Multi-Objective Workflow Scheduling in Cloud Using Archimedes Optimization Algorithm

Abstract

Cloud computing has changed the technology landscape for over a decade and led to an astounding growth in the number of applications it may be used for. Consequently, there has been a significant spike in the demand for improved algorithms to schedule workflows efficiently. These were mostly concerned with heuristic, metaheuristic, and hybrid approaches to workflow scheduling that mostly suffer from the problem of local optima entrapment. Due to such heavy traffic on the cloud resources, there is still a need for less computationally complex approaches. In light of this, this article proposes a novel approach: a multi-objective Modified Local Escaping Archimedes Optimization (MLEAO) algorithm for workflow scheduling. This strategy involves initialization of the population of Archimedes Optimization algorithm through the HEFT algorithm to provide an inclination towards the solutions with improved makespan while achieving a cost-efficient workflow scheduling decision and avoiding the problem of local optima entrapment using a local escaping operation. To validate the efficacy of our approach, we conducted extensive experiments using scientific workflows as benchmarks. Through our investigations, we significantly improved makespan, cost, resource utilization, and energy consumption. Moreover, the effectiveness of our proposed approach is also verified by performance metrics such as hypervolume, s-metric, and dominance relationships between the proposed and state-of-the-art approaches.