Despite opening attractive perspectives, the concept of Software Defined Networking raises doubts about the performance and practical feasibility. To contradict these concerns, we propose a deployment-ready system aimed at proactive and periodic optimization of flow paths. The modular system consists of modules responsible for traffic prediction, static optimization, measurements, flow management, and validation of optimization results. To make the system efficient, we resolved several scientific issues and proposed novel and valuable solutions, for example methods for efficient proactive flow management and periodic re-optimization of routing policies. Simultaneously, to make the system production-ready and create a reliable research environment, we provide solutions to several technical obstacles. We validate the proposed system with three network topologies, each with three load levels, following real-life traffic models. We consider Equal-Cost Multi-Path Routing as a baseline. The results indicate that the system allows network operators to handle more traffic (packet loss reduced by up to 30%), improve quality of service (less congested links resulted in even 2.5 times lower latency), and reduce operational expenses (energy consumption lowered by up to 10%).

The majority of Internet traffic is caused by a relatively small number of flows (so-called elephant flows). This phenomenon can be exploited to facilitate traffic engineering: resource-costly individual flow forwarding entries can be created only for elephants while serving mice over the shortest paths. Although this idea already appeared in proposed TE systems, it was not examined by itself. It remains unknown what extent of flow table occupancy and operations number reduction can be achieved or how to select thresholds or sampling rates to cover the desired fraction of traffic. In this paper, we use reproducible traffic models obtained from a 30-day-long campus trace covering 4 billion flows, to answer these questions. We establish theoretical boundaries for flow table usage reduction algorithms that classify flows since the first packet, after reaching a predefined counter threshold or detect elephants by sampling. An important finding is that simple packet sampling performs surprisingly well on realistic traffic, reducing the number of flow entries by a factor up to 400, still covering 80% of the traffic. We also provide an open-source software package allowing the replication of our experiments or the performing of similar evaluations for other algorithms or flow distributions.

We demonstrate tests of a flow-based router enhanced with the additional mechanisms: Emergency Connections, Efficient Congestion Control, Global Protected Flow List and Per-User Fairness. The tests were conducted in the Click environment. The analyzed mechanisms allow for immediate acceptance of high priority traffic, protection of streaming flows in congestion, and ensure high reliability and fairness. In this paper, we show that these mechanisms work successfully in a laboratory network. Moreover, they all work at the same time providing high-level coordinated performance. Test results show significant advantages of the cross-protect router architecture over standard IP routers in several areas.