A method, system and storage medium for predicting highway traffic flow during holidays

Abstract

The present invention provides a method, system and storage medium for predicting highway traffic flow on holidays. The traffic conditions of a highway to be calculated are observed through existing observation stations, and there is no need to re-install highway observation equipment, which ensures effective prediction of the highway to be calculated in all time periods and saves the construction cost and time of highway observation stations. In the method for predicting highway traffic flow on holidays provided by the present invention, flow operation characteristic parameters are obtained through observation station data, and further integrated upward based on the observation station data, thereby realizing daily and time-based flow prediction of the line.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent traffic management and control, and in particular to a method, system and storage medium for predicting highway traffic flow during holidays. Background Art

[0002] With the development of economy, the increase of per capita car ownership and the rapid development of logistics industry, large-scale road congestion has become the norm; especially during some holidays, in order to facilitate people's travel, highways are exempted from tolls, and congestion at important road nodes is a common phenomenon. Therefore, using scientific methods to predict the traffic flow of road networks during holidays is an effective means to assist traffic management departments in formulating measures and ensuring the smooth operation of road networks, thereby reducing road network congestion, improving tourists' travel satisfaction, and improving travel efficiency.

[0003] However, due to the sparse distribution of continuous highway traffic survey observation sites, it is difficult to provide large-scale traffic information, and simply increasing the number of detection equipment also makes the construction and maintenance costs high.

[0004] In view of this, it is necessary to provide a holiday highway traffic flow prediction method to solve or at least alleviate the defects of the above-mentioned sparsely distributed observation stations, incomplete flow information provision and increased construction and maintenance costs due to the addition of detection equipment. Summary of the invention

[0005] The main purpose of the present invention is to provide a method for predicting highway traffic flow on holidays, aiming to solve the technical problems that the above-mentioned observation sites are sparsely distributed and the flow information is not comprehensive, and adding detection equipment increases the construction and maintenance costs.

[0006] To achieve the above object, the present invention provides a method for predicting highway traffic flow during holidays, comprising:

[0007] S1, obtain the traffic data information of each observation station i during the preset holidays and two weeks before the preset holidays in the history of the highway to be calculated for M years, i∈[1,Z], Z is the total number of observation stations on the highway to be calculated;

[0008] S2, according to the formula Calculate the average daily flow rate D during holidays at observation station i on the highway to be calculated avg,i , where i is the observation station number, k is the kth day of the holiday, k∈[1,T], T is the total number of days of the holiday, D d,i,k is the daily flow rate of observation station i on the kth day;

[0009] S3, according to the weighted moving average formula P t =w1D avg，i，y(t) +w2Davg，i，y(t+1) +…+w N D avg，i，y(t-1+N) , Get the forecast data value of the average daily flow trend during the holiday period of the observation station i in the forecast year Where N is the number of items in the preset moving average group, t is the order of the moving average group, y(t) is the corresponding t-th year in the moving average group, and D d，i，k，y(t) is the daily flow rate of the observation station i on the kth day of the holiday in the tth year in the moving average group, D avg，i，y(t) is the average daily flow rate of the observation station i in the moving average group during the holiday of the tth year, w N is the weight, N<M, with M years of data in total;

[0010] S4, according to the formula Calculate the correction coefficient C of the observation station i i ,in, is the average daily flow rate of the observation station i in the two weeks before the holiday in the forecast year, is the average daily flow rate of the observation station i in the two weeks before the holiday in the year before the forecast year;

[0011] S5, according to the formula β1+β2=1, calculate the daily average corrected forecast flow data value of the observation station i in the forecast year Among them, D avg，i，y(last) is the average daily flow rate of the observation station i during the holidays in the year before the forecast year, β1 is the weight of the trend forecast, and β2 is the weight of the revised forecast.

[0012] Furthermore, step S2 includes the steps of obtaining the hourly flow rate D of the observation station i at the jth hour of the kth day h，i，k，j , according to the hourly flow D of the observation station i h，i，k，j , through the formula Calculate the daily flow D of the observation station i during holidays d，i，k , where d represents the daily flow data of the observation station i, and h represents the hourly flow data of the observation station i.

