This paper explores the feasibility of and challenges in developing methods for black-box monitoring of the power usage of a virtual machine (VM) at run-time, on shared virtualized compute platforms, including those with complex memory hierarchies. We demonstrate that VM-level power utilization can be accurately estimated, or estimated with accuracy with bound error margins. The use of bounds permits more lightweight online monitoring of fewer events, while relaxing the fidelity of the estimates in a controlled manner. Our methodology is evaluated on the Intel Core i7 and Core2 x86-64 platforms, running synthetic and SPEC benchmarks.

Concurrency and exchanging design knowledge among thermal and IT management are required to achieve an energy efficient operational data center. In this paper, a design approach is presented to bring adaptability and concurrency for coordinated minimization of cooling and IT power consumption in data centers. The presented approach is centered on a proper orthogonal decomposition based reduced order thermal modeling approach, and power profiling of the IT equipment to identify the optimal parameters of the air cooling systems along with optimal dynamic workload distribution among the servers. The method is applied to a data center cell with different rack and server architectures. The results show that the design approach results in 12–70% saving in the total energy consumption of the data center cell for various scenarios, compared with a baseline design.

No abstract

No abstract

No abstract