A traffic flow dynamic control method and system for two-way multi-lane highways based on traffic simulation

Abstract

The present invention discloses a method and system for dynamic control of traffic flow on a two-way multi-lane highway based on traffic simulation. First, a traffic simulation platform is used to construct a virtual sensor network covering two-way multi-lane to perform full-factor perception of traffic flow and obtain collected data. Then, a double sliding window mechanism and an IQR algorithm are combined to filter out abnormal values ​​in the collected data to obtain filtered data. The present invention realizes the function of real-time dynamic control of highway traffic flow by constructing a closed-loop optimization system of perception, decision-making, control and evaluation, and by integrating dynamic traffic simulation with real-time data-driven technology, it can accurately perceive, intelligently decide and collaboratively control traffic flow. At the same time, the time-space coupled traffic state prediction model can improve the ability to predict the evolution trend of traffic flow, thereby improving the overall traffic capacity of the highway and protecting the life and property of road users. The system is suitable for wide promotion and use.

Description

Technical Field

[0001] The present invention relates to the technical field of highway traffic flow control, and in particular to a traffic simulation-based method and system for dynamic traffic flow control on a bidirectional multi-lane highway. Background Art

[0002] With the acceleration of urbanization and the continuous growth of the number of motor vehicles, the traffic flow on highways has shown explosive growth, and the traffic pressure faced by two-way multi-lane highways is increasing.

[0003] At present, existing traffic control methods generally rely on fixed parameter models and are difficult to adapt to the dynamically changing traffic environment, resulting in frequent traffic congestion, low traffic efficiency and prominent safety hazards on highways. In addition, there is a lack of in-depth exploration of the spatiotemporal dynamic characteristics of traffic flow, which not only makes it difficult to accurately predict the evolution trend of traffic status, but also unable to respond to emergencies and random disturbances in real time. At the same time, there is also the problem of insufficient accuracy in micro-traffic behavior modeling and difficulty in reflecting the characteristics of real driving behavior. Therefore, it is necessary to design a dynamic traffic control method and system for two-way multi-lane highways based on traffic simulation. Summary of the Invention

[0004] The purpose of the present invention is to overcome the shortcomings of the existing technology and to better and effectively solve the problems of frequent traffic congestion, low traffic efficiency and prominent safety hazards on highways caused by the existing traffic control methods, which generally rely on fixed parameter models and are difficult to adapt to dynamically changing traffic environments. In addition, the existing traffic control methods lack in-depth exploration of the spatiotemporal dynamic characteristics of traffic flow, making it difficult to accurately predict the evolution trend of traffic status and respond to emergencies and random disturbances in real time. At the same time, there are also problems such as insufficient accuracy in micro-traffic behavior modeling and difficulty in reflecting the characteristics of real driving behavior. A two-way multi-lane highway traffic flow dynamic control method and system based on traffic simulation are provided. For a two-way multi-lane highway scenario, mixed traffic control of random traffic flow and focused route traffic flow is performed. Then, multi-dimensional data of traffic flow position, speed, and lane occupancy are collected in real time through simulated virtual sensors, and traffic status is evaluated after Kalman filtering and fuzzy logic processing. Then, the generation rate of random traffic flow is dynamically adjusted using a time-varying Poisson process. Then, for focused route traffic flow, departure timing, lane allocation and speed initialization are managed through priority queues, and an improved MOBIL algorithm and PID are combined. The control implements lane change decisions and following distance optimization, and also supports the hierarchical activation of emergency lanes and conflict resolution mechanisms. Subsequently, through closed-loop feedback, the generated parameters and control models are adjusted in real time to improve road traffic efficiency and safety in complex traffic scenarios, providing a simulation-driven solution for intelligent traffic control on highways.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] A traffic flow dynamic control method for a two-way multi-lane highway based on traffic simulation includes the following steps:

[0007] Step A: Use the traffic simulation platform to build a virtual sensor network covering two-way and multi-lane traffic to perceive all elements of traffic flow and obtain collected data;

[0008] Step B: using a double sliding window mechanism and an IQR algorithm to filter outliers in the collected data to obtain filtered data;

[0009] Step C, constructing a multidimensional vector containing spatiotemporal features to enhance the feature vector in the filtered data and obtain enhanced data;

[0010] Step D: Based on the enhanced data, a hierarchical generation control framework and micro-driving behavior refined control are established to optimize the dynamic traffic flow and obtain the control optimization results;

[0011] In step E, the control optimization results are subjected to full-process control logic and closed-loop feedback, and emergency scenario enhanced control rules are established to complete the dynamic control of traffic flow on two-way multi-lane highways.

[0012] The aforementioned method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation includes step A, which uses a traffic simulation platform to build a virtual sensor network covering two-way multi-lane to perform full-factor perception of traffic flow and obtain collected data. The full-factor perception includes dynamic flow monitoring, road environment perception, and vehicle generation characteristics. The specific steps are as follows:

[0013] Step A1: Dynamic traffic monitoring, specifically deploying virtual induction coils on each road section, and then collecting the instantaneous number of vehicles on the road section every second. , lane occupancy and headway Building a real-time traffic matrix ,in is the time window, and the lane occupancy λ is as shown in formula (1),

[0014] (1)

[0015] in, For the Vehicle length, is the lane length, is the number of lanes;

[0016] Step A2: road environment perception, specifically integrating the weather simulation module to dynamically update the road friction coefficient , and then monitor the emergency lane occupancy rate through the emergency lane virtual camera ;

[0017] Step A3, vehicle generation features, specifically vehicle generation features are divided into random traffic flow and focused traffic flow, the random traffic flow is specifically generated by setting a generator at the boundary node of the road network to record the coordinates of the generated point , initial velocity and vehicle type ratio, the focused traffic flow is specifically for the target route Collect the vehicle's desired lane sequence .

[0018] In the aforementioned method for dynamic control of traffic flow on a two-way multi-lane highway based on traffic simulation, step B is to filter the abnormal values ​​in the collected data by combining a double sliding window mechanism and an IQR algorithm to obtain filtered data, wherein the double sliding window mechanism includes a short window and long windows , the short window For detecting sudden anomalies, the long window Used to identify trend noise, the specific steps are as follows:

[0019] Step B1: Initialize the short window and long window and store the data of the most recently set number of seconds respectively. Then, add each newly collected data point to the short window and long window and remove the oldest data point in the window to keep the size of the short window and long window unchanged.

[0020] Step B2: Calculate the statistical characteristics of the data in the short window and the long window. Specifically, determine whether the new data point in the short window causes a traffic surge exceeding a threshold. If so, the data point is determined to be a sudden anomaly. Then, compare the statistical characteristics of the new data point in the long window with the data in the long window to determine whether there is trend noise.

[0021] Step B3, headway Apply the IQR algorithm, specifically sort the headway data, and then sort by the first quartile. and the third quartile Calculate the interquartile range , as shown in formula (2),

[0022] (2);

[0023] Step B4, determining a valid interval, wherein data points in the headway data that exceed the valid interval are treated as invalid data;

[0024] Step B5: fill the invalid data using linear interpolation. Specifically, the linear interpolation method calculates the invalid data point value based on the adjacent valid data point values.

