Job Scheduling In Big Data Using Cuckoo Optimization Technique

Abstract

To examine large volume of data and to extract hidden data, applications of big data analytics is
used. To schedule the job and data, cuckoo search scheduling algorithm is used in this proposed study. The cuckoo
search algorithm permits providers and consumers of resources to perform the decisions for scheduling on their own. So
depending on their requirement, providers and consumers achieve enough amounts of data. The objective of this paper is
to minimize the overall turnaround timing and execution cost and to maximize the utilization of the resources. To achieve
this objective, Cuckoo Search Algorithm (CSA)is designed depending on Confidence Time Gap (CTG). Hadoop is a
software framework that stores huge volume of data in a cluster and allows to process data from all nodes. Map Reduce
is a application framework used to process huge volume of data in clusters. The efficiency of Big Data Analytics is
improved by implementing job scheduling using Cuckoo Search Algorithm. This algorithm is more efficient and
convenient than the available resource brokers implementing various data-based job scheduling algorithms.