DocumentCode :
2662573
Title :
A Predictive Technique for Replica Selection in Grid Environment
Author :
Rahman, Rashedur M. ; Barker, Ken ; Alhajj, Reda
Author_Institution :
Dept. of Comput. Sci., Univ. of Calgary, Calgary, AB
fYear :
2007
fDate :
14-17 May 2007
Firstpage :
163
Lastpage :
170
Abstract :
Replication in a data grid reduces access latency and bandwidth consumption. However, when different sites hold replicas of a particular file, there is a significant benefit realized by selecting the best replica from among them. The best replica is the one that optimizes the desired performance criterion such as absolute performance (i.e. speed), cost, security or transfer time. By selecting the best replica, the access latency can be minimized. We develop a predictive framework that uses data from various sources and predicts transfer times of the sites that host replicas. With this estimate, one site can request the replica from the site that has the lowest transfer time. We use a neural network (NN) for transfer time prediction of different sites that currently hold file replicas. We compare the results with a multi-regression model and the simulation results demonstrate that the neural network technique is capable of predicting transfer time more accurately than the regression based model.
Keywords :
grid computing; neural nets; regression analysis; access latency; bandwidth consumption; data grid replication; file replicas; grid environment; multiregression model; neural network; replica selection; transfer time prediction; Availability; Bandwidth; Computational modeling; Cost function; Delay; High energy physics instrumentation computing; Neural networks; Power engineering computing; Predictive models; Throughput;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Cluster Computing and the Grid, 2007. CCGRID 2007. Seventh IEEE International Symposium on
Conference_Location :
Rio De Janeiro
Print_ISBN :
0-7695-2833-3
Type :
conf
DOI :
10.1109/CCGRID.2007.8
Filename :
4215378
Link To Document :
بازگشت