An Intelligent Chimp Optimizer for Scheduling of IoT Application Tasks in Fog Computing

Mathematics

Samia Allaoua Chelloug¹  Doaa Elsadek²  Ibrahim Attiya²  Mohamed Abd Elaziz³  Laith Abualigah⁴ 

[1] Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia;Department of Mathematics, Faculty of Science, Zagazig University, Zagazig 44519, Egypt;Faculty of Computer Science & Engineering, Galala University, Suze 435611, Egypt;Faculty of Computer Sciences and Informatics, Amman Arab University, Amman 11953, Jordan;

关键词: chimp optimization algorithm;    marine predators algorithm;    cloud computing;    fog computing;    task scheduling;    makespan;   

DOI  :  10.3390/math10071100

来源: DOAJ

【 摘 要 】

The cloud computing paradigm is evolving rapidly to address the challenges of new emerging paradigms, such as the Internet of Things (IoT) and fog computing. As a result, cloud services usage is increasing dramatically with the recent growth of IoT-based applications. To successfully fulfill application requirements while efficiently harnessing cloud computing power, intelligent scheduling approaches are required to optimize the scheduling of IoT application tasks on computing resources. In this paper, the chimp optimization algorithm (ChOA) is incorporated with the marine predators algorithm (MPA) and disruption operator to determine the optimal solution to IoT applications’ task scheduling. The developed algorithm, called CHMPAD, aims to avoid entrapment in the local optima and improve the exploitation capability of the basic ChOA as its main drawbacks. Experiments are conducted using synthetic and real workloads collected from the Parallel Workload Archive to demonstrate the applicability and efficiency of the presented CHMPAD method. The simulation findings reveal that CHMPAD can achieve average makespan time improvements of 1.12–43.20% (for synthetic workloads), 1.00–43.43% (for NASA iPSC workloads), and 2.75–42.53% (for HPC2N workloads) over peer scheduling algorithms. Further, our evaluation results suggest that our proposal can improve the throughput performance of fog computing.

【 授权许可】

Unknown