Modeling and experimenting combined smart sleep and power scaling algorithms in energy-aware data center networks

Joint flow routing-scheduling for energy efficient software defined data center networks

“…Then the platform leverages the same routing algorithm with ElasticTree in POX controllers based on the power profiling of NetFPGA switches. Thanh et al (2013) improved the previous routing algorithm to enable an adaptive link rate technique. In order to further save power in data centers, Jin et al (2013) converted the VM placement problem into a routing problem, which combined hosts and network based power optimization.…”

Energy-aware routing based on power profile of devices in data center networks using SDN

“…In our work, we deploy the power scaling approach that allows reducing energy consumption greatly by adaptively changing the working rate of the processing engines or links such as reducing operating clock of devices or decreasing the link rate of a switchport. The diagram in Fig.4 shows the operation of the proposed power scaling algorithm [18]. Based on the traffic state measured by the monitoring module, the optimizer determines which state must be used on this link then sends the results to the power control and routing modules.…”

“…In cases of a small size topology that is up to K=6 (support 54 servers), we use the real testbed that is addressed in [18], while in large topology we use the Reliable Analyzer for Energy-Saving simulation tool [19]. Table III shows the average energy-saving level ratio of our Power Scaling with Energy-Profiling-aware algorithm to the conventional Power-Scaling.…”