Magotra Bhagyalakshmi, Malhotra Deepti, Dogra Amit Kr
MIET: Model Institute of Engineering and Technology, Jammu, India.
Central University of Jammu, Jammu, India.
Arch Comput Methods Eng. 2023;30(3):1789-1818. doi: 10.1007/s11831-022-09852-2. Epub 2022 Nov 27.
Cloud Computing has emerged as a computing paradigm where services are provided through the internet in recent years. Offering on-demand services has transformed the IT companies' working environment, leading to a linearly increasing trend of its usage. The provisioning of the Computing infrastructure is achieved with the help of virtual machines. A great figure of physical devices is required to satisfy the users' resource requirements. To meet the requirements of the submitted workloads that are usually dynamic, the cloud data centers cause the over-provisioning of cloud resources. The result of this over-provisioning is the resource wastage with an increase in the levels of energy consumption, causing a raised operational cost. High CO emissions result from this huge energy consumption by data centers, posing a threat to environmental stability. The environmental concern demands for the controlled energy consumption, which can be attained by optimal usage of resources to achieve in the server load, by minimizing the number of active nodes, and by minimizing the frequency of switching between active and de-active server mode in the data center. Motivated by these actualities, we discuss numerous statistical, deterministic, probabilistic, machine learning and optimization based computational solutions for the cloud computing environment. A comparative analysis of the computational methods, on the basis of architecture, consolidation step involved, objectives achieved, simulators involved and resources utilized, has also been presented. A taxonomy for virtual machine (VM) consolidation has also been derived in this research article followed by emerging challenges and research gaps in the field of VM consolidation in cloud computing environment.
近年来，云计算已成为一种通过互联网提供服务的计算模式。提供按需服务改变了IT公司的工作环境，导致其使用量呈线性增长趋势。计算基础设施的供应借助虚拟机来实现。需要大量物理设备来满足用户的资源需求。为了满足通常动态变化的提交工作负载的需求，云数据中心导致了云资源的过度供应。这种过度供应的结果是资源浪费，能源消耗水平增加，导致运营成本上升。数据中心的巨大能源消耗导致高碳排放，对环境稳定性构成威胁。环境问题要求控制能源消耗，这可以通过优化资源使用以实现服务器负载、减少活动节点数量以及最小化数据中心中活动和非活动服务器模式之间的切换频率来实现。受这些实际情况的推动，我们讨论了针对云计算环境的众多基于统计、确定性、概率性、机器学习和优化的计算解决方案。还基于架构、涉及的整合步骤、实现的目标、涉及的模拟器和使用的资源对计算方法进行了比较分析。在这篇研究文章中还得出了虚拟机（VM）整合的分类法，随后介绍了云计算环境中VM整合领域的新出现的挑战和研究空白。
