On a Hopfield Net Arising in the Modelling and Control of Over-Saturated Signalized Intersections

摘要

We present a neural method – based on the Hopfield net – for the modelling and control of over-saturated signalized intersections. The problem is to look, in real-time, for lights signal setting which minimize a given traffic criterion such as waiting time. The use of the Hopfield model is straightforward justified by its optimization capabilities, especially its fast time computing (by its own dynamic), which is of a great interest in real-time problems like the traffic control one. The original Hopfield algorithm is modified to take into account proper constraints of the traffic problem. This approach is illustrated by numerical examples of traffic conditions generated by a simulator. We extend the method to urban nets of several interconnected intersections.