A Novel Controller Placement Using Petri-Nets for SDNs

Abstract

Software defined networking (SDN) separates the control and the data planes. This separation brings flexibility to the network. But the decoupling has some drawbacks such as the controller placement problem (CPP). Controller placement is a crucial task which affects the overall networks’ performance. This paper proposes a novel controller placement model that is based on petri-nets to place the SDN’s controllers. The proposed model is called controller placement using petri-nets for SDNs (CPPNSDN). CPPNSDN aims to reduce the average propagation latency among switches and their associated controllers. CPPNSDN divides the network into sub-networks. Each sub-network is governed by a controller. Experiments were conducted on the Internet2/OS3E topology to evaluate the performance of CPPNSDN. Experiments show that CPPNSDN reduces the average latency significantly compared to two reference models. The first reference model is the Modified Density Peaks Clustering (MDPC) and the Optimized Kmeans model. In terms of the overall average latency, the CPPNSDN has shown promising results as it outperformed the MDPC and optimized Kmeans reference models by 7% and 17% respectively. Confidence Interval (CI) used was 90%. This is an ongoing work and the results are promising for more future investigation.