A multi-objective optimization method for the layout of road traffic facilities considering quantity constraints

Abstract

This invention discloses a multi-objective optimization method for the deployment of road traffic facilities considering quantity constraints, comprising: 1. determining the experimental area and acquiring data on traffic volume, traffic accident volume, and traffic violation volume; 2. calculating the average values ​​of traffic volume, traffic accident volume, and traffic violation volume for each candidate point set; 3. constructing an objective function for the constrained multi-objective problem; 4. solving the constructed objective function; and 5. determining the monitoring deployment scheme. This invention, considering quantity constraints, analyzes the indicators to be optimized for three candidate points—traffic congestion, traffic accident volume, and traffic violation volume—to increase the deployment density of monitoring points in the road network, achieving comprehensive regional control. This not only fully leverages the role of law enforcement monitoring but also saves significant transportation funds, playing a crucial role in improving urban traffic congestion and maintaining traffic safety, thus demonstrating substantial social benefits.

Description

Technical Field

[0001] This invention relates to the field of transportation facility construction technology, specifically a multi-objective optimization method for the layout of road transportation facilities considering quantity constraints. Background Technology

[0002] In recent years, my country's economy and society have developed rapidly, with the number of motor vehicles and drivers increasing year by year. Traditional manual management is clearly insufficient to meet the growing demands of traffic management. Therefore, some researchers have proposed using camera deployment to comprehensively control regional security and traffic. Typical front-end equipment usually includes image acquisition and shooting equipment, image and video processing equipment, auxiliary light sources, brackets, and other related supporting products. Surveillance facilities, due to their 24 / 7 operation, have advantages that cannot be replaced by manual monitoring, playing a crucial role in improving urban traffic congestion and maintaining traffic safety. However, the deployment planning of surveillance facilities largely determines the actual monitoring effect, and the existing deployment of surveillance facilities lacks unified standards, resulting in overly haphazard placement of monitoring points.

[0003] In such a vast road system, monitoring systems, as an electronic traffic management method, are safer, more convenient, and more economical than manual control, and have been widely used. The rational deployment of road monitoring facilities can maximize the control function of intelligent transportation systems while also saving materials and yielding significant social benefits. Existing urban road monitoring systems cannot meet the needs of urban traffic management, necessitating the construction, expansion, and optimization of these systems. In the past, the lack of specific and unified deployment standards and evaluation systems for road monitoring facilities hindered their effective operation. Summary of the Invention

[0004] To overcome the shortcomings of existing technologies, this invention proposes a multi-objective optimization method for the deployment of road traffic facilities that considers quantity constraints. The aim is to increase the deployment density of monitoring points in the road network, thereby achieving a comprehensive monitoring effect without blind spots and improving the deployment efficiency of road traffic monitoring.

[0005] To achieve the above-mentioned objectives, the present invention adopts the following technical solution:

[0006] The present invention provides a multi-objective optimization method for the layout of road traffic facilities considering quantity constraints, characterized by the following steps:

[0007] Step 1: Define the candidate point set as the intersections in the area to be monitored that have monitoring points installed; add the intersections in the area to be monitored that have pre-installed monitoring points to the candidate point set; select important intersections from the candidate point set and use the coordinate picker of the GIS platform to obtain the latitude and longitude data of the important intersections.

[0008] Let the interval between two adjacent time points be Δt, then the sequence number of any time interval is denoted as t;

[0009] Obtain the traffic volume M of any i-th candidate point in the candidate point set during the t-th time interval. i (t);

[0010] Obtain the number of traffic accidents V at the i-th candidate point during the t-th time interval. i (t);

[0011] Obtain the number of traffic violations S at the i-th candidate point during the t-th time interval. i (t); where i∈{1,2,…,N},t∈{1,2,…,T}; N represents the number of candidate points in the candidate point set; T represents the total number of time intervals;

[0012] Step 2: Calculate the average traffic volume, traffic accident volume, and traffic violation volume for each candidate location;

[0013] Step 2.1: Calculate the average traffic volume AFMT of the i-th candidate point during the t-th time interval according to equation (1). i ;

