Dynamic virtual machine (VM) migration technology plays a crucial role in cloud computing environments, significantly enhancing overall resource scheduling capabilities. In response to the rapidly increasing user scale and business pressure, data centers typically scale out by adding more servers; however, this leads to a surge in energy consumption and an explosion in the number of virtual machines, exacerbating resource scheduling challenges. Existing research on dynamic VM migration often fails to simultaneously address migration frequency and system load balancing. To tackle this, this paper proposes the DY-BAL algorithm, a dynamic VM migration strategy tailored for cloud computing environments. It comprehensively considers migration timing, migration target selection, and destination server choice, aiming to reduce migration frequency while ensuring balanced resource load. Experimental results demonstrate that, while maintaining service quality, the algorithm achieves at least a 29% reduction in average VM migrations and a minimum 24% decrease in average energy consumption.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

A Dynamic Virtual Machine Migration Strategy for Load Balancing in Cloud Computing Environments

  • Zhigang Huang,
  • Chenggang Deng,
  • Wei Liu,
  • Feifan Xiao

摘要

Dynamic virtual machine (VM) migration technology plays a crucial role in cloud computing environments, significantly enhancing overall resource scheduling capabilities. In response to the rapidly increasing user scale and business pressure, data centers typically scale out by adding more servers; however, this leads to a surge in energy consumption and an explosion in the number of virtual machines, exacerbating resource scheduling challenges. Existing research on dynamic VM migration often fails to simultaneously address migration frequency and system load balancing. To tackle this, this paper proposes the DY-BAL algorithm, a dynamic VM migration strategy tailored for cloud computing environments. It comprehensively considers migration timing, migration target selection, and destination server choice, aiming to reduce migration frequency while ensuring balanced resource load. Experimental results demonstrate that, while maintaining service quality, the algorithm achieves at least a 29% reduction in average VM migrations and a minimum 24% decrease in average energy consumption.