LBFTFB fault tolerance mechanism for software defined networking
Wael Hosny Fouad Aly · 2017 International Conference on Electrical and Computing Technologies and Applications (ICECTA) · 2017
Software Defined Networking (SDN) paradigm brings flexibility and programmability to the network management. Deploying a set of SDN controllers to manage a Wide Area Network is challenging as it implies to determine the right number of controllers to install and their locations within the network in addition to minimize the effect of their failures. In this paper, we give a methodology that should be taken into consideration to provide a fault tolerance in SDN networks. In this paper a new model is proposed. The model is called load balancing to support fault tolerance using feedback control for SDNs (LBFTFB). LBFTFB uses feedback control theoretic techniques and uses least squares regression to find the goodness of the model. LBFTFB provides load balancing constraints for several level of backup controllers. Cascading controller failures is one of the popular controller failures. The LBFTFB model reduces the cascading failure problem effect. In order to test the efficiency of the proposed model, a reference model was used. The reference model used is the HyperFlow model. The HyperFlow model is a distributed control plane for OpenFlow. HyperFlow is an application developed on the top of the NOX controller, to enable logically centralized multi-controller architectures. Experimented were conducted to compare the performance of LBFTFB when compared to the HyperFlow. This is an ongoing research. Tentative emulation results show promising controlled results indicating that LBFTFB model outperforms the HyperFlow by 16% on average in terms of packet loss and packet delays.