Disclosure of Invention
The invention provides a variable speed limit optimization method based on intelligent network coupling and driver compliance, which is used for solving the defects in the prior art.
The invention is realized by the following technical scheme:
the variable speed limit optimization method based on intelligent network coupling and driver compliance comprises the following steps:
1) Designing a three-dimensional road scene of the expressway, constructing the three-dimensional road scene of the expressway based on a group driving simulation platform, and simultaneously importing the scene into micro-traffic simulation software;
2) Constructing an interactive simulation experiment platform based on the microscopic traffic simulation software and the group driving simulation platform;
3) After the experimental platform is started, the simulated traffic flow data are exported in real time, the current traffic flow risk level and the compliance of different drivers for controlling the simulated vehicles are calculated by using a traffic flow risk detection algorithm, and a preset lane-level variable speed limit control instruction is issued by using a lane-level variable speed limit issuing system in a road scene according to a preset lane-level variable speed limit control strategy;
4) Recruiting a plurality of drivers to carry out virtual simulation group driving by utilizing a driving simulator to wear VR glasses, controlling the running states of simulated vehicles by the drivers, loading the drivers in a unified scene for interaction in the driving process aiming at large-scale group drivers and drivers in different driving styles under different traffic states and scenes, and loading background vehicles generated based on parallel simulation according to different traffic states; acquiring basic information of a driver by using a questionnaire investigation mode, and simultaneously acquiring experimental road section road environment information data, vehicle running state data and traffic state data;
5) Calculating the compliance degree of each driver in the simulated driving, wherein the compliance degree is defined as:
wherein the ratio is i (t) is the compliance of the vehicle at time i,for i speed of the vehicle 250m upstream of the location receiving the variable speed limit information,/i>For i vehicle speed 200m downstream of the location receiving variable speed limit information, VSL i And (t) is a variable speed limit value issued to the i vehicle at the moment t.
Wherein whenWhen the compliance was considered to be 100%;
6) The compliance degree of a background vehicle generated based on simulation in a micro traffic simulation platform to a variable speed limit instruction is adjusted, one part of the compliance degree can be selected to be set to be 100% as an automatic driving vehicle, and the other part of the compliance degree is set to be different compliance degrees according to requirements;
7) The driver and the vehicle are defined as high, medium and low compliance with 100% compliance and 80% compliance as limits; wherein compliance level is defined as:
8) Dividing drivers and vehicles into three data sets according to compliance grades, namely a high compliance data set, a medium compliance data set and a low compliance data set; and carrying out cluster analysis on parameter matrixes of vehicles with different compliance data sets in each time period by adopting a K-means clustering algorithm, wherein each column in the matrix is a time sequence of one parameter, and the parameter matrixes comprise the following parameters: (1) a road environment information data matrix: black/daytime, weather, illumination, current road alignment, gradient, current lane speed limit and distance variable speed limit plate distance; (2) a driver information data matrix: the sex of the driver, the driving age of the driver and the age of the driver; (3) a vehicle operating state data matrix: time, vehicle center longitudinal position, vehicle center lateral position, vehicle longitudinal speed, vehicle longitudinal acceleration, vehicle lateral speed, vehicle lateral acceleration, lane offset, steering wheel angle, and vehicle speed product; (4) a traffic state data matrix: the longitudinal speed of the front vehicle of the lane, the time interval of the vehicle head, the distance between the front vehicles of the adjacent lanes, the longitudinal speed of the front vehicles of the adjacent lanes, the distance between the front vehicles and the rear vehicles of the lane, the traffic saturation, the average speed of the current road section and the current traffic flow; the Euclidean distance is used as an index for measuring the similarity of the data points, the distance between each data point in the sample set and the initial particle is calculated, and the closest principle is adopted to distribute the data points to the closest particles, so that the similar data can be classified into a cluster; dividing the parameter matrix data set into 3 clusters, namely, exciting, resisting and taking care; the drivers are finally classified into 9 categories: high aggressive compliance, high careless compliance, high careful compliance, aggressive compliance, medium-care compliance, small careful compliance, low aggressive compliance, low careless compliance, low careful compliance, constructing a driver personality style matrix;
9) Taking the style of the driver as a dependent variable and a parameter matrix as an independent variable, and training a deep learning model based on SAEs;
training a SAEs-based deep learning model, taking a training set as input, the first layer being trained as an automatic encoder; after the first hidden layer is obtained, the output of the mth hidden layer is used as the input of the (m+1) th hidden layer; the model structure consists of SAEs for extracting short-time traffic flow characteristics and a logistic regression layer for supervised parameter matrix prediction; training a deep network by adopting a Back Propagation (BP) algorithm based on a gradient optimization technology, wherein a greedy layered unsupervised learning algorithm shows advantages due to training each layer of parameters in the deep network from bottom to top in sequence; after the pre-training stage is completed, parameters of the prediction model are adjusted from top to bottom by means of the BP neural network, and finally a driving characteristic type judging model based on a parameter matrix is obtained;
10 The variable speed limit decision module is used for optimizing speed limit instructions for drivers of different driving styles under different roads and traffic scenes respectively, searching for a proper variable speed limit control strategy with higher compliance for the driving styles, using the comprehensive risk level based on individual vehicle safety and traffic flow overall safety as an actual rewarding value, using the driver compliance as a correction factor, establishing lane-level variable speed limit control schemes taking the driver compliance into consideration under the intelligent networking environment and the man-machine mixed traffic environment, forming a control scheme strategy library, and the variable speed limit information release module is used for releasing speed limit information for road users by using RSU (reactive power unit), so as to provide personalized speed limit guidance for different drivers under complex traffic environment.
