Profile-based virtual machine placement for energy optimization of data centers
Zhe Ding · Queensland University of Technology · 2017
This thesis provides a framework for virtual resource placement to optimize energy consumption in data centers. The framework consists of three phases: profiling, task classification, and virtual machine placement, and automatically conducts virtual resource placement for given jobs and tasks. It is shown to achieve a 12% cut of energy consumption in comparison with benchmark methods, implying a save of millions of dollars for an enterprise.