Study of Energy-Efficient Virtual Machine Migration with Assurance of Service-Level Agreements

With the rising usage of cloud services, data centers (DC) are improving the services to their customers. The substantial energy consumption (EC) of cloud DCs poses significant economic and environmental challenges. To address this issue, server consolidation through virtualization technology has emerged as a widely adopted approach to decrease energy consumption rates, minimize virtual machine (VM) migration, and prevent breaches of service-level agreements (SLAs) within data centers. Cloud DCs are becoming larger, consuming more energy, and capable of delivering quality of service (QoS) with service-level assurance. People all around the world can use cloud computing to have instant access to resources. It provides pay-per-use services via a vast network of data center locations. The data centers that house cloud servers are kept operational to provide a variety of services, which uses a lot of electricity and has an adverse environmental impact. The primary goal of cloud computing is to offer uninterrupted and continuous Internet-based services, while using virtualization technologies to satisfy end users’ QoS requirements. With the balanced EC and service quality, it is challenging to supply cloud services. The rapid expansion of cloud services significantly rises energy and power consumption daily. This paper reviews previous studies on multiple parameters such as EC, SLA violation, and VM migration by different approaches based on statistical techniques, machine learning approaches, heuristic, and metaheuristic methods. Prediction of host CPU, identifying underload or overload hosts, VM consolidation have been applied to manage the resources using the PlanetLab and Bitbrains workload on different performance metrics. This review paper presents a detailed comparative study of different algorithms to analyze the influence of several parameters such as energy consumption, SLAV, virtual machine migration, active hosts, etc. on the performance of cloud resources. As a result, effective VM consolidation reduces power consumption, VM migration, and SLA assurance during service provisioning. It has been found that the statistical methods save up to 28% of energy, 90% SLAV, and 90% VM migration. The machine learning-based method reduces energy consumption up to 45%, SLAV up to 63%, VM migration up to 50%, the heuristic approaches save up to 72% energy, 78% SLAV, 46% VM migration, and the metaheuristic methods reduce 25% energy consumption, 79% SLAV, 89% VM migration compared to the related benchmark methods for a variety of parameters and configurations.