Open Access

ARTICLE

A Bioinspired Method for Optimal Task Scheduling in Fog-Cloud Environment

Ferzat Anka¹, Ghanshyam G. Tejani^2,3,*, Sunil Kumar Sharma⁴, Mohammed Baljon⁵

1 Data Science Application and Research Center (VEBIM), Fatih Sultan Mehmet Vakif University, Istanbul, 34445, Türkiye
2 Department of Industrial Engineering and Management, Yuan Ze University, Taoyuan, 320315, Taiwan
3 Applied Science Research Center, Applied Science Private University, Amman, 11937, Jordan
4 Department of Information System, College of Computer and Information Sciences, Majmaah University, Majmaah, 11952, Saudi Arabia
5 Department of Computer Engineering, College of Computer and Information Sciences, Majmaah University, Majmaah, 11952, Saudi Arabia

* Corresponding Author: Ghanshyam G. Tejani. Email:

Computer Modeling in Engineering & Sciences 2025, 142(3), 2691-2724. https://doi.org/10.32604/cmes.2025.061522

Received 26 November 2024; Accepted 01 February 2025; Issue published 03 March 2025

Abstract

Due to the intense data flow in expanding Internet of Things (IoT) applications, a heavy processing cost and workload on the fog-cloud side become inevitable. One of the most critical challenges is optimal task scheduling. Since this is an NP-hard problem type, a metaheuristic approach can be a good option. This study introduces a novel enhancement to the Artificial Rabbits Optimization (ARO) algorithm by integrating Chaotic maps and Levy flight strategies (CLARO). This dual approach addresses the limitations of standard ARO in terms of population diversity and convergence speed. It is designed for task scheduling in fog-cloud environments, optimizing energy consumption, makespan, and execution time simultaneously three critical parameters often treated individually in prior works. Unlike conventional single-objective methods, the proposed approach incorporates a multi-objective fitness function that dynamically adjusts the weight of each parameter, resulting in better resource allocation and load balancing. In analysis, a real-world dataset, the Open-source Google Cloud Jobs Dataset (GoCJ_Dataset), is used for performance measurement, and analyses are performed on three considered parameters. Comparisons are applied with well-known algorithms: GWO, SCSO, PSO, WOA, and ARO to indicate the reliability of the proposed method. In this regard, performance evaluation is performed by assigning these tasks to Virtual Machines (VMs) in the resource pool. Simulations are performed on 90 base cases and 30 scenarios for each evaluation parameter. The results indicated that the proposed algorithm achieved the best makespan performance in 80% of cases, ranked first in execution time in 61% of cases, and performed best in the final parameter in 69% of cases. In addition, according to the obtained results based on the defined fitness function, the proposed method (CLARO) is 2.52% better than ARO, 3.95% better than SCSO, 5.06% better than GWO, 8.15% better than PSO, and 9.41% better than WOA.

---

Keywords

---