Live migration of virtual machines proves to be inexorable in providing load balancing among physical devices and allowing scalability and flexibility in resource allocation. The existing approaches exhibit different policies, distinct performance characteristics, and side effects such as power consumption and performance degradation. Therefore, determining the most optimal live migration algorithm in certain situations remains an open challenge. In this work, a new prediction-based model to manage the live migration process of VMs is introduced. Our adaptive model dynamically identifies the optimal live migration algorithm for a given performance metric based on a prior diagnosis of the system. The model is developed by considering the assumption of different workloads alongside certain resource constraints for any of the currently available migration algorithms. The proposed model consists of an ensemble-learning strategy that involves linear and non-parametric regression methods to predict six live migration key metrics, provided by the operator and/or the user, for each live migration algorithm. Our model allows considering the best combination which is constituted of the algorithm-metric pair to migrate a VM. The experimental results show that the proposed model allows to significantly alleviate the service level agreement violation rate by between \(31\%\) and \(60\%\), along with decreasing the total CPU time required for the prediction process.

事实证明，虚拟机的实时迁移在提供物理设备之间的负载平衡以及允许资源分配的可扩展性和灵活性方面是不可阻挡的。现有的方法表现出不同的策略、不同的性能特征和副作用，例如功耗和性能下降。因此，在某些情况下确定最佳实时迁移算法仍然是一个开放的挑战。在这项工作中，引入了一种新的基于预测的模型来管理 VM 的实时迁移过程。我们的自适应模型根据系统的先前诊断动态识别给定性能指标的最佳实时迁移算法。该模型是通过考虑不同工作负载的假设以及任何当前可用迁移算法的某些资源限制来开发的。所提出的模型由集成学习策略组成，该策略涉及线性和非参数回归方法，以预测运营商和/或用户为每个实时迁移算法提供的六个实时迁移关键指标。我们的模型允许考虑由算法-度量对组成的最佳组合来迁移 VM。实验结果表明，所提出的模型可以显着降低服务水平协议违反率 由运营商和/或用户为每个实时迁移算法提供。我们的模型允许考虑由算法-度量对组成的最佳组合来迁移 VM。实验结果表明，所提出的模型可以显着降低服务水平协议违反率 由运营商和/或用户为每个实时迁移算法提供。我们的模型允许考虑由算法-度量对组成的最佳组合来迁移 VM。实验结果表明，所提出的模型可以显着降低服务水平协议违反率\(31\%\)和\(60\%\)，同时减少预测过程所需的总 CPU 时间。