Study On Dynamic Traffic Assignment Based On Parasitic Immune Particle Swarm Optimization Algorithm

With the rapid development of the economy and the increase of automobiles on the roads,traffic congestion is becoming more and more severe,and how to apply traffic control and traffic guidance to relieve it has become a burning problem to solve.Dynamic traffic assignment is one of the kernel theories of the intelligent transportation system,where it can provide a basis from which to solve this problem,and plays an important role in traffic control and guidance.Since the dynamic traffic equilibrium assignment model is difficult to solve because of its high dimension,multivariable and complex constraints,etc.,a particle swarm optimization(PSO)algorithm is applied to solve it.The specific work in this paper is as follows:Firstly,based on the summary of the research status of dynamic traffic assignment models and methods,this paper introduces the problems to be considered in dynamic traffic assignment modeling and their mathematic expressions,and finally chooses the optimal dynamic system assignment model to study.Secondly,particle swarm algorithm,genetic algorithm and simulated annealing are used to solve the optimal traffic assignment model of dynamic systems.It is proved that PSO has more advantages in solving this problem.On the basis of this,the important parameter-inertia weight in particle swarm optimization is improved.The nonlinear dynamic inertia weight improvement strategy is adopted and the results are analyzed systematically.The results of the algorithm are finally improved.Finally,considering the instability of computing performance in PSO,the idea of parasitics and immunity is introduced into the PSO,which means that the PSO with parasitic immune mechanism is adopted to solve the dynamic traffic assignment.Specifically,the parasite group with strong parasitism can adopt the elite learning mechanism to improve the ability of the algorithm to jump out of the local extremum,and the host will acquire immunity to the parasitic behavior of the parasite group,so as to enhance the diversity of the host population.Parasitic behavior occurs when a given iterations algebra is established.The optimization performance of PI-PSO algorithm and NIW-PSO algorithm are compared and analyzed.Experimental results show that the PI-PSO algorithm has higher stability and optimization ability than the other algorithms.