The main advantage of software defined networking (SDN) is that it allows intelligent control and management of networking though programmability in real time. It enables efficient utilization of network resources through traffic engineering, and offers potential attack defense methods when abnormalities arise. However, previous studies have only identified individual solutions for respective problems, instead of finding a more global solution in real time that is capable of addressing multiple situations in network status. To cover diverse network conditions, this paper presents a comprehensive reactive system for simultaneously monitoring failures, anomalies, and attacks for high availability and reliability. We design three main modules in the SDN controller for a robust and agile defense (RAD) system against network anomalies: a traffic analyzer, a traffic engineer, and a rule manager. RAD provides reactive flow rule generation to control traffic while detecting network failures, anomalies, high traffic volume (elephant flows), and attacks. The traffic analyzer identifies elephant flows, traffic anomalies, and attacks based on attack signatures and network monitoring. The traffic engineer module measures network utilization and delay in order to determine the best path for multi-dimensional routing and load balancing under any circumstances. Finally, the rule manager generates and installs a flow rule for the selected best path to control traffic. We implement the proposed RAD system based on Floodlight, an open source project for the SDN controller. We evaluate our system using simulation with and without the aforementioned RAD modules. Experimental results show that our approach is both practical and feasible, and can successfully augment an existing SDN controller in terms of agility, robustness, and efficiency, even in the face of link failures, attacks, and elephant flows.
Mihui Kim, Younghee Park, and Rohit Kotalwar. "Robust and Agile System against Fault and Anomaly Traffic in Software Defined Networks" Applied Sciences (2017). https://doi.org/10.3390/app7030266
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.