A Density-based Controller Placement Algorithm for Software Defined Networks

Software Defined Network (SDN) is a new type of network structure, which decouples the data plane from the control planes, and improves network flexibility. However, this separation creates a problem called Controller Placement Problem (CPP), that is, how many controllers are required and where they should be placed. In this paper, we propose an improved Density-based Controller Placement Algorithm (DCPA), which can obtain the required number of controllers through traversing candidate values of radius, and then divide the entire network into multiple sub-networks. In each sub-network, the controllers are deployed with the purpose of minimizing the average propagation latency and worst-case propagation latency between controllers and switches simultaneously. We conduct experiments on 100 real network topologies from the Internet Topology Zoo to evaluate the performance of algorithm, and the results verify that DCPA can always find out the controller placement scheme with a low time consumption to reduce the propagation latency for different network scales, with a less than 10% margin from the optimal solution.