[0013] Furthermore, the method further comprises the following steps:

[0014] Based on the daily flow D of the observation station i d，i，k , according to the observed mileage weighted formula Calculate the daily traffic volume D of route l during holidays d，l，k , where l is a road section, route or road network, L i is the observation mileage of the observation station i, δ iis a binary function of the observation station i, and x represents the total number of the observation stations i in line l;

[0015] Based on the hourly flow D of the observation station i h，i，k，j , according to the observed mileage weighted formula Calculate the hourly flow rate D of the route l during holidays h，l，k，j , where D h，l，k，j is the hourly flow rate of the line l at the jth hour on the kth day, D h，i，k，j is the hourly flow rate at the jth hour on the kth day at the observation station i;

[0016] Based on the average daily flow D of the observation station i avg，i , according to the observed mileage weighted formula Calculate the average daily flow D of the route l during holidays avg，l .

[0017] Furthermore, before step S3, the method further includes processing the daily average flow data of the observation station i in the line to be calculated; the data processing includes removing abnormal values ​​and interpolating and filling.

[0018] Furthermore, the method further comprises the following steps:

[0019] According to the formula Calculate the daily traffic ratio R of the route l during holidays d，l，k ;

[0020] According to the formula Calculate the time-sharing flow ratio R of the line l during holidays h，l，k，j .

[0021] Furthermore, after step S5, step S6 is further included: based on the daily average corrected predicted flow data of the observation station i By observing the mileage weighted formula Calculate the daily average corrected predicted flow data of the line l

[0022] Furthermore, the method further comprises the following steps:

[0023] Based on the daily flow ratio R of the line l during the holidays in year M d，l，k , according to the formula Calculate the predicted daily flow ratio of the forecast year by weight R d，l，k，y(M) is the daily traffic proportion on the kth day of the holiday in the Mth year, s M is the weight of the Mth year, and y(M) corresponds to the year of the Mth year;

[0024] Based on the time-sharing flow ratio R of the line l during the holidays in year M h，l，k，j , according to the formula Calculate the predicted time-of-day traffic ratio of the forecast year by weight R h，l，k，j，y(M) It is the time-sharing traffic ratio at the jth hour on the kth day of the holiday in the Mth year.

[0025] Furthermore, after step S6, the following steps are also included:

[0026] Based on the daily average modified predicted flow data of the route l Multiply by the predicted daily flow ratio of the corresponding line l By formula Calculate the predicted daily flow of the line l in the predicted year in, is the predicted daily flow of the line l on the kth day; is the predicted daily flow ratio of the route l on the kth day;

[0027] Based on the predicted daily traffic of the route l Multiply by the predicted time-sharing flow ratio of the corresponding line l By formula Calculate the predicted time-sharing traffic of the line l in the predicted year in, The predicted time-sharing flow of the line l at the jth hour on the kth day; is the predicted time-sharing traffic proportion of the line l at the jth hour on the kth day.

[0028] The present invention also provides a holiday highway traffic flow prediction system, characterized in that it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of a holiday highway traffic flow prediction method as described in any one of the above items are implemented.

[0029] The present invention also provides a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the holiday highway traffic flow prediction method as described in any one of the above items.

[0030] Compared with the prior art, the present invention has the following advantages:

[0031] The present invention provides a method for predicting highway traffic flow during holidays. By analyzing the flow data information collected by existing highway traffic survey observation sites, and obtaining flow operation characteristic parameters through observation site data, the method further integrates upward based on the observation site data, thereby realizing daily and time-divided flow prediction of the route, and no additional highway detection equipment is required, which not only ensures the effective prediction of the highway to be calculated in all periods, but also saves construction and maintenance costs. In a method for predicting highway traffic flow during holidays provided by the present invention, the daily average corrected predicted flow of observation station i in the predicted year is obtained by calculating the flow data information of each observation station i during the preset holidays of the historical M years of the highway and two weeks before the preset holidays. The predicted daily and time-divided flow of the highway section to be calculated is obtained through the daily average corrected predicted flow, which can realize the observation of the flow of a certain route and the observation of the entire highway to be calculated. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0033] Figure 1 The present invention is a flowchart of a method for predicting highway traffic flow during holidays.

[0034] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with the implementation methods and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0035] 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.

