Multi-agent fuzzy signal control with bus priority

An urban region traffic intelligent coordinated control method based on multi-agent is presented, and the control target is to make bus-weighted vehicle average delay least. A two-layer hierarchical control architecture is used. The high-layer is the zone intelligent controller (ZCA) deciding key intersection and adjusting common cycle length real-time. The low-layer is constructed by intersection intelligent controllers (ICA). An ICA is divided into 3 modules: phase choosing module, green observation module and decision module. ICAs cooperating with each other, can optimize phase sequence and phase length. Multi-agent fuzzy signal control strategy with bus priority is used and the fuzzy rules are optimized by genetic algorithm (GA). Simulation results indicate, compared with fixed-time control, this control strategy can reduce social vehicles mean delay efficiently, and reduce bus mean delay more.