Intersection Free-Flow Velocity Analysis Method Based on Monte Carlo Sampling

Abstract

This invention belongs to the field of traffic technology, and particularly relates to a method for analyzing free-flow velocity at intersections based on Monte Carlo sampling. First, a traffic intersection model, a traffic scenario database, and a target vehicle database are constructed. Then, historical periodic data of the traffic intersection is acquired. Based on the historical periodic data, traffic scenarios and target vehicles are extracted from the traffic scenario database and the target vehicle database and imported into the traffic intersection model to generate traffic intersection operation data. Next, multiple sets of traffic intersection operation data within different time periods are randomly selected using Monte Carlo sampling. An optimization algorithm is constructed to iterate and optimize the extracted traffic intersection operation data. After a preset number of iterations, the optimal traffic intersection operation data set is output. Finally, the free-flow velocity is calculated from the data in the optimal traffic intersection operation data set. This invention can solve the limitations and inconsistencies of existing methods for free-flow velocity analysis.

Description

Technical Field

[0001] This invention belongs to the field of transportation technology, and in particular relates to a method for analyzing free-flow velocity at intersections based on Monte Carlo sampling. Background Technology

[0002] Free-flow speed refers to the speed at which a driver naturally chooses based on road characteristics when there is no interference from other vehicles, obvious speed enforcement, or other external environmental factors. Free-flow speed reflects the influence of the road and traffic environment and is also an important indicator for measuring road capacity and traffic efficiency.

[0003] Currently, the technology for free-flow velocity analysis is relatively mature, and various methods can be used for estimation and analysis, such as traditional observation methods and data-based analysis methods. However, existing technologies have certain limitations and inconsistencies. Limitations include the use of traditional observation methods to estimate free-flow velocity by directly observing vehicle speeds. Due to the complexity and variability of traffic flow, observation methods can lead to inaccuracies due to variations in traffic conditions, observation duration, and location selection. Similarly, data analysis methods are affected by the dynamic and complex traffic environment; changes in traffic flow, traffic management measures, temporary weather factors, and traffic accidents can all impact free-flow velocity analysis. Inconsistencies arise from the inconsistencies in the existing definitions and measurements of free-flow velocity. Different studies and practices may use different definitions and measurement methods, such as average speed or 85% speed, leading to incomparability of research results and difficulties in understanding and interpreting them in practical applications.

[0004] Therefore, there is a need for a free-flow velocity analysis method that can overcome the limitations and inconsistencies of existing methods. Summary of the Invention

[0005] The technical problem solved by this invention is to provide a Monte Carlo sampling-based method for analyzing free-flow velocity at intersections, in order to address the limitations and inconsistencies in existing methods for analyzing free-flow velocity.

[0006] The basic solution provided by this invention is a method for analyzing free-flow velocity at intersections based on Monte Carlo sampling, comprising:

[0007] S1: Collect structural data of traffic intersections, construct traffic intersection models, and build a traffic scenario database and a target vehicle database;

[0008] S2: Obtain historical periodic data of traffic intersections, extract traffic scenarios and target vehicles from the traffic scenario database and target vehicle database based on the historical periodic data, import them into the traffic intersection model, and generate traffic intersection operation data after simulation.

[0009] S3: Randomly sample multiple sets of traffic intersection operation data within a time period using Monte Carlo sampling, optimize and iterate the sampled traffic intersection operation data using an optimization algorithm, and output the optimal set of traffic intersection operation data after a preset number of iterations.

[0010] S4: Extract the average speed of the target vehicles from the optimal traffic intersection operation data set, and take the arithmetic mean of the average speeds to obtain the free-flow speed.

[0011] Furthermore, S1 includes:

[0012] S1-1: Collect information on the location of traffic intersections, road signs and markings, shape and size of intersections, road surface conditions, lane settings, equipment installation, traffic control, and historical accidents at traffic intersections to generate traffic intersection structure data.

[0013] S1-2: Construct a traffic intersection model based on the collected traffic intersection structure data.

[0014] Furthermore, S1 also includes:

[0015] S1-3: Obtain traffic scene data and target vehicles from the standard library and knowledge base, and construct a traffic scene library and a target vehicle database based on the obtained traffic scene data and vehicle data.