In the above variable speed limit optimization method based on intelligent network coupling and driver compliance, in the step 2), the running state of the micro traffic flow is controlled by the micro traffic simulation software, the simulated vehicles controlled by the driver are generated by group driving simulation software, and the information of the simulated vehicles is synchronously updated in real time in the micro traffic simulation software and the group driving simulation software, wherein the group driving simulation vehicles can interact with each other, and meanwhile, the group driving simulation vehicles can interact with the simulated vehicles generated by the micro traffic simulation software.
According to the variable speed limit optimization method based on intelligent network coupling and driver compliance, in the step 3), RSUs distributed on the road side are information instruction issuing devices of the variable speed limit system, the information instruction issuing devices are distributed at intervals of 500m, different variable speed limit information is issued for different lanes by each instruction, namely lane-level speed limit instructions on different lanes and upstream and downstream can have different speed limit values, and the speed limit values of the variable speed limit marks are adjusted through real-time change, so that the running state of road traffic flow is changed in real time.
In the step 6), an online simulation module is implanted in a microscopic traffic simulation platform, wherein an automatic driving vehicle adopts an IDM (integrated digital matrix) following and lane changing model to simulate the vehicle position in real time, the intelligent network vehicle utilizes a Q-learning reinforcement learning algorithm to simulate the vehicle position in real time, a manual driving vehicle utilizes a Gipps following and lane changing model to simulate the vehicle position in real time, and three models are loaded into the online simulation module according to different proportions and speed limiting compliance.
In the above-mentioned variable speed limit optimization method based on intelligent network coupling and driver compliance, in the step 8), the parameter value rule of the parameter matrix is as follows: the extraction positions are 200m, 800m, 1400m and 2000m upstream of the position where the vehicle receives the variable speed limit instruction, and 400m and 1000m downstream of the position where the vehicle receives the variable speed limit instruction, the extraction time granularity is 5min, and the extraction time is 5min, 10min, 15min, 20min, 25min and 30min before the vehicle receives the variable speed limit instruction.
In the step 9), aiming at driving styles of different drivers, an improved particle swarm optimization algorithm is adopted to find an optimal variable speed limit control strategy, comprehensive risks are used as actual rewarding values, individual vehicle compliance is used as a correction factor, and finally a variable speed limit control scheme suitable for each driving style is established to form a control scheme strategy library. The method comprises the following steps:
1) Judging the driving style of a driver by using a driving style judging method, initializing the speed limit after the judgment is finished, and initializing the variable speed limit speed change gradient and the speed change period;
2) Initializing and setting a variable speed limiting speed change threshold;
3) Controlling the variable speed limit change according to the driving risk, if Q is more than 0.30, changing the variable speed limit, calculating the driving risk at the end of the control period, if Q is still more than 0.30, traversing, adjusting and optimizing the variable speed limit plate speed change gradient and speed change period of the current variable speed limit strategy until the driving risk benefit E (mu) of the combined control strategy p ) And (3) highest, incorporating the control strategy into a variable speed limit strategy library, thereby obtaining targeted variable speed limit control strategies aiming at different driving styles.
In the step 9), parameters in the parameter matrix are used as input variables and are subjected to data standardization processing, an original data set is established by using the driving style type obtained in the step 8), and a random forest method is adopted to perform dimension reduction processing on data dimensions to obtain a training data set.