[0014]

[0015] Step 2.2: Calculate the average traffic accident volume (TAV) of the i-th candidate point during the t-th time interval according to equation (2). i ;

[0016]

[0017] Step 2.3: Calculate the average number of traffic violations (TVS) at the i-th candidate point during the t-th time interval according to formula (3). i ;

[0018]

[0019] Step 3: Construct the objective function for the constrained multi-objective problem;

[0020] Step 3.1: Calculate the traffic volume index value a after reverse processing of the i-th candidate point according to equation (4). 1i ;

[0021]

[0022] In equation (4), Max AFMT Min represents the maximum traffic volume of the candidate point set during the t-th time interval; AFMT This represents the minimum traffic volume of the candidate point set during the t-th time interval.

[0023] Step 3.2: Calculate the traffic accident occurrence index value a after reverse processing of the i-th candidate point according to formula (5). 2i ;

[0024]

[0025] In equation (5), Max TAV Min represents the maximum number of traffic accidents occurring in the candidate point set during the t-th time interval; TAV This represents the minimum number of traffic accidents occurring in the candidate point set during the t-th time interval.

[0026] Step 3.3: Calculate the traffic violation occurrence index value a of the i-th candidate point after reverse processing according to formula (6). 3i ;

[0027]

[0028] In equation (6), Max TVS Min represents the maximum number of traffic violations occurring in the candidate point set during the t-th time interval; TVS This represents the minimum number of traffic violations occurring in the candidate point set during the t-th time interval.

[0029] Step 3.4: Construct the factor function f1(X) for monitoring traffic volume according to equation (7);

[0030]

[0031] In equation (7), x i ∈{0,1} represents the selection status of the i-th candidate point; X represents the scheme of the number of monitoring points to be deployed.

[0032] Step 3.5: Construct a factor function f2(X) that can monitor the number of traffic accidents based on equation (8);

[0033]

[0034] Step 3.6: Construct a factor function f3(X) that can monitor the number of traffic violations based on equation (9);

[0035]

[0036] Step 3.7: Construct the objective function F(X) for the constrained multi-objective problem according to equation (10);

[0037]

[0038] In equation (10), C is the maximum number of cameras that can be installed;

[0039] Define X f To satisfy the f-th layout scheme of equation (10), i.e. Where f∈{0,1,…,P}; P represents the total number of layout schemes;

[0040] Step 4: Solve the objective function F(X) of the constrained multi-objective problem;

[0041] Step 4.1: Define variable m and distance variable d;

[0042] Step 4.2: Initialize f = 1, m = 0, d = +∞;

[0043] Step 4.3: Construct the z-th reference vector according to equation (11).

[0044]

[0045] In equation (11), H is a positive integer; Representing the z-th reference vector respectively The first, second, and third elements in the text; Let z represent the j-th element in the z-th reference vector; where z∈{0,1,…,P};

[0046] Step 4.4: According to equation (12), the z-th reference vector Transform into unit reference vector

[0047]

[0048] In equation (12), |||| is the symbol for the computational norm;

[0049] Step 4.5: Construct the target vector according to equation (13).

[0050]

[0051] In equation (13), f1(X) f ),f2(X f ),f3(X f Let f represent the first, second, and third elements of the f-th target vector, respectively.

[0052] Step 4.6: Calculate the target vector according to equation (14). and unit reference vector Angle between cosine value

[0053]

[0054] Step 4.7: Calculate the unit reference vector according to equation (15). Angle that forms the smallest included angle among other unit reference vectors

[0055]

[0056] In equation (15), Representation and vector Form the vector with the smallest included angle;

[0057] Step 4.8: Construct a formula about the angle based on equation (16). penalty function

[0058]

[0059] In equation (16), τ max τ represents the maximum preset algebra; τ represents the current preset algebra; α is a user-defined parameter.

[0060] Step 4.9: Calculate the angle penalty distance according to formula (17).

[0061]

[0062] Step 4.10, Judgment Does it satisfy equation (18)? If it does, then... If the value is assigned to d and f is assigned to m, then proceed to step 4.11; otherwise, proceed directly to step 4.11.

