Enhancement of Task Scheduling Technique of Big Data Cloud Computing

Abstract

Big Data refers to the large size chunks of data that traditional computing approaches can handle. Despite the truth of having huge cloud systems to manage this data nowadays, there are many challenges related to performing the tasks in the cloud within the expected timeframe using the minimum number of resources possible. The necessity to fulfil user requirements is the main reason of having studies for optimizing the cloud computing of big data in terms of latency, bandwidth, execution time and resource utilization. Therefore, we proposed an efficient task scheduling technique capable to manage big data processing and storage in the cloud in an efficient way that meets user expectations. We provide a solution that involves multiple number of metrics necessary to optimize the solution of big data cloud computing. Our designed model consists of multiple control nodes that control the work done on multiple compute nodes. We used a load balancing algorithm to manage task scheduling on the compute nodes so we make sure that all nodes have equal balance of loads at all times. We simulate different scenarios to prove the concept of the study including latency, task execution time, bandwidth and resource utilization. This study achieved 31.4% as an average decrease percentage in task execution time and this has led to 11.36% utilization of resources.