CN115862322A - A vehicle variable speed limit control optimization method, system, medium and equipment - Google Patents

Abstract

The invention provides a method, a system, a medium and equipment for optimizing variable speed limit control of a vehicle, relating to the technical field of vehicle control and comprising the steps of determining a path to be implemented by the variable speed limit control, selecting a target road section and acquiring traffic flow data of the target road section; constructing a real road network model of a target road section, and carrying the real road network model into the road network model according to the position information of the real electromechanical equipment of the road; calibrating the road network model according to the traffic flow data of the target road section, and simulating the condition that the number of main road lanes is reduced due to accidents of all sub-road sections under different service levels by using the road network model; and constructing a variable speed-limiting dual-target optimization model, transmitting the simulated traffic flow data under each condition to the variable speed-limiting dual-target optimization model, and solving a corresponding variable speed-limiting control strategy by using an NSGA-II algorithm. The safety and efficiency of the road section are optimized and improved through variable speed limit control.

Description

A vehicle variable speed limit control optimization method, system, medium and equipment

technical field

The present disclosure relates to the technical field of vehicle control, in particular to a vehicle variable speed limit control optimization method, system, medium and equipment.

Background technique

The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

Variable Speed Limit (Variable Speed Limit, VSL) is a kind of traffic control measures. It refers to the active intervention of road traffic flow on expressways or urban expressways according to traffic conditions, weather conditions, traffic accidents and other factors. Adjust the speed limit value of the road section, so as to achieve the purpose of improving traffic flow, alleviating traffic congestion, and improving road safety.

The research scenarios of variable speed limit control usually include bad weather such as rain and fog, traffic accidents ahead, road construction, and congestion caused by ramps. In the congestion formed under the environment, the safety and efficiency of road sections are often optimized and improved through variable speed limit control. Since the variable speed limit control strategy technology is difficult to test in actual scenarios, most of the related research is carried out in combination with simulation models. In the variable speed limit research aimed at improving traffic efficiency, most of the macro simulation models are used for analysis, mainly including METANET model and CTM model; in the variable speed limit research aimed at improving road safety, PARAMICS, VISSIM, etc. Microscopic simulation models are widely used. Macro models such as MEATNET and CTM cannot analyze the driving characteristics of a single vehicle, cannot describe the driver's behaviors such as acceleration, deceleration, and speed limit compliance, and cannot directly calculate and describe safety indicators; micro models such as PARAMICS and VISSIM can overcome macro models. However, there are few related studies on simulation optimization based on microscopic simulation models. At the same time, most of the existing research regards a single optimization objective as the influencing factor of strategy selection, and there are few researches on the variable speed limit strategy of multi-objective optimization.

Contents of the invention

In order to solve the above problems, this disclosure proposes a vehicle variable speed limit control optimization method, system, medium and equipment, which takes road traffic efficiency and traffic safety as optimization goals, combines VISSIM microscopic simulation of traffic flow status, and adopts NSGA-II multi- The objective optimization algorithm is used to solve and generate a multi-level variable speed limit control strategy divided into time periods and road sections.

According to some embodiments, the present disclosure adopts the following technical solutions:

A vehicle variable speed limit control optimization method, comprising:

Determine the path to be implemented by the variable speed limit control, select the target road section, and obtain the traffic flow data of the target road section;

Construct the real road network model of the target road section, and load it into the road network model according to the real location information of electromechanical equipment on the road;

Calibrate the road network model according to the traffic flow data of the target road section, and use the road network model to simulate the reduction of the number of main road lanes caused by accidents in each sub-road section under different service levels;

A variable speed limit dual-objective optimization model is constructed, and the traffic flow data simulated in each case is transmitted to the variable speed limit dual-objective optimization model, and the corresponding variable speed limit control strategy is solved by using the NSGA-Ⅱ algorithm.

According to some embodiments, the present disclosure adopts the following technical solutions:

A vehicle variable speed limit control optimization system, comprising:

The data initialization module is used to determine the path to be implemented by the variable speed limit control, select the target road section, and obtain the traffic flow data of the target road section;

The model construction module is used to construct the real road network model of the target road section, and load it into the road network model according to the real location information of the electromechanical equipment on the road;

The strategy solving module is used to calibrate the road network model according to the traffic flow data of the target road section, and use the road network model to simulate the reduction of the number of main road lanes caused by accidents in each sub-road section under different service levels; construct a variable speed limit dual-objective To optimize the model, the simulated traffic flow data in each case is transferred to the variable speed limit dual-objective optimization model, and the NSGA-II algorithm is used to solve the corresponding variable speed limit control strategy.

