CONTROLLER LOCALIZATION IN SOFTWARE-DEFINED NETWORK USING NAKED MOLE-RAT (NMR) ALGORITHM

Abstract

Software-defined Network (SDN) is the novel network paradigm where decoupling of the control plane from data plane has its inherent advantages but introduces controller placement problem (CPP). CPP involves placing optimal number of the controllers while meeting prerequisites of conflicting nature such as latency, load balancing, and computational time. To achieve scalability, deployment of multiple controllers in large scale SDN is one of the key challenges. CPP can be addressed as a multi-objective combinatorial optimization problem whose solution is a trade-off between multiple optimization parameters. In this thesis, a novel population-based meta-heuristic algorithm, Naked-mole rat (NMR) has been proposed to optimize the controller placement based on switch-controller (SC) latency, controller-controller (CC) latency while maintaining load balancing among the controllers. The ideas and mechanisms are illustrated using two publically available topologies, viz. Savvis and Ernet, from Topology-zoo. The performance of NMR algorithm is compared with Bat algorithm and NMR algorithm slightly performed better.