Data Replication in Cloud Systems

Abstract

This paper presents a survey of data replication strategies in cloud systems. Based on the survey and reviews of existing classifications, we propose another classification of replication strategies based on the following five dimensions: (i) static vs. dynamic, (ii) reactive vs. proactive workload balancing, (iii) provider vs. customer centric, (iv) optimal number vs. dynamic adjustment of the replica factor and (v) objective function. Ideally, a good replication strategy must simultaneously consider multiple criteria: (i) the reduction of access time, (ii) the reduction of the bandwidth consumption, (iii) the storage resource availability, (iv) a balanced workload between replicas and (v) a strategic placement algorithm including an adjusted number of replicas. Therefore, selecting a data replication strategy is a classic example of multiple criteria decision making problems. The taxonomy we present can be a useful guideline for IT managers to select the data replication strategy for their organization.