According to some embodiments, the present disclosure adopts the following technical solutions:

A computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are suitable for being loaded and executed by a processor of a terminal device to execute the above-mentioned optimization method for variable speed limit control of a vehicle.

According to some embodiments, the present disclosure adopts the following technical solutions:

A terminal device, including a processor and a computer-readable storage medium, the processor is used to implement instructions; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the described one Optimization method for vehicle variable speed limit control.

Compared with the prior art, the beneficial effects of the present disclosure are:

The method proposed in this disclosure simulates the target road section, and performs simulation optimization with a microscopic simulation model, and uses the NSGA-II multi-objective optimization algorithm to solve the method of generating a multi-level variable speed limit control strategy for time periods and road sections. In the event of bad weather such as rain and fog, traffic accidents ahead, road construction, and congestion caused by ramps, the number of lanes on the main road will decrease, and the traffic congestion caused by the impact of the entrance and exit ramps will be reduced. Variable speed limit control optimizes and improves the safety and efficiency of road sections, relieves congestion in congested areas, improves overall traffic efficiency, and improves road safety.

Description of drawings

The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure, and the exemplary embodiments and descriptions of the present disclosure are used to explain the present disclosure, and do not constitute improper limitations to the present disclosure.

FIG. 1 is a schematic diagram of the implementation process of a variable speed limit control strategy in an embodiment of the present disclosure;

FIG. 2 is a schematic flowchart of a method for combining a road network simulation model and an optimization algorithm in an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of fast non-dominated sorting in an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of calculating the degree of congestion in an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of selection of the NSGA-II algorithm in an embodiment of the present disclosure;

Fig. 6 is a calculation flowchart of the NSGA-II algorithm in the embodiment of the present disclosure.

Detailed ways:

The present disclosure will be further described below in conjunction with the accompanying drawings and embodiments.

It should be noted that the following detailed description is exemplary and intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

It should be noted that the terminology used herein is only for describing specific embodiments, and is not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and/or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and/or combinations thereof.

The research scenarios of variable speed limit control usually include bad weather such as rain and fog, traffic accidents ahead, road construction, and congestion caused by ramps. Influenced by traffic congestion, the safety and efficiency of road sections are optimized and improved through variable speed limit control.

Example 1

An embodiment of the present disclosure provides a vehicle variable speed limit control optimization method, including:

Step 1: Determine the path to be implemented by variable speed limit control, select the target road section, and obtain the traffic flow data of the target road section;

Step 2: Construct the real road network model of the target road section, and load it into the road network model according to the real location information of electromechanical equipment on the road;

Step 3: Calibrate the road network model according to the traffic flow data of the target road section, and use the road network model to simulate the reduction of the number of main road lanes caused by accidents in each sub-road section under different service levels;

Step 4: Build a variable speed limit dual-objective optimization model, transmit the simulated traffic flow data in each case to the variable speed limit dual-objective optimization model, and use the NSGA-II algorithm to solve the corresponding variable speed limit control strategy.

Among them, the key elements of the variable speed limit control include the location selection of the speed limit sign, the length of the control cycle of the speed limit and the size of the change range, etc. Different values will have an impact on the control effect of the variable speed limit. Therefore, This disclosure serves as the following control definition:

(1) The distance between the starting point of the bottleneck road section and the upstream speed limit control section ranges from 500m to 700m;

(2) Determine that the distance between two control sections should be kept at least 1.5km;

(3) A suitable control period is 5 to 10 minutes, and in the present invention, the control period is 10 minutes.

(4) The speed limit range is determined according to the maximum and minimum speed limit of the road section, and the speed limit value is generally a multiple of 10;

(5) The maximum variation range of the speed limit is usually 20km/h or 10km/h, and this disclosure takes 10km/h.

As an embodiment, in step 1, according to the provisions in the setting of the key elements of the variable speed limit, determine road sections that meet the conditions for implementing the variable speed limit control strategy.