[0016] Furthermore, the target vehicles include passenger cars, buses, trucks, and articulated vehicles.

[0017] Furthermore, S2 includes:

[0018] S2-1: Obtain historical periodic data of traffic intersections, wherein the historical periodic data is traffic data of traffic intersections collected within a preset number of days;

[0019] S2-2: Based on historical periodic data, retrieve the corresponding traffic scenarios from the traffic scenario database and the corresponding target vehicles from the target vehicle database, import them into the traffic intersection model, simulate the traffic intersection operation status for the preset number of days, and generate traffic intersection operation data.

[0020] Furthermore, S3 includes:

[0021] S3-1: Traffic intersection operation data for a preset number of days is randomly selected using Monte Carlo sampling to serve as the initial population;

[0022] S3-2: Construct fitness functions, which include traffic flow fitness functions and coverage fitness functions;

[0023] S3-3: Optimize the initial population according to the fitness function, and after a preset number of iterations, generate the optimal set of traffic intersection operation data.

[0024] Furthermore, S3-3 specifically refers to:

[0025] Based on the traffic flow fitness function and the coverage fitness function, calculate the traffic flow fitness function value and the coverage fitness function value of the traffic intersection operation data for each time period of the preset number of days.

[0026] Based on the traffic flow fitness function value and coverage fitness function value of the traffic intersection operation data for each time period of the extracted preset number of days, sort them from high to low to obtain two sorted sets of traffic intersection operation data.

[0027] Based on the traffic flow fitness function value and the coverage fitness function value, traffic intersection operation data at a single time node are extracted from the two sorted sets by Monte Carlo sampling, and a new sorted set is generated according to the original sorting of the time period to which it belongs.

[0028] An improved ant colony algorithm is constructed, with 6 AM as the initial node and 12 AM as the ending node for a preset number of days. The node selection function is executed sequentially according to the preset number of days to select nodes until the number of nodes meets the boundary conditions and multiple paths are generated. Then, the ant colony movement is simulated until, after a preset number of iterations, the path with the highest pheromone concentration is selected as the optimal traffic intersection operation data set.

[0029] Furthermore, the improved ant colony algorithm is specifically constructed as follows:

[0030] Determine the free-flow velocity boundary conditions at traffic intersections, including free-flow velocity thresholds and time points;

[0031] Initialize the improved ant colony algorithm parameters, setting the initial number of ants, initial pheromone concentration, and pheromone volatilization rate;

[0032] Construct a heuristic function, the expression of which is:

[0033]

[0034] in, Let N represent the heuristic of the ant's movement from node i to node j, N represent the time range of the collected traffic intersection operation data, n represent the time nodes within the time range n at preset time intervals, and V represent the heuristic. ni It is the impact value on the free flow speed at the traffic intersection, where p represents the traffic flow through the intersection, t represents the green light cycle time, and L represents the average vehicle length.

[0035] Construct a node selection function, the expression of which is:

[0036]

[0037] in, δ represents the probability that ant k chooses point j from point i. ij Let be the pheromone concentration between nodes ij, and allowedk represent the set of all nodes that ant k can reach;

[0038] For each ant, starting from the initial node, the node selection function is executed sequentially to select nodes until the number of nodes meets the boundary condition, and the nodes selected by the ants form a path.

[0039] Construct a pheromone update function, the expression of which is:

[0040]

[0041] Where, δ ij (d+1) represents the updated pheromone concentration, ρ represents the pheromone evaporation rate, and δ ij (d) represents the pheromone concentration before the update, Δδ ij (d) represents the increase in pheromone concentration between nodes i and j in ant k during d iterations;

[0042] After all ants have completed one path, the pheromone concentration on each path is updated according to the pheromone update function;

[0043] Determine if the preset number of iterations is met. If so, terminate the iteration and select the path with the highest pheromone concentration as the optimal traffic intersection operation data set.

[0044] Furthermore, the formula for calculating the coverage fitness function is as follows:

[0045]

[0046] ω x f(D x )=ω1*f(1)+ω2*f(2)+ω3*f(3)+…

[0047] Where, ω xf(D) represents the weighting factor. x () indicates the indicator parameters that affect coverage;

[0048] The formula for calculating the traffic flow fitness function is as follows:

[0049]

[0050] ω y f(D y )=ω1*f(a)+ω2*f(b)+ω3*f(c)+…

[0051] Where, ω y f(D) represents the weighting factor. y () indicates the parameters that affect traffic flow.