[0036] It should be noted that all directional indications (such as up, down, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0037] In addition, in the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0038] Furthermore, the technical solutions between the various embodiments of the present invention may be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in the field. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0039] Please see attached Figure 1 The present invention provides a method for predicting highway traffic flow during holidays, comprising the following steps:

[0040] S1, obtain the traffic data information of each observation station i during the preset holidays of the historical M years of the highway to be calculated and two weeks before the preset holidays, i∈[1,Z], Z is the total number of observation stations on the highway to be calculated.

[0041] Specifically, the highway to be calculated includes information on each highway section, each highway route and each observation station node; as shown in Table 1, the observation station node information includes fields such as the observation station number, observation station name, observation mileage, technical level and city and state; as shown in Table 2, the highway section information includes fields such as the number of lanes in the section, the direction of the section and the name of the section; as shown in Table 3, the highway route information includes fields such as the route name and route type.

[0042] Table 1 Observation station information

[0043]

[0044] Table 2 Highway section information table

[0045]

[0046] Table 3 Highway route information table

[0047]

[0048] S2, according to the formula Calculate the average daily flow rate D during holidays at observation station i on the highway to be calculated avg,i , where i is the observation station number, k is the kth day of the holiday, k∈[1,T], T is the total number of days of the holiday, D d，i，k is the daily flow at observation station i on the kth day.

[0049] Specifically, the formula The average daily flow rate during holidays at observation station i in the highway to be calculated is calculated. Meanwhile, those skilled in the art may also use other calculation formulas according to actual needs.

[0050] S3, according to the weighted moving average formula P t =w1D avg，i，y(t) +w2D avg，i，y(t+1) +…+w N D avg，i，y(t-1+N) , Get the forecast data value of the average daily flow trend during the holiday period of the observation station i in the forecast year Where N is the number of items in the preset moving average group, t is the order of the moving average group, y(t) is the corresponding t-th year in the moving average group, and D d，i，k，y(t) is the daily flow rate of the observation station i on the kth day of the holiday in the tth year in the moving average group, D avg，i，y(t) is the average daily flow rate of the observation station i in the moving average group during the holiday of the tth year, w N is the weight, N<M, with M years of data in total;

[0051] Specifically, the weighted moving average method used is a method of giving different weights to the observed values, obtaining moving averages according to the different weights, and determining the predicted value based on the final moving average. It is worth noting that the weighted moving average method is used because the recent observed values ​​in the observation period have a greater impact on the predicted value, and it can better reflect the trend of recent highway traffic changes. Therefore, a larger weight value is given to the observed values ​​close to the observation period, and a smaller weight value is given to the observed values ​​far from the observation period. Different weight values ​​are used to adjust the role of each observed value on the predicted value, so that the predicted value can more closely reflect the future traffic trend of the highway. The number of items N in the preset moving average group represents the number of year data in the preset moving average group.

[0052] S4, according to the formula Calculate the correction factor C for the observation station i i ,in, is the average daily flow rate of the observation station i in the two weeks before the holiday in the forecast year, is the average daily flow rate of the observation station i in the two weeks before the holiday in the year before the prediction year.

[0053] Specifically, the correction coefficient refers to the coefficient added to the calculation formula to make it reflect the actual performance as much as possible when there is a deviation between ideal and reality, reality and investigation, etc. in data calculation and formula expression. It should be noted that the correction coefficient of the observation station i is based on the average daily flow of the observation station i under normal conditions. When the average daily flow of the observation station i under normal conditions changes due to certain factors originally set, it is necessary to make local adjustments and corrections to the average daily flow value of the observation station i, so that technicians in this field can obtain a more accurate correction coefficient C of the observation station i. i .

[0054] S5, according to the formula β1+β2=1, calculate the daily average corrected forecast flow data value of the observation station i in the forecast year Among them, D avg，i，y(last) is the average daily flow rate of the observation station i during the holidays in the year before the forecast year, β1 is the weight of the trend forecast, and β2 is the weight of the revised forecast.

[0055] Specifically, according to the calculated correction coefficient C of the observation station i i , can be obtained by the formula β1+β2=1 calculates the average daily revised predicted flow data value of the observation station i in the predicted year. It should be noted that due to the strong uncertainty of the flow change trend before the festival, it is generally believed that the historical trend has a greater impact. If the recent epidemic, weather and other sudden factors have a greater impact, or the historical data fluctuates greatly, such as the overlap of National Day and Mid-Autumn Festival, then the weight of the revised prediction β2 should be appropriately increased.

