$\text{E}^{3}$ MC: Improving Energy Efficiency via Elastic Multi-Controller SDN in Data Center Networks

Abstract

Energy consumed by network constitutes a significant portion of the total power budget in modern data centers. Thus, it is critical to understand the energy consumption and improve the power efficiency of data center networks (DCNs). In doing so, one straightforward and effective way is to make the size of DCNs elastic along with traffic demands, i.e., turning off unnecessary network components to reduce the energy consumption. Today, software defined networking (SDN), as one of the most promising solutions for data center management, provides a paradigm to elastically control the resources of DCNs. However, to the best of our knowledge, the features of SDN have not been fully leveraged to improve the power saving, especially for large-scale multi-controller DCNs. To address this problem, we propose $\text{E}^{3}$ MC, a mechanism to improve DCN’s energy efficiency via the elastic multi-controller SDN. In $\text{E}^{3}$ MC, the energy optimizations for both forwarding and control plane are considered by utilizing SDN’s fine-grained routing and dynamic control mapping. In particular, the flow network theory and the bin-packing heuristic are used to deal with the forwarding plane and control plane, respectively. Our simulation results show that $\text{E}^{3}$ MC can achieve more efficient power management, especially in highly structured topologies such as Fat-Tree and BCube, by saving up to 50% of network energy, at an acceptable level of computation cost.