[0025] In the aforementioned traffic flow dynamic control method for a two-way multi-lane highway based on traffic simulation, step C is to construct a multidimensional vector containing spatiotemporal features to enhance the feature vector in the filtered data and obtain enhanced data, wherein the multidimensional vector is used to provide richer information for subsequent traffic flow analysis and control, as shown in formula (3),

[0026] (3)

[0027] in, is a multidimensional vector, is the vehicle generation time, and the vehicle generation time It is used to record the specific time when a vehicle is generated in the road network and reflect the time distribution characteristics of the traffic flow. For car models, is the target route, the target route Used to analyze the flow direction and destination distribution of traffic, is the initial lane, is the target lane, is the initial density of the road section where the generating point is located. Used to predict the impact of traffic inflow on road traffic conditions.

[0028] In the aforementioned method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation, step D is to establish a hierarchical generation control framework based on the enhanced data and fine-tune the micro-driving behavior to optimize the control of dynamic traffic flow and obtain the control optimization results. The specific steps are as follows:

[0029] Step D1: Establish a hierarchical generation control framework, specifically constructing background traffic flow and focus traffic flow to carry out refined management of traffic flow on two-way multi-lane highways;

[0030] Step D2: Establishing refined control of micro-driving behavior, specifically establishing a time-space weighted lane usage cost function and achieving dynamic balanced distribution of traffic flow. The refined control of micro-driving behavior includes a lane change decision model and an adaptive vehicle following model.

[0031] The aforementioned method for dynamic control of traffic flow on a two-way multi-lane highway based on traffic simulation, step D1 specifically comprises the following steps:

[0032] In step D11, a random generation mode is used to generate background traffic flow, wherein the background traffic flow is specifically modeled based on a time-varying Poisson process, and the generation rate is dynamically adjusted as shown in formula (4).

[0033] (4)

[0034] in, is the car generation rate at time t, is the peak period benchmark value, is congestion sensitivity, is the smoothing coefficient, is the traffic density at time t, is the critical traffic density, tanh is the hyperbolic tangent function;

[0035] Step D12: Generate focused traffic flow using a directional generation mode, specifically using a priority queue to manage the target route. The specific steps are as follows:

[0036] Step D121: construct the departure sequence control, specifically using the safe following distance model, as shown in formula (5):

[0037] (5)

[0038] in, The safe departure time for the following vehicle, is the time taken by the preceding vehicle to pass the same reference point, is the safety time baseline, is the relative speed difference between the rear and front vehicles, The maximum acceleration or deceleration that the vehicle can achieve;

[0039] Step D122: construct an initial lane assignment algorithm, specifically, establish a lane selection cost function, as shown in formula (6):

[0040] (6)

[0041] in, Choose a price for the vehicle, is the real-time density of the target lane, For the emergency lane penalty item, is a constant offset term, Lane offset weight, is the current lane;

[0042] Step D123, calculate the optimal lane, as shown in formula (7),

[0043] (7)

[0044] in, is the optimal lane, L is the set of available lanes;

[0045] Step D124, establish a speed initialization strategy, specifically dynamically adjust the initial speed according to the real-time congestion level, as shown in formula (8),

[0046] (8)

[0047] in, The maximum speed of the vehicle under ideal conditions, The maximum density when traffic is completely congested, is the shape index, This is a model correction item.

[0048] The aforementioned method for dynamic control of traffic flow on a two-way multi-lane highway based on traffic simulation, step D2 specifically comprises the following steps:

[0049] Step D21: Constructing a lane change decision model. The specific steps are as follows:

[0050] Step D211 introduces the lane change condition of the emergency lane yield rule, as shown in formula (9):

[0051] (9)

[0052] in, is the expected acceleration of the vehicle after changing lanes to the target lane, is the acceleration of the vehicle in the current lane, and are the acceleration of the vehicle in front of the target lane and the acceleration of the vehicle behind the target lane respectively;

[0053] Step D212: Setting the emergency lane exit resistance coefficient. The emergency lane exit resistance coefficient is used to prevent vehicles from frequently entering and exiting the emergency lane and ensure efficient use of the emergency lane. Specifically, when a vehicle needs to return to the normal lane from the emergency lane, it must not only meet the basic conditions for changing lanes in the normal lane, but also overcome the emergency lane exit resistance coefficient.

[0054] Step D213: Establish an emergency lane prohibition mechanism, which is used to ensure that the emergency lane is unobstructed in an emergency, specifically at the current vehicle density. When driving, cars are prohibited from occupying the emergency lane;

[0055] Step D214: Establishing a lane change decision model and a specific lane change decision algorithm. The specific steps are as follows:

[0056] Step D2141, setting the input and output of the lane change decision model. The input of the lane change decision model includes the vehicle's current lane information, driving direction, destination information, vehicle type, current road density, and real-time traffic conditions. The output of the lane change decision model includes the decision result of whether to change lanes and the target lane.

[0057] Step D2142: Initialize the lane change decision result to False and the target lane to None, then perform a lane change demand check. If there is a lane change demand, evaluate the target lane change.

[0058] The specific process of lane change detection is to first calculate the remaining distance to the target exit. If the remaining distance is less than 500 meters and the current lane is not the lane where the target exit is located, a lane change request is triggered. Then, the traffic density of the current lane and the speed of the preceding vehicle are obtained. If the traffic density is greater than 1.2 times the critical density and the preceding vehicle speed is less than the threshold, a lane change request is triggered. Then, the driver checks whether there are obstacles ahead. If there are obstacles, a lane change request is triggered.

[0059] The specific process of evaluating the target lane change is to first select the target lane based on the driving direction and destination, then obtain the distance to the preceding vehicle, the speed of the preceding vehicle, the acceleration of the preceding vehicle, the distance to the following vehicle, the speed of the following vehicle, the acceleration of the following vehicle, the type of vehicle, and the current density for each target lane, and then calculate the target lane evaluation index, which includes the expected acceleration after the target lane change.

[0060] Step D2143: Determine the lane change conditions of the target lane. If multiple target lanes meet the lane change conditions, select the target lane with the greatest lane change benefit.

[0061] The specific process of judging the lane change condition of the target lane is to first calculate the lane change benefit, which is the difference between the expected acceleration after the lane change and the current acceleration, and then calculate the yield cost and take into account the acceleration of the vehicle in front and behind the target lane. Then, if the target lane is an emergency lane and if the vehicle type is a car and the current density is less than the critical density, then the target lane does not meet the lane change condition. Otherwise, an additional resistance value is added to the yield cost. Then, if the lane change benefit is greater than the yield cost, then the target lane meets the lane change condition. Finally, if there are multiple target lanes that meet the lane change condition at the same time, the target lane with the largest lane change benefit is selected and the decision result of whether to change lanes is updated. and the ID of the selected target lane;

[0062] Step D22: Establish an adaptive vehicle-following model. The specific steps are as follows:

[0063] Step D221, dynamically calculate the following distance, as shown in formula (10),

[0064] (10)

[0065] in, is the minimum distance that the vehicle needs to maintain with the vehicle in front at time t, is the instantaneous speed of the vehicle at time t, is the time interval between the vehicle and the vehicle ahead, is the maximum deceleration, is the minimum safe distance;

[0066] Step D222, calculate the acceleration control, as shown in formula (11),

[0067] (11)

[0068] in, is the acceleration of the vehicle at time t, is the error, 、 and These are all PID parameters.

