| With the rapid development of national economy and the increase of car ownership year by year,the problem of urban road congestion is becoming more and more serious.In order to ensure the smooth passage of trunk vehicles,it is necessary to coordinate and control the signal lights at each intersection of trunk lines,so as to achieve the goal of minimizing vehicle delay,so as to improve the traffic capacity of trunk lines.Therefore,this paper establishes the vehicle delay model according to different traffic flow states at the intersection,and solves the phase difference with the goal of minimizing the delay without changing the phase scheme.Firstly,this paper processes,counts and classifies the collected data(the traffic flow of each entrance lane at each intersection),and then uses LSTM neural network to predict the short-term traffic flow of each entrance lane at each intersection in combination with the influencing factors(weather,working day / non working day).Secondly,taking urban trunk roads as the research object,this paper studies the coordinated control of trunk roads under unsaturated flow and saturated flow.The operation characteristics of intersection traffic flow under different saturated flow conditions are analyzed,and the corresponding trunk line coordinated control strategy is proposed.The phase difference is selected as the decision variable,and the minimum delay model of trunk line coordinated control is established for different traffic flow states.Finally,Dalian Malan square Xishan Street section is selected for example simulation.The LSTM neural network is used to predict the traffic flow of each entrance lane at each intersection,and the signal timing of each intersection is rescheduled according to the predicted traffic flow value.According to whether the predicted traffic flow is saturated or unsaturated,it is substituted into the established delay model to obtain the optimal phase difference.The traffic simulation software synchro is used to establish the corresponding trunk line simulation model.Through the simulation results,it can be seen from the green wave band that the uplink and downlink green wave bandwidth of the two-way delay model is wider than the green wave bandwidth of the numerical solution,and the uplink and downlink green wave bandwidth is more balanced.The total delay of trunk line controlled by two-way delay model is 13.9% lower than that controlled by numerical method.The experimental results verify the correctness of the model,and verify the effectiveness of using the trunk traffic coordination optimization control model to improve the traffic operation. |
