MQRC: QoS aware multimedia data replication in cloud

Abstract

Multimedia data need stringent Quality of Service (QoS) requirements to handle it effectively. Replication is performed to enhance data availability and fault tolerance. Selection of node for replication is important to place multimedia content. Several replication algorithms have been proposed in the literature to replicate data in different computing architectures such as Client-Server distributed systems, Peer to Peer, Wireless Sensor networks, Mobile Ad hoc networks, Vehicular Ad hoc network and Cloud. The underlying difference in the architecture demands a custom replication approach for each of computing/network environment. Since multimedia data require a stringent QoS measures, we propose an algorithm to replicate Multimedia data with QoS awareness in the cloud environment (MQRC). We study the architecture of Hadoop Distributed File System (HDFS) and propose an efficient Multimedia QoS aware replication algorithm which allocates replica considering the QoS requirements of multimedia data such as delay, jitter, bandwidth, loss rate and error rate. We have performed a simulation using the proposed approach. The results obtained shows a significant reduction in the number of QoS violated replicas compared to the existing approach used by Hadoop such as Random replication.