Inefficient resource usage is one of the greatest causes of high energy consumption in cloud data centers. Virtual Machine (VM) consolidation is an effective method for improving energy related costs and environmental sustainability for modern data centers. While dynamic VM consolidation algorithms can improve energy efficiency, virtualisation technologies cannot guarantee performance isolation between co-located VMs resulting in interference issues. We address the problem by introducing an energy and interference aware VM consolidation algorithm which uses predictive modelling to classify workloads using their resource usage features to make more informed consolidation decisions. The use of ensemble methods plays a pivotal role for improving predictive performance for many different problems. Using recent workload data from Microsoft Azure we present a comparative analysis of several ensemble methods using state-of-the-art prediction models and propose an ensemble based VM consolidation algorithm. Our empirical results demonstrate how our approach improves energy efficiency by 34% while also reducing service violations by 77%.

资源使用效率低下是云数据中心高能耗的最大原因之一。虚拟机（VM）整合是一种有效的方法，可以提高现代数据中心与能源有关的成本和环境的可持续性。尽管动态VM整合算法可以提高能源效率，但虚拟化技术无法保证位于同一位置的VM之间的性能隔离，从而导致干扰问题。我们通过引入一种能量和干扰感知的VM整合算法来解决该问题，该算法使用预测性建模来利用其资源使用功能对工作负载进行分类，以做出更明智的整合决策。集成方法的使用对于改善许多不同问题的预测性能起着关键作用。使用来自Microsoft Azure的最新工作负载数据，我们使用最新的预测模型对几种集成方法进行了比较分析，并提出了基于集成的VM整合算法。我们的经验结果表明，我们的方法如何将能源效率提高了34％，同时还减少了77％的服务违规情况。