Real-time control of traffic signal with genetic algorithms optimizing urban intersections

A real-time dynamic model on multiphase traffic flows is conducted at an urban intersection and an optimal control method with Genetic Algorithms (GA) is developed in this paper. Using data of the traffic flows in the current cycle and the cycle before, the traffic flows in the next cycle may be estimated through linear extrapolation and each phase time in the next cycle is determined with a GA optimizing method. A simulation experiment for the traffic model at a four-phase intersection is also performed in the last section. The results show that the method is effective.