A system and method for optimizing urban and rural traffic planning based on big data

Abstract

The invention relates to the technical field of traffic management, in particular to a system and method for optimizing urban and rural traffic planning based on big data. The system comprises an urban and rural traffic sub-section division module, a real-time traffic flow data collection module, a first traffic flow threshold data matrix setting module, a congestion state determination module, a historical data collection module and a congestion degree determination module. The real-time traffic flow of each urban and rural traffic sub-section obtained by collection is compared with a set traffic flow threshold to determine whether the urban and rural traffic sub-section is in a congested state, and the congestion degree of the urban and rural traffic sub-section in a congested state is determined according to historical data, thereby avoiding waste of traffic resources and realizing reasonable management of urban and rural traffic. The urban and rural traffic planning scheme is optimized by a frog leaping algorithm, simulating the behavior of frogs jumping in a wetland and searching for food, constructing a mathematical model, ensuring the accuracy of the optimization result, and improving the speed and efficiency of the optimization process.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and in particular to an urban and rural traffic planning optimization system and method based on big data. Background Art

[0002] With the rapid development of the national economy, the connection between cities and villages has become increasingly close, and it has become urgent to promote the development of urban-rural integration. Among them, the development of urban and rural transportation has gradually been paid attention to.

[0003] Urban and rural transportation planning is to collect current urban and rural transportation data, analyze and process it, find the shortcomings of urban and rural transportation in the actual process, and formulate the most reasonable urban and rural transportation planning scheme based on existing conditions.

[0004] The Chinese patent application with publication number CN110837904A introduces a traffic planning control system and method, which obtains the vehicle traffic conditions at each traffic intersection in the area by counting the vehicle traffic conditions on each street in the area and planning the routes, and then determines the signal light phase green signal ratio at each traffic intersection according to the vehicle traffic conditions. When special circumstances occur, the traffic flow that the street should bear is allocated to other streets according to the vehicle traffic conditions, so as to realize the planning and control of the traffic flow in the entire area. The upper limit of the traffic flow that each street can bear is not taken into consideration, and no specific solution is given when special circumstances occur.

[0005] In the existing technology, urban and rural traffic planning is often carried out by manually collecting traffic data, but the labor cost is too high, and it is difficult to avoid the error caused by obtaining data. Alternatively, the collected traffic data is analyzed using machine learning methods to achieve specific urban and rural traffic planning, but there is a lack of consideration for the development between urban and rural areas. As time goes by, it is easy to cause excessive waste of traffic resources. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In order to address the shortcomings of the background technology, the present invention proposes an urban and rural traffic planning optimization system and method based on big data. By comparing the real-time traffic flow of each urban and rural traffic sub-section collected with the set traffic flow threshold, it is determined whether the urban and rural traffic sub-section is in a congested state. At the same time, the congestion degree of the urban and rural traffic sub-section in a congested state is determined according to historical data, so as to achieve reasonable management of urban and rural traffic.

[0008] (II) Technical solution

[0009] A method for optimizing urban and rural transportation planning based on big data, the method comprising the following steps:

[0010] S1. Set an urban-rural traffic road set and an urban-rural traffic road intersection set, and divide each urban-rural traffic road in the urban-rural traffic road set according to the urban-rural traffic road intersection set to obtain an urban-rural traffic sub-section set;

[0011] S2, setting a traffic flow unit collection period, collecting the traffic flow within the unit period of each urban and rural traffic sub-section in the urban and rural traffic sub-section matrix in real time through the sensing device, and obtaining a first real-time traffic flow data matrix;

[0012] S3, setting a section traffic flow threshold for each urban and rural traffic sub-section in the urban and rural traffic sub-section matrix by using an intelligent optimization algorithm to obtain a first traffic flow threshold data matrix;

[0013] S4, comparing the corresponding values ​​of the same urban-rural traffic sub-section in the first traffic flow threshold data matrix and the first real-time traffic flow data matrix, to determine whether the urban-rural traffic sub-section is in a congested state;

[0014] S5, setting a traffic flow cycle set, collecting the traffic flow of urban and rural traffic sub-sections in a congested state in historical data according to the traffic flow cycle set, obtaining a first historical traffic flow set, and collecting the vehicle data of traffic accidents in the first historical traffic flow set, to establish a first historical traffic accident vehicle set;

[0015] S6. Determine the congestion degree of the urban and rural traffic sub-sections that are in a congested state, and issue corresponding instructions according to the determination result.

[0016] By dividing each urban and rural traffic road according to the set of urban and rural traffic road intersections to obtain an urban and rural traffic sub-section set, and collecting real-time traffic flow data in real time through sensing equipment, a data basis is provided for subsequent operations; by comparing the corresponding values ​​of the same urban and rural traffic sub-section in the first traffic flow threshold data matrix and the first real-time traffic flow data matrix, it is determined whether the urban and rural traffic sub-section is in a congested state, thereby ensuring the accuracy of the determination result; by collecting historical data, the historical traffic accident rate of the urban and rural traffic sub-section in a congested state is calculated, thereby ensuring the accuracy of the calculation result; according to the numerical values ​​of the historical traffic accident rate and the traffic congestion ratio, the congestion degree of the urban and rural traffic sub-section is determined, and corresponding instructions are issued to avoid unnecessary waste of traffic resources and realize the reasonable management of urban and rural traffic;