[0069] In the aforementioned method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation, step E is to perform full-process control logic and closed-loop feedback on the control optimization results and establish emergency scenario enhanced control rules to complete the dynamic traffic flow control operation on the two-way multi-lane highway. The specific steps are as follows:

[0070] Step E1: Perform full-process control logic and closed-loop feedback on the control optimization results. The specific steps are as follows:

[0071] Step E11, data collection and status evaluation, specifically using a simulated sensor network to obtain real-time traffic flow, density, and vehicle type distribution data for all lanes, and then calculate the congestion index of each road section It is divided into smooth, lightly congested, moderately congested and severely congested states, and the road congestion index As shown in formula (12),

[0072] (12)

[0073] Among them, if When the state is smooth, if If the traffic is slightly congested, Moderate congestion occurs when It is a serious congestion state;

[0074] Step E12: Traffic flow generation mode decision. If the traffic flow is smooth or slightly congested, the random generation mode is activated and the background traffic flow is generated according to the benchmark rate. If the traffic flow is moderately or severely congested, the directional generation mode is activated to generate the focused traffic flow and prioritize the target route. The traffic flow merges in and the emergency lane is opened at the same time;

[0075] Step E13, dynamic configuration of generation parameters, specifically including random generation mode parameter configuration and directional generation mode parameter configuration, the specific steps are as follows:

[0076] Step E131, configure the parameters of the random generation mode, specifically adjust the car generation rate according to the real-time density and maintain a balanced density across lanes;

[0077] Step E132 configures parameters for the directional generation mode. Specifically, vehicles are generated based on the target route priority and the departure sequence is ensured to meet the safe following distance. Large vehicles are then allocated emergency lanes and their initial lane is prioritized upstream of the target lane to avoid cutting directly into the inner, high-speed lane.

[0078] Step E14: Micro-behavior control execution. The micro-behavior includes lane change decision-making and vehicle following control. The lane change decision specifically updates the lane selection every 500ms and prioritizes the lane change needs of the focused traffic flow. The vehicle following control specifically calculates the safe distance in real time and adjusts the acceleration using a PID controller.

[0079] Step E15, closed-loop feedback and parameter optimization, the specific steps are as follows:

[0080] Step E151: Count the average vehicle speed every 10 seconds and lane balance , where lane balance As shown in formula (13),

[0081] (13)

[0082] in, is the maximum value of lane density, is the minimum value in lane density, The average of all lane densities;

[0083] Step E152: If the average vehicle speed Lane balance , then the PID parameters are triggered to adjust themselves as shown in formula (14),

[0084] (15);

[0085] Step E2: Establish emergency scenario enhanced control rules to complete the dynamic control of traffic flow on a two-way multi-lane highway, wherein the emergency scenario enhanced control rules include a hierarchical activation mechanism for emergency lanes and a conflict resolution strategy.

[0086] The aforementioned method for dynamic control of traffic flow on a two-way multi-lane highway based on traffic simulation, step E2 specifically comprises the following steps:

[0087] Step E21: Establish a hierarchical activation mechanism for emergency lanes. Specifically, in moderate congestion, trucks and buses are allowed to use the emergency lanes with a maximum speed limit of 90 km / h and no lane changes. In severe congestion, the emergency lanes are open to all types of vehicles with a speed limit of 80 km / h. Mandatory lane change points are set every 2 kilometers, and vehicles are directed back to their normal lanes. Priority vehicles in the focused traffic flow, including ambulances and buses, are allowed to use the emergency lanes throughout their journey.

[0088] Step E22: Build a conflict resolution strategy. Specifically, when a vehicle in the emergency lane needs to return to the normal lane, it activates its turn signal in advance at the response distance threshold and sends a lane change request to surrounding vehicles. Vehicles in the normal lane, if they detect the request and their own safety distance allows, will actively slow down and yield. If the lane change is not completed within the specified time, the emergency lane's mandatory speed limit mechanism is triggered.

[0089] A traffic simulation-based dynamic control system for bidirectional, multi-lane highway traffic flow includes a data acquisition module, a data filtering module, a data enhancement module, a control optimization module, and a dynamic control module. The data acquisition module is used to construct a virtual sensor network covering bidirectional, multi-lane highways using a traffic simulation platform to perform full-factor perception of traffic flow and obtain collected data.

[0090] The data filtering module is used to filter outliers in the collected data by combining a double sliding window mechanism and an IQR algorithm to obtain filtered data;

[0091] The data enhancement module is used to construct a multidimensional vector containing spatiotemporal features to enhance the feature vector in the filtered data and obtain enhanced data;

[0092] The control optimization module is used to establish a hierarchical generation control framework based on the enhanced data and fine-tune the micro-driving behavior to optimize the control of dynamic traffic flow and obtain the control optimization results;

[0093] The dynamic control module is used to perform full-process control logic and closed-loop feedback on the control optimization results and establish emergency scenario enhanced control rules to complete the dynamic control operation of traffic flow on two-way multi-lane highways.

[0094] The beneficial effects of the present invention are:

[0095] (1) The present invention first uses a traffic simulation platform to build a virtual sensor network covering two-way and multi-lane traffic to perform full-factor perception of traffic flow and obtain collected data. Then, a double sliding window mechanism and an IQR algorithm are combined to filter out the abnormal values ​​in the collected data to obtain filtered data. Subsequently, a multi-dimensional vector containing spatiotemporal features is constructed to enhance the feature vectors in the filtered data and obtain enhanced data. Then, based on the enhanced data, a hierarchical generation control framework and micro-driving behavior fine control are established to optimize the control of dynamic traffic flow and obtain control optimization results. Finally, the control optimization results are subjected to full-process control logic and closed-loop feedback, and emergency scenario enhanced control rules are established to complete the two-way multi-lane highway traffic flow. Traffic flow dynamic control operation; effectively realizes that the traffic flow dynamic control method and system have the function of constructing a closed-loop optimization system of perception, decision-making, control and evaluation for the complex traffic characteristics of two-way multi-lane highways to perform real-time dynamic control of highway traffic flow, and through the integration of dynamic traffic simulation and real-time data-driven technology, it can accurately perceive, intelligently decide and collaboratively control the traffic flow, and at the same time, through the spatiotemporal coupling traffic state prediction model, it can improve the ability to predict the evolution trend of traffic flow, and through the design of multi-objective collaborative optimization control strategy, it can balance efficiency, safety and fairness. The present invention can not only support the rapid iterative optimization of control strategies by constructing a virtual-real combination simulation verification platform, but also perform online optimization and adjustment of control parameters.