[0056] Furthermore, step S2 includes the steps of obtaining the hourly flow rate D of the observation station i at the jth hour of the kth day h，i，k，j , according to the hourly flow D of the observation station i h，i，k，j , through the formula Calculate the daily flow D of the observation station i during holidays d，i，k , where d represents the daily flow data of the observation station i, and h represents the hourly flow data of the observation station i.

[0057] As a preferred embodiment, based on the hourly flow D of the observation station i h，i，k，j , can be obtained by the formula Calculate the daily flow rate D of the observation station i during holidays d，i，k At the same time, technicians in this field can also use other formulas to calculate the daily flow rate D of the observation station i during holidays according to actual needs. d，i，k .

[0058] Furthermore, the method further comprises the following steps:

[0059] Based on the daily flow D of the observation station i d，i，k , according to the observed mileage weighted formula Calculate the daily traffic volume D of route l during holidays d，l，k , where l is a road section, route or road network, L i is the observation mileage of the observation station i, δ i is a binary function of the observation station i, and x represents the total number of the observation stations i in line l;

[0060] Based on the hourly flow D of the observation station i h，i，k，j , according to the observed mileage weighted formula Calculate the hourly flow rate D of the route l during holidays h，l，k，j , where D h，l，k，j is the hourly flow rate of the line l at the jth hour on the kth day, D h，i，k，j is the hourly flow rate at the jth hour on the kth day at the observation station i;

[0061] Based on the average daily flow D of the observation station i avg，i , according to the observed mileage weighted formula Calculate the average daily flow D of the route l during holidays avg，l .

[0062] As a preferred embodiment, based on the daily flow D of the observation station i d，i，k Hourly flow rate D h，i，k，j And the average daily flow D avg，i , the daily flow D of the route l during holidays can be calculated by the observed mileage weighted formula d，l，k Hourly flow rate D h，l，k，j And the average daily flow D avg，l , where if the observation station i belongs to the line l, then δ i =1, otherwise δ i =0.

[0063] Furthermore, before step S3, the method further includes processing the daily average flow data of the observation station i in the line to be calculated; the data processing includes removing abnormal values ​​and interpolating and filling.

[0064] Specifically, firstly, the daily average flow data of observation station i in the line to be calculated is processed to remove abnormal values. The method of removing abnormal values ​​can be adopted by technicians in this field according to actual needs, and then the average of the daily average flow of the observation station i in the previous and next years is interpolated and filled, and the abnormal data in the daily average flow of the observation station i is removed by interpolation and filling, wherein the abnormal data may be caused by a failure of the system itself, weather influence, special traffic flow, or the impact of the epidemic. For example, due to the impact of the epidemic, the flow of the Spring Festival in 2020 dropped significantly, and the average of the daily average flow of the observation station i in 2021 and 2019 can be used for interpolation and filling.

[0065] Furthermore, the method further comprises the following steps:

[0066] According to the formula Calculate the daily traffic ratio R of the route l during holidays d，l，k ;

[0067] According to the formula Calculate the time-sharing flow ratio R of the line l during holidays h，l，k，j .

[0068] Furthermore, after step S5, step S6 is further included: based on the daily average corrected predicted flow data of the observation station i By observing the mileage weighted formula Calculate the daily average corrected predicted flow data of the line l It should be noted that if the observation station i belongs to the line l, then δ i =1, otherwise δ i =0.

[0069] Furthermore, the method further comprises the following steps:

[0070] Based on the daily flow ratio R of the line l during the holidays in year M d，l，k , according to the formula Calculate the predicted daily flow ratio of the forecast year by weight R d，l，k，y(M) is the daily traffic proportion on the kth day of the holiday in the Mth year, s M is the weight of the Mth year, and y(M) corresponds to the year of the Mth year;

[0071] Based on the time-sharing flow ratio R of the line l during the holidays in year M h，l，k，j , according to the formula Calculate the predicted time-of-day traffic ratio of the forecast year by weight R h，l，k，j，y(M) It is the time-sharing traffic ratio at the jth hour on the kth day of the holiday in the Mth year.

