Multi-phase Traffic Signal Control for Isolated Intersections Based on Genetic Fuzzy Logic

Dynamic signal control is complex but important to increase intersection capacity and decrease delays at the same time. A genetic fuzzy logic model for multi-phase signal control at isolated intersections is developed in this study. This model is based on the sufficient fusion of hierarchical genetic algorithms with fuzzy logic, which can ensure the performance of the controller and reduce the structure as well. In this paper, the detailed formulation of the genetic structure is given and the required procedures for coding the fuzzy membership function and rules into the chromosome are described. Validation of the effectiveness of this model is carried out by simulation techniques. An isolated four-arm intersection is selected to compare the performance of three models, which are respectively GFL model proposed in this paper, the traffic-actuated model and the Pappis model. Results of the comparison show that the performance of this model is close to that of the traffic-actuated model and the Pappis model at less traffic flows but better than both the other two models in the case of greater traffic flows