[0096] (2) The present invention performs mixed traffic control of random traffic and focused route traffic in a two-way multi-lane highway scenario, and then uses simulated virtual sensors to collect multi-dimensional data of traffic position, speed, and lane occupancy in real time and evaluates the traffic status after Kalman filtering and fuzzy logic processing. Then, the random traffic is dynamically adjusted by the time-varying Poisson process to generate the rate, and the focused route traffic is managed by priority queues. The departure sequence, lane allocation and speed initialization are combined with the improved MOBIL algorithm and PID The control realizes lane change decision and following distance optimization, and also supports emergency lane hierarchical activation and conflict resolution mechanism. Subsequently, the generated parameters and control models are adjusted in real time through closed-loop feedback to improve road traffic efficiency and safety in complex traffic scenarios, and effectively realize the function of the traffic dynamic control method and system to quickly reduce traffic congestion by accurately and dynamically controlling traffic and focused route traffic. It not only improves the overall traffic capacity of the highway, but also shortens the driving time of vehicles. It also reduces conflicts between vehicles through reasonable traffic distribution and control, which not only reduces the probability of traffic accidents, but also protects the lives and property of road users. At the same time, by using the simulation platform for research and testing, a large number of actual road tests are avoided, which greatly reduces the cost and risk of traffic control strategy research and development. This provides new ideas and methods for the intelligent development of highway traffic control, which helps to promote the entire transportation field to a more intelligent and efficient direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] Figure 1 This is an overall flow chart of a traffic simulation-based method for dynamic control of traffic flow on a two-way multi-lane highway according to the present invention. DETAILED DESCRIPTION

[0098] The present invention will be further described below with reference to the accompanying drawings.

[0099] like Figure 1 As shown, the present invention provides a traffic simulation-based two-way multi-lane highway traffic flow dynamic control method, comprising the following steps:

[0100] Step A: Use the traffic simulation platform to build a virtual sensor network covering two-way multi-lane to perform full-factor perception of traffic flow and obtain collected data. Full-factor perception includes dynamic flow monitoring, road environment perception, and vehicle generation characteristics. The specific steps are as follows:

[0101] Step A1: Dynamic traffic monitoring, specifically deploying virtual induction coils on each road section, and then collecting the instantaneous number of vehicles on the road section every second. , lane occupancy and headway Building a real-time traffic matrix ,in is the time window, and the lane occupancy λ is as shown in formula (1),

[0102] (1)

[0103] in, For the Vehicle length, is the lane length, is the number of lanes;

[0104] Step A2: road environment perception, specifically integrating the weather simulation module to dynamically update the road friction coefficient , and then monitor the emergency lane occupancy rate through the emergency lane virtual camera ;

[0105] Preferably, the dry road friction coefficient =0.7, friction coefficient in rainy and snowy weather =0.3, and when When triggering an early warning;

[0106] Step A3, vehicle generation features, specifically vehicle generation features are divided into random traffic flow and focused traffic flow, the random traffic flow is specifically generated by setting a generator at the boundary node of the road network to record the coordinates of the generated point , initial velocity and vehicle type ratio, the focused traffic flow is specifically for the target route Collect the vehicle's desired lane sequence .

[0107] Preferably, the initial speed Normal distribution The specific vehicle type ratio is 70% cars, 20% trucks and 10% buses. The target route A continuous path from an entry ramp to an exit ramp is included, and the vehicle's desired lane sequence includes lane change requirements that gradually converge from the outer lane to the inner lane;

[0108] Step B, using a dual sliding window mechanism and an IQR algorithm to filter the outliers in the collected data to obtain filtered data, wherein the dual sliding window mechanism includes a short window and long windows , the short window For detecting sudden anomalies, the long window Used to identify trend noise, the specific steps are as follows:

[0109] Preferably, Second, Second;

[0110] Step B1: Initialize the short window and long window and store the data of the most recently set number of seconds respectively. Then, add each newly collected data point to the short window and long window and remove the oldest data point in the window to keep the size of the short window and long window unchanged.

[0111] Preferably, the short window of seconds is set to seconds, the long window is Second;

[0112] Step B2: Calculate the statistical characteristics of the data in the short window and the long window. Specifically, determine whether the new data point in the short window causes a traffic surge exceeding a threshold. If so, the data point is determined to be a sudden anomaly. Then, compare the statistical characteristics of the new data point in the long window with the data in the long window to determine whether there is trend noise.

[0113] Step B3, headway Apply the IQR algorithm, specifically sort the headway data, and then sort by the first quartile. and the third quartile Calculate the interquartile range , as shown in formula (2),

[0114] (2);

[0115] Step B4, determining a valid interval, wherein data points in the headway data that exceed the valid interval are treated as invalid data;

[0116] Preferably, the effective range is ;

[0117] Step B5: fill the invalid data using linear interpolation. Specifically, the linear interpolation method calculates the invalid data point value based on the adjacent valid data point values.

[0118] Step C: Construct a multidimensional vector containing spatiotemporal features to enhance the feature vector in the filtered data and obtain enhanced data, wherein the multidimensional vector is used to provide richer information for subsequent traffic flow analysis and control, as shown in formula (3).

[0119] (3)

[0120] in, is a multidimensional vector, is the vehicle generation time, and the vehicle generation time It is used to record the specific time when a vehicle is generated in the road network and reflect the time distribution characteristics of the traffic flow. For car models, is the target route, the target route Used to analyze the flow direction and destination distribution of traffic, is the initial lane, is the target lane, is the initial density of the road section where the generating point is located. Used to predict the impact of traffic inflow on road traffic conditions.

[0121] Step D: Based on the enhanced data, a hierarchical generation control framework and micro-driving behavior refined control are established to optimize the dynamic traffic flow and obtain the control optimization results. The specific steps are as follows:

[0122] Step D1: Establish a hierarchical generation control framework, specifically to build background traffic flow and focus traffic flow to carry out refined management of traffic flow on two-way multi-lane highways. The specific steps are as follows:

[0123] In step D11, a random generation mode is used to generate background traffic flow, wherein the background traffic flow is specifically modeled based on a time-varying Poisson process, and the generation rate is dynamically adjusted as shown in formula (4).

