Expressway traffic flow index unified expression method based on space-time relevance

Abstract

The invention discloses an expressway traffic flow index unified expression method based on space-time relevance, and the method comprises the specific steps: obtaining expressway traffic flow index data based on an Internet of Things monitoring device; based on the highway network and spatial information, dividing pile ends, and determining a time scale; the method comprises the following steps: simplifying traffic flow index data into a speed-vehicle number model, storing the speed-vehicle number model in different time and space dimensions, and establishing a basic data model; calculating flow and density under different time and space according to a speed-vehicle number model, and performing statistics so as to construct a flow density actual model and an optimization theoretical model; and storing the flow density theoretical model in different spatial dimensions, and mutually verifying the flow density theoretical model with the actual model. According to the method, all basic data are reserved, the space-time relevance between the data and the relation between the data indexes are reflected, the traffic flow data and the indexes are efficiently expressed, the data searching time is shortened, and an effective data layer model is established for data prediction.

Description

Technical Field

[0001] The invention belongs to the technical field of traffic monitoring, and in particular relates to a unified expression method for highway traffic flow indicators based on time-space correlation. Background Art

[0002] There are massive amounts of multi-source heterogeneous traffic data on highways, for example: dynamic data includes data collected by multi-source heterogeneous traffic sensors such as toll booth card swiping data, gantry ETC data, surveillance camera data, key vehicle GPS data, etc.; static data includes highway network, entrances and exits, interchanges, pile sections, tunnels, service areas, etc., and traffic indicator data includes flow, speed, density, congestion mileage, travel time, and evolution information of traffic indicators in different time periods in the time dimension, etc. These data have the characteristics of many types of data, different structures, and complex spatiotemporal correlation. However, the existing highway data expression and modeling methods are inefficient and difficult to use data, and the correlation between data is not strong, resulting in a waste of computing resources and difficulty in effectively evaluating traffic conditions in real time, thus affecting urban development.

[0003] Therefore, the existing technology has the technical problems of low correlation between multi-source heterogeneous traffic data and long search time. Summary of the invention

[0004] In order to make up for the deficiencies of the prior art, the present invention provides a unified expression method for highway traffic flow indicators based on spatiotemporal correlation to reduce the search time for traffic data and establish an effective data layer model for data prediction.

[0005] The technical problem solved by the present invention can be achieved by adopting the following technical solutions:

[0006] The unified expression method of highway traffic flow indicators based on time-space correlation specifically includes the following steps:

[0007] S1. Obtain highway traffic flow index data based on IoT monitoring equipment;

[0008] S2. Based on the highway network and spatial information, divide the pile ends and determine the time scale;

[0009] S3. Simplify the traffic flow index data into a speed-vehicle number model, and store it in different time and space dimensions to establish a basic data model;

[0010] S4. Calculate the flow and density at different times and spaces according to the speed-vehicle number model, and make statistics to build a practical flow density model and an optimization theoretical model;

[0011] S5. Store the theoretical flow density model in different spatial dimensions and verify it with the actual model.

[0012] Furthermore, in step S2, the specific operations are:

[0013] S21. Divide each road into multiple equal-length pile segments, the length of the pile segment is L, set the large time period T and the small time period t according to the length of the pile segment, and adjust the size of the time period as needed;

[0014] S22. Using the road name and pile segment as the horizontal and vertical coordinate axes, establish a spatial coordinate system T1, i.e., a spatial relationship layer;

[0015] S23. According to the pile segment length L, a large time period T and a small time period t are set. In order to effectively analyze the time correlation of the data, the small time period t and the large time period T are used as the horizontal and vertical axes respectively to establish a time coordinate system T2, i.e., a time relationship layer.

[0016] Furthermore, in step S3, the specific steps are:

[0017] S31. Simplifying the high-dimensional vector constructed by the traffic flow index data into speed and its corresponding vehicle number data;

[0018] S32. Based on the statistical data of vehicle speed, establish the speed of each pile segment at different times - the number of vehicles model;

[0019] S33. The time coordinate system T2 is stored at each discrete point of the space coordinate system T1, and is established as a basic data model to represent the traffic flow data of a certain section of a certain road at different times.

[0020] Furthermore, the step of establishing the speed-vehicle number model in step S32 is: counting the average speed of each vehicle, and establishing a basic data coordinate system T3 with the average speed and the number of vehicles as the horizontal and vertical axes, and storing the basic data coordinate system T3 at each discrete point of the time coordinate system T2 to represent the speed and corresponding vehicle number data of a certain section of a certain road at a certain time.