[0072] It is worth noting that the more recent years are given greater weights. At the same time, technicians in this field can also use other methods to calculate the predicted daily flow ratio of the predicted year according to actual needs. Predicted time-sharing traffic ratio

[0073] Furthermore, after step S6, the following steps are also included:

[0074] Based on the daily average modified predicted flow data of the route l Multiply by the predicted daily flow ratio of the corresponding line l By formula Calculate the predicted daily flow of the line l in the predicted year in, is the predicted daily flow of the line l on the kth day; is the predicted daily flow ratio of the route l on the kth day;

[0075] Specifically, the predicted daily flow of the line l in the predicted year The daily average corrected predicted flow data of line l can be used Multiply by the predicted daily flow ratio of the corresponding line l It is calculated. This provides an effective means to assist traffic management departments in formulating measures and ensuring the smooth operation of highways, and is of great significance in alleviating road network congestion, improving tourists' travel satisfaction and improving travel efficiency.

[0076] Based on the predicted daily traffic of the route l Multiply by the predicted time-sharing flow ratio of the corresponding line l By formula Calculate the predicted time-sharing traffic of the line l in the predicted year in, The predicted time-sharing flow of the line l at the jth hour on the kth day; is the predicted time-sharing traffic proportion of the line l at the jth hour on the kth day.

[0077] Specifically, the predicted time-sharing traffic of the line l in the predicted year The predicted daily flow of line l can be Multiply by the predicted time-sharing flow ratio of the corresponding line l It is calculated. This provides an effective means to assist traffic management departments in formulating measures and ensuring the smooth operation of highways, and is of great significance in alleviating road network congestion, improving tourists' travel satisfaction and improving travel efficiency.

[0078] The present invention also provides a holiday highway traffic flow prediction system, characterized in that it includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the computer program is executed by the processor, the steps of a holiday highway traffic flow prediction method as described in any one of the above are implemented. In a specific embodiment of the present invention, when the processor of the computing system executes the computer program, the steps of the holiday highway traffic flow prediction method are implemented, and the traffic conditions of the highway to be calculated are observed by the existing observation station, and there is no need to re-install highway observation equipment, which ensures the effective prediction of the highway to be calculated in all time periods and saves the construction cost and time of the highway observation station.

[0079] The present invention also provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned method for predicting highway traffic flow during holidays. In a specific embodiment of the present invention, when the processor of the computing system executes the computer program, the steps of the above-mentioned method for predicting highway traffic flow during holidays are implemented, and the traffic conditions of the highway to be calculated are observed by the existing observation station, and there is no need to re-install highway observation equipment, which ensures the effective prediction of the highway to be calculated during all periods, and saves the construction cost and time of the highway observation station.

[0080] The above technical solutions of the present invention are only preferred embodiments of the present invention, and the patent scope of the present invention is not limited thereto. All equivalent structural changes made by using the contents of the present invention specification and drawings under the technical concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A method for predicting highway traffic flow during holidays, characterized in that: include: S1, obtain the traffic data information of each observation station i during the preset holidays and two weeks before the preset holidays in the history of the highway to be calculated for M years, i∈[1,Z], Z is the total number of observation stations on the highway to be calculated; S2, according to the formula Calculate the average daily flow rate D during holidays at observation station i on the highway to be calculated avg,i , where i is the observation station number, k is the kth day of the holiday, k∈[1,T], T is the total number of days of the holiday, D d,i,k is the daily flow rate of observation station i on the kth day; S3. According to the weighted moving average method formula P t = w1D avg,i,y(t) + w2D avg,i,y(t+1) +... + w N D avg,i,y(t -1 + N), obtain the predicted data value of the daily average flow trend of the holiday dates of the observation station i in the predicted year where N is the number of items in the preset moving average group, t is the sorting of N, y(t) is the year corresponding to the t-th period in the moving average group, and D d,i,k,y(t) is the daily flow on the k-th day of the holiday of the observation station i within the year corresponding to the t-th period in the moving average group, and D avg,i,y(t) is the daily average flow of the observation station i during the holiday period of the year corresponding to the t-th period in the moving average group, and w1, w2, w N are weights, N < M, with a total of M years of data; S4, according to the formula Calculate the correction factor C for the observation station i i ,in, is the average daily flow rate of the observation station i in the two weeks before the holiday in the forecast year, is the average daily flow rate of the observation station i in the two weeks before the holiday in the year before the forecast year; S5, according to the formula Calculate the daily average corrected forecast flow data value of the observation station i in the forecast year Among them, D avg,i,y(last) is the average daily flow rate during holidays at the observation station i in the year before the forecast year, β1 is the weight of trend forecast, and β2 is the weight of revised forecast; The step S6 is further comprised of: correcting the predicted flow data based on the daily average of the observation station i. By observing the mileage weighted formula Calculate the daily average corrected predicted flow data of the line l 2. A method for predicting highway traffic flow during holidays according to claim 1, characterized in that: The step S2 comprises the steps of: Get the hourly flow D of the observation station i at the jth hour of the kth day h,i,k,j , according to the hourly flow D of the observation station i h,i,k,j , through the formula Calculate the daily flow D of the observation station i during holidays d,i,k , where d represents the daily flow data of the observation station i, and h represents the hourly flow data of the observation station i.

