A Hybrid Meta-Heuristic for Optimal Load Balancing in Cloud Computing

• Published in: Journal of grid computing Vol. 19; no. 2
• Main Authors: Annie Poornima Princess, G., Radhamani, A. S.
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.06.2021; Springer Nature B.V
• Subjects: Algorithms; Ant colony optimization; Beans; Cloud computing; Computer Science; Computing time; Cost analysis; Heuristic methods; Load balancing; Management of Computing and Information Systems; Optimization algorithms; Processor Architectures; Response time; User Interfaces and Human Computer Interaction; Virtual environments; Pigeon optimization algorithm (POA); Virtual machines; Load balancing; Hawks optimization algorithm (HOA)
• ISSN: 1570-7873; 1572-9184
• DOI: 10.1007/s10723-021-09560-4

Nowadays, a trending technology that provides a virtualized computer resources based on the internet is named as cloud computing, these clouds performance mostly depends on the various factors among the load balancing. The allocation of the dynamic workload in between the cloud systems and equally shares the resources so that no database server is overloaded or under loaded is technically referred to as load balancing (LB). Therefore, in cloud an active load balancing scheme can perhaps enhance the reliability, services and the utilization of resources as well. In this manuscript, the benefits are integrated for Harries Hawks Optimization and Pigeon inspired Optimization Algorithm to create efficient load balancing scheme, which ensures the optimal resources utilizations with tasks response time. The proposed approach is implemented in JAVA Net beans IDE incorporated in the cloudsim framework that is analyzed based on different number of task in order to assess the performance. However, the simulation outcomes demonstrate that the proposed Hawks Optimization and Pigeon inspired Optimization algorithm based load balancing scheme is significantly balance the load optimally amid the Virtual Machines within a shorter period of time than the existing algorithms. The efficiency of the proposed method is 97% compared to the other existing methods. The computational time, cost, throughput analysis, make span, latency, execution time are determined and gets analysed, compared with the Harries Hawks Optimization, Spider Monkey Algorithm, Ant Colony Optimization and Honey Bee Optimization.