[0052] The principle and advantages of this invention are as follows: In this application, firstly, for the construction of different traffic intersections, the corresponding structural data of the traffic intersections are obtained, including intersection location information, intersection signage and marking information, intersection shape and size information, intersection road surface condition information, intersection lane setting information, intersection equipment installation information, intersection traffic control information, and intersection historical accident information, etc., to construct a traffic intersection model. In this model, traffic operation can be simulated by importing road traffic scenarios and target scenarios from historical periodic data.

[0053] Based on the simulation results, the generated traffic intersection operation data is sampled using Monte Carlo sampling. The sample data obtained by Monte Carlo sampling is already close to the optimal data and can effectively solve the limitation problem. On this basis, the sampled data is further optimized and iterated using an improved ant colony algorithm to obtain the optimal set of traffic intersection operation data that can characterize the free flow velocity of the intersection. Based on the obtained optimal set, the free flow velocity of the traffic intersection is calculated, which can effectively solve the problem of data inconsistency. Attached Figure Description

[0054] Figure 1 This is a flowchart of an embodiment of the present invention. Detailed Implementation

[0055] The following detailed description illustrates the specific implementation method:

[0056] The basic implementation examples are as follows: Figure 1 As shown: A method for analyzing free-flow velocity at intersections based on Monte Carlo sampling, including:

[0057] S1: Collect structural data of traffic intersections, construct traffic intersection models, and build a traffic scenario database and a target vehicle database; S1 includes:

[0058] S1-1: Collect information on the location of traffic intersections, road signs and markings, shape and size of intersections, road surface conditions, lane settings, equipment installation, traffic control, and historical accidents at traffic intersections to generate traffic intersection structure data.

[0059] S1-2: Construct a traffic intersection model based on the collected traffic intersection structure data.

[0060] In this embodiment, the free-flow speed at traffic intersections is greatly affected, partly because the structure of the intersections varies. When the layout of a traffic intersection is unreasonable and the traffic volume is high, the free-flow speed will be greatly affected, resulting in a free-flow speed lower than the normal value. Therefore, by constructing a traffic intersection model, we can analyze the operation of the traffic intersection and use it as a basis for traffic construction decisions.

[0061] In traffic intersections, key factors include location information, road markings and signage, shape and dimensions, road surface conditions, lane configuration, equipment installation, traffic control information, and historical accident data. Location information indicates the daily traffic volume at the intersection. Road markings and signage, including stop lines, pedestrian crossings, and walkway lights, provide insights into the intersection's layout rationality. The shape and dimensions of the intersection directly affect vehicle movement, while road surface conditions directly reflect... The lifespan of road materials, the condition and smoothness of the road surface, etc., are all factors considered at this traffic intersection. Lane configuration directly reflects the traffic flow and vehicle capacity of the intersection, while equipment installation directly affects the completeness and real-time nature of data collection. Traffic control information directly reflects the congestion level of the intersection, and historical accident information directly reflects the accident rate. Therefore, by using the above data, the specific situation of the traffic intersection can be well characterized, thereby ensuring the authenticity and effectiveness of the data in the traffic simulation.

[0062] Furthermore, S1 also includes S1-3: acquiring traffic scene data and target vehicles from a standard library and a knowledge base, and constructing a traffic scene library and a target vehicle database based on the acquired traffic scene data and vehicle data. In this application, target vehicles include passenger cars, large buses, large trucks, and articulated vehicles. The standard library and knowledge base are obtained through an urban management center. The constructed traffic scene library and target vehicle database can be used to simulate the operation of traffic intersections, thereby providing a real-time and more intuitive display of the traffic intersection's operation.