3. A method for predicting highway traffic flow during holidays according to claim 2, characterized in that: Also includes , the following steps: Based on the daily flow D of the observation station i d,i,k , according to the observed mileage weighted formula Calculate the daily traffic volume D of route l during holidays d,l,k , where l is a road section, route or road network, L i is the observation mileage of the observation station i, δ i is a binary function of the observation station i, and x represents the total number of the observation stations i in line l; Based on the hourly flow D of the observation station i h,i,k,j , according to the observed mileage weighted formula Calculate the hourly flow rate D of the route l during holidays h,l,k,j , where D h,l,k,j is the hourly flow rate of the line l at the jth hour on the kth day, D h,i,k,j is the hourly flow rate at the jth hour on the kth day at the observation station i; Based on the average daily flow D of the observation station i avg,i , according to the observed mileage weighted formula Calculate the average daily flow D of the route l during holidays avg,l .

4. A method for predicting highway traffic flow during holidays according to claim 1, characterized in that: Before step S3, the method also includes processing the daily average flow data of observation station i in the line to be calculated; the data processing includes interpolation filling.

5. A method for predicting highway traffic flow during holidays according to claim 3, characterized in that: Also includes , the following steps: According to the formula Calculate the daily traffic ratio R of the route l during holidays d,l,k ; According to the formula Calculate the time-sharing flow ratio R of the line l during holidays h,l,k,j .

6. A method for predicting highway traffic flow during holidays according to claim 1, characterized in that: Also includes the following steps: Based on the daily flow ratio R of the line l during the holidays in year M d,l,k,j , according to the formula Calculate the predicted daily flow ratio of the forecast year by weight R d,l,k,y(M) is the daily traffic proportion on the kth day of the holiday in the Mth year, s1, s2, s M is the weight of the Mth year, and y(M) corresponds to the year of the Mth year; Based on the time-sharing flow ratio R of the line l during the holidays in year M h,l,k,j , according to the formula Calculate the predicted time-of-day traffic ratio of the forecast year by weight R h,l,k,j,y(M) It is the time-sharing traffic ratio at the jth hour on the kth day of the holiday in the Mth year.

7. A method for predicting highway traffic flow during holidays according to claim 6, characterized in that: After step S6, the following steps are also included , the following steps: Based on the daily average modified predicted flow data of the route l Multiply by the predicted daily flow ratio of the corresponding line l By formula Calculate the predicted daily flow of the line l in the predicted year in, is the predicted daily flow of the line l on the kth day; is the predicted daily flow ratio of the route l on the kth day; Based on the predicted daily flow of the line l Multiply by the predicted time-sharing flow ratio of the corresponding line l By formula Calculate the predicted time-sharing traffic of the line l in the predicted year in, The predicted time-sharing flow of the line l at the jth hour on the kth day; is the predicted time-sharing traffic proportion of the line l at the jth hour on the kth day.

8. A holiday highway traffic flow prediction system, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of a method for predicting highway traffic flow during holidays as described in any one of claims 1 to 7 are implemented.

9. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the holiday highway traffic flow prediction method according to any one of claims 1 to 7 are implemented.

Images