[0017] Preferably, the specific steps of setting an urban-rural traffic road set and an urban-rural traffic road intersection set, dividing each urban-rural traffic road in the urban-rural traffic road set according to the urban-rural traffic road intersection set, and obtaining the urban-rural traffic sub-section set are as follows:

[0018] S11. Set up urban and rural traffic road sets ,in, represents the ith urban-rural traffic road, and k represents the total number of urban-rural traffic roads;

[0019] S12. Set up the intersection set of urban and rural traffic roads ,in, represents the total number of intersections in the i-th urban and rural traffic road;

[0020] S13, based on the urban and rural traffic road intersection Urban and rural traffic road collection The urban and rural traffic roads in are divided into the following sets B of urban and rural traffic sub-sections:

[0021]

[0022] in, Represents the jth urban-rural traffic sub-section in the i-th urban-rural traffic road.

[0023] According to the set of urban and rural traffic road intersections, each urban and rural traffic road is divided into an urban and rural traffic sub-section set, which provides a data basis for subsequent operations.

[0024] Preferably, the specific steps of setting a traffic flow unit collection period, collecting the traffic flow within the unit period of each urban and rural traffic sub-section in the urban and rural traffic sub-section concentration in real time through the sensing device, and obtaining the first real-time traffic flow data matrix are as follows:

[0025] S21, set a traffic flow unit collection period, collect the traffic flow in each urban and rural traffic sub-section unit period in the urban and rural traffic sub-section matrix B in real time through the sensing device, and obtain the first real-time traffic flow data matrix C as follows:

[0026]

[0027] in, Indicates i The first of the urban and rural traffic roads j The total number of vehicles passing through each urban and rural traffic sub-section within a unit cycle; k It is the urban-rural traffic road dimension, indicating the total number of urban-rural traffic roads; is the dimension of the urban and rural traffic sub-section, indicating the i There are 1,000 urban and rural traffic roads. Urban and rural traffic sub-sections, Indicates k The first of the urban and rural traffic roads The total number of vehicles passing through the urban-rural traffic sub-section in a unit cycle. If the dimension of the urban-rural traffic sub-section in a row is less than that of other rows, it is set to 0 to fill the gap.

[0028] Through perception and recognition, the traffic flow of each urban and rural traffic sub-section within a unit cycle is collected in real time, ensuring the accuracy of the collected data.

[0029] Preferably, the specific steps of setting the section traffic flow threshold for each urban-rural traffic sub-section in the urban-rural traffic sub-section matrix by an intelligent optimization algorithm to obtain the first traffic flow threshold data matrix are as follows:

[0030] S31. Construct a fireworks population, set the population size to N, and the maximum number of iterations to , the maximum number of explosion sparks is , the minimum number of explosion sparks is And the initial position set of the fireworks population , represents the initial position of the i-th firework individual;

[0031] S32, calculating the fitness function value of each firework individual in the firework population; the fitness function value calculation formula is as follows:

[0032]

[0033] in, represents the fitness function value of the i-th firework individual, represents the ability of the i-th firework individual to accept traffic flow under normal conditions, Indicates the correction value;

[0034] S33, perform explosion operation according to the fitness function value of each firework individual, and the explosion radius of each firework individual explosion and explosion spark number Will be affected by other fireworks in the firework population; explosion radius and explosion spark number The calculation formula is as follows:

[0035]

[0036] Among them, P represents the random constant for adjusting the explosion radius, Q represents the random constant for adjusting the number of explosion sparks, and They represent the minimum and maximum values ​​of the fitness function of each firework individual in the firework population, respectively. Represents a very small random number;

[0037] During the explosion operation, the number of explosion sparks generated is controlled; the control formula is as follows:

[0038]

[0039] in, Indicates the number of explosion sparks after control;

[0040] The explosion formula for the explosion operation of individual fireworks is as follows:

[0041]

[0042] in, Indicates the position of the jth explosion spark generated by the i-th firework;

[0043] S34. Perform a Gaussian mutation operation on each individual firework in the firework population. The Gaussian mutation formula is as follows:

[0044]

[0045] Among them, g(1,1) represents a Gaussian distribution with a mean of 1 and a variance of 1;

[0046] S35, merging all fireworks individuals, spark individuals generated after the explosion, and Gaussian mutation spark individuals into a population, calculating the fitness function values ​​of all individuals in the population, retaining the individual with the largest fitness function value to join the next generation of fireworks population, and selecting N-1 individuals from the remaining individuals by roulette to join the next generation of fireworks population, to obtain a new fireworks population;

[0047] S36: Determine whether the maximum number of iterations has been reached If not, return to S33; if reached, take the fireworks individual with the largest fitness function value in the current fireworks population as the current global optimal solution, output the traffic flow thresholds of each urban and rural traffic sub-section, and obtain the first traffic flow threshold matrix F as follows:

[0048]

[0049] in, represents the traffic flow threshold of the jth urban-rural traffic sub-section in the i-th urban-rural traffic road, k It is the urban-rural traffic road dimension, indicating the total number of urban-rural traffic roads; is the dimension of the urban and rural traffic sub-section, indicating the i There are 1,000 urban and rural traffic roads. Urban and rural traffic sub-sections, Indicates k The first of the urban and rural traffic roads The traffic flow threshold of the urban-rural traffic sub-segment. If the dimension of the urban-rural traffic sub-segment in a row is less than that of other rows, it is set to 0 to fill the gap.

[0050] Compared with manually collecting data for calculation and analysis and setting the corresponding traffic flow threshold, setting the first traffic flow threshold data matrix through the fireworks algorithm can not only avoid unnecessary human resource consumption, but also simulate the process of fireworks explosion to construct a mathematical model, which can effectively prevent falling into local optimality, ensure the accuracy of the set results, and speed up the convergence process.

[0051] Preferably, the specific steps of comparing the corresponding values ​​of the same urban-rural traffic sub-section in the first traffic flow threshold data matrix and the first real-time traffic flow data matrix to determine whether the urban-rural traffic sub-section is in a congested state are as follows:

[0052] S41, comparing the traffic flow threshold value per unit cycle of the jth urban-rural traffic sub-section in the ith urban-rural traffic road in the first traffic flow threshold value data matrix F The total number of vehicles passing through the jth urban-rural traffic sub-section in the i-th urban-rural traffic road in the first real-time traffic flow data matrix C within a unit cycle The numerical value of

[0053] like , it is determined that the urban-rural traffic sub-section is in a normal state;

[0054] like , it is determined that the urban-rural traffic sub-section is in a congested state, the determination result is fed back to the main control unit and an early warning is issued.

[0055] By comparing the corresponding values ​​of the same urban-rural traffic sub-section in the first traffic flow threshold data matrix and the first real-time traffic flow data matrix, it is determined whether the urban-rural traffic sub-section is in a congested state, thereby ensuring the accuracy of the determination result.

[0056] Preferably, a traffic flow cycle set is set, and the traffic flow of urban and rural traffic sub-sections in a congested state in historical data is collected according to the traffic flow cycle set to obtain a first historical traffic flow set, and the vehicle data of traffic accidents in the first historical traffic flow set are collected. The specific steps of establishing the first historical traffic accident vehicle set are as follows:

[0057] S51. Setting traffic flow cycle set ,in represents the i-th traffic flow period, Indicates the total number of traffic flow cycles;

[0058] S52, according to the traffic flow cycle set Collect the traffic flow of urban and rural traffic sub-sections in congestion in historical data to obtain the first historical traffic flow set ,in represents the total number of vehicles that pass through the urban-rural traffic sub-section in the i-th traffic flow cycle before the congestion occurs;

[0059] S53: Collect the first historical traffic flow set The vehicle data of traffic accidents in the first historical traffic accident vehicle dataset is established. ,in, represents the i-th vehicle involved in a traffic accident in the first historical traffic flow set, Indicates the total number of vehicles involved in traffic accidents in the first historical traffic flow set;

[0060] S54. Calculate the historical traffic accident rate of urban and rural traffic sub-sections in congestion .

[0061] According to the traffic flow cycle set, the traffic flow of urban and rural traffic sub-sections in congested state and the vehicle data of traffic accidents in historical data are collected, and the historical traffic accident rate of urban and rural traffic sub-sections in congested state is calculated to ensure the reliability of the calculation results and provide a data basis for subsequent operations.

[0062] Preferably, the specific steps of determining the congestion degree of the urban-rural traffic sub-section in a congested state and issuing a corresponding instruction according to the determination result are as follows:

[0063] S61, compare the traffic flow threshold corresponding to the urban-rural traffic sub-section in the congested state in the first traffic flow threshold data matrix with the numerical values ​​of each historical traffic flow in the first historical traffic flow set, record the number v of historical traffic flows greater than the traffic flow threshold in the first historical traffic flow set, and calculate the traffic congestion ratio of the urban-rural traffic sub-section in the congested state ;

[0064] S62, setting the low congestion threshold to , the high congestion threshold is and traffic accident rate threshold , determine the congestion degree of the urban and rural traffic sub-sections in a congested state;

[0065] S621, when , it is determined that the urban-rural traffic sub-section is in a lightly congested state, and a temporary road clearing instruction is issued through the main control unit according to the determination result;

[0066] S622, when and , it is determined that the urban-rural traffic sub-section is in a moderate congestion degree, and according to the determination result, the main control unit adjusts the duration of the traffic lights at each urban-rural traffic road intersection on the urban-rural traffic road where the urban-rural traffic sub-section is located, and re-determines whether the urban-rural traffic sub-section is in a congested state. If it is not in a congested state, the operation is terminated; if it is still in a congested state, the congestion degree of the urban-rural traffic sub-section is determined to be a severe congestion degree;

[0067] S623, when and or , it is determined that the urban-rural traffic sub-section is in a severe congestion level, and the current urban-rural traffic planning scheme is optimized through the main control unit according to the determination result;

[0068] S6231, build a frog population, set the maximum number of iterations to , the population size is M,

[0069] S6232, randomly dividing the frog population into m frog subgroups, each frog subgroup contains n frog individuals, calculating the fitness function values ​​of all frog individuals, and recording the position of the frog individual with the largest fitness function value in the frog population as ; The fitness function formula is as follows:

[0070]

[0071] in, represents the fitness function value of the i-th frog individual, represents the ability of the i-th frog individual to solve the congestion of urban and rural traffic sub-sections, and q represents the correction value;

[0072] S6233. According to the value of the fitness function, the optimal individual frog position in the i-th frog subgroup is recorded as , the worst frog individual position is recorded as , update the position of the worst frog individual in the frog subgroup according to the moving step length D from the worst frog individual to the best frog individual; the position update formula is as follows:

[0073]

[0074] Among them, rand represents a random number between (0,1), represents the updated position of the worst frog individual in the i-th frog subgroup;

[0075] S6234, calculate the fitness function value of the worst frog individual after the update. If the fitness function value of the worst frog individual after the update is higher than the fitness function value of the original worst frog individual, replace the original worst frog individual with the updated worst frog individual; otherwise, replace the original worst frog individual with the updated worst frog individual. replace Re-update the position of the worst frog individual;

[0076] S6235, calculating the fitness function value of the worst frog individual after the update, if the fitness function value of the worst frog individual after the update is higher than the fitness function value of the original worst frog individual, then the updated worst frog individual replaces the original worst frog individual; otherwise, then randomly generating a position in the search space to replace the original worst frog position;

[0077] S6236, merging all frog subgroups into a new frog population, calculating the fitness function values ​​of all frog individuals, and taking the frog individual with the largest fitness function value as the current global optimal solution;

[0078] S6237, determine whether the maximum number of iterations has been reached If not, return to S6232; if reached, output the current global optimal solution to obtain the optimized urban and rural transportation planning scheme.

[0079] According to the numerical values ​​of the historical traffic accident rate and the traffic congestion ratio, the congestion degree of the urban and rural traffic sub-sections is determined, and corresponding instructions are issued to avoid unnecessary waste of traffic resources and realize the reasonable management of urban and rural traffic. Compared with the traditional method of analyzing the collected data through machine learning methods to optimize the existing urban and rural traffic planning schemes, the present invention optimizes the urban and rural traffic planning schemes through the frog leaping algorithm, which not only takes into account the development of urban and rural traffic, but also reduces the amount of calculation and improves the convergence speed. A mathematical model is constructed according to the optimization behavior of three frogs for optimization to avoid falling into the problem of local optimal solutions.

[0080] The present invention also discloses an urban and rural traffic planning optimization system based on big data, including an urban and rural traffic sub-section division module, a real-time traffic flow data acquisition module, a first traffic flow threshold data matrix setting module, a congestion state determination module, a historical data collection module and a congestion degree determination module;

[0081] The urban-rural traffic sub-section division module divides each urban-rural traffic road in the urban-rural traffic road set through the urban-rural traffic road intersection set to obtain the urban-rural traffic sub-section set;

[0082] The real-time traffic flow data collection module collects the traffic flow in a unit period of each urban and rural traffic sub-section in the urban and rural traffic sub-section set in real time through a sensing device to obtain a first real-time traffic flow data matrix;

[0083] The first traffic flow threshold data matrix setting module finds the traffic flow threshold of each urban and rural traffic sub-section through a fireworks algorithm to obtain a first traffic flow threshold matrix;

[0084] The congestion state determination module determines whether the urban-rural traffic sub-section is in a congested state by comparing the corresponding values ​​of the same urban-rural traffic sub-section in the first traffic flow threshold data matrix and the first real-time traffic flow data matrix;

[0085] The historical data collection module collects the traffic flow of the urban and rural traffic sub-sections in a congested state and the vehicle data of traffic accidents in the historical data according to the traffic flow cycle set, and calculates the historical traffic accident rate of the urban and rural traffic sub-sections in a congested state;

[0086] The congestion level determination module determines the congestion level of the urban and rural traffic sub-section in a congested state according to the numerical values ​​of the historical traffic accident rate and the traffic congestion ratio, and issues corresponding instructions according to the determination result.

[0087] (III) Beneficial effects

[0088] 1. The present invention obtains a set of urban and rural traffic sub-sections by dividing each urban and rural traffic road, and collects real-time traffic flow data in real time through sensing equipment to provide a data basis for subsequent operations; by comparing the traffic flow threshold value of the same urban and rural traffic sub-section with the real-time traffic flow, it is determined whether the urban and rural traffic sub-section is in a congested state, thereby ensuring the accuracy of the determination result; by collecting historical data, the historical traffic accident rate of the urban and rural traffic sub-section in a congested state is calculated, thereby ensuring the accuracy of the calculation result; according to the numerical value of the historical traffic accident rate and the traffic congestion ratio, the congestion degree of the urban and rural traffic sub-section is determined, and corresponding instructions are issued to avoid unnecessary waste of traffic resources and realize the reasonable management of urban and rural traffic;

[0089] 2. Compared with manually collecting data for calculation and analysis and setting the corresponding traffic flow threshold, setting the first traffic flow threshold data matrix through the fireworks algorithm can not only avoid unnecessary human resource consumption, but also simulate the process of fireworks explosion to build a mathematical model, which can effectively prevent falling into the local optimum, ensure the accuracy of the setting results, and speed up the convergence process;

[0090] 3. Compared with the traditional method of analyzing the collected data through machine learning methods to optimize the existing urban and rural traffic planning schemes, the present invention optimizes the urban and rural traffic planning schemes through the frog leaping algorithm, which not only takes into account the development of urban and rural traffic, but also reduces the amount of calculation and improves the convergence speed. It also constructs a mathematical model based on the optimization behavior of three frogs for optimization, avoiding falling into the problem of local optimal solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0092] Figure 1 A flowchart of an urban and rural transportation planning optimization method based on big data provided by the present invention;

[0093] Figure 2 A module schematic diagram of an urban and rural transportation planning optimization system based on big data provided by the present invention. DETAILED DESCRIPTION

[0094] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0095] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0096] The first embodiment of the urban and rural traffic planning optimization system and method based on big data is as follows:

[0097] See also Figure 1 , an urban and rural transportation planning optimization method based on big data, the method comprises the following steps:

[0098] S1. Set an urban-rural traffic road set and an urban-rural traffic road intersection set, and divide each urban-rural traffic road in the urban-rural traffic road set according to the urban-rural traffic road intersection set to obtain an urban-rural traffic sub-section set;

[0099] S11. Set up urban and rural traffic road sets ,in, represents the ith urban-rural traffic road, and k represents the total number of urban-rural traffic roads;

[0100] S12. Set up the intersection set of urban and rural traffic roads ,in, represents the total number of intersections in the i-th urban and rural traffic road;

[0101] S13, based on the urban and rural traffic road intersection Urban and rural traffic road collection The urban and rural traffic roads in are divided into the following sets B of urban and rural traffic sub-sections:

[0102]

[0103] in, Represents the jth urban-rural traffic sub-section in the i-th urban-rural traffic road.

[0104] S2, setting a traffic flow unit collection period, collecting the traffic flow within the unit period of each urban and rural traffic sub-section in the urban and rural traffic sub-section matrix in real time through the sensing device, and obtaining a first real-time traffic flow data matrix;

[0105] S21, set a traffic flow unit collection period, collect the traffic flow in each urban and rural traffic sub-section unit period in the urban and rural traffic sub-section matrix B in real time through the sensing device, and obtain the first real-time traffic flow data matrix C as follows:

[0106]

[0107] in, Indicates i The first of the urban and rural traffic roads j The total number of vehicles passing through each urban and rural traffic sub-section within a unit cycle; k It is the urban-rural traffic road dimension, indicating the total number of urban-rural traffic roads; is the dimension of the urban and rural traffic sub-section, indicating the i There are 1,000 urban and rural traffic roads. Urban and rural traffic sub-sections, Indicates k The first of the urban and rural traffic roads The total number of vehicles passing through the urban-rural traffic sub-section in a unit cycle. If the dimension of the urban-rural traffic sub-section in a row is less than that of other rows, it is set to 0 to fill the gap.

[0108] S3, setting a section traffic flow threshold for each urban and rural traffic sub-section in the urban and rural traffic sub-section matrix by using an intelligent optimization algorithm to obtain a first traffic flow threshold data matrix;

[0109] S31. Construct a fireworks population, set the population size to N, and the maximum number of iterations to , the maximum number of explosion sparks is , the minimum number of explosion sparks is And the initial position set of the fireworks population , represents the initial position of the i-th firework individual;

[0110] S32, calculating the fitness function value of each firework individual in the firework population; the fitness function value calculation formula is as follows:

[0111]

[0112] in, represents the fitness function value of the i-th firework individual, represents the ability of the i-th firework individual to accept traffic flow under normal conditions, Indicates the correction value;

[0113] S33, perform explosion operation according to the fitness function value of each firework individual, and the explosion radius of each firework individual explosion and explosion spark number Will be affected by other fireworks in the firework population; explosion radius and explosion spark number The calculation formula is as follows:

[0114]

[0115] Among them, P represents the random constant for adjusting the explosion radius, Q represents the random constant for adjusting the number of explosion sparks, and They represent the minimum and maximum values ​​of the fitness function of each firework individual in the firework population, respectively. Represents a very small random number;

[0116] During the explosion operation, the number of explosion sparks generated is controlled; the control formula is as follows:

[0117]

[0118] in, Indicates the number of explosion sparks after control;

[0119] The explosion formula for the explosion operation of individual fireworks is as follows:

[0120]

[0121] in, Indicates the position of the jth explosion spark generated by the i-th firework;

[0122] S34. Perform a Gaussian mutation operation on each individual firework in the firework population. The Gaussian mutation formula is as follows:

[0123]

[0124] Among them, g(1,1) represents a Gaussian distribution with a mean of 1 and a variance of 1;

[0125] S35, merging all fireworks individuals, spark individuals generated after the explosion, and Gaussian mutation spark individuals into a population, calculating the fitness function values ​​of all individuals in the population, retaining the individual with the largest fitness function value to join the next generation of fireworks population, and selecting N-1 individuals from the remaining individuals by roulette to join the next generation of fireworks population, to obtain a new fireworks population;

[0126] S36: Determine whether the maximum number of iterations has been reached If not, return to S33; if reached, take the fireworks individual with the largest fitness function value in the current fireworks population as the current global optimal solution, output the traffic flow thresholds of each urban and rural traffic sub-section, and obtain the first traffic flow threshold matrix F as follows:

[0127]

[0128] in, represents the traffic flow threshold of the jth urban-rural traffic sub-section in the i-th urban-rural traffic road, k It is the urban-rural traffic road dimension, indicating the total number of urban-rural traffic roads; is the dimension of the urban and rural traffic sub-section, indicating the i There are 1,000 urban and rural traffic roads. Urban and rural traffic sub-sections, Indicates k The first of the urban and rural traffic roads The traffic flow threshold of the urban-rural traffic sub-segment. If the dimension of the urban-rural traffic sub-segment in a row is less than that of other rows, it is set to 0 to fill the gap.

[0129] S4, comparing the corresponding values ​​of the same urban-rural traffic sub-section in the first traffic flow threshold data matrix and the first real-time traffic flow data matrix, to determine whether the urban-rural traffic sub-section is in a congested state;

[0130] S41, comparing the traffic flow threshold value per unit cycle of the jth urban-rural traffic sub-section in the ith urban-rural traffic road in the first traffic flow threshold value data matrix F The total number of vehicles passing through the jth urban-rural traffic sub-section in the i-th urban-rural traffic road in the first real-time traffic flow data matrix C within a unit cycle The numerical value of

[0131] like , it is determined that the urban-rural traffic sub-section is in a normal state;

[0132] like , it is determined that the urban-rural traffic sub-section is in a congested state, the determination result is fed back to the main control unit and an early warning is issued.

[0133] S5, setting a traffic flow cycle set, collecting the traffic flow of urban and rural traffic sub-sections in a congested state in historical data according to the traffic flow cycle set, obtaining a first historical traffic flow set, and collecting the vehicle data of traffic accidents in the first historical traffic flow set, to establish a first historical traffic accident vehicle set;

[0134] S51. Setting traffic flow cycle set ,in represents the i-th traffic flow period, Indicates the total number of traffic flow cycles;

[0135] S52, according to the traffic flow cycle set Collect the traffic flow of urban and rural traffic sub-sections in congestion in historical data to obtain the first historical traffic flow set ,in represents the total number of vehicles that pass through the urban-rural traffic sub-section in the i-th traffic flow cycle before the congestion occurs;

[0136] S53: Collect the first historical traffic flow set The vehicle data of traffic accidents in the first historical traffic accident vehicle dataset is established. ,in, represents the i-th vehicle involved in a traffic accident in the first historical traffic flow set, Indicates the total number of vehicles involved in traffic accidents in the first historical traffic flow set;

[0137] S54. Calculate the historical traffic accident rate of urban and rural traffic sub-sections in congestion .

[0138] S6, determining the congestion degree of the urban and rural traffic sub-section in a congested state, and issuing corresponding instructions according to the determination result;

[0139] S61, compare the traffic flow threshold corresponding to the urban-rural traffic sub-section in the congested state in the first traffic flow threshold data matrix with the numerical values ​​of each historical traffic flow in the first historical traffic flow set, record the number v of historical traffic flows greater than the traffic flow threshold in the first historical traffic flow set, and calculate the traffic congestion ratio of the urban-rural traffic sub-section in the congested state ;

[0140] S62, setting the low congestion threshold to , the high congestion threshold is and traffic accident rate threshold , determine the congestion degree of the urban and rural traffic sub-sections in a congested state;

[0141] S621, when , it is determined that the urban-rural traffic sub-section is in a lightly congested state, and a temporary road clearing instruction is issued through the main control unit according to the determination result;

[0142] S622, when and , it is determined that the urban-rural traffic sub-section is in a moderate congestion degree, and according to the determination result, the main control unit adjusts the duration of the traffic lights at each urban-rural traffic road intersection on the urban-rural traffic road where the urban-rural traffic sub-section is located, and re-determines whether the urban-rural traffic sub-section is in a congested state. If it is not in a congested state, the operation is terminated; if it is still in a congested state, the congestion degree of the urban-rural traffic sub-section is determined to be a severe congestion degree;

[0143] S623, when and or , it is determined that the urban-rural traffic sub-section is in a severe congestion level, and the current urban-rural traffic planning scheme is optimized through the main control unit according to the determination result;

[0144] S6231, build a frog population, set the maximum number of iterations to , the population size is M,

[0145] S6232, randomly dividing the frog population into m frog subgroups, each frog subgroup contains n frog individuals, calculating the fitness function values ​​of all frog individuals, and recording the position of the frog individual with the largest fitness function value in the frog population as ; The fitness function formula is as follows:

[0146]

[0147] in, represents the fitness function value of the i-th frog individual, represents the ability of the i-th frog individual to solve the congestion of urban and rural traffic sub-sections, and q represents the correction value;

[0148] S6233. According to the value of the fitness function, the optimal individual frog position in the i-th frog subgroup is recorded as , the worst frog individual position is recorded as , update the position of the worst frog individual in the frog subgroup according to the moving step length D from the worst frog individual to the best frog individual; the position update formula is as follows:

[0149]

[0150] Among them, rand represents a random number between (0,1), represents the updated position of the worst frog individual in the i-th frog subgroup;

[0151] S6234, calculate the fitness function value of the worst frog individual after the update. If the fitness function value of the worst frog individual after the update is higher than the fitness function value of the original worst frog individual, replace the original worst frog individual with the updated worst frog individual; otherwise, replace the original worst frog individual with the updated worst frog individual. replace Re-update the position of the worst frog individual;

[0152] S6235, calculating the fitness function value of the worst frog individual after the update, if the fitness function value of the worst frog individual after the update is higher than the fitness function value of the original worst frog individual, then the updated worst frog individual replaces the original worst frog individual; otherwise, then randomly generating a position in the search space to replace the original worst frog position;

[0153] S6236, merging all frog subgroups into a new frog population, calculating the fitness function values ​​of all frog individuals, and taking the frog individual with the largest fitness function value as the current global optimal solution;

[0154] S6237, determine whether the maximum number of iterations has been reached If not, return to S6232; if reached, output the current global optimal solution to obtain the optimized urban and rural transportation planning scheme.

[0155] The second embodiment of the urban and rural traffic planning optimization system and method based on big data is as follows:

[0156] See also Figure 2 , an urban and rural traffic planning optimization system based on big data, including an urban and rural traffic sub-section division module, a real-time traffic flow data acquisition module, a first traffic flow threshold data matrix setting module, a congestion state determination module, a historical data collection module and a congestion degree determination module;

[0157] The urban-rural traffic sub-section division module divides each urban-rural traffic road in the urban-rural traffic road set through the urban-rural traffic road intersection set to obtain the urban-rural traffic sub-section set;

[0158] The real-time traffic flow data collection module collects the traffic flow in a unit period of each urban and rural traffic sub-section in the urban and rural traffic sub-section set in real time through a sensing device to obtain a first real-time traffic flow data matrix;

[0159] The first traffic flow threshold data matrix setting module finds the traffic flow threshold of each urban and rural traffic sub-section through a fireworks algorithm to obtain a first traffic flow threshold matrix;

[0160] The congestion state determination module determines whether the urban-rural traffic sub-section is in a congested state by comparing the corresponding values ​​of the same urban-rural traffic sub-section in the first traffic flow threshold data matrix and the first real-time traffic flow data matrix;

[0161] The historical data collection module collects the traffic flow of the urban and rural traffic sub-sections in a congested state and the vehicle data of traffic accidents in the historical data according to the traffic flow cycle set, and calculates the historical traffic accident rate of the urban and rural traffic sub-sections in a congested state;

[0162] The congestion level determination module determines the congestion level of the urban and rural traffic sub-section in a congested state according to the numerical values ​​of the historical traffic accident rate and the traffic congestion ratio, and issues corresponding instructions according to the determination result.

[0163] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0164] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A method for optimizing urban and rural transportation planning based on big data, characterized in that: The steps include: S1. Set an urban-rural traffic road set and an urban-rural traffic road intersection set, and divide each urban-rural traffic road in the urban-rural traffic road set according to the urban-rural traffic road intersection set to obtain an urban-rural traffic sub-section set; S2, setting a traffic flow unit collection period, collecting the traffic flow within the unit period of each urban and rural traffic sub-section in the urban and rural traffic sub-section matrix in real time through the sensing device, and obtaining a first real-time traffic flow data matrix; S3, setting a traffic flow threshold for each urban and rural traffic sub-section in the urban and rural traffic sub-section matrix through an intelligent optimization algorithm, and obtaining a first traffic flow threshold data matrix, specifically including: S31, construct a fireworks population, set the population number to N, the maximum number of iterations, the maximum number of explosion sparks, the minimum number of explosion sparks, and the initial position set of the fireworks population; S32, calculating the fitness function value of each firework individual in the firework population; S33, performing explosion operation according to the fitness function value of each firework individual to generate explosion sparks, and the explosion radius and number of explosion sparks generated by the explosion of each firework individual will be affected by other firework individuals in the firework population; S34, performing a Gaussian mutation operation on each individual firework in the firework population; S35, merging all firework individuals, spark individuals generated after the explosion, and individuals generated after Gaussian mutation into a population, calculating the fitness function values ​​of all individuals in the population, retaining the individual with the largest fitness function value to join the next generation of fireworks population, and selecting N-1 individuals from the remaining individuals by roulette to join the next generation of fireworks population, to obtain a new fireworks population; S36: Determine whether the maximum number of iterations has been reached If not, return to S33; if reached, take the fireworks individual with the largest fitness function value in the current fireworks population as the current global optimal solution, output the traffic flow thresholds of each urban and rural traffic sub-section, and obtain the first traffic flow threshold matrix F as follows: ; in, represents the traffic flow threshold of the jth urban-rural traffic sub-section in the i-th urban-rural traffic road, k It is the urban-rural traffic road dimension, indicating the total number of urban-rural traffic roads; is the dimension of the urban and rural traffic sub-section, indicating the i There are 1,000 urban and rural traffic roads. Urban and rural traffic sub-sections, Indicates k The first of the urban and rural traffic roads The traffic flow threshold of each urban-rural traffic sub-segment. If the dimension of an urban-rural traffic sub-segment in a row is less than that in other rows, it is set to 0 to fill the gap. S4. Compare the corresponding values ​​of the same urban-rural traffic sub-section in the first traffic flow threshold data matrix and the first real-time traffic flow data matrix to determine whether the urban-rural traffic sub-section is in a congested state, as follows: S41. Compare the traffic flow threshold value per unit period of the j-th urban-rural traffic sub-section in the i-th urban-rural traffic road in the first traffic flow threshold data matrix F. The total number of vehicles passing through the jth urban-rural traffic sub-section in the i-th urban-rural traffic road in the first real-time traffic flow data matrix C within a unit cycle The numerical value of like , it is determined that the urban-rural traffic sub-section is in a normal state; like , it is determined that the urban-rural traffic sub-section is in a congested state, the determination result is fed back to the main control unit and an early warning is issued; S5. Set a traffic flow cycle set, collect the traffic flow of urban and rural traffic sub-sections in a congested state in historical data according to the traffic flow cycle set, obtain a first historical traffic flow set, and collect vehicle data of traffic accidents in the first historical traffic flow set to establish a first historical traffic accident vehicle set, specifically including: S51. Setting traffic flow cycle set ,in represents the i-th traffic flow period, Indicates the total number of traffic flow cycles; S52: Collect the traffic flow of urban and rural traffic sub-sections in a congested state in the historical data according to the traffic flow cycle set to obtain a first historical traffic flow set. ,in represents the total number of vehicles that pass through the urban-rural traffic sub-section in the i-th traffic flow cycle before the congestion occurs; S53, collecting the vehicle data of traffic accidents in the first historical traffic flow set, and establishing a first historical traffic accident vehicle set ,in, represents the i-th vehicle involved in a traffic accident in the first historical traffic flow set, Indicates the total number of vehicles involved in traffic accidents in the first historical traffic flow set; S54. Calculate the historical traffic accident rate of urban and rural traffic sub-sections in congestion ； S6. Determine the congestion level of the urban and rural traffic sub-sections in a congested state, and issue corresponding instructions according to the determination results, including: S61, comparing the traffic flow threshold corresponding to the urban and rural traffic sub-section in the congested state in the first traffic flow threshold data matrix with the numerical values ​​of each historical traffic flow in the first historical traffic flow set, and recording the number of historical traffic flows in the first historical traffic flow set that are greater than the traffic flow threshold , calculate the traffic congestion ratio of the urban and rural traffic sub-sections in congestion ; S62, setting the low congestion threshold to , the high congestion threshold is and traffic accident rate threshold , determine the congestion degree of the urban and rural traffic sub-sections in a congested state; S621, when , it is determined that the urban-rural traffic sub-section is in a lightly congested state, and a temporary road clearing instruction is issued through the main control unit according to the determination result; S622, when and , it is determined that the urban-rural traffic sub-section is in a moderate congestion degree, and according to the determination result, the main control unit adjusts the duration of the traffic lights at each urban-rural traffic road intersection on the urban-rural traffic road where the urban-rural traffic sub-section is located, and re-determines whether the urban-rural traffic sub-section is in a congested state. If it is not in a congested state, the operation is terminated; if it is still in a congested state, the congestion degree of the urban-rural traffic sub-section is determined to be a severe congestion degree; S623, when and or , it is determined that the urban-rural traffic sub-section is in a state of severe congestion, and the current urban-rural traffic planning scheme is optimized through the main control unit according to the determination result.