[0063] S2: Obtain historical periodic data of the traffic intersection; extract traffic scenarios and target vehicles from the traffic scenario database and target vehicle database based on the historical periodic data; import them into the traffic intersection model; and generate traffic intersection operation data after simulation. S2 includes:

[0064] S2-1: Obtain historical periodic data of traffic intersections, wherein the historical periodic data is traffic data of traffic intersections collected within a preset number of days;

[0065] S2-2: Based on historical periodic data, retrieve the corresponding traffic scenarios from the traffic scenario database and the corresponding target vehicles from the target vehicle database, import them into the traffic intersection model, simulate the traffic intersection operation status for the preset number of days, and generate traffic intersection operation data.

[0066] In this embodiment, the historical periodic data of the traffic intersection is acquired according to a preset number of days. Specifically, the preset number of days is the historical traffic data of the previous 30 days. The historical traffic data of the previous 30 days contains information such as corresponding traffic scenarios, traffic emergencies and traffic accidents. It also includes data such as vehicle speed, vehicle type and traffic flow that can reflect the operation of the traffic intersection. Therefore, by importing the historical periodic data into the traffic intersection model for simulation, the traffic operation status can be presented in real time, and the corresponding traffic operation data can be displayed under the presented traffic operation status.

[0067] S3: Randomly sample multiple sets of traffic intersection operation data within a time period using Monte Carlo sampling. Optimize and iterate the sampled traffic intersection operation data using a constructed optimization algorithm. After a preset number of iterations, output the optimal set of traffic intersection operation data. S3 includes:

[0068] S3-1: Traffic intersection operation data for a preset number of days is randomly selected using Monte Carlo sampling to serve as the initial population;

[0069] S3-2: Construct fitness functions, which include traffic flow fitness functions and coverage fitness functions;

[0070] S3-3: Optimize the initial population according to the fitness function, and after a preset number of iterations, generate the optimal set of traffic intersection operation data.

[0071] In this embodiment, for traffic intersection operation data extracted using Monte Carlo sampling within a preset number of days, specifically, the preset number of days is defined as 30 days, and the collection time period is defined as 6:00 AM to 12:00 AM. Within this defined time period, traffic intersection operation data is extracted using Monte Carlo sampling. The time nodes corresponding to the extracted data may be 6:00 AM, 6:10 AM, 6:20 AM, 7:00 AM, 7:30 AM, etc., with varying time nodes. Alternatively, data at fixed time intervals can be set according to requirements, such as sampling every 15 minutes, to meet different needs. In the intermediate nodes, the traffic intersection operation data for different vehicles are different. For example, the traffic vehicles sampled at point 6 include different types of vehicles such as passenger cars and large trucks, and the speeds of the sampled vehicles are also different. Therefore, even the sample data obtained through Monte Carlo sampling still suffers from inconsistent data types and large data errors. To address this, after Monte Carlo sampling, this application first filters the sampled data using fitness functions. In this application, fitness functions include a traffic flow fitness function and a coverage fitness function. The calculation formula for the coverage fitness function is as follows:

[0072]

[0073] ω x f(D x )=ω1*f(1)+ω2*f(2)+ω3*f(3)+…

[0074] Where, ω x f(D) represents the weighting factor. x () indicates the indicator parameters that affect coverage;

[0075] The formula for calculating the traffic flow fitness function is as follows:

[0076]

[0077] ω y f(D y )=ω1*f(a)+ω2*f(b)+ω3*f(c)+…

[0078] Where, ω y f(D) represents the weighting factor. y () indicates the parameters that affect traffic flow.

[0079] The optimal traffic intersection operation data at each time point is obtained through iterative calculation using an optimization algorithm. In this application, the optimization algorithm iteration specifically involves:

[0080] Based on the traffic flow fitness function and the coverage fitness function, calculate the traffic flow fitness function value and the coverage fitness function value of the traffic intersection operation data for each time period of the preset number of days.

[0081] Based on the traffic flow fitness function value and coverage fitness function value of the traffic intersection operation data for each time period of the extracted preset number of days, sort them from high to low to obtain two sorted sets of traffic intersection operation data.

[0082] Based on the traffic flow fitness function value and the coverage fitness function value, traffic intersection operation data at a single time node are extracted from the two sorted sets by Monte Carlo sampling, and a new sorted set is generated according to the original sorting of the time period to which it belongs.