In step 2, build the real road network model of the target road section, and load it into the road network model according to the real location information of electromechanical equipment on the road; specifically, according to the location information of the real road detector, variable information information board and other electromechanical equipment Loaded into the road network simulation model.

Because macro traffic flow models such as METANET and CTM are difficult to provide information such as the position and speed of each vehicle in the road section, the micro simulation software VISSIM is selected to build and calculate the road network simulation model.

In step 3, the road network model is calibrated according to the traffic flow data of the target road section, and the specific steps of using the road network model to simulate the reduction of the number of main road lanes caused by accidents in each sub-road section under different service levels are as follows: The position of the board is used as the speed limit control section, and the sub-sections are divided between the sections. At the same time, the traffic operation situation is divided according to the service level. The road network model generated by VISSIM is used to simulate the reduction of the number of main road lanes caused by accidents in each sub-section under different service levels. Condition.

Among them, the process of calibrating the road network model by using the real traffic flow data of the road section is as follows:

(1) Select the calibration index that includes at least traffic volume or capacity, and select the system operation index as the condition for judging the stop of the calibration;

(2) Select the driving behavior model parameters as the parameters to be calibrated;

(3) Use experimental optimization method and heuristic algorithm to calibrate parameters;

(4) Use the actual data to test the credibility of the model through the statistical verification method.

As an example, in step 4, a variable speed limit dual-objective optimization model is constructed, the simulated traffic flow data in each case is transferred to the variable speed limit dual-objective optimization model, and the NSGA-II algorithm is used to solve the corresponding Variable speed limit control strategy.

Firstly, a variable speed limit dual-objective optimization model is constructed, and the NSGA-II algorithm in the multi-objective genetic algorithm is selected for the variable speed limit dual-objective optimization model to optimize traffic efficiency and road safety. Because the two objective functions of safety and efficiency are considered at the same time, and the intelligent optimization algorithm is selected to solve it, the NSGA-Ⅱ algorithm in the multi-objective genetic algorithm is selected as the optimization algorithm. According to the idea of optimizing SBO by simulation, the output value of the simulation model is used as the adaptive value of the optimization algorithm, and the solution idea of constructing the dual-objective optimization model for variable speed limit is shown in Figure 2, namely: first, establish the basic VISSIM simulation Model, build the interface between the simulation model and the optimization algorithm through Python secondary development; then, the NSGA-II algorithm generates possible speed limit strategies, input them into the VISSIM simulation model, and calculate the target corresponding to each speed limit strategy through the intersection simulation model function, NSGA-II obtains the value of the objective function, performs evolutionary iterations, and searches for new variable speed limit strategies until the evolution is completed; finally, the optimal set of variable speed limit control strategies is obtained.

Non-dominated Sorting Genetic Algorithms (NSGA) is an extension of the genetic algorithm based on the Pareto optimal concept, and the individuals are stratified according to the dominance relationship. After improving the NSGA algorithm, the NSGA-Ⅱ algorithm with lower computational complexity, guaranteed population diversity and retained high-quality individuals was obtained.

The objective function is constructed based on the two optimization objectives of traffic efficiency and road safety. Among them, the average travel time is used as the traffic efficiency index, and the conflict probability is used as the road safety index. The difference between the given speed limit values must be less than or equal to 10km/h and within the same control period, the difference between the speed limit values on adjacent control sections must also be less than or equal to 10km/h.

The specific implementation process is as follows:

In order to alleviate congestion in congested areas, improve overall traffic efficiency, and improve road safety, the present invention selects two objectives of efficiency and safety for optimization.

(1) Objective function based on traffic efficiency improvement

The average travel time (Average Travel Time, ATT) is the average time it takes a vehicle to travel on a road segment, and the total travel time (Total Travel Time, TTT) refers to the total time it takes for all vehicles in the road segment to travel from the beginning of the road segment to the end of the road segment , the relationship between TTT and ATT is shown in formula (1).

In the formula: N is the total number of vehicles.

The reduction of the total travel time and the average travel time represents the improvement of the overall traffic efficiency of the road section, and the smaller the average travel time means that each driver spends less time passing through the congested road section.

(2) Objective function based on road safety improvement

Alternative safety indicators can be used to analyze vehicle conflicts on the road and realize the evaluation of road safety. Therefore, Time To Collision (TTC) in the alternative safety indicators is used as a safety indicator, which is defined as: if two The driving state of the car remains unchanged, the time required for the rear car to collide with the front car, and if appropriate preventive measures such as deceleration of the rear car can be taken within this time interval, the collision can be avoided. The calculation formula As shown in formula (2).