The variable speed limit optimization method based on intelligent network coupling and driver compliance as described above, in the step 10), the comprehensive risk level algorithm based on individual vehicle safety and traffic flow overall safety, the method comprises the following steps:
1) Establishing individual vehicle safety risk level judgment and evaluation standards, wherein dangerous behaviors are defined as follows:
TTC i i the collision time of the vehicle relative to the front vehicle at the time t, because the vehicle position acquired by data is the position of the vehicle head, X is the position of the vehicle head i (t) is the position of the head of the vehicle at the moment i, X h (t) is the position of the front h head of the front car at the moment i, l h Is the length of the body of the h car, V i (t) is the instantaneous speed of the i-car at time t, V h (t) is the instantaneous speed of the vehicle at time t;
the individual vehicle security risk level definition method comprises the following steps of:
wherein,
wherein,representing the collision risk of i vehicles relative to the preceding vehicle at the moment t, TTC p TTC representing all individual vehicles at that moment i Is a mean value of (c).
2) By using a K-means clustering methodThe clusters are three categories, high risk level, medium risk level and low risk level, respectively. Using Risk (i) to represent i car relative to the front at time tCollision risk level of the vehicle, namely:
3) And constructing a traffic flow overall safety risk level judgment and evaluation standard, and counting the proportion of vehicles with high, medium and low risk levels in the road section at the moment t. Wherein the overall security risk level of the traffic flow is defined as:
4) Building a comprehensive risk algorithm based on individual vehicle safety and overall traffic flow safety:
wherein α+β=1
5) Aiming at drivers with different driving styles, an improved particle swarm optimization algorithm is adopted to find an optimal variable speed limit control strategy, the comprehensive risk Q is used as an actual rewarding value, and the individual vehicle compliance rate is adopted i And (t) taking the variable speed limit control scheme as a correction factor, and finally establishing a variable speed limit control scheme suitable for each driving style to form a control scheme strategy library.
Wherein the individual vehicle security risk benefits of the combined control strategy are defined as:
wherein E (mu) p ) Representing the risk benefit under the control strategy,the risk is integrated before the control strategy is implemented,the risk is integrated after implementation for the control strategy.
Compliance combining loss for a combined control strategy is defined as:
wherein the ratio is i (t) b Individual vehicle compliance, compactness, prior to implementation of the control strategy i (t) a Individual vehicle compliance after implementation of the control strategy.
6) The variable speed limit information release module utilizes RSUs arranged on the road sides to release speed limit information to road users.
The invention has the advantages that:
1. the method is based on a group driving simulation platform to build a three-dimensional road scene of the expressway; based on the interactive microscopic traffic simulation platform, background traffic is loaded to the three-dimensional road scene, and the problem that personalized speed limiting guidance is difficult to conduct for different drivers in an intelligent network environment and a man-machine mixed traffic environment and the problem of personalized speed limiting guidance under the mixed running condition of vehicles with different compliance degrees are solved by adjusting the compliance of the background vehicles generated based on simulation in the microscopic traffic simulation platform to the variable speed limiting instructions.
2. According to the invention, a variable speed limit decision module is utilized to respectively optimize speed limit instructions for drivers of different driving styles under different roads and traffic scenes, a proper variable speed limit control strategy with higher compliance for the driving styles is searched, an individual traffic safety index is utilized as an actual rewarding value, the driver compliance is utilized as a correction factor, lane-level variable speed limit control schemes considering the driver compliance under an intelligent networking environment and a man-machine mixed traffic environment are established, and a control scheme strategy library is formed. The method solves the problem that the driving risk of part of driving vehicles is increased due to lower compliance of drivers in the traditional variable speed limit control method. Meanwhile, the method has the characteristics of replicable popularization and strong robustness.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The variable speed limit optimization method based on intelligent network coupling and driver compliance comprises the following steps:
1) Designing a three-dimensional road scene of the expressway, constructing the three-dimensional road scene of the expressway based on a group driving simulation platform, and simultaneously importing the scene into micro-traffic simulation software;
2) Constructing an interactive simulation experiment platform based on the microscopic traffic simulation software and the group driving simulation platform;
3) After the experimental platform is started, the simulated traffic flow data are exported in real time, the current traffic flow risk level and the compliance of different drivers for controlling the simulated vehicles are calculated by using a traffic flow risk detection algorithm, and a preset lane-level variable speed limit control instruction is issued by using a lane-level variable speed limit issuing system in a road scene according to a preset lane-level variable speed limit control strategy;
4) Recruiting a plurality of drivers to carry out virtual simulation group driving by utilizing a driving simulator to wear VR glasses, controlling the running states of simulated vehicles by the drivers, loading the drivers in a unified scene for interaction in the driving process aiming at large-scale group drivers and drivers in different driving styles under different traffic states and scenes, and loading background vehicles generated based on parallel simulation according to different traffic states; acquiring basic information of a driver by using a questionnaire investigation mode, and simultaneously acquiring experimental road section road environment information data, vehicle running state data and traffic state data;
5) Calculating the compliance degree of each driver in the simulated driving, wherein the compliance degree is defined as:
wherein the ratio is i (t) is the compliance of the vehicle at time i,for i speed of the vehicle 250m upstream of the location receiving the variable speed limit information,/i>For i vehicle speed 200m downstream of the location receiving variable speed limit information, VSL i And (t) is a variable speed limit value issued to the i vehicle at the moment t.
