In the current scenario, there is a need to store large amount of data for an application. All these data are stored in a single computer and they have to be shared by many users with accuracy, fairness and security. If any crash occurs in the system, then the whole data will be lost. In large-scale Grid, data replication provides a suitable solution for managing data files where data reliability and data availability are enhanced. Replica selection is one of the major functions of data replication that decides which replica location is the best for Grid users. In order to provide minimum response time, the replicas as a resource must be allocated among the users fairly. Replication systems create multiple copies of the same data file, and distribute these copies (replicas) into different site locations. Thus, there is a significant difference in selecting one replica among many replicas widely distributed. Hence, it is feasible to focus on the replica selection strategies in order to select the best replica location according to some criteria.  The criteria set such as reliability, security and response time are considered to provide the best replica of high quality in minimum response time.
Replicas are selected using Random and Analytical Hierarchy Process (AHP) algorithms. The best replica is selected based on the reliability and security values. The performance of these two algorithms is evaluated in this paper.

Index Terms - Data grid, fairness, analytic hierarchy process, fairness.