[0021] Furthermore, in step S4, based on the basic data coordinate system T3, the flow q at this pile segment is calculated from the total number of vehicles, the density ρ is calculated from the number of vehicles and the pile segment length L, and the average speed v is calculated from the speed v and its corresponding number of vehicles. The density ρ and flow q are used as the horizontal and vertical axes to establish a flow density relationship coordinate system T4, and the flow and density at each time in the pile segment are represented in the form of scattered points in the flow density relationship coordinate system T4, which is used to represent the flow density correspondence distribution diagram of a pile segment of a certain road.

[0022] Furthermore, in step S4, the specific operations include:

[0023] S41. Store the speed-vehicle number model as a node in its corresponding spatiotemporal relationship layer.

[0024] S42. According to the speed-vehicle number model, the average speed at the pile section is calculated:

[0025]

[0026] In the formula, the unit of average speed is km / h, the speed of each vehicle is taken as the middle value of the speed range, and low-speed and speeding vehicles are not counted;

[0027] S43. According to the speed-vehicle number model, the flow rate at the pile section is calculated: The unit is vehicle / h, and the road section taken for the flow rate is the section at the center of the pile section;

[0028] S44. According to the speed-vehicle number model, the density at the pile section is calculated: ρ = q / L, in units of vehicles / km;

[0029] S45. Draw a scatter plot based on the calculated velocity density traffic flow index, and draw a fitting curve of the flow-density relationship using the Underwood flow-density model method in the flow-density relationship coordinate system T4, the formula of which is:

[0030]

[0031] Where k is the density, u f is the free-running speed, k m is the optimal density;

[0032] S46. Use actual traffic flow indicators to optimize the parameters of the relationship analysis model, and improve the fit between the Underwood flow density model and the actual traffic flow indicators by adjusting the parameters in the Underwood flow density model.

[0033] Furthermore, the specific operation of step S5 is: storing the flow density relationship coordinate system T4 with the Underwood fitting curve into the spatial coordinate system T1, the flow density relationship coordinate system T4 can be mutually verified with the basic data coordinate system T3. When the data in the flow density relationship coordinate system T4 deviates greatly from the actual data, it is specifically manifested as large deviations in the flow density data of multiple time dimensions of the same road pile section. At this time, the parameters of the Underwood flow-density model should be modified according to the actual data to improve the fitting of the model. In addition to the case of large deviation from the actual data, the Underwood flow-density model should also be updated regularly.

[0034] Compared with the prior art, the present invention has the following advantages: the present invention processes the data through existing sensor data and static data, and performs dimensionality reduction processing on multi-dimensional indicator data, simplifies multiple traffic flow indicators into a relationship model between speed and its corresponding number of vehicles, the time period size can be adjusted in the time relationship layer, and the traffic flow data under different time periods are analyzed for characteristics. This expression method retains all basic data, and reflects the spatiotemporal correlation between data, the relationship between data indicators, and efficiently expresses highway traffic flow data and indicators, reduces data search time, and establishes an effective data layer model for data prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a flow chart of the method of the present invention;

[0036] Figure 2 It is a schematic diagram of the speed-vehicle number model of the present invention;

[0037] Figure 3 This is a schematic diagram of the space model of the present invention;

[0038] Figure 4 It is a schematic diagram of a time model of a certain high-speed pile section in an embodiment of the present invention;

[0039] Figure 5 Schematic diagram of the speed-vehicle number model of the first Monday of the expressway in an embodiment of the present invention;

[0040] Figure 6 It is a scatter plot of flow rate and density traffic flow index of the present invention;

[0041] Figure 7 It is a schematic diagram of the fitting curve of the Underwood flow density model in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following is a further description of a unified expression method of highway traffic flow indicators based on time-space correlation according to the present invention in conjunction with the accompanying drawings.

[0043] This embodiment takes the K0+000 to K3+000 area of ​​the Guangdong-Guangxi Expressway as an example. This area contains multi-source heterogeneous data such as toll station data, gantry ETC data, surveillance camera data, GPS data, etc. The following method is used to express and model the traffic flow data and indicators in this area.

[0044] like Figure 1 As shown, a unified expression method of highway traffic flow indicators based on spatiotemporal correlation includes the following steps:

[0045] (1) Obtain highway traffic flow indicator data based on IoT monitoring equipment.

[0046] It connects the sensor data of toll booths, gantries ETC, surveillