Development of Traffic Flow in a Mega City Using Neural Network Controller

This paper focuses on improving vehicular traffic flow using neural network controller system. Such real time simulation software was currently used as a tool for optimizing the design of vehicular controls in traffic related matters. In this paper, field data were collected from Digital Security Company Enugu which included measurement from the average waiting time for the red light duration and different green light durations. The testbed environment is made up of a junction, ABCD. It was observed that the morning hour otherwise known as busy hour, more vehicles enters into the testbed environment through lane A and B while less vehicle queue in lane C and D respectively. With the introduction of neural network in the design, this will help in decongesting the vehicular problem both in the busy hour and less busy hour. This characterisation of testbed environment were neural network is used is not so with junctions where traditional traffic flow control is used, a lane with no vehicle on it is still has time allotted to it while those with long queues of vehicles are asked to stop and wait until they are asked to move.