Research And Application Of Swarm Algorithm In Intelligent Transportation System

With the quick industrialization, urbanization, motorization, the urban traffic problems have become increasingly prominent, and frequent traffic jams. The development of intelligent transportation systems is one of the effective ways to solve the problems.The paper first introduces particle swarm optimization algorithm and its improvement. As the problems of easily getting into the local optimum and slowly converging speed of the Particle Swarm Optimization (PSO) algorithm, a new PSO algorithm based on adaptive chaos search is proposed. The adaptive adjustment of search scopes, which can avoid the redundant computation and accelerate the convergence speed of the evolutionary process. Finally, Experimental results show that the new introduced algorithm outperforms several other famous improved PSO algorithms on many well-known benchmark problems.Based on the analysis the intelligent optimization algorithms such as wavelet analysis, genetic algorithm, neural network, chaos, swarm intelligence and other improvements , a new approach has been proposed for traffic flow prediction. Finally, the real detected traffic data are used to testify the precision of the model, and the results show that the model can produce more accurate predictions than that of traditional artificial neural network model.The paper focus on how to quickly adjust traffic signal timing based on traffic flow prediction. First analysis the traffic flow of intersection, the control parameters and the relationship between the objectives, a multi-objective optimization model is established. Then traffic signal control parameters at intersection can be obtained by particle swarm optimization and genetic algorithm. Finally a case study with an Intersection in Chongqing is given, where the advantages with this method are shown.A simulation model of intersection based on GIS has been developed, which can combine various traffic flow prediction and control model for the Intersection optimization. It can obtainedOptimal parameters of the model through Adjust the basic parameters of the model and Different models and different parameter settings.