[0063]

[0064] Step 4.11: Determine if f≤P is true. If true, assign f+1 to f and return to step 4.8; otherwise, output the value of m.

[0065] Step 5, use the Xth... m One approach involves deploying monitoring points in the area to be monitored.

[0066] The present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store a program that supports the processor in executing the multi-objective layout optimization method for road traffic facilities, and the processor is configured to execute the program stored in the memory.

[0067] The present invention discloses a computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, performs the steps of the multi-objective layout optimization method for road traffic facilities.

[0068] Compared with existing technologies, the beneficial technical effects of this invention are reflected in:

[0069] 1. Under the condition of considering quantity constraints, this invention analyzes the indicators to be optimized for three candidate points: traffic congestion, traffic accident volume, and traffic violation volume; and constructs a multi-objective optimization objective function with constraints based on these three indicators, thereby improving the deployment density of monitoring points in the road network and achieving the task of area-wide blind spot control.

[0070] 2. This invention uses three indicators—traffic congestion, traffic accidents, and traffic violations—as the basis for monitoring points, avoiding the irrationality of using a single indicator as the basis for monitoring points. This is more in line with the principles of road monitoring facility deployment and improves the applicability of road traffic control facilities.

[0071] 3. Under the condition of quantity constraints, the present invention can install more monitoring points and cover a wider range. It can not only give full play to its law enforcement monitoring role, but also save a lot of traffic deployment materials. It plays an important role in improving urban traffic congestion and maintaining traffic safety, and has good social benefits. Attached Figure Description

[0072] Figure 1 This is the overall flowchart of the present invention;

[0073] Figure 2 This is a schematic diagram showing the area to be deployed in the GIS platform of this invention;

[0074] Figure 3 This is a flowchart of the objective function solution for this invention;

[0075] Figure 4 Distribution map of monitoring points for candidate sites in existing technology;

[0076] Figure 5 This is a distribution map of the monitoring points for the candidate points of this invention;

[0077] Figure 6 This is a distribution map of monitoring points optimized by the RVEA system of this invention. Detailed Implementation

[0078] In this embodiment, as Figure 1 As shown, a multi-objective layout optimization method for road traffic facilities considering quantity constraints includes the following steps:

[0079] Step 1: Define the candidate point set as the intersections in the area to be monitored that have monitoring points installed; add the intersections in the area to be monitored that have pre-installed monitoring points to the candidate point set; select important intersections from the candidate point set and use the coordinate picker of the GIS platform to obtain the latitude and longitude data of the important intersections.

[0080] Let the interval between two adjacent time points be Δt, then the sequence number of any time interval is denoted as t;

[0081] Obtain the traffic volume M of any i-th candidate point in the candidate point set during the t-th time interval. i (t);

[0082] Obtain the number of traffic accidents V at the i-th candidate point during the t-th time interval. i (t);

[0083] Obtain the number of traffic violations S at the i-th candidate point during the t-th time interval. i (t); where i∈{1,2,…,N},t∈{1,2,…,T}; N represents the number of candidate points in the candidate point set; T represents the total number of time intervals;

[0084] Step 2: Calculate the average traffic volume, traffic accident volume, and traffic violation volume for each candidate location;

[0085] Step 2.1: Calculate the average traffic volume AFMT of the i-th candidate point during the t-th time interval according to equation (1). i ;

[0086]

[0087] Step 2.2: Calculate the average traffic accident volume (TAV) of the i-th candidate point during the t-th time interval according to equation (2). i ;

[0088]

[0089] Step 2.3: Calculate the average number of traffic violations (TVS) at the i-th candidate point during the t-th time interval according to formula (3). i ;

[0090]

[0091] Step 3: Construct the objective function for the constrained multi-objective problem;

[0092] Step 3.1: Calculate the traffic volume index value a after reverse processing of the i-th candidate point according to equation (4). 1i ;

[0093]

[0094] In equation (4), Max AFMT Min represents the maximum traffic volume of the candidate point set during the t-th time interval; AFMT This represents the minimum traffic volume of the candidate point set during the t-th time interval.

