisions:	Engineering
Date Deposited:	13 Mar 2017 12:06
Last Modified:	03 Sep 2021 23:30
DOI or ID number:	10.24377/LJMU.t.00005903
URI:	https://researchonline.ljmu.ac.uk/id/eprint/5903

View Item