Wherein whenWhen the compliance was considered to be 100%;
6) The compliance degree of a background vehicle generated based on simulation in a micro traffic simulation platform to a variable speed limit instruction is adjusted, one part of the compliance degree can be selected to be set to be 100% as an automatic driving vehicle, and the other part of the compliance degree is set to be different compliance degrees according to requirements;
7) The driver and the vehicle are defined as high, medium and low compliance with 100% compliance and 80% compliance as limits; wherein compliance level is defined as:
8) Dividing drivers and vehicles into three data sets according to compliance grades, namely a high compliance data set, a medium compliance data set and a low compliance data set; and carrying out cluster analysis on parameter matrixes of vehicles with different compliance data sets in each time period by adopting a K-means clustering algorithm, wherein each column in the matrix is a time sequence of one parameter, and the parameter matrixes comprise the following parameters: (1) a road environment information data matrix: black/daytime, weather, illumination, current road alignment, gradient, current lane speed limit and distance variable speed limit plate distance; (2) a driver information data matrix: the sex of the driver, the driving age of the driver and the age of the driver; (3) a vehicle operating state data matrix: time, vehicle center longitudinal position, vehicle center lateral position, vehicle longitudinal speed, vehicle longitudinal acceleration, vehicle lateral speed, vehicle lateral acceleration, lane offset, steering wheel angle, and vehicle speed product; (4) a traffic state data matrix: the longitudinal speed of the front vehicle of the lane, the time interval of the vehicle head, the distance between the front vehicles of the adjacent lanes, the longitudinal speed of the front vehicles of the adjacent lanes, the distance between the front vehicles and the rear vehicles of the lane, the traffic saturation, the average speed of the current road section and the current traffic flow; the Euclidean distance is used as an index for measuring the similarity of the data points, the distance between each data point in the sample set and the initial particle is calculated, and the closest principle is adopted to distribute the data points to the closest particles, so that the similar data can be classified into a cluster; dividing the parameter matrix data set into 3 clusters, namely, exciting, resisting and taking care; the drivers are finally classified into 9 categories: high aggressive compliance, high careless compliance, high careful compliance, aggressive compliance, medium-care compliance, small careful compliance, low aggressive compliance, low careless compliance, low careful compliance, constructing a driver personality style matrix;
9) Taking the style of the driver as a dependent variable and a parameter matrix as an independent variable, and training a deep learning model based on SAEs;
training a SAEs-based deep learning model, taking a training set as input, the first layer being trained as an automatic encoder; after the first hidden layer is obtained, the output of the mth hidden layer is used as the input of the (m+1) th hidden layer; the model structure consists of SAEs for extracting short-time traffic flow characteristics and a logistic regression layer for supervised parameter matrix prediction; training a deep network by adopting a Back Propagation (BP) algorithm based on a gradient optimization technology, wherein a greedy layered unsupervised learning algorithm shows advantages due to training each layer of parameters in the deep network from bottom to top in sequence; after the pre-training stage is completed, parameters of the prediction model are adjusted from top to bottom by means of the BP neural network, and finally a driving characteristic type judging model based on a parameter matrix is obtained;
10 The variable speed limit decision module is used for optimizing speed limit instructions for drivers of different driving styles under different roads and traffic scenes respectively, searching for a proper variable speed limit control strategy with higher compliance for the driving styles, using the comprehensive risk level based on individual vehicle safety and traffic flow overall safety as an actual rewarding value, using the driver compliance as a correction factor, establishing lane-level variable speed limit control schemes taking the driver compliance into consideration under the intelligent networking environment and the man-machine mixed traffic environment, forming a control scheme strategy library, and the variable speed limit information release module is used for releasing speed limit information for road users by using RSU (reactive power unit), so as to provide personalized speed limit guidance for different drivers under complex traffic environment.