In the formula: t is the time interval, i is the vehicle number, vehicle i+1 represents the car following vehicle i, TTC _i,t represents the collision time of vehicle i at time t, x _i (t) represents the location of vehicle i at time t position, v _i (t) represents the speed of vehicle i at time t.

Bachmann improved the formula (2) and divided the speed relationship when the vehicle is following a car. The improved collision time formula is shown in formula (3). When the speed of the rear vehicle is less than or equal to the speed of the vehicle in front, the collision Time is set to infinity.

The collision time can be used to calculate the conflict probability of the entire road segment within the time period. The calculation formula is shown in formula (4), which means: set a collision time threshold, and the number of conflicts in the road segment below the collision time threshold accounts for all conflicts The ratio of the number is the conflict probability. According to general regulations, when the calculated collision time is less than 1.5s, the corresponding conflict should be defined as serious conflict, so the threshold of collision time in formula (4) is 1.5s.

In the formula: F _CL is the collision probability, n _CL is the number of collisions less than the collision time threshold, and n _TTC is the total number of collisions.

(3) Dual-objective optimization function

Using the method based on intelligent optimization algorithm, the two objectives of safety and efficiency are optimized at the same time to give the Pareto optimal solution of safety and efficiency. The objective function is shown in formula (5).

Also, for constraints,

Combined with the maximum change range of 10km/h, it should be determined that: on the same control section, the difference between the speed limit values assigned in adjacent control periods must be less than or equal to 10km/h; The difference between the speed limit values of , also needs to be less than or equal to 10km/h, as shown in formula (6).

In the formula: v _vsl,l (k) represents the kth control cycle, the speed limit value of the lth control section.

The location of the variable information information board is used as the speed limit control section, and sub-sections are divided between the sections, and the traffic operation situation is divided by the service level. VISSIM is used to simulate the reduction of the number of main road lanes caused by accidents in various sub-sections under different service levels. For each case, the simulated traffic flow data is transmitted to the multi-objective optimization genetic algorithm through the COM interface, and the corresponding variable limit is solved. speed control strategy.

Compared with the ordinary genetic algorithm, the key steps of the NSGA-II algorithm include the following three steps:

(1) Fast non-dominated sorting

The individual a in the population is given the parameter _na and the set S _a , the meaning of the parameter is: individual a will be dominated by n _a individuals in the population, and the individuals dominated by individual a constitute S _a . In the first step, add all the solutions in the population that cannot be dominated by any other solutions, that is, all the solutions with n _a =0, into the set R ₁ , and the individuals dominated by the individual b in R ₁ form the set S _b , and _the 1 is subtracted from n _k of individual k, and if n _k -1=0, it is added to set H. R ₁ becomes a set of non-dominated individuals whose Pareto rank is 1, and the non-dominated rank a _rank of all individuals in the set is the same. In the second step, the classification operation is continued on the set H until each individual gets a grade.

(2) Calculation of congestion degree

The degree of crowding a _d represents the density value of individuals in the population, and the degree of crowding of the i-th individual in the dual-objective problem is the difference between the length and width of the dotted quadrilateral composed of i-1 and i+1 as shown in Figure 4 and.

(3) Selection sort

After the above two steps, all individuals are assigned a Pareto rank a _rank and a degree of congestion a _d , and the partial order relationship < _n is defined as shown in formula (7), that is, when the Pareto ranks are different, the individual with a lower rank is selected; When the levels are the same, the individual with the higher degree of crowding is selected.

The parent generation P _t is merged with the offspring Q _t , sorted and selected according to the above steps, and n _size individuals are selected from the merged population to form a new parent generation P _t+1 , as shown in Figure 5.

The process of the overall algorithm is as follows: first, initialize the population according to the _{size n size} of the population, perform fast non-dominated sorting on the obtained initial population, and obtain the first-generation offspring according to the basic operation of the genetic algorithm; update the evolution times, adopt the elite strategy, Perform fast non-dominated sorting on the population of merged parents and offspring, and screen out new parents on the basis of calculating the degree of crowding; until the number of evolution n _gen is reached, the evolution is complete. The algorithm flow chart is shown in Figure 6.