[0124] (4)

[0125] in, is the car generation rate at time t, is the peak period benchmark value, is congestion sensitivity, is the smoothing coefficient, is the traffic density at time t, is the critical traffic density, tanh is the hyperbolic tangent function;

[0126] Preferably, , , ,when hour, Upgrade to To fill the empty road sections;

[0127] Step D12: Generate focused traffic flow using a directional generation mode, specifically using a priority queue to manage the target route. The specific steps are as follows:

[0128] Step D121: construct the departure sequence control, specifically using the safe following distance model, as shown in formula (5):

[0129] (5)

[0130] in, The safe departure time for the following vehicle, is the time taken by the preceding vehicle to pass the same reference point, is the safety time baseline, is the relative speed difference between the rear and front vehicles, The maximum acceleration or deceleration that the vehicle can achieve;

[0131] Preferably, Second, , and if seconds, the start will be delayed to avoid collision;

[0132] Step D122: construct an initial lane assignment algorithm, specifically, establish a lane selection cost function, as shown in formula (6):

[0133] (6)

[0134] in, Choose a price for the vehicle, is the real-time density of the target lane, For the emergency lane penalty item, is a constant offset term, Lane offset weight, is the current lane;

[0135] Preferably, , , ;

[0136] Step D123, calculate the optimal lane, as shown in formula (7),

[0137] (7)

[0138] in, is the optimal lane, L is the set of available lanes;

[0139] Step D124, establish a speed initialization strategy, specifically dynamically adjust the initial speed according to the real-time congestion level, as shown in formula (8),

[0140] (8)

[0141] in, The maximum speed of the vehicle under ideal conditions, The maximum density when traffic is completely congested, is the shape index, This is the model correction item;

[0142] Preferably, , , .

[0143] Step D2: Establishing refined control of micro-driving behavior, specifically establishing a time-space weighted lane usage cost function and achieving dynamic balanced distribution of traffic flow. The refined control of micro-driving behavior includes a lane change decision model and an adaptive vehicle following model. The specific steps are as follows:

[0144] Step D21: Constructing a lane change decision model. The specific steps are as follows:

[0145] Step D211 introduces the lane change condition of the emergency lane yield rule, as shown in formula (9):

[0146] (9)

[0147] in, is the expected acceleration of the vehicle after changing lanes to the target lane, is the acceleration of the vehicle in the current lane, and are the acceleration of the vehicle in front of the target lane and the acceleration of the vehicle behind the target lane respectively;

[0148] Step D212: Setting the emergency lane exit resistance coefficient. The emergency lane exit resistance coefficient is used to prevent vehicles from frequently entering and exiting the emergency lane and ensure efficient use of the emergency lane. Specifically, when a vehicle needs to return to the normal lane from the emergency lane, it must not only meet the basic conditions for changing lanes in the normal lane, but also overcome the emergency lane exit resistance coefficient.

[0149] Among them, the emergency lane exit resistance coefficient ;

[0150] Step D213: Establish an emergency lane prohibition mechanism, which is used to ensure that the emergency lane is unobstructed in an emergency, specifically at the current vehicle density. When driving, cars are prohibited from occupying the emergency lane;

[0151] Among them, only when the congestion reaches a certain level are cars allowed to use the emergency lane reasonably according to actual conditions; for trucks and large buses, although they are allowed to use the emergency lane when necessary, in order to avoid long-term occupation affecting emergency response, the maximum occupation time is limited to t minutes; when the occupation time reaches t minutes, the vehicle must return to the normal lane as soon as possible.

[0152] Step D214: Establishing a lane change decision model and a specific lane change decision algorithm. The specific steps are as follows:

[0153] Step D2141, setting the input and output of the lane change decision model. The input of the lane change decision model includes the vehicle's current lane information, driving direction, destination information, vehicle type, current road density, and real-time traffic conditions. The output of the lane change decision model includes the decision result of whether to change lanes and the target lane.

[0154] Step D2142: Initialize the lane change decision result to False and the target lane to None, then perform a lane change demand check. If there is a lane change demand, evaluate the target lane change.

[0155] The specific process of lane change detection is to first calculate the remaining distance to the target exit. If the remaining distance is less than 500 meters and the current lane is not the lane where the target exit is located, a lane change request is triggered. Then, the traffic density of the current lane and the speed of the preceding vehicle are obtained. If the traffic density is greater than 1.2 times the critical density and the preceding vehicle speed is less than the threshold, a lane change request is triggered. Then, the driver checks whether there are obstacles ahead. If there are obstacles, a lane change request is triggered.

[0156] The specific process of evaluating the target lane change is to first select the target lane based on the driving direction and destination, then obtain the distance to the preceding vehicle, the speed of the preceding vehicle, the acceleration of the preceding vehicle, the distance to the following vehicle, the speed of the following vehicle, the acceleration of the following vehicle, the type of vehicle, and the current density for each target lane, and then calculate the target lane evaluation index, which includes the expected acceleration after the target lane change.

[0157] Step D2143: Determine the lane change conditions of the target lane. If multiple target lanes meet the lane change conditions, select the target lane with the greatest lane change benefit.

[0158] The specific process of judging the lane change condition of the target lane is to first calculate the lane change benefit, which is the difference between the expected acceleration after the lane change and the current acceleration, and then calculate the yield cost and take into account the acceleration of the vehicle in front and behind the target lane. Then, if the target lane is an emergency lane and if the vehicle type is a car and the current density is less than the critical density, then the target lane does not meet the lane change condition. Otherwise, an additional resistance value is added to the yield cost. Then, if the lane change benefit is greater than the yield cost, then the target lane meets the lane change condition. Finally, if there are multiple target lanes that meet the lane change condition at the same time, the target lane with the largest lane change benefit is selected and the decision result of whether to change lanes is updated. and the ID of the selected target lane;

[0159] Step D22: Establish an adaptive vehicle-following model. The specific steps are as follows:

[0160] Step D221, dynamically calculate the following distance, as shown in formula (10),

[0161] (10)

[0162] in, is the minimum distance that the vehicle needs to maintain with the vehicle in front at time t, is the instantaneous speed of the vehicle at time t, is the time interval between the vehicle and the vehicle ahead, is the maximum deceleration, is the minimum safe distance;

[0163] Preferably, = 1.5 seconds, , rice;

[0164] Step D222, calculate the acceleration control, as shown in formula (11),

[0165] (11)

[0166] in, is the acceleration of the vehicle at time t, is the error, 、 and All are PID parameters;

[0167] Preferably, .

[0168] Step E: Perform full-process control logic and closed-loop feedback on the control optimization results and establish emergency scenario enhanced control rules to complete the dynamic control of traffic flow on two-way multi-lane highways. The specific steps are as follows:

[0169] Step E1: Perform full-process control logic and closed-loop feedback on the control optimization results. The specific steps are as follows:

[0170] Step E11, data collection and status evaluation, specifically using a simulated sensor network to obtain real-time traffic flow, density, and vehicle type distribution data for all lanes, and then calculate the congestion index of each road section It is divided into smooth, lightly congested, moderately congested and severely congested states, and the road congestion index As shown in formula (12),

[0171] (12)

[0172] Among them, if When the state is smooth, if If the traffic is slightly congested, Moderate congestion occurs when It is a serious congestion state;

[0173] Step E12: Traffic flow generation mode decision. If the traffic flow is smooth or slightly congested, the random generation mode is activated and the background traffic flow is generated according to the benchmark rate. If the traffic flow is moderately or severely congested, the directional generation mode is activated to generate the focused traffic flow and prioritize the target route. The traffic flow merges in and the emergency lane is opened at the same time;

[0174] Step E13, dynamic configuration of generation parameters, specifically including random generation mode parameter configuration and directional generation mode parameter configuration, the specific steps are as follows:

[0175] Step E131, configure the parameters of the random generation mode, specifically adjust the car generation rate according to the real-time density and maintain a balanced density across lanes;

[0176] Step E132 configures parameters for the directional generation mode. Specifically, vehicles are generated based on the target route priority and the departure sequence is ensured to meet the safe following distance. Large vehicles are then allocated emergency lanes and their initial lane is prioritized upstream of the target lane to avoid cutting directly into the inner, high-speed lane.

