Abstract
In distributed database systems, replication is the most widely used approach to offering high data availability, increased fault tolerance, and improved scalability of the overall system. However, the primary concern with this technique is not only to provide high availability and reliability but also to boost the performance of data replication, i.e. to minimize response time and maximize throughput. We propose an analytical model for asynchronous replication technique (ART) by copying the data and replicating it to remote sites on a continuous basis. A remote copy of the data is created at a subsequent time after the primary copy is updated. The model is based on the M/G/1 queuing system by taking into account intersite communication between sites in the systems.