The combined algorithm of the NSGA-II algorithm for the variable speed limit problem in this disclosure is as follows:

(1) Coding

Assuming that the speed limit value is an integer between 40 and 80, using integer coding, a gene represents the speed limit value at a time and on a section, and a set of variable speed limit strategies constitutes a possible solution. Taking the rate-limiting strategy with 4 control sections and 5 control cycles as an example, the chromosome length is 4×5, {80, 80, 70, 60; 80, 70, 70, 60; 70, 70, 70, 60; 70 , 60, 60, 50; 70, 70, 70, 60}, which is a set of possible solutions.

(2) Generate initial population

For adjacent sections and adjacent time, the speed limit value needs to be less than or equal to the constraint condition of 10km/h, which needs to be met when generating the initial population: firstly, generate the speed limit of the first control section in the first control period Speed value v _vsl,1 (1), randomly generate v _vsl,1 (2), v _vsl,2 (1) under the condition that the difference is guaranteed to be less than or equal to 10, and then generate v _vsl,1 (3), etc., until Generate the entire solution entity. Generate solution individuals repeatedly until the population size requirement is reached.

(3) Crossover operator

Select a single-point crossover as the crossover operator, that is, for a variable speed limit strategy father-a, choose another variable speed limit strategy father-b as the parent, randomly select a point (m, n), from this point to The speed limit value of the variable speed limit policy father-a is replaced by the speed limit value of the same position of policy father-b. After the intersection is completed, check the newly generated child-a, which needs to meet the constraint condition that the speed change difference between adjacent sections and adjacent time periods is less than 10; otherwise, perform the intersection again and generate another child-a until the constraint is satisfied condition.

In the specific implementation, a variety of simulated large traffic conditions are corresponding to the corresponding variable speed limit strategies, and a variable speed limit control strategy library for the target road section is constructed.

The actual road operation is judged by the detector, input into the variable speed limit control strategy library for matching, and the corresponding variable speed limit strategy is given, and released and implemented through the variable information intelligence board.

This disclosure uses the proposed method to simulate and apply a section of urban expressway on Shanghai Inner Ring Elevated Road, and compare and analyze three variable speed limit strategies with the traffic state without variable speed limit. The results show that: variable speed limit Under the speed control strategy, the improvement of safety indicators (-3.21%) and the reduction of traffic time (-6.41%) can be realized at the same time, and the road can be greatly improved without affecting the traffic efficiency (+0.87%) Safety (-26.47%), and when the safety index is improved more (-40.12%), a certain efficiency index (+15.78%) will be sacrificed; through the analysis of the average speed, speed standard deviation, and contour map The implementation effect is verified.

Example 2

An embodiment of the present disclosure provides a vehicle variable speed limit control optimization system, including:

The data initialization module is used to determine the path to be implemented by the variable speed limit control, select the target road section, and obtain the traffic flow data of the target road section;

The model construction module is used to construct the real road network model of the target road section, and load it into the road network model according to the real location information of the electromechanical equipment on the road;

The strategy solving module is used to calibrate the road network model according to the traffic flow data of the target road section, and use the road network model to simulate the reduction of the number of main road lanes caused by accidents in each sub-road section under different service levels; construct a variable speed limit dual-objective To optimize the model, the simulated traffic flow data in each case is transferred to the variable speed limit dual-objective optimization model, and the NSGA-II algorithm is used to solve the corresponding variable speed limit control strategy.

Example 3

An embodiment of the present disclosure provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor of a terminal device and executing the vehicle variable speed limit control Optimization method steps.

Example 4

An embodiment of the present disclosure provides a terminal device, including a processor and a computer-readable storage medium, the processor is used to implement various instructions; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being executed by The processor loads and executes the steps of the method for optimizing the vehicle variable speed limit control.

The above-mentioned embodiments 2, 3, and 4 specifically implement the steps of the method described in embodiment 1.

The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

Although the specific implementation of the present disclosure has been described above in conjunction with the accompanying drawings, it does not limit the protection scope of the present disclosure. Those skilled in the art should understand that on the basis of the technical solutions of the present disclosure, those skilled in the art do not need to pay creative work Various modifications or variations that can be made are still within the protection scope of the present disclosure.

