Using metaheuristics to improve the placement of multi-controllers in software-defined networking enabled clouds

Abstract

SDN is a model that separates the control and the data levels in an arrangement to enhance capability to program and configure the network in a more agile and efficient manner. Multiple controller modules have been used in the SDN engineering to empower programmable and adaptable configurations such as improving scalability and reliability. The distance and time calculations and other performance measures have to be considered in solving the Multi-Controller Position Problem (MCPP). This paper investigates the use of metaheuristic algorithms to build an MCPP mathematical model. Both the symmetric Harmony Search (HS) modelling and the Particle Swarm Optimization (PSO) algorithm are considered in this respect. Thus, our hybrid approach is proposed and known as Harmony Search with Particle Swarm Optimization (HSPSO) is applied and we compared the extracted results with the state-of-the-art techniques in the previous literature. Besides the development of the mathematical model, a simulation study has been done considering the relevant parameters including the link distance description and the access time between the SDN entities. The console simulation uses NetBeans with CloudsimSDN procedure files in the SDN-based cloud environment.