EM-ACO-ARM: An Enhanced Multiple Ant Colony Optimization Algorithm for Adaptive Resource Management in Cloud Environment

Abstract

Ant Colony Optimization (ACO) is an intelligent algorithm ensuring optimal resource management in cloud environments. This paper proposes an enhanced version of the ACO algorithm called Enhanced Multiple Ant Colony Optimization for Adaptive Resource Management (EM-ACO-ARM). Our approach uses multiple ant colonies undergoing several iterations of optimizations to find the optimal Virtual Machine (VM) and adapt to the convergence uncertain-ties, unlike a single ant colony in the existing ACO, which can hinder Quality of Service (QoS)-based performance parameters. We conducted experiments in a cloud-simulated environment to evaluate EM-ACO-ARM in two phases. In the first phase, we computed real-time Montage tasks using the existing ACO algorithm on VMs across ten scenarios. To ensure an unbiased comparison, the same cloud configuration was maintained in the second phase, and the same tasks were computed using the proposed EM-ACO-ARM algorithm in all ten scenarios. The experimental results demonstrate that EM-ACO-ARM improves Execution Cost and Execution Time, leading to a 14.73% increase in Resource Utilization. This ultimately improves the management of cloud resources. Additionally, a stability evaluation was conducted using regression models, and it outputted EM-ACO-ARM to provide more stability than the existing ACO algorithm. The cloud can provide better QoS with the proposed EM-ACO-ARM algorithm while abiding by Service Level Agreements.