A Dynamic Replication Aware Load Balanced Scheduling for Data Grids in Distributed Environments of Internet of Things

Grid computing is a powerful distributed and scalable computing infrastructure that deals with massive data-intensive applications. Efficient utilization of the available computing grid resources remains a challenge. Moreover, it becomes even more challenging in the highly dynamic and distributed environment of the Internet of Things (IoT). Replication is considered a key optimization technique in data grids. However, the extent state of-the-art replication algorithms do not consider the position of the replica at the time of the scheduling rather it sends the job request to the Site and then Replica Manager of the Site checks the replica existence. We propose a novel dynamic Replication Aware Load Balanced Scheduling (DRALBS) algorithm, that considers the replica location dynamically at the time of scheduling of the job. The simulation of the proposed algorithm shows promising results and better performance compared to the current state-of-the-art Modified Dynamic Hierarchical Replication (MDHR) algorithm. The response and average access time has been significantly decreased, thus reducing the overall mean job execution time.