[0083] An improved ant colony algorithm is constructed, with 6 AM as the initial node and 12 AM as the ending node for a preset number of days. The node selection function is executed sequentially according to the preset number of days to select nodes until the number of nodes meets the boundary conditions and multiple paths are generated. Then, the ant colony movement is simulated until, after a preset number of iterations, the path with the highest pheromone concentration is selected as the optimal traffic intersection operation data set.

[0084] The improved ant colony algorithm is constructed as follows:

[0085] The boundary conditions for free-flow velocity at traffic intersections are determined. These boundary conditions include a free-flow velocity threshold and time nodes. In this embodiment, the free-flow velocity threshold is the road speed limit, and the time nodes are nodes within the time period collected.

[0086] Initialize the improved ant colony algorithm parameters, setting the initial number of ants, initial pheromone concentration, and pheromone volatilization rate;

[0087] Construct a heuristic function, the expression of which is:

[0088]

[0089] in, Let N represent the heuristic of the ant's movement from node i to node j, N represent the time range of the collected traffic intersection operation data, n represent the time nodes within the time range n at preset time intervals, and V represent the heuristic. ni It is the impact value on the free flow speed at the traffic intersection, where p represents the traffic flow through the intersection, t represents the green light cycle time, and L represents the average vehicle length.

[0090] Construct a node selection function, the expression of which is:

[0091]

[0092] in, δ represents the probability that ant k chooses point j from point i. ij Let be the pheromone concentration between nodes ij, and allowedk represent the set of all nodes that ant k can reach;

[0093] For each ant, starting from the initial node, the node selection function is executed sequentially to select nodes until the number of nodes meets the boundary condition, and the nodes selected by the ants form a path.

[0094] Construct a pheromone update function, the expression of which is:

[0095]

[0096] Where, δ ij (d+1) represents the updated pheromone concentration, ρ represents the pheromone evaporation rate, and δ ij (d) represents the pheromone concentration before the update, Δδ ij (d) represents the increase in pheromone concentration between nodes i and j in ant k during d iterations;

[0097] After all ants have completed one path, the pheromone concentration on each path is updated according to the pheromone update function;

[0098] Determine if the preset number of iterations is met. If so, terminate the iteration and select the path with the highest pheromone concentration as the optimal traffic intersection operation data set.

[0099] Therefore, in this application, based on Monte Carlo sampling, the multi-type vehicle data in the sample are further optimized and iterated to select the traffic intersection operation data with the best performance. This is of great help in extracting the optimal performance of the free flow speed of traffic intersections at different times, and avoids the limitations of the sample and the inconsistency of the data.

[0100] S4: Extract the average speed of the target vehicles from the optimal traffic intersection operation data set, and take the arithmetic mean of the average speeds to obtain the free-flow speed.

[0101] Therefore, based on the optimal set of traffic intersection operation data obtained, the average driving speed is extracted, and then the free-flow speed is calculated, which can characterize the free-flow speed of the traffic intersection during that period.

