首页> 外文会议>International Conference on Cloud Computing and Security >Workload-Aware VM Consolidation in Cloud Based on Max-Min Ant System
【24h】

Workload-Aware VM Consolidation in Cloud Based on Max-Min Ant System

机译:基于Max-Min蚂蚁系统的工作负载感知VM整合在云端

获取原文

摘要

With the increasing consumption of energy in cloud data center, the cloud providers pay more attention to the green cloud computing for saving energy. The most effective way in green cloud computing is using virtual machine (VM) consolidation to pack VMs into a smaller amount of physical machines (PMs), which can save energy by switching off the idle PMs. However, in traditional static workload approach, VMs are over-provisioned with a static capacity to guarantee peak performance, which increases the unnecessary energy consumption. In this paper, we propose an innovative approach WAVMC to achieve efficient VM consolidation by using multi-dimensional time-varying workloads based on the Max-Min Ant System (MMAS). In the MMAS, we employ the complementary of both workload patterns and multi-dimensional resources usage as heuristic factors. Extensive simulations on production workloads demonstrate that the proposed model outperforms state-of-the-art baselines in active server counts and resources wastage.
机译:随着云数据中心能源消耗的增加,云提供商更加关注绿色云计算以节省能源。绿云计算中最有效的方法是使用虚拟机(VM)整合,将VM打包到更少量的物理机(PM)中,这可以通过关闭空闲的PM来节省能源。但是,在传统的静态工作负载方法中,为VM提供了过多的静态容量以保证最佳性能,从而增加了不必要的能耗。在本文中,我们提出了一种创新方法WAVMC,该方法通过使用基于Max-Min Ant System(MMAS)的多维时变工作负载来实现有效的VM整合。在MMAS中,我们将工作负载模式和多维资源使用两者的补充作为启发式因素。对生产工作负载的大量仿真表明,在活动服务器数量和资源浪费方面,所提出的模型优于最新的基准。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号