Preferably, in the step 2), the running state of the micro traffic flow is controlled by the micro traffic simulation software, the simulated vehicles controlled by the driver are generated by group driving simulation software, and the information of the simulated vehicles is synchronously updated in real time in the micro traffic simulation software and the group driving simulation software, wherein the group driving simulation vehicles can interact with each other, and meanwhile, the group driving simulation vehicles can interact with the simulated vehicles generated by the micro traffic simulation software.
According to the variable speed limit optimization method based on intelligent network coupling and driver compliance, in the step 3), RSUs distributed on the road side are information instruction issuing devices of the variable speed limit system, the information instruction issuing devices are distributed at intervals of 500m, different variable speed limit information is issued for different lanes by each instruction, namely lane-level speed limit instructions on different lanes and upstream and downstream can have different speed limit values, and the speed limit values of the variable speed limit marks are adjusted through real-time change, so that the running state of road traffic flow is changed in real time.
Preferably, in the step 6), an online simulation module is implanted in the micro-traffic simulation platform, wherein the automatic driving vehicle adopts an IDM (integrated digital matrix) following and lane changing model to simulate the vehicle position in real time, the intelligent network vehicle utilizes a Q-learning reinforcement learning algorithm to simulate the vehicle position in real time, the manual driving vehicle utilizes a Gipps following and lane changing model to simulate the vehicle position in real time, and the three models are loaded into the online simulation module according to different proportions and speed limiting compliance.
Preferably, the parameter value rule of the parameter matrix is as follows: the extraction positions are 200m, 800m, 1400m and 2000m upstream of the position where the vehicle receives the variable speed limit instruction, and 400m and 1000m downstream of the position where the vehicle receives the variable speed limit instruction, the extraction time granularity is 5min, and the extraction time is 5min, 10min, 15min, 20min, 25min and 30min before the vehicle receives the variable speed limit instruction.
Preferably, aiming at driving styles of different drivers, an improved particle swarm optimization algorithm is adopted to find an optimal variable speed limit control strategy, comprehensive risks are used as actual rewarding values, individual vehicle compliance is used as a correction factor, and finally, a variable speed limit control scheme suitable for each driving style is established to form a control scheme strategy library. The method comprises the following steps:
1) Judging the driving style of a driver by using a driving style judging method, initializing the speed limit after the judgment is finished, and initializing the variable speed limit speed change gradient and the speed change period;
2) Initializing and setting a variable speed limiting speed change threshold;
3) Controlling the variable speed limit change according to the driving risk, if Q is more than 0.30, changing the variable speed limit, calculating the driving risk at the end of the control period, if Q is still more than 0.30, traversing, adjusting and optimizing the variable speed limit plate speed change gradient and speed change period of the current variable speed limit strategy until the driving risk benefit E (mu) of the combined control strategy p ) And (3) highest, incorporating the control strategy into a variable speed limit strategy library, thereby obtaining targeted variable speed limit control strategies aiming at different driving styles.
Preferably, in the step 9), the parameters in the parameter matrix are used as input variables and data standardization processing is performed, the driving style type obtained in the step 8) is used for establishing an original data set, and a random forest method is used for performing dimension reduction processing on the data dimension to obtain a training data set.
Preferably, in the step 10), the comprehensive risk level algorithm based on the individual vehicle safety and the overall traffic flow safety comprises the following steps:
1) Establishing individual vehicle safety risk level judgment and evaluation standards, wherein dangerous behaviors are defined as follows:
TTC i i the collision time of the vehicle relative to the front vehicle at the time t, because the vehicle position acquired by data is the position of the vehicle head, X is the position of the vehicle head i (t) is the position of the head of the vehicle at the moment i, X h (t) is the position of the front h head of the front car at the moment i, l h Is the length of the body of the h car, V i (t) is the instantaneous speed of the i-car at time t, V h (t) is the instantaneous speed of the vehicle at time t;
the individual vehicle security risk level definition method comprises the following steps of:
wherein,
wherein,representing the collision risk of i vehicles relative to the preceding vehicle at the moment t, TTC p TTC representing all individual vehicles at that moment i Is a mean value of (c).
