QOS-BASED RESOURCE ALLOCATION USING ANT COLONY OPTIMIZATION IN CLOUD COMPUTING

Abstract

This research introduces a novel Quality of Service (QoS)-based Ant Colony Optimization meta-heuristic algorithm. Its main aim is to evaluate the performance of this newly proposed method in task scheduling within cloud computing environments and to gauge students' acceptance of cloud computing in educational settings, validating a modified UTAUT2 model specifically tailored for cloud computing. To assess the algorithm's effectiveness and efficiency, the study conducts a thorough comparison with various existing scheduling algorithms, including Monarch Butterfly Optimization (MBO), Honeybee, and Particle Swarm Optimization (PSO). Evaluation is based on critical metrics such as makespan, resource utilization, response time, and Degree of Imbalance (DOI). Simulation results indicate that the proposed method surpasses other algorithms, particularly with increased cloudlet numbers. The simulated outcomes demonstrate reduced makespan, response time, and DOI, alongside enhanced resource utilization and throughput. Additionally, the survey findings reveal that all UTAUT2 model constructs—performance expectancy (PE), effort expectancy (EE), social influence (SI), facilitating conditions (FC), and anxiety (AX)—significantly influence the acceptance and utilization of cloud computing systems, shedding light on the effectiveness of load balancing strategies and their implications in cloud environments.