Alzboon, M. S. and Ariffin, Ahmad Shabudin and Mahmuddin, Massudi (2016) Towards self-resource discovery and selection models in grid computing. ARPN Journal of Engineering and Applied Sciences, 11 (10). pp. 6269-6274. ISSN 1819-6608

PDF Restricted to Registered users only Download (392kB) | Request a copy

Abstract

Global computational grids nowadays are suffered from ossification problems due to the following fundamental challenges related to different existing solutions in grid computing: scalability, adaptability, security, reliability, availability and manageability.The management difficulty is due to heterogeneity, dynamicity and locality of the resources within global grid networks.Large-scale grids make the fundamental problem of resource discovery a great challenge.This paper presents a self-resource discovery mechanism (SRDM) that achieves efficient grid resource discovery and takes advantage of the strengths of both hierarchy and decentralized approaches that were previously developed for grid based P2P resource discovery.P2P systems offer potential strengths such as self-organization, self-healing, and robustness to failure or attacks. Unfortunately, the majority of existing Distributed Hash Table (DHT) based P2P overlays are lacking of attributes range queries that are familiar in resource discovery lookups.The proposed model builds an effective distributed hierarchy that providing scalable, decentralized resource discovery and allocation as well as load balancing for distributed computing using large scale pools of heterogeneous computers. Fundamentally, SRDM employs the spatial index and partitions the overlay space to build a distributed quad tree; each computational resource in the network can calculate its Nodepower.Next, it encodes the information about each node’s available computational resources power in the structure of the links connecting the nodes in the network.This distributed encoding is self-organized, with each node managing its in-degree and local connectivity via its available Nodepower.Assignment of incoming jobs to nodes with the freest resources is also accomplished by sampling it.

Item Type:	Article
Uncontrolled Keywords:	grid computing, resource discovery, quad-tree.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	School of Computing
Depositing User:	Mr. Ahmad Shabudin Ariffin
Date Deposited:	08 Aug 2016 04:20
Last Modified:	08 Aug 2016 04:20
URI:	https://repo.uum.edu.my/id/eprint/18476

Actions (login required)

View Item