Title: A multi-controller placement strategy in software defined networks using affinity propagation

Authors: C.N. Sminesh; E. Grace Mary Kanaga; A.G. Sreejish

Addresses: Department of Computer Science and Engineering, Government Engineering College, Thrissur, India ' Department of Computer Sciences Technology, Karunya Institute of Technology and Sciences, Coimbatore, India ' Department of Computer Science and Engineering, Government Engineering College, Thrissur, India

Abstract: In software defined networking (SDN) when the number of network elements and traffic flows escalate, a single controller cannot efficiently handle the growing load, resulting in the deployment of multiple controllers. To develop computationally less intensive solutions for the controller placement problem in WAN, clustering-based network partitioning algorithms can be employed. The proposed method partitions the network using a modified-AP clustering algorithm which automatically computes the number of clusters and uses the candidate exemplars identified for the placement of SDN controllers. The similarity measure that considers both the Euclidean distance and link bandwidth is the input to the proposed algorithm, and the simulation is carried out using standard network topologies from the Internet Topology Zoo. The simulation results show that the observed number and location of SDN controllers minimises average case, worst-case, inter-controller latency and improved controller imbalance factors which ensure the optimal number and placement of SDN controllers.

Keywords: software defined networking; SDN; controller placement; traffic engineering; affinity propagation.

DOI: 10.1504/IJITST.2020.104581

International Journal of Internet Technology and Secured Transactions, 2020 Vol.10 No.1/2, pp.229 - 253

Received: 20 Feb 2018
Accepted: 27 Jun 2018

Published online: 20 Jan 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article