An Enhanced Load Balancing Technique for Big-data Cloud Computing Environments

Abstract

The need for cloud computing load balancing is a peculiar area of interest for researchers because it affects both the quality of service provided to users and resource utilisation on the part of cloud service providers. Due to the requirement to minimise processing costs, enhance throughput, improve resource efficiency, and optimise cloud node arrangement, existing cloud computing load balancing methods have been found to be restricted in their capacity to manage big-data cloud system load distribution. This research developed a novel Central-Regional Architecture Based Load Balancing Technique (CRLBT) different from the known central, distributive, and hierarchical cloud architectures. The proposed technique was developed by combining a formulated throughput maximisation algorithm with the algorithms; Throughput Maximised-Particle Swarm Optimisation (TM-PSO) and Throughput Maximised-Firefly optimisation (TM-Firefly). The developed technique was implemented using the MATLAB R2018 software package. The performance of the CRLBT in comparison to the already-in-use PSO and Firefly algorithms was evaluated using response time, throughput, job rejection ratio, and CPU utilisation rate. The significance of the improvement in load balancing brought about by the new approach was further assessed using a statistical T-Test. The results showed that the proposed CRLBT significantly outperformed the PSO and Firefly techniques regarding response time, throughput CPU utilisation rate, and task rejection ratio. Finally, significant improvements in response time, tax rejection ratio, CPU utilisation rate, and network throughput proved the ability of the proposed technique to handle task-resource distribution of big-data cloud centres superiorly.