Real-coded genetic algorithm for signal timing optimization of a single intersection

For a single two-way intersection with multi-lanes, a dynamic traffic flow model based on four-phase control is formulated, and a real-coded genetic algorithm (RGA) is used for optimizing the green time and cycle time. For examining the validity of the dynamical model and its RGA optimization method, comparisons are made between the method proposed in this paper and the conventional control method (fixed-time control). The simulation result shows that the dynamical model and its RGA optimization method are feasible and have a better result than the conventional method.