HHO-ACO hybridized load balancing technique in cloud computing

• Published in: International journal of information technology (Singapore. Online) Vol. 15; no. 3; pp. 1357 - 1365
• Main Authors: Sumathi, Muruganandam, Vijayaraj, Natarajan, Raja, Soosaimarian Peter, Rajkamal, Murugesan
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.03.2023; Springer Nature B.V
• Subjects: Algorithms; Ant colony optimization; Artificial Intelligence; Cloud computing; Computer centers; Computer Imaging; Computer Science; Data storage; Energy consumption; Food; Heuristic; Heuristic methods; Image Processing and Computer Vision; Infrastructure; Load balancing; Machine Learning; Optimization algorithms; Optimization techniques; Original Research; Pattern Recognition and Graphics; Performance degradation; Performance measurement; Pheromones; Scheduling; Software Engineering; Virtual environments; Vision; Workload; Cloud computing; Ant colony optimization; Hybridized load balancing; Harries haws optimization; Virtual machine
• ISSN: 2511-2104; 2511-2112
• DOI: 10.1007/s41870-023-01159-0

Due to on-demand requirement of computing resources, cloud computing (C C ) is the widely used technology in data storage, software and platform. C C provides everything as a service to requester. In an Infrastructure as a Service (IaaS), virtual machines (VMs) play a vital role to provide infrastructure to the requester. The performance VMs depends on the distribution of work (load balancing) between VMs. The process of distributing a set of tasks or workloads over a set of VM resources is called as Load Balancing (LB). Unbalanced task distribution leads to overloaded or under-loaded issues and performance degradation. Hence, LB is a desirable and essential task in C C . To improve the LB performance the two different meta-heuristic optimization algorithms, Harries Hawks Optimization (HHO) and Ant Colony Optimization (ACO) are hybridized in the proposed technique. The hybridized load balancing (HLB) algorithm performance is compared to HHO and ACO. The factors that are analyzed in the proposed system are the average waiting time (A WT ), average execution time (A ET ), average response time (A RT ), make-span, throughput analysis, turnaround time and LB time. The HLB mechanism is implemented and simulated in java and Cloudsim respectively. By the allocation of workloads to VMs will shows which one gives the best efficiency in LB among the VM’s. The proposed HLB technique takes 9.29% A ET , 2.65% of A RT , 0% of A WT, less turnaround time and LB time than the basic HHO and ACO algorithms. Thus, the proposed HLB provided better performance than HHO and ACO is proven with different performance metrics.