Performance bounded energy efficient virtual machine allocation in the global cloud

• We analyze the effects of global virtual machine allocation on energy consumption, using a variety of real-world policies and a realistic testing scenario.
• We found that by using an allocation policy designed to minimize energy, total energy consumption could be reduced by up to 14%, and total monetary energy costs could be reduced by up to 26%.
• We have begun performance qualification of our energy cost driven allocation policies through network capability tests.
• Our results indicate that performance and IaaS provider implementation costs have a significant influence on selection of optimal virtual machine allocation policies.

Reducing energy consumption is a critical step in lowering data center operating costs for various institutions. As such, with the growing popularity of cloud computing, it is necessary to examine various methods by which energy consumption in cloud environments can be reduced. We analyze the effects of global virtual machine allocation on energy consumption, using a variety of real-world policies and a realistic testing scenario. We found that by using an allocation policy designed to minimize energy, total energy consumption could be reduced by up to 14%, and total monetary energy costs could be reduced by up to 26%. Further, we have begun performance qualification of our energy cost driven allocation policies through network capability tests. Our results indicate that performance and IaaS provider implementation costs have a significant influence on selection of optimal virtual machine allocation policies.