In cloud data center (CDC), reducing energy consumption while maintaining performance has always been a hot issue. In server consolidation, the traditional solution is to divide the problem into multiple small problems such as host overloading detection, virtual machine (VM) selection and VM placement and solve them step by step. However, the design of host overloading detection strategies and VM selection strategies cannot be directly linked to the ultimate goal of reducing energy consumption and ensuring performance. This paper proposes a learning-based VM selection strategy that selects appropriate VMs for migration without direct host overloading detection. Thereby reducing the generation of SLAV, ensuring the performance and reducing the energy consumption of CDC. Simulations driven by real VM workload traces show that our method outperforms the existing methods in reducing SLAV generation and CDC energy consumption.
翻译:在云数据中心(CDC),在保持性能的同时减少能源消耗始终是一个热点问题。在服务器整合方面,传统的解决办法是将问题分为多个小问题,如宿主超载检测、虚拟机器(VM)选择和VM安置,并一步一步地解决这些问题。然而,宿主超载检测战略和VM选择战略的设计不能直接与减少能源消耗和确保性能的最终目标挂钩。本文件提出基于学习的VM选择战略,在不直接发现宿主超载的情况下选择适当的VMs进行移徙。通过减少SLV的生成,确保CDC的性能并减少其能源消耗。由实际VM工作量驱动的模拟记录显示,我们的方法在减少SLV的产生和CDC的能源消耗方面超过了现有的方法。