[0102] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A method for analyzing free-flow velocity at intersections based on Monte Carlo sampling, characterized by: include: S1: Collect structural data of traffic intersections, construct traffic intersection models, and build a traffic scenario database and a target vehicle database; S2: Obtain historical periodic data of traffic intersections, extract traffic scenarios and target vehicles from the traffic scenario database and target vehicle database based on the historical periodic data, import them into the traffic intersection model, and generate traffic intersection operation data after simulation. S3: Randomly sample multiple sets of traffic intersection operation data within a time period using Monte Carlo sampling, optimize and iterate the sampled traffic intersection operation data using an optimization algorithm, and output the optimal set of traffic intersection operation data after a preset number of iterations. S4: Extract the average speed of the target vehicles from the optimal traffic intersection operation data set, and take the arithmetic mean of the average speeds to obtain the free flow speed; S3 includes: S3-1: Traffic intersection operation data for a preset number of days is randomly selected using Monte Carlo sampling to serve as the initial population; S3-2: Construct fitness functions, which include traffic flow fitness functions and coverage fitness functions; S3-3: Optimize the initial population according to the fitness function, and after a preset number of iterations, generate the optimal set of traffic intersection operation data; Specifically, S3-3 is: Based on the traffic flow fitness function and the coverage fitness function, calculate the traffic flow fitness function value and the coverage fitness function value of the traffic intersection operation data for each time period of the preset number of days. Based on the traffic flow fitness function value and coverage fitness function value of the traffic intersection operation data for each time period of the extracted preset number of days, sort them from high to low to obtain two sorted sets of traffic intersection operation data. Based on the traffic flow fitness function value and the coverage fitness function value, traffic intersection operation data at a single time node are extracted from the two sorted sets by Monte Carlo sampling, and a new sorted set is generated according to the original sorting of the time period to which it belongs. An improved ant colony algorithm is constructed, with 6 AM as the initial node and 12 AM as the ending node for a preset number of days. The node selection function is executed sequentially according to the preset number of days to select nodes until the number of nodes meets the boundary conditions and multiple paths are generated. Then, the ant colony movement is simulated until, after a preset number of iterations, the path with the highest pheromone concentration is selected as the optimal traffic intersection operation data set. The improved ant colony algorithm is specifically constructed as follows: Determine the free-flow velocity boundary conditions at traffic intersections, including free-flow velocity thresholds and time points; Initialize the improved ant colony algorithm parameters, setting the initial number of ants, initial pheromone concentration, and pheromone volatilization rate; Construct a heuristic function, the expression of which is: in, Let N represent the heuristic of the ant's movement from node i to node j, N represent the time range of the collected traffic intersection operation data, and n represent the time nodes within the time range n according to the preset time interval. This is the value affecting the free-flow velocity at traffic intersections. The value represents the traffic flow through the intersection, t represents the green light cycle time, and L represents the average length of the vehicles. Construct a node selection function, the expression of which is: in, This represents the probability that ant k chooses point j from point i. Let be the pheromone concentration between nodes ij. Let represent the set of all nodes that ant k can reach; For each ant, starting from the initial node, the node selection function is executed sequentially to select nodes until the number of nodes meets the boundary condition, and the nodes selected by the ants form a path. Construct a pheromone update function, the expression of which is: in, This indicates the updated pheromone concentration. Indicates the pheromone evaporation rate. This indicates the pheromone concentration before the update. This represents the increase in pheromone concentration between nodes i and j in ant k during d iterations; After all ants have completed one path, the pheromone concentration on each path is updated according to the pheromone update function; Determine if the preset number of iterations is met. If so, terminate the iteration and select the path with the highest pheromone concentration as the optimal traffic intersection operation data set.

2. The method for analyzing free-flow velocity at intersections based on Monte Carlo sampling according to claim 1, characterized in that: S1 includes: S1-1: Collect information on the location of traffic intersections, road signs and markings, shape and size of intersections, road surface conditions, lane settings, equipment installation, traffic control, and historical accidents at traffic intersections to generate traffic intersection structure data. S1-2: Construct a traffic intersection model based on the collected traffic intersection structure data.

3. The method for analyzing free-flow velocity at intersections based on Monte Carlo sampling according to claim 2, characterized in that: S1 further includes: S1-3: Obtain traffic scene data and target vehicles from the standard library and knowledge base, and construct a traffic scene library and a target vehicle database based on the obtained traffic scene data and vehicle data.

4. The method for analyzing free-flow velocity at intersections based on Monte Carlo sampling according to claim 3, characterized in that: The target vehicles include passenger cars, buses, trucks, and articulated vehicles.

5. The method for analyzing free-flow velocity at intersections based on Monte Carlo sampling according to claim 4, characterized in that: S2 includes: S2-1: Obtain historical periodic data of traffic intersections, wherein the historical periodic data is traffic data of traffic intersections collected within a preset number of days; S2-2: Based on historical periodic data, retrieve the corresponding traffic scenarios from the traffic scenario database and the corresponding target vehicles from the target vehicle database, import them into the traffic intersection model, simulate the traffic intersection operation status for the preset number of days, and generate traffic intersection operation data.

6. The method for analyzing free-flow velocity at intersections based on Monte Carlo sampling according to claim 1, characterized in that: The formula for calculating the coverage fitness function is as follows: in, Indicates the weighting factor. Indicator parameters that affect coverage; The formula for calculating the traffic flow fitness function is as follows: in, Indicates the weighting factor. These are the parameters that affect traffic flow.

Images