[0095] The traffic flow data of the candidate points is processed as described above to obtain the sorted traffic flow data of the candidate points. Since the data may have different dimensions than other indicators, it needs to be dimensionless here; in order to ensure that the relative values ​​are the same as the other two indicators, it needs to be normalized; the optimization objective is to increase the monitorable traffic volume, and the optimization model is to minimize it, so the indicators need to be reversed here.

[0096] Step 3.2: Calculate the traffic accident occurrence index value a after reverse processing of the i-th candidate point according to formula (5). 2i ;

[0097]

[0098] In equation (5), Max TAV Min represents the maximum number of traffic accidents occurring in the candidate point set during the t-th time interval; TAV This represents the minimum number of traffic accidents occurring in the candidate point set during the t-th time interval.

[0099] The above processing is applied to the traffic accident occurrence data within a certain range of the candidate points to obtain the traffic accident occurrence data corresponding to the candidate points. Since the data may differ in dimension from other indicators, it needs to be dimensionless; to ensure that the relative values ​​are the same as the other two indicators, it needs to be normalized; and since the optimization objective is to increase the number of monitorable traffic accidents, the optimization model is to minimize it, so the indicators need to be reversed.

[0100] Step 3.3: Calculate the traffic violation occurrence index value a of the i-th candidate point after reverse processing according to formula (6). 3i ;

[0101]

[0102] In equation (6), Max TVS Min represents the maximum number of traffic violations occurring in the candidate point set during the t-th time interval; TVS This represents the minimum number of traffic violations occurring in the candidate point set during the t-th time interval.

[0103] The above processing is applied to the traffic violation data within a certain range of the candidate points to obtain the traffic violation data corresponding to the candidate points. Since the data may differ in dimension from other indicators, it needs to be dimensionless; to ensure that the relative values ​​are the same as the other two indicators, it needs to be normalized; and since the optimization objective is to increase the number of monitorable traffic violations, the optimization model is to minimize it, so the indicators need to be reversed.

[0104] Step 3.4: Construct the factor function f1(X) for monitoring traffic volume according to equation (7);

[0105]

[0106] In equation (7), x i ∈{0,1} represents the selection status of the i-th candidate point; X represents the scheme for deploying monitoring points;

[0107] Step 3.5: Construct a factor function f2(X) that can monitor the number of traffic accidents based on equation (8);

[0108]

[0109] Step 3.6: Construct a factor function f3(X) that can monitor the number of traffic violations based on equation (9);

[0110]

[0111] Step 3.7: Construct the objective function F(X) for the constrained multi-objective problem according to equation (10);

[0112]

[0113] In equation (10), C is the maximum number of cameras that can be installed;

[0114] Define X f To satisfy the f-th layout scheme of equation (10), i.e. Where f∈{0,1,…,P}; P represents the total number of layout schemes;

[0115] Step 4: Solve the objective function F(X) of the constrained multi-objective problem;

[0116] Step 4.1: Define variable m and distance variable d;

[0117] Step 4.2: Initialize f = 1, m = 0, d = +∞;

[0118] Step 4.3: Construct the z-th reference vector according to equation (11).

[0119]

[0120] In equation (11), H is a positive integer; Representing the z-th reference vector respectively The first element, the second element, and the third element; Let z represent the j-th element in the z-th reference vector; where z∈{0,1,…,P};

[0121] Step 4.4: According to equation (12), the z-th reference vector Transform into unit reference vector

[0122]

[0123] In equation (12), |||| is the symbol for the computational norm;

[0124] Step 4.5: Construct the target vector according to equation (13).

[0125]

[0126] In equation (13), f1(X) f ),f2(X f ),f3(X f Let f represent the first, second, and third elements of the f-th target vector, respectively.

