Intelligent Multipath Routing in Software Defined Networks Based on Ant Colony Optimization Algorithms

Abstract

The software defined networks (SDN) are a modern trend in building of new generation computer networks. The SDN provide flexibility and control in management of data flows in the network, as well as requirement level of quality of service for applications. An approach to intelligent multipath routing in SDN based on ant colony optimization algorithms is proposed in this paper. Research and analysis of two types of ant colony optimization algorithms was carried out: ant system (AS) and ant colony system (ACS). The visual software system SDNLoadBalancer was developed and the experimental SDN topology was designed. They make it possible to research in detail the processes of multipath routing in SDN based on the proposed approach. Also comparative analysis of the proposed approach, results of the Yen algorithm and the genetic algorithm was carried out. The results of experimental research show the effectiveness of the use of ant colony optimization algorithms in solving the problem of multipath routing in SDN, allow to obtain results close to optimal in an acceptable time, and also reduce the transmission delay jitter in the network.