Prairie Dog Optimization Based Efficient Task Scheduling in the Cloud Computing

In Cloud Computing CC, scheduling the algorithms depicts the significant role of identifying the possible tasks scheduling. An efficient task scheduling is considerable to achieve the cost-effective execution as well as enhance the resource utilization. The task scheduling problem is to classified a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2023 International Conference on Integrated Intelligence and Communication Systems (ICIICS) S. 1 - 5
Hauptverfasser: Hussein, Abbas Hameed Abdul, Sunil, G, Kotha, Mahesh, Alzubaidi, Laith H., Arunasree, B
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 24.11.2023
Schlagworte:
Cloud computing
Dogs
Genetic algorithms
Nondeterministic Polynomial
Optimization
Prairie Dog Optimization
Processor scheduling
Scheduling
Task analysis
Task Scheduling
Virtual Machine
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In Cloud Computing CC, scheduling the algorithms depicts the significant role of identifying the possible tasks scheduling. An efficient task scheduling is considerable to achieve the cost-effective execution as well as enhance the resource utilization. The task scheduling problem is to classified as the Nondeterministic Polynomial (NP)-hard problem. To solve this issue, this research proposed an efficient metaheuristic algorithm named Prairie Dog Optimization (PDO) to enhance the task scheduling behaviour in the cloud. The PDO is proposed to improve the task transmitting performance by the cloud network based on the workload of the cloud resources. The proposed method utilizes four prairie dog activities to attains the two basic optimization phases such as exploration and exploitation. The PDO utilizes the two strategies named burrow and foraging to attains the efficient and effective resource allocation. The PDO is modelled for scheduling and distributing the tasks are developed by utilizing the Virtual Machine (VM) factors, time as well as cost. The proposed PDO method attains better results and it achieves the makespan of 112.65, energy consumption of 90.47 and Degree of Imbalance (DoI) of 1.1 respectively when compared to the existing methods like Particle Swarm Optimization, Antlion Optimization (ALO) and Genetic Algorithm (GA).
DOI:10.1109/ICIICS59993.2023.10421562