2) By using a K-means clustering methodThe clusters are three categories, high risk level, medium risk level and low risk level, respectively. The collision Risk level of i vehicles relative to the preceding vehicle at time t is represented by Risk (i), namely:
3) And constructing a traffic flow overall safety risk level judgment and evaluation standard, and counting the proportion of vehicles with high, medium and low risk levels in the road section at the moment t. Wherein the overall security risk level of the traffic flow is defined as:
4) Building a comprehensive risk algorithm based on individual vehicle safety and overall traffic flow safety:
wherein α+β=1
5) Aiming at drivers with different driving styles, the driver adoptsSearching for an optimal variable speed limit control strategy by using an improved particle swarm optimization algorithm, and utilizing the comprehensive risk Q as an actual rewarding value to enable individual vehicles to follow the rate i And (t) taking the variable speed limit control scheme as a correction factor, and finally establishing a variable speed limit control scheme suitable for each driving style to form a control scheme strategy library.
Wherein the individual vehicle security risk benefits of the combined control strategy are defined as:
wherein E (mu) p ) Representing the risk benefit under the control strategy,the risk is integrated before the control strategy is implemented,the risk is integrated after implementation for the control strategy.
Compliance combining loss for a combined control strategy is defined as:
wherein the ratio is i (t) b Individual vehicle compliance, compactness, prior to implementation of the control strategy i (t) a Individual vehicle compliance after implementation of the control strategy.
And judging the driving style of the driver by using the driving style judging method, initializing the speed limit after the judgment, and initializing the variable speed limit speed change gradient and the speed change period.
And initializing and setting a variable speed limiting speed change threshold.
And initializing and setting the variable speed limiting guide speed of each vehicle, wherein the initial speed limit is 100km/h.
And initializing and setting a speed change gradient, wherein the speed change gradient is 5km/h.
And initializing and setting a speed change period which is 1min.
And acquiring the driving risk according to the real-time traffic track of the road section, and changing the variable speed limit by adopting initialization setting if the risk level is more than 0.30. Calculating the benefit E (mu) of the combined control strategy at the future time of 5 minutes after the speed limit is changed p ) And loss Risk of combined control strategy p 。
Benefit E (μ) of combining control strategies p ) And loss Risk of combined control strategy p As a target optimization function, as input into the particle swarm optimization algorithm model.
Initializing a particle group, setting the group size as N, and initializing the speed and the position of the particles.
And setting a fitness function, and calculating the fitness of each particle through the fitness function. And respectively storing the optimal positions and the optimal fitness of the particles, wherein the optimal positions and the optimal fitness of the population are respectively stored.
And comparing the fitness of each particle with the fitness Pi of the historical optimal point, and if the fitness of the particle is better than the historical optimal point, taking the current position as the historical optimal position of the particle, and meanwhile, the fitness of the particle also becomes the historical optimal fitness so as to find the individual optimal.
The update of the position and velocity of the particles is based on:
wherein the acceleration factor c 1 Regulating maximum step length of individual optimum position flying, c 2 And adjusting the maximum step length of the global optimal position flight. If the acceleration factor is too large, particles can fly out of the target area rapidly, and if the acceleration factor is too small, particles can be caused to fly out of the target area rapidlyThe particles reach the target area too slowly. Suitable c 1 And c 2 The value can promote the convergence rate of the particle swarm algorithm and avoid sinking into local optimum. c 1 And c 2 Value of [0,4 ]]In between, the present embodiment is set to 2.
Representing the influence of the speed left by the previous generation of the particles on the flying behavior of the particles, the influence can be regarded as the inertia of the particles; second part->The method is that the individual cognition is realized, the particles find out the optimal solution direction found by the individual cognition, and the learning of past experience of the particles is represented; third part->The method belongs to social cognition, and the particles refer to learning to other particles in the population, and represent acceptance of the particles to the overall searching condition of the population.
And comparing the adaptation value corresponding to the historical optimal position of each particle with the population optimal adaptation degree Pg, and if the adaptation value is better, updating the historical optimal position and the historical adaptation of the population so as to find global optimal.
If the condition is met, the vehicle is stopped, otherwise, the vehicle risk is acquired according to the real-time traffic track of the road section, and if the risk level is more than 0.30, the variable speed limit is changed by adopting the initialization setting. Calculating the benefit E (mu) of the combined control strategy at the future time of 5 minutes after the speed limit is changed p ) And loss Risk of combined control strategy p The operation continues here and again. Until the optimal speed limit value V under the condition is obtained t 。
The variable speed limit information release module utilizes RSUs arranged on the road sides to release speed limit information to road users.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.