Research On Optimal Control Of Regional Traffic Coordination Based On Game Theory

With the rapid development of social economy and traffic urban road network,traffic congestion and other phenomena often occur at intersections.In order to alleviate traffic pressure and improve traffic efficiency,the research of regional coordinated optimal control has become one of the hot spots.Aiming at the shortcomings of the existing regional traffic signal coordination optimization control research,thesis is based on the regional traffic multi-agent control architecture,using game theory to analyze the mutual influence relationship between various intersection agents,and establishing a coordination mechanism to phase the intersections.A multi-junction traffic optimization model is constructed with the goal of average vehicle delay time,vehicle queue length and regional in-out ratio minimization.A dynamic chaotic particle swarm optimization algorithm is proposed for the complexity characteristics of multi-parameter of the optimization model.Finally,the dynamic chaotic particle swarm optimization algorithm is used to optimize the coordinated optimization model globally.The coordinated optimization control of all intersections in the region is realized according to the effective green light time,which effectively reduces the average delay time of vehicles at each intersection and the average queue length of vehicles.The main research contents are as follows:Firstly,thesis uses game theory to analyze the mutual influence and mutual restraint relationship between various intersection agents,establish a coordination mechanism to coordinate the phase games of each intersection,find the balance point through the game tree and finally reach the Nash equilibrium,and realize the phase coordination of each intersection.A multi-junction traffic optimization model was constructed with the goal of vehicle average delay time,vehicle queue length and regional in-out ratio minimization.The simulation experiment proves that the coordinated optimization model based on game theory can effectively provide optimization strategies for various intersections and improve traffic efficiency.Secondly,a dynamic chaotic particle swarm optimization algorithm is proposed to overcome the complexity of multi-peak and multi-peak of the above regional coordination optimization model.In order to enhance the diversity of the initial population,improve the convergence speed and local search ability of the algorithm,tent mapping is used to optimize particle speed,position,inertia weight,learning factor and random number to enhance the diversity of the population.In the iteration process,tabu search strategy is introduced to further improve the convergence speed of the optimization algorithm.The advantages of dynamic integer chaotic optimization algorithm and particle swarm optimization algorithm are fully utilized to make the hybrid algorithm have faster search efficiency and better search ability.The simulation results show that the proposed dynamic chaotic particle swarm optimization algorithm can obtain more effective coordination optimization strategy.Finally,using VISSIM traffic simulation modeling tool,the regional coordination control system based on the above multi-agent coordination control model and optimization algorithm is constructed.Regional traffic network objects,regional coordination control module,regional signal optimization module and signal timing output module are constructed,and system simulation experiments are carried out.The experimental results show that the proposed multi-agent coordinated optimal control model can effectively reduce vehicle queue length and average delay time,and improve traffic efficiency.