Dynamic flow scheduling for Power-efficient Data Center Networks

Abstract

Power-efficient Data Center Networks (DCNs) have been proposed to save power of DCNs using OpenFlow. In these DCNs, the OpenFlow controller adaptively turns on and off links and OpenFlow switches to form a minimum-power subnet that satisfies traffic demand. As the subnet changes, flows are scheduled dynamically to routes composed of active switches and links. However, existing flow scheduling schemes could cause undesired results: (1) power inefficiency: due to unbalanced traffic allocation on active routes, extra switches and links may be activated to cater to bursty traffic surges on congested routes, and (2) Quality of Service (QoS) fluctuation: because of the limited flow entry processing ability, switches cannot timely install/delete/update flow entries to properly schedule flows. In this paper, we propose AggreFlow, a dynamic flow scheduling scheme that achieves power efficiency in DCNs and improved QoS using two techniques: Flow-set Routing and Lazy Rerouting. Flow-set Routing achieves load balancing and reduces the number of entry installment on switches by routing flows in a coarse-grained flow-set fashion. Lazy Rerouting maintains load balancing and spreads rerouting operations over a relatively long period of time, reducing the burstiness of entry installment/deletion/update on switches. We built a NS3 based fat-tree network simulation platform to evaluate AggreFlow's performance. The simulation results show AggreFlow reduces power consumption by about 18%, achieves load balancing and improved QoS (i.e., low packet loss rate and reducing the number of processing entries for flow scheduling by 98%), compared with baseline schemes.