Estimation of Effect of using ACO in Dynamic Routing on a Communication Network

Abstract

Although an ant is a small and simple creature, but collection of ants or a a colony of ants performs useful tasks such as finding the shortest path to a food source and sharing this information with other ants by depositing pheromone. In the field of ant colony optimization (ACO), models of collective intelligence of ants are transformed into useful optimization techniques that find applications in computer networking. In this paper we present an implementation of Artificial Intelligence on any communication network and compare the results thus produced with the traditional routing algorithm like the shortest node first. The problem of routing and congestion are of utmost concern for the design and implementation of any communication network. Here in this paper we present an approach of performing routing with automatic congestion control and loop removal using artificial intelligence. For the purpose of demonstrating the results of our findings we have designed a simulation of a communication network. We also performed a search space optimization process in order to find out the most appropriate algorithm to be implemented. The comparison and analysis of AI and Non AI modes is performed and is displayed in terms of different graphs. The proposed implementation of AI techniques in routing and congestion control provides a better solution than the traditionally available methods. The algorithm used for dynamic routing is ACO (Ant Colony Optimization) Algorithm which is a metaheuristic algorithm belonging to the class of Swarm Intelligence Algorithms.

Keywords – ACO, Ants, Networks, Routing, and Swarm Intelligence.