[0127] Step 4.6: Calculate the target vector according to equation (14). and unit reference vector Angle between cosine value

[0128]

[0129] Step 4.7: Calculate the unit reference vector according to equation (15). Angle that forms the smallest included angle among other unit reference vectors

[0130]

[0131] In equation (15), Representation and vector Form the vector with the smallest included angle;

[0132] Step 4.8: Construct a formula about the angle based on equation (16). penalty function

[0133]

[0134] In equation (16), τ max τ represents the maximum preset algebra; τ represents the current preset algebra; α is a user-defined parameter.

[0135] Step 4.9: Calculate the angle penalty distance according to formula (17).

[0136]

[0137] Step 4.10, Judgment Does it satisfy equation (18)? If it does, then... If the value is assigned to d and f is assigned to m, then proceed to step 4.11; otherwise, proceed directly to step 4.11.

[0138]

[0139] Step 4.11: Determine if f≤P is true. If true, assign f+1 to f and return to step 4.8; otherwise, output the value of m.

[0140] Step 5, use the Xth... m One approach involves deploying monitoring points in the area to be monitored.

[0141] In this embodiment, an electronic device includes a memory and a processor. The memory is used to store a program that supports the processor in executing the above-described multi-objective layout optimization method for road traffic facilities. The processor is configured to execute the program stored in the memory.

[0142] In this embodiment, a computer-readable storage medium stores a computer program, which, when run by a processor, executes the steps of the above-described multi-objective layout optimization method for road traffic facilities.

[0143] like Figure 2As shown, the geographical scope of the experimental area selected in this embodiment is a rectangular area bounded by Ludang Road to the north, Tiyu Road to the south, Songling Avenue to the west, extending to the shore of Taihu Lake in Wujiang District, Suzhou City. The latitude and longitude range of the rectangular area selected for the experimental area is as follows: minimum coordinates: longitude 120.57756900787354, latitude 31.11551284790039; maximum coordinates: longitude 120.63700675964355, latitude 31.14997386932373 (decimal degrees). In Excel, the original monitoring points, traffic violation datasets, traffic accident datasets, and intersection traffic volume datasets were filtered according to the latitude and longitude of the experimental area to obtain four datasets: the original monitoring point dataset, the experimental area traffic violation data, the experimental area traffic accident data, and the experimental area traffic volume data. The number of candidate points selected in this case is 43, therefore, the total funding constraint is set to 30c for calculation.

[0144] like Figure 3 The flowchart shown is a flowchart of this algorithm.

[0145] The known solution algorithm is RVEA. The problem to be solved is to optimize the design of 43 candidate monitoring points in the experimental area to achieve the optimization goals of increasing the amount of traffic that can be monitored, the number of traffic accidents, and the number of traffic violations, while considering the financial constraints.

[0146] The point selection scheme in the solution set is analyzed. A value of 1 for a candidate point indicates that the point is selected as a monitoring point, while a value of 0 indicates that the point is not selected. The final point selection scheme from the solution set is then imported into the GIS platform. Using the "WGS 1984" coordinate system as the geographic coordinate system, the monitoring point distribution map is obtained as follows: Figure 4 The image shown is a map showing the original distribution of monitoring points; as follows: Figure 5 The image shows the distribution map of the candidate monitoring points; as shown... Figure 6 The image shows the distribution of monitoring points after RVEA optimization.

