The Control Method And Simulation Research Of Urban Intelligent Traffic Signal

A novel discrete model of traffic signal control is proposed based on the research of the situation of an intersection. It is composed of branches of each direction of an intersection and divided the cycle time into several equal time segments. According to the discrete input information of traffic flow in each branch of each direction, the performance indexes of traffic signal control can be achieved.The model shows the discrete and inconstant character of the traffic flows of the intersection and closed to the fact of traffic.At the same time, the paper presented two kinds of forecasting model about the vehicle's arrival of the intersection based on the Momentum Backpropagation Neural Network. The two forecasting model can adapt the discrete model of traffic signal control.The paper summarized the basic control model of the areas control of urban traffic signal system by researching and comparing several classic systems, and builded the simulation model of traffic signal control of five intersections.A hybrid algorithm, adaptive mutation-particle swarm optimization algorithm, which combined mutation operator in real-code genetic algorithm with adaptive particle swarm optimization algorithm, was presented. Adaptive particle swarm optimization algorithm have the problem on getting in the local best point easily ,beacause the algorithm update the best point of the individual and the best point of the global according to the search points of them before the current generation. The hybrid algorithm increased its convergence rate and stability using the mutation operator to update the best point of the individual and the best point of the global, because of the ability to mutation operator in local searching.In order to validate the effectiveness of the hybrid algorithm, the paper simulated with Matlab.The simulation results in an intersection demonstrated the hybrid algorithm is better than real-code genetic algorithm and adaptive particle swarm optimization algorithm.It could greatly increase the capacity of traffic, reduce the delay time and realize the optimal control of in traffic signal.At the same time it can meet the real-time control of the intersection and adapt the variety of the traffic flow.The simulation in five intersections also showed the effectiveness of the hybrid algorithm.