Claims (10)

1. A vehicle variable speed limit control optimization method, characterized in that, comprising: Determine the path to be implemented by the variable speed limit control, select the target road section, and obtain the traffic flow data of the target road section; Construct the real road network model of the target road section, and load it into the road network model according to the real location information of electromechanical equipment on the road; Calibrate the road network model according to the traffic flow data of the target road section, and use the road network model to simulate the reduction of the number of main road lanes caused by accidents in each sub-road section under different service levels; A variable speed limit dual-objective optimization model is constructed, and the traffic flow data simulated in each case is transmitted to the variable speed limit dual-objective optimization model, and the corresponding variable speed limit control strategy is solved by using the NSGA-Ⅱ algorithm. 2. A kind of vehicle variable speed limit control optimization method as claimed in claim 1, is characterized in that, described variable speed limit dual-objective optimization model selects the NSGA-Ⅱ algorithm in the multi-objective genetic algorithm to use traffic efficiency and road Safety is optimized as a goal. 3. A method for optimizing vehicle variable speed limit control according to claim 1, wherein the real road network model of the target road section is constructed by VISSIM. 4. A kind of vehicle variable speed limit control optimization method as claimed in claim 2, it is characterized in that, in the two optimization objectives of described traffic efficiency and road safety, wherein, with average travel time as traffic efficiency index, with conflict Probability is used as a road safety index, and the constraint conditions are determined as follows: on the same control section, the difference between the speed limit values assigned in adjacent control cycles must be less than or equal to 10km/h and in the same control cycle, the speed limit value on adjacent control sections The difference between the speed limit values also needs to be less than or equal to 10km/h. 5. A kind of vehicle variable speed limit control optimization method as claimed in claim 1, is characterized in that, said road network model is calibrated according to target section traffic flow data, utilizes road network model to simulate each The specific steps for the reduction of the number of lanes on the main road due to accidents in sub-sections are as follows: take the position of the variable information board as the speed limit control section, divide the sub-sections into sub-sections, and divide the traffic operation situation by service level, and use VISSIM to generate The road network model simulates the reduction of the number of main road lanes caused by accidents on each sub-section under different service levels. 6. a kind of vehicle variable speed limit control optimization method as claimed in claim 1, is characterized in that, the process of the solution of described variable speed limit dual-objective optimization model is: Build the interface between VISSIM road network model and optimization algorithm through secondary development of Python; generate possible speed limit strategies by NSGA-Ⅱ algorithm, input them into VISSIM road network model, and calculate the target corresponding to each speed limit strategy through VISSIM road network model function, NSGA-II obtains the value of the objective function, performs evolutionary iterations, and searches for new variable speed limit strategies until the evolution is completed. 7. A kind of vehicle variable speed limit control optimization method as claimed in claim 1, is characterized in that, the flow process step of described NSGA-II algorithm is: S1: Initialize the population according to the size of the population; S2: After performing fast non-dominated sorting on the obtained initial population, obtain the first generation of offspring according to the basic operation of the genetic algorithm; S3: Update the number of evolutions, adopt the elite strategy, perform fast non-dominated sorting on the population of the merged parent and offspring, and screen out new parents on the basis of calculating the degree of congestion; until the number of evolutions is reached, the evolution is complete. 8. A vehicle variable speed limit control optimization system, characterized in that it comprises: The data initialization module is used to determine the path to be implemented by the variable speed limit control, select the target road section, and obtain the traffic flow data of the target road section; The model construction module is used to construct the real road network model of the target road section, and load it into the road network model according to the real location information of the electromechanical equipment on the road; The strategy solving module is used to calibrate the road network model according to the traffic flow data of the target road section, and use the road network model to simulate the reduction of the number of main road lanes caused by accidents in each sub-road section under different service levels; construct a variable speed limit dual-objective To optimize the model, the simulated traffic flow data in each case is transferred to the variable speed limit dual-objective optimization model, and the NSGA-II algorithm is used to solve the corresponding variable speed limit control strategy. 9. A computer-readable storage medium, wherein a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor of a terminal device and executing the vehicle according to any one of claims 1-7. Optimization method for variable speed limit control. 10. A terminal device, characterized in that it includes a processor and a computer-readable storage medium, the processor is used to implement instructions; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and Executing a vehicle variable speed limit control optimization method according to any one of claims 1-7.

Images