A Threshold-based Tournament Resource Allocation in Cloud Computing Environment
I. P. Oladoja *
Department of Computer Science, the Federal University of Technology Akure, Nigeria.
O. S. Adewale
Department of Computer Science, the Federal University of Technology Akure, Nigeria.
S. A. Oluwadare
Department of Computer Science, the Federal University of Technology Akure, Nigeria.
E. O. Oyekanmi
Department of Mathematical Science, Achievers University Owo, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
Cloud computing environments provide an apparition of infinite computing resources to cloud users so that they can increase or decrease resource consumption rate according to their demands. In the Cloud, computing resources need to be allocated and scheduled in a way that providers can achieve high resource utilization and users can meet their applications’ performance requirements with minimum expenditure. Due to these different intentions, there is the need to develop a scheduling algorithm to outperform appropriate allocation of tasks on resources. The paper focuses on the resource optimization using a threshold-based tournament selection probability for virtual machines used in the execution of tasks. The proposed approach was designed to create metatask and the proposed algorithm used was Median-Based improved Max-Min algorithm. The experimental results showed that the algorithm had better performance in terms of makespan, utilization of resources and throughput. The load balance of tasks was also fairly distributed on the two datacenters.
Keywords: Cloud computing, genetic algorithm, resource allocation, threshold-based tournament.