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

作     者：George, Shelly Shiju Pramila, R. Suji 

作者机构：Noorul Islam Ctr Higher Educ Kumaracoil Tamil Nadu India Amal Jyothi Coll Engn Dept Comp Applicat Kottayam Kerala India 

出 版 物：《INTERNATIONAL JOURNAL OF WIRELESS INFORMATION NETWORKS》 (国际无线信息网络杂志)

年 卷 期：2023年第30卷第1期

页      面：58-74页

核心收录：

学科分类：0810[工学-信息与通信工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

主　　题：Load balancing Fractional calculus Deep embedded clustering Social optimization algorithm Resource utilization 

摘      要：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.