Claims

1. A method for multi-objective optimization of road traffic facilities layout considering quantity constraints, characterized in that, Includes the following steps: Step 1: Define the candidate point set as the intersections in the area to be monitored that have monitoring points installed; add the intersections in the area to be monitored that have pre-installed monitoring points to the candidate point set; select important intersections from the candidate point set and use the coordinate picker of the GIS platform to obtain the latitude and longitude data of the important intersections. Let the interval between two adjacent times be The serial number of any time interval is denoted as t; acquiring traffic volume of any i-th candidate point in the candidate point set in a t-th time interval ; Obtain the number of traffic accidents occurring at the i-th candidate point during the t-th time interval. ; Get the number of traffic violations occurring at the i-th candidate point during the t-th time interval. ;in, , ; This indicates the number of candidate points in the candidate point set; Indicates the total number of time intervals; Step 2: Calculate the average traffic volume, traffic accident volume, and traffic violation volume for each candidate location; Step 2.1: Calculate the average traffic volume of the i-th candidate point during the t-th time interval according to equation (1). ; (1) Step 2.2: Calculate the average number of traffic accidents occurring at the i-th candidate point during the t-th time interval according to equation (2). ; (2) Step 2.3: Calculate the average number of traffic violations occurring at the i-th candidate point during the t-th time interval according to formula (3). ; (3) Step 3: Construct the objective function for the constrained multi-objective problem; Step 3.1: Calculate the traffic volume index value of the i-th candidate point after reverse processing according to equation (4). ; (4) In equation (4), This represents the maximum traffic volume of the candidate point set during the t-th time interval; This represents the minimum traffic volume of the candidate point set during the t-th time interval. Step 3.2: Calculate the traffic accident occurrence index value of the i-th candidate point after reverse processing according to formula (5). ; (5) In equation (5), This represents the maximum number of traffic accidents occurring in the candidate point set during the t-th time interval. This represents the minimum number of traffic accidents occurring in the candidate point set during the t-th time interval. Step 3.3: Calculate the traffic violation occurrence index value of the i-th candidate point after reverse processing according to formula (6). ; (6) In equation (6), This represents the maximum number of traffic violations occurring in the candidate point set during the t-th time interval; This represents the minimum number of traffic violations occurring in the candidate point set during the t-th time interval. Step 3.4: Construct a factor function for monitoring traffic volume based on equation (7). ; (7) In equation (7), This indicates the selection status of the i-th candidate point; The plan indicates the number of monitoring points that need to be deployed. Step 3.5: Construct a factor function to monitor the number of traffic accidents based on equation (8). ; (8) Step 3.6: Construct a factor function that can monitor the number of traffic violations based on equation (9). ; (9) Step 3.7: Construct the objective function of the constrained multi-objective problem according to equation (10). ; (10) In equation (10), C is the maximum number of cameras that can be installed; definition To satisfy the f-th layout scheme of equation (10), i.e. ,in P represents the total number of deployment schemes; Step 4: Construct the objective function for the constrained multi-objective problem. Solve the problem; Step 4.1: Define variable m and distance variable d; Step 4.2: Initialize f=1, m=0. ; Step 4.3: Construct the first equation according to formula (11). reference vectors ; (11) In equation (11), H is a positive integer; They represent the first reference vectors The first, second, and third elements in the text; Indicates the first The j-th element in the reference vectors; where, ; Step 4.4: According to equation (12), the first... reference vectors Transform into unit reference vector ; (12) In equation (12), It is the symbol for the computational norm; Step 4.5: Construct the target vector according to equation (13). ; (13) In equation (13), These represent the first, second, and third elements in the f-th target vector, respectively. Step 4.6: Calculate the target vector according to equation (14). and unit reference vector Angle between cosine value ; (14) Step 4.7: Calculate the unit reference vector according to equation (15). Angle that forms the smallest included angle among other unit reference vectors ; (15) In equation (15), Representation and vector Form the vector with the smallest included angle; Step 4.8: Construct a formula about the angle based on equation (16). penalty function : (16) In equation (16), Represents the largest preset algebra; This represents the current preset algebra; These are custom parameters; Step 4.9: Calculate the angle penalty distance according to formula (17). ; (17) Step 4.10, Judgment Does it satisfy equation (18)? If it does, then... If the value is assigned to d and f is assigned to m, then proceed to step 4.11; otherwise, proceed directly to step 4.

11. (18) Step 4.11, Judgment Check if the condition is true. If true, assign f+1 to f and return to step 4.8; otherwise, output the value of m. Step 5, adopt the first One approach involves deploying monitoring points in the area to be monitored.

2. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store programs that support the processor in executing the multi-objective layout optimization method for road traffic facilities as described in claim 1, and the processor is configured to execute the programs stored in the memory.

3. A computer-readable storage medium storing a computer program, characterized in that, The computer program, when run by the processor, executes the steps of the multi-objective layout optimization method for road traffic facilities as described in claim 1.

Images