Dynamic routing with ant system and memory-based decision-making process

Abstract

Dynamic routing is an essential tool for today’s cities. Dynamic routing problems can be solved by modelling them as dynamic optimization problems (DOPs). DOPs can be solved using Swarm Intelligence and specially ant colony optimization (ACO) algorithms. Although different versions of ACO have already been presented for DOPs, there are still limitations in preventing stagnation and premature convergence and increasing convergence rate. To address these issues, we present an in-memory pheromone trail and an algorithm based on it (named AS-gamma) in the framework of ACO. In-memory pheromone trail is effectively increasing diversity after a change in an environment. Results of experimenting AS-gamma in three scenarios on a real-world transportation network with different simulated traffic conditions demonstrated the effectiveness of the presented in-memory pheromone trail method. The advantages of AS-gamma over three existing DOP algorithms have been illustrated in terms of solutions quality. Offline performance and accuracy measures indicate that AS-gamma faces less stagnation, premature convergence and it is suitable for crowded environments.