NetLogo implementation of an ant colony optimisation solution to the traffic problem

Current traffic control systems regulate traffic flows only by switching traffic lights according to historical data. Status-prediction and routing services also rely on historical data and as such the accuracy of such predictions cannot be fully relied upon. This paper models the traffic control problem as a multi-agent-multi-purpose system (MAMP) inspired by ant colony optimization (ACO). Traffic information is collected by the vehicles, rather than fixed roadside infrastructure in this system. Moreover, the information is collected and shared among the vehicles in a distributed manner. The proposed distributed intelligent traffic system (DITS) is implemented in NetLogo and experiments are conducted on two variations of the system, one with ACO, the other without ACO, to investigate the impact of ACO on the solution to the traffic problem. Three performance parameters; average speed, average waiting time of vehicles and the average number of stopped vehicles are recorded and studied for different traffic densities and road topologies. The results have shown that for various initial distributions of vehicles, the ACO-strategy obtains higher average speeds, smaller average waiting times and number of stopped vehicles than the non-ACO-strategy. This observation holds for all experiments with different traffic densities and different road network topologies.