A Controller Placement Algorithm Based on Density Clustering in SDN

Abstract

Software-defined networks(SDNs) are improving the controllability and flexibility of networks as an innovative network architecture paradigm. The reasonable placement of the controller in SDN would effectively improve the performance of entire network. In this paper, we study clustering-based controller placement algorithm. The clustering by fast search and find of density peaks (CFSFDP) algorithm is a density-based clustering algorithm with less initial parameters and faster execution speed. However, the CFSFDP algorithm does not consider other performance indicators in the network and the number of the clustering centers needs to be manually determined. In this paper, we propose a controller placement algorithm in SDN to reduce propagation delay and communication consumption in the intra-controller and inter-controller. And the number and the location of controllers are discovered automatically through the inflection point of decision graph. We evaluate the performance of the proposed algorithm on internet2 OS3E network topology. The experimental results show that the proposed algorithm provides better performance than the traditional approaches in terms of communication consumption and propagation delay.