2. The method for optimizing urban and rural transportation planning based on big data according to claim 1 is characterized in that: The S1 comprises the following steps: S11. Setting urban and rural traffic road sets; S12, setting a set of urban and rural traffic road intersections; S13. Divide each urban and rural traffic road in the urban and rural traffic road set according to the urban and rural traffic road intersection set to obtain an urban and rural traffic sub-section set B.

3. The method for optimizing urban and rural transportation planning based on big data according to claim 2 is characterized in that: The S2 comprises the following steps: S21, set a traffic flow unit collection period, collect the traffic flow in each urban and rural traffic sub-section unit period in the urban and rural traffic sub-section matrix B in real time through the sensing device, and obtain the first real-time traffic flow data matrix C as follows: ; in, Indicates i The first of the urban and rural traffic roads j The total number of vehicles passing through each urban and rural traffic sub-section within a unit cycle; k It is the urban-rural traffic road dimension, indicating the total number of urban-rural traffic roads; is the dimension of the urban and rural traffic sub-section, indicating the i There are 1,000 urban and rural traffic roads. Urban and rural traffic sub-sections, Indicates k The first of the urban and rural traffic roads The total number of vehicles passing through the urban-rural traffic sub-section in a unit cycle. If the dimension of the urban-rural traffic sub-section in a row is less than that of other rows, it is set to 0 to fill the gap.

4. The method for optimizing urban and rural transportation planning based on big data according to claim 1 is characterized in that: Optimizing the current urban and rural transportation planning scheme in S623 includes the following steps: S6231, build a frog population, set the maximum number of iterations to , the population size is M; S6232, randomly dividing the frog population into m frog subgroups, each frog subgroup contains n frog individuals, calculating the fitness function values ​​of all frog individuals, and recording the position of the frog individual with the largest fitness function value in the frog population as ; S6233. According to the value of the fitness function, the optimal individual frog position in the i-th frog subgroup is recorded as , the worst frog individual position is recorded as , update the position of the worst frog individual according to the moving step length D from the worst frog individual to the best frog individual; S6234, calculate the fitness function value of the worst frog individual after the update. If the fitness function value of the worst frog individual after the update is higher than the fitness function value of the original worst frog individual, replace the original worst frog individual with the updated worst frog individual; otherwise, replace the original worst frog individual with the updated worst frog individual. replace Re-update the position of the worst frog individual; S6235, calculating the fitness function value of the worst frog individual after the update, if the fitness function value of the worst frog individual after the update is higher than the fitness function value of the original worst frog individual, then the updated worst frog individual replaces the original worst frog individual; otherwise, then randomly generating a position in the search space to replace the original worst frog position; S6236, merging all frog sub-populations into a new frog population, calculating the fitness function values ​​of individual frogs, and taking the frog individual with the largest fitness function value as the current global optimal solution; S6237, determine whether the maximum number of iterations has been reached If not, return to S6232; if reached, output the current global optimal solution to obtain the optimized urban and rural transportation planning scheme.

5. A system for realizing the optimization of urban and rural traffic planning based on big data as described in any one of claims 1-4, comprising an urban and rural traffic sub-section division module, a real-time traffic flow data acquisition module, a first traffic flow threshold data matrix setting module, a congestion status determination module, a historical data collection module and a congestion degree determination module.

Images