Machine-Learning-Based Approach for Virtual Machine Allocation and Migration

Abstract

Due to its ability to supply reliable, robust and scalable computational power, cloud computing is becoming increasingly popular in industry, government, and academia. High-speed networks connect both virtual and real machines in cloud computing data centres. The system’s dynamic provisioning environment depends on the requirements of end-user computer resources. Hence, the operational costs of a particular data center are relatively high. To meet service level agreements (SLAs), it is essential to assign an appropriate maximum number of resources. Virtualization is a fundamental technology used in cloud computing. It assists cloud providers to manage data centre resources effectively, and, hence, improves resource usage by creating several virtualmachine (VM) instances. Furthermore, VMs can be dynamically integrated into a few physical nodes based on current resource requirements using live migration, while meeting SLAs. As a result, unoptimised and inefficient VM consolidation can reduce performance when an application is exposed to varying workloads. This paper introduces a new machine-learning-based approach for dynamically integrating VMs based on adaptive predictions of usage thresholds to achieve acceptable service level agreement (SLAs) standards. Dynamic data was generated during runtime to validate the efficiency of the proposed technique compared with other machine learning algorithms.

An Energy Efficient VM Selection Using Updated Dragonfly Algorithm in Cloud Computing

“…Figure 8 shows the comparison of proposed dragonfly technique with the existing technique for 100 numbers of VMs. The average value for SLA violation using the dragonfly technique is 0.107 while technique proposed by [26]et al 2022 and [2] shows SLA of about 0.148 and 0.5 respectively. Thus, proposed technique is improved by about 3% from [26]et al 2022 and 7.4% from [2].…”

“…The average value for SLA violation using the dragonfly technique is 0.107 while technique proposed by [26]et al 2022 and [2] shows SLA of about 0.148 and 0.5 respectively. Thus, proposed technique is improved by about 3% from [26]et al 2022 and 7.4% from [2]. The improvement in the proposed technique is due to energy efficient technique employed with dragonfly technique that consumes the less energy in comparison to existing techniques.…”

“…9 Comparison with existing technique for number of VM migrationFigure9shows the comparison of proposed dragonfly technique with the existing technique for 100 numbers of VMs. The average value for migrations using the proposed dragonfly technique is 8 while 8.5 migrations shown by[27] and Santhosh 2022 and 9 shown by[26]et al 2022. Thus, proposed technique is improved by 11.1% from[26]et al 2022 and 5.8% from[27] and Santhosh 2022.…”

“…The limitation of the study was needed to study the extended features for VM placement. [26] provided a suitable maximum number of resources in order to fulfil service level agreements. An essential technology in cloud computing is virtualization.…”

“…The results using the proposed dragonfly are better as compared to CS, ACO, PSO and DF technique. The existing techniques proposed by [26]et al 2022 using the K-Nearest Neighbour (KNN) for VM migration and allocation in the data center. The proposed work also compared with the [27] and Santhosh 2022, in which hybrid model using the CS and PSO technique is proposed for VM migration.…”