Fractional IWSOA-LB: Fractional Improved Whale Social Optimization Based VM Migration Strategy for Load Balancing in Cloud Computing

Data centres have seen significant growth recently as a result of the phenomenal rise of cloud computing. These data centres typically use more energy, which significantly raises operational costs. The management of server consolidation involves moving all Virtual Machines (VMs) to idle servers. How...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of wireless information networks Vol. 30; no. 1; pp. 58 - 74
Main Authors George, Shelly Shiju, Pramila, R. Suji
Format Journal Article
LanguageEnglish
Published New York Springer US 01.03.2023
Springer Nature B.V
Subjects
Algorithms
Cloud computing
Clustering
Data centers
Electrical Engineering
Engineering
Fractional calculus
Load balancing
Optimization
Optimization algorithms
Resource management
Resource scheduling
Task scheduling
Virtual environments
Resource utilization
Social optimization algorithm
Load balancing
Fractional calculus
Deep embedded clustering
Online AccessGet full text

Cover

More Information
Summary:Data centres have seen significant growth recently as a result of the phenomenal rise of cloud computing. These data centres typically use more energy, which significantly raises operational costs. The management of server consolidation involves moving all Virtual Machines (VMs) to idle servers. However, performance suffers as a result of migration as migration volume and time increase. The Cloud computing model generates computational cooperative of huge computing services and systems. Recently, resource sharing, task scheduling and resource management between users are familiar research areas. In this paper, Fractional Improved Whale Social Optimization Algorithm (Fractional IWSOA) is developed for load balancing in the cloud model. The developed Fractional IWSOA is newly devised by incorporating Social Optimization Algorithm (SOA) and Improved Whale Optimization Algorithm (IWOA) along with Fractional Calculus (FC). Moreover, the categorization of VM is performed based on Deep Embedded Clustering (DEC) which is categorized into two types, underloaded VMs and overloaded VMs. Additionally, the tasks in underloaded VM is assigned based on various factors. As a result, the developed Fractional IWSOA performed better than other existing techniques in terms of load, capacity, and resource usage, which were respectively 0.1160, 0.5898, and 0.7168.
ISSN:1068-9605
1572-8129
DOI:10.1007/s10776-023-00591-0