On energy-aware aggregation of dynamic temporal demand in cloud computing

The proliferation of cloud computing faces social and economic concerns on energy consumption. We present formulations for cloud servers to minimize energy consumption as well as server hardware cost under three different models (homogeneous, heterogeneous, mixed hetero-homogeneous clusters) by considering dynamic temporal demand. To be able to compute optimal configurations for large scale clouds, we then propose static and dynamic aggregation methods, which come at the additional cost on energy consumption; however, they still result in significant savings compared to the scenario when all servers are on during the entire duration. Our studies show that the homogeneous model takes four time less computational time than the heterogeneous model. The dynamic aggregation scheme results in 8% to 40% savings over the static aggregation scheme when the degree of aggregation is high.