UTHM Institutional Repository

A model for federated data grid systems based on network core area

Mohamad, Zarina (2013) A model for federated data grid systems based on network core area. PhD thesis, Universiti Tun Hussein Onn Malaysia.


Download (1MB)


Data grid technology is developed to permit data sharing and collaboration activities across many organizations in geographically dispersed locations. Due to collaboration activities in distributed data grid, optimising data access is one of the issues that needs to be carefully addressed. The process of data access optimisation can be achieved through data replication, where identical copies of data are generated and stored at various globally distributed sites. If the required files are replicated in some site where the job is executed, then the job is able to process data without any communication delay. In this thesis, a model for federation data grid system called Sub-Grid-Federation had been proposed to improve access latency by accessing data from the nearest possible sites. A strategy in optimising data access is based on the process of searching into the area identified as "Network Core Area" (NCA). The proposed system will require access to be initially restricted from within the local site. If the needed data is not found, the system will continue the search from within a bigger scope, known as the local cluster. If the search still failed, the scope of search will continue from within the local sub-grid and other sub-grids consecutively until the data is successfully accessed. The performance of access latency in Sub-Grid-Federation had been tested based on the mathematical proving and simulated using OptorSim simulator. Four case studies had been chosen and tested in Optimal Downloading Replication Strategy (ODRS) and the Sub-Grid-Federation. The results showed that Sub-Grid-Federation is 20% better in terms of access latency and 21% better in terms of reducing remote sites access compared to ODRS. Hence, Sub-Grid-Federation is a better alternative for the implementation of collaboration and data sharing in data grid system.

Item Type: Thesis (PhD)
Subjects: Q Science > QA Mathematics > QA75 Calculating machines
Depositing User: Normajihan Abd. Rahman
Date Deposited: 19 Jun 2013 00:50
Last Modified: 19 Jun 2013 00:50
URI: http://eprints.uthm.edu.my/id/eprint/3947
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item


Downloads per month over past year