An Efficient Priority Weight based Modified Firefly Algorithm for Task scheduling in Cloud Computing

Abstract

In cloud computing, task scheduling poses a significant challenge and is widely adopted by service providers and clients. The primary issue for task schedulers lies in identifying suitable resources (virtual machines) for given tasks while optimizing key metrics such as makespan, cost, energy consumption, and resource utilization. Traditional heuristic approaches often result in suboptimal schedules, resource wastage, or degraded service quality. Meta-heuristic algorithms have gained prominence for tackling task scheduling as a discrete optimization problem. The main objective of this article is to propose a task scheduling algorithm that delivers near-optimal solutions for multi-objective task scheduling in cloud environments. This article proposes an efficient priority weight based modified firefly algorithm (PWMFA) for task scheduling to tackle the problem faced in heuristic approach. The key innovation of this work lies in computing priority weights using a Hamming distance function. The proposed algorithm enhances solution diversity and avoids local optima by leveraging this distance function and priority weighting mechanism. CloudSim was employed to evaluate PWMFA’s performance in terms of makespan, total execution time, degree of imbalance, and energy consumption. The results demonstrate that the proposed approach outperforms recent methods by reducing makespan, total execution time, degree of imbalance, and energy consumption.