Regional Traffic Coordination Research Based On The Subarea Of Weighted Network

Urban traffic signal control is the main means to alleviate the traffic congestion of road network and improve the utilization rate of road network resources.Reasonable and effective traffic signal control strategy,not only need to study the road network in a single intersection of signal control,but also need to consider the overall road network overall efficiency.Because the traffic network is too complex and huge,it is very difficult to study the whole road network directly.It is an effective solution to divide the traffic network into several reasonable signal control sub-areas,and then coordinate the control for each sub-area.In this thesis,a reasonable and correct method is proposed to solve the problem of partition of complex network.Then,based on each sub-area,the multi-objective optimization model is constructed.Finally,the NSGA-II algorithm is improved to solve the signal timing of sub-area coordinated control.The main research works are as follows:(1)In order to solve the problem that the existing complex network community partition algorithm is difficult to effectively partition the complex traffic network,an improved Newman community partition algorithm is proposed,which could effectively divide the sub-area of the complex traffic network.This thesis chooses the distance between two junctions in traffic network and the traffic flow per unit time to construct the border right,then combining the degree characteristics of complex network to construct point right,redefining the concept of modularity.As the traffic flow is a dynamic value,select the traffic flow in different time periods and realize the dynamic division of the regional road network.The test results show that the improved algorithm can identify the degree of coupling between the road segments and realize the reasonable and correct division of the regional road network.(2)Aiming at the deficiency of the existing regional coordinated traffic control,a muti-objective optimization model of sub-area coordinated control is constructed based on the sub-area division.According to the characteristics of the sub-area,the signal cycle of sub-area as optimization variables,the average delay time of the regional traffic network and the average parking rate of the downstream sub-area as optimization indexes,constructing the muti-objective optimization model of sub-area coordinated control,which overcomes the shortcomings of single objective optimization,complex operation,or the need for strong experience.(3)According to the problem that use NSGA-II algorithm solve the signal timing of the coordinated control of the sub-area exist the distribution of the solution is uneven and the diversity of population is weak,based on the original mutation operator,this thesis proposes a mutation operator based on the Poisson random number,and when the initial population is generated,the population is first screened to ensure that the quality of the individual is retained.The simulation results show that the improved algorithm has a strong ability to explore the Pareto frontier and can maintain the diversity of the population.The improved algorithm is used to solve the signal timing of the sub-area coordinated control,so that the average delay time and the parking rate of the traffic subway are improved.