[0177] Step E14: Micro-behavior control execution. The micro-behavior includes lane change decision-making and vehicle following control. The lane change decision specifically updates the lane selection every 500ms and prioritizes the lane change needs of the focused traffic flow. The vehicle following control specifically calculates the safe distance in real time and adjusts the acceleration using a PID controller.

[0178] Step E15, closed-loop feedback and parameter optimization, the specific steps are as follows:

[0179] Step E151: Count the average vehicle speed every 10 seconds and lane balance , where lane balance As shown in formula (13),

[0180] (13)

[0181] in, is the maximum value of lane density, is the minimum value in lane density, The average of all lane densities;

[0182] Step E152: If the average vehicle speed Lane balance , then the PID parameters are triggered to adjust themselves as shown in formula (14),

[0183] (15);

[0184] Step E2: Establish emergency scenario enhanced control rules to complete the dynamic control of traffic flow on a two-way multi-lane highway. The emergency scenario enhanced control rules include a hierarchical activation mechanism for emergency lanes and a conflict resolution strategy. The specific steps are as follows:

[0185] Step E21: Establish a hierarchical activation mechanism for emergency lanes. Specifically, in moderate congestion, trucks and buses are allowed to use the emergency lanes with a maximum speed limit of 90 km / h and no lane changes. In severe congestion, the emergency lanes are open to all types of vehicles with a speed limit of 80 km / h. Mandatory lane change points are set every 2 kilometers, and vehicles are directed back to their normal lanes. Priority vehicles in the focused traffic flow, including ambulances and buses, are allowed to use the emergency lanes throughout their journey.

[0186] Step E22: Build a conflict resolution strategy. Specifically, when a vehicle in the emergency lane needs to return to the normal lane, it activates its turn signal in advance at the response distance threshold and sends a lane change request to surrounding vehicles. Vehicles in the normal lane, if they detect the request and their own safety distance allows, will actively slow down and yield. If the lane change is not completed within the specified time, the emergency lane's mandatory speed limit mechanism is triggered.

[0187] A traffic simulation-based dynamic control system for bidirectional, multi-lane highway traffic flow includes a data acquisition module, a data filtering module, a data enhancement module, a control optimization module, and a dynamic control module. The data acquisition module is used to construct a virtual sensor network covering bidirectional, multi-lane highways using a traffic simulation platform to perform full-factor perception of traffic flow and obtain collected data.

[0188] The data filtering module is used to filter outliers in the collected data by combining a double sliding window mechanism and an IQR algorithm to obtain filtered data;

[0189] The data enhancement module is used to construct a multidimensional vector containing spatiotemporal features to enhance the feature vector in the filtered data and obtain enhanced data;

[0190] The control optimization module is used to establish a hierarchical generation control framework based on the enhanced data and fine-tune the micro-driving behavior to optimize the control of dynamic traffic flow and obtain the control optimization results;

[0191] The dynamic control module is used to perform full-process control logic and closed-loop feedback on the control optimization results and establish emergency scenario enhanced control rules to complete the dynamic control operation of traffic flow on two-way multi-lane highways.

[0192] In summary, the present invention provides a method and system for dynamic control of traffic flow on a two-way multi-lane highway based on traffic simulation. First, a traffic simulation platform is used to construct a virtual sensor network covering two-way multi-lane to perform full-factor perception of traffic flow and obtain collected data. Then, a double sliding window mechanism and an IQR algorithm are combined to filter out abnormal values ​​in the collected data to obtain filtered data. Subsequently, a multi-dimensional vector containing spatiotemporal features is constructed to enhance the feature vectors in the filtered data and obtain enhanced data. Then, based on the enhanced data, a hierarchical generation control framework and micro-driving behavior fine control are established to control and optimize the dynamic traffic flow and obtain control optimization results. Finally, the control optimization results are subjected to full-process control logic and closed-loop feedback, and emergency scenario enhancement control rules are established to complete the dynamic control operation of traffic flow on a two-way multi-lane highway. This effectively realizes that the method and system for dynamic control of traffic flow have the closed-loop optimization function of perception, decision-making, control and evaluation for the complex traffic characteristics of two-way multi-lane highways. The system has the function of real-time dynamic control of highway traffic flow, and by integrating dynamic traffic simulation with real-time data-driven technology, it can accurately perceive, make intelligent decisions and collaboratively control traffic flow. At the same time, the time-space coupled traffic state prediction model can improve the ability to predict the evolution trend of traffic flow, and by designing a multi-objective collaborative optimization control strategy, it can balance efficiency, safety and fairness. It also realizes that the traffic flow dynamic control method and system have the function of quickly reducing traffic congestion by accurately and dynamically controlling traffic flow and focused route traffic flow, thereby improving the overall traffic capacity of the highway. It can also reduce conflicts between vehicles through reasonable traffic distribution and control, and protect the lives and property of road users. At the same time, by using the simulation platform for research and testing, a large number of actual road tests are avoided, which greatly reduces the cost and risk of traffic control strategy research and development. This provides new ideas and methods for the intelligent development of highway traffic control, which helps to promote the entire transportation field to a more intelligent and efficient direction.

[0193] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation, characterized by: The following steps are included: Step A: Use the traffic simulation platform to build a virtual sensor network covering two-way and multi-lane traffic to perceive all elements of traffic flow and obtain collected data; Step B: using a double sliding window mechanism and an IQR algorithm to filter outliers in the collected data to obtain filtered data; Step C, constructing a multidimensional vector containing spatiotemporal features to enhance the feature vector in the filtered data and obtain enhanced data; Step D: Based on the enhanced data, a hierarchical generation control framework and micro-driving behavior refined control are established to optimize the dynamic traffic flow and obtain the control optimization results. The specific steps are as follows: Step D1: Establish a hierarchical generation control framework, specifically to build background traffic flow and focus traffic flow to carry out refined management of traffic flow on two-way multi-lane highways. The specific steps are as follows: In step D11, a random generation mode is used to generate background traffic flow, wherein the background traffic flow is specifically modeled based on a time-varying Poisson process, and the generation rate is dynamically adjusted as shown in formula (4). Where λ(t) is the car generation rate at time t, λ0 is the peak hour benchmark value, β is the congestion sensitivity, σ is the smoothing coefficient, ρ(t) is the traffic density at time t, ρ crit is the critical traffic density, tanh is the hyperbolic tangent function; Step D12, using the directional generation mode to generate focused traffic flow, specifically using the priority queue to manage the target route r tar The specific steps are as follows: Step D121: construct the departure sequence control, specifically using the safe following distance model, as shown in formula (5): Among them, t depart is the safe departure time of the following vehicle, t prev is the time taken by the preceding vehicle to pass the same reference point, is the safety headway baseline, Δv is the relative speed difference between the rear vehicle and the front vehicle, a max The maximum acceleration or deceleration that the vehicle can achieve; Step D122: construct an initial lane assignment algorithm, specifically, establish a lane selection cost function, as shown in formula (6): Where J(l) is the vehicle selection cost, ρ l (t) is the real-time density of the target lane, δ is the penalty term for the emergency lane, is the constant offset term, ω is the lane offset weight, and l is the current lane; Step D123, calculate the optimal lane, as shown in formula (7), L init =argmin l∈L J(l) (7) Among them, l init is the optimal lane, L is the set of available lanes; Step D124: Establish a speed initialization strategy, specifically dynamically adjust the initial speed according to the real-time congestion level, as shown in formula (8): Among them, v free The maximum speed of the vehicle under ideal conditions, ρ jam The maximum density when traffic is completely congested, η is the shape index, v adj This is the model correction item; Step D2: Establishing refined control of micro-driving behavior, specifically establishing a time-space weighted lane usage cost function and achieving dynamic balanced distribution of traffic flow. The refined control of micro-driving behavior includes a lane change decision model and an adaptive vehicle following model. In step E, the control optimization results are subjected to full-process control logic and closed-loop feedback, and emergency scenario enhanced control rules are established to complete the dynamic control of traffic flow on two-way multi-lane highways.

2. The method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation according to claim 1, characterized in that: Step A: Use the traffic simulation platform to build a virtual sensor network covering two-way multi-lane to perform full-factor perception of traffic flow and obtain collected data. Full-factor perception includes dynamic flow monitoring, road environment perception, and vehicle generation characteristics. The specific steps are as follows: Step A1: Dynamic traffic monitoring. Specifically, virtual induction coils are deployed on each road section, and the number of vehicles N on each road section is collected every second. seg , lane occupancy λ and headway h t Building a real-time traffic matrix Where T is the time window, and the lane occupancy λ is as shown in formula (1), Among them, l i is the length of the i-th vehicle, L is the lane length, and m is the number of lanes; Step A2: road environment perception. Specifically, the weather simulation module is integrated to dynamically update the road friction coefficient μ, and the emergency lane virtual camera is used to monitor the emergency lane occupancy rate γ. Step A3, vehicle generation features, specifically vehicle generation features are divided into random traffic flow and focused traffic flow, the random traffic flow is specifically achieved by setting a generator at the boundary node of the road network to record the coordinates of the generated point (x gen ,y gen ), initial speed v0 and vehicle type ratio, the focused traffic flow is specifically for the target route r tar Collect the vehicle's desired lane sequence {l1,l2,…,l n }.

3. The method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation according to claim 2, characterized in that: Step B, using a dual sliding window mechanism and an IQR algorithm to filter the outliers in the collected data to obtain filtered data, wherein the dual sliding window mechanism includes a short window W s and long window W l , the short window W s For detecting sudden anomalies, the long window W l Used to identify trend noise, the specific steps are as follows: Step B1: Initialize the short window and long window and store the data of the most recently set number of seconds respectively. Then, add each newly collected data point to the short window and long window and remove the oldest data point in the window to keep the size of the short window and long window unchanged. Step B2: Calculate the statistical characteristics of the data in the short window and the long window. Specifically, determine whether the new data point in the short window causes a traffic surge exceeding a threshold. If so, the data point is determined to be a sudden anomaly. Then, compare the statistical characteristics of the new data point in the long window with the data in the long window to determine whether there is trend noise. Step B3, headway h t Apply the IQR algorithm, specifically sort the headway data, and then calculate the interquartile range IQR from the first quartile Q1 and the third quartile Q3, as shown in formula (2): IQR=Q3-Q1(2); Step B4, determining a valid interval, wherein data points in the headway data that exceed the valid interval are treated as invalid data; Step B5: fill the invalid data using linear interpolation. Specifically, the linear interpolation method calculates the invalid data point value based on the adjacent valid data point values.

4. The method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation according to claim 3, characterized in that: Step C: Construct a multidimensional vector containing spatiotemporal features to enhance the feature vector in the filtered data and obtain enhanced data, wherein the multidimensional vector is used to provide richer information for subsequent traffic flow analysis and control, as shown in formula (3): F=[t gen ,x gen ,y gen ,v0,type,r tar ,l init ,l end ,m,g,r init ] (3) Among them, F is a multidimensional vector, t gen is the vehicle generation time, and the vehicle generation time t gen It is used to record the specific time when a vehicle is generated in the road network and reflect the time distribution characteristics of the traffic flow. type is the vehicle type, r tar is the target route, the target route r tar Used to analyze the flow direction and destination distribution of traffic, init is the initial lane, l end is the target lane, ρ init is the initial density of the road section where the generating point is located, and the initial density of the road section where the generating point is located ρ init Used to predict the impact of traffic inflow on road traffic conditions.

5. The method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation according to claim 1, characterized in that: The specific steps of step D2 are as follows: Step D21: Constructing a lane change decision model. The specific steps are as follows: Step D211: introduce the lane change condition of the emergency lane yield rule, as shown in formula (9): Among them, a new is the expected acceleration of the vehicle after changing lanes to the target lane, a old is the acceleration of the vehicle in the current lane, a new,front and a new,rear are the acceleration of the vehicle in front of the target lane and the acceleration of the vehicle behind the target lane respectively; Step D212: Setting the emergency lane exit resistance coefficient. The emergency lane exit resistance coefficient is used to prevent vehicles from frequently entering and exiting the emergency lane and ensure efficient use of the emergency lane. Specifically, when a vehicle needs to return to the normal lane from the emergency lane, it must not only meet the basic conditions for changing lanes in the normal lane, but also overcome the emergency lane exit resistance coefficient. Step D213: Establish an emergency lane occupation prohibition mechanism, which is used to ensure that the emergency lane is unobstructed in an emergency, specifically when the current vehicle density ρ < ρ crit When driving, cars are prohibited from occupying the emergency lane; Step D214: Establishing a lane change decision model and a specific lane change decision algorithm. The specific steps are as follows: Step D2141, setting the input and output of the lane change decision model. The input of the lane change decision model includes the vehicle's current lane information, driving direction, destination information, vehicle type, current road density, and real-time traffic conditions. The output of the lane change decision model includes the decision result of whether to change lanes and the target lane. Step D2142: Initialize the lane change decision result to False and the target lane to None, then perform a lane change demand check. If there is a lane change demand, evaluate the target lane change. The specific process of lane change detection is to first calculate the remaining distance to the target exit. If the remaining distance is less than 500 meters and the current lane is not the lane where the target exit is located, a lane change request is triggered. Then, the traffic density of the current lane and the speed of the preceding vehicle are obtained. If the traffic density is greater than 1.2 times the critical density and the preceding vehicle speed is less than the threshold, a lane change request is triggered. Then, the driver checks whether there are obstacles ahead. If there are obstacles, a lane change request is triggered. The specific process of evaluating the target lane change is to first select the target lane based on the driving direction and destination, then obtain the distance to the preceding vehicle, the speed of the preceding vehicle, the acceleration of the preceding vehicle, the distance to the following vehicle, the speed of the following vehicle, the acceleration of the following vehicle, the type of vehicle, and the current density for each target lane, and then calculate the target lane evaluation index, which includes the expected acceleration after the target lane change. Step D2143: Determine the lane change conditions of the target lane. If multiple target lanes meet the lane change conditions, select the target lane with the greatest lane change benefit. The specific process of judging the lane change condition of the target lane is to first calculate the lane change benefit, which is the difference between the expected acceleration after the lane change and the current acceleration, and then calculate the yield cost and take into account the acceleration of the vehicle in front and behind the target lane. Then, if the target lane is an emergency lane, if the vehicle type is a car, and the current density is less than the critical density, then the target lane does not meet the lane change condition. Otherwise, an additional resistance value is added to the yield cost. Then, if the lane change benefit is greater than the yield cost, then the target lane meets the lane change condition. Finally, if there are multiple target lanes that meet the lane change condition at the same time, the target lane with the largest lane change benefit is selected and the decision result of whether to change lanes is updated to True and the ID of the selected target lane is updated. Step D22: Establish an adaptive vehicle-following model. The specific steps are as follows: Step D221, dynamically calculate the following distance, as shown in formula (10), Among them, d safe (t) is the minimum distance that the vehicle needs to maintain with the vehicle in front at time t, v(t) is the instantaneous speed of the vehicle at time t, and t head is the time interval between the vehicle and the preceding vehicle, a dec is the maximum deceleration, d0 is the minimum safety distance; Step D222, calculate the acceleration control, as shown in formula (11), Where a(t) is the acceleration of the vehicle at time t, e d is the error, K p , K i and K d These are all PID parameters.

6. The method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation according to claim 1, characterized in that: Step E: Perform full-process control logic and closed-loop feedback on the control optimization results and establish emergency scenario enhanced control rules to complete the dynamic control of traffic flow on two-way multi-lane highways. The specific steps are as follows: Step E1: Perform full-process control logic and closed-loop feedback on the control optimization results. The specific steps are as follows: Step E11, data collection and status evaluation, specifically uses a simulated sensor network to obtain the flow, density and vehicle type distribution data of all lanes in real time, and then calculates the congestion index CI of each road section and divides it into unblocked, lightly congested, moderately congested and severely congested states. The road section congestion index CI is shown in formula (12): Among them, if CI < 0.3, it is a smooth state; if 0.3 ≤ CI < 0.6, it is a lightly congested state; if 0.6 ≤ CI < 0.8, it is a moderately congested state; if CI ≥ 0.8, it is a severely congested state; Step E12, traffic flow generation mode decision, if it is a smooth or lightly congested state, the random generation mode is activated and the background traffic flow is generated according to the benchmark rate. If it is a moderate or severe congested state, the directional generation mode is activated to generate the focused traffic flow and give priority to the target route r tar The traffic flow merges in and the emergency lane is opened at the same time; Step E13, dynamic configuration of generation parameters, specifically including random generation mode parameter configuration and directional generation mode parameter configuration, the specific steps are as follows: Step E131 , configuring parameters for the random generation mode, specifically adjusting the car generation rate λ(t) according to the real-time density and maintaining a balanced density across lanes; Step E132 configures parameters for the directional generation mode. Specifically, vehicles are generated based on the target route priority and the departure sequence is ensured to meet the safe following distance. Large vehicles are then allocated emergency lanes and their initial lane is prioritized upstream of the target lane to avoid cutting directly into the inner, high-speed lane. Step E14: Micro-behavior control execution, where the micro-behavior includes lane change decision-making and vehicle following control. The lane change decision specifically updates the lane selection every 500ms and prioritizes the lane change needs of the focused traffic flow. The vehicle following control specifically calculates the safe distance in real time and adjusts the acceleration using a PID controller. Step E15, closed-loop feedback and parameter optimization, the specific steps are as follows: Step E151: Count the average vehicle speed every 10 seconds and lane balance E, where lane balance E is as shown in formula (13), Among them, max(ρ l ) is the maximum value of lane density, min(ρ l ) is the minimum value in lane density, ρ avg The average of all lane densities; Step E152: If the average vehicle speed If the lane balance E>0.4, the PID parameters are triggered to adjust themselves as shown in formula (14). K p ←K p ·(1+0.1·E),K d ←K d ·(1-0.05·E) (14); Step E2: Establish emergency scenario enhanced control rules to complete the dynamic control of traffic flow on a two-way multi-lane highway, wherein the emergency scenario enhanced control rules include a hierarchical activation mechanism for emergency lanes and a conflict resolution strategy.

7. The method for dynamic traffic flow control on a two-way multi-lane highway based on traffic simulation according to claim 6, characterized in that: The specific steps of step E2 are as follows: Step E21: Establish a hierarchical activation mechanism for emergency lanes. Specifically, in moderate congestion, trucks and buses are allowed to use the emergency lanes with a maximum speed limit of 90 km / h and no lane changes. In severe congestion, the emergency lanes are open to all types of vehicles with a speed limit of 80 km / h. Mandatory lane change points are set every 2 kilometers, and vehicles are directed back to their normal lanes. Priority vehicles in the focused traffic flow, including ambulances and buses, are allowed to use the emergency lanes throughout their journey. Step E22: Build a conflict resolution strategy. Specifically, when a vehicle in the emergency lane needs to return to the normal lane, it activates its turn signal in advance at the response distance threshold and sends a lane change request to surrounding vehicles. Vehicles in the normal lane, if they detect the request and their own safety distance allows, will actively slow down and yield. If the lane change is not completed within the specified time, the emergency lane's mandatory speed limit mechanism is triggered.

8. A traffic simulation-based dynamic control system for a two-way multi-lane highway, wherein the specific control process of the dynamic control system is based on the method for dynamic control of highway traffic flow according to any one of claims 1 to 7, and is characterized by: It includes a data acquisition module, a data filtering module, a data enhancement module, a control optimization module and a dynamic control module. The data acquisition module is used to use a traffic simulation platform to build a virtual sensor network covering two-way multi-lane to perform full-factor perception of traffic flow and obtain collected data; The data filtering module is used to filter outliers in the collected data by combining a double sliding window mechanism and an IQR algorithm to obtain filtered data; The data enhancement module is used to construct a multidimensional vector containing spatiotemporal features to enhance the feature vector in the filtered data and obtain enhanced data; The control optimization module is used to establish a hierarchical generation control framework based on the enhanced data and fine-tune the micro-driving behavior to optimize the control of dynamic traffic flow and obtain the control optimization results; The dynamic control module is used to perform full-process control logic and closed-loop feedback on the control optimization results and establish emergency scenario enhanced control rules to complete the dynamic control operation of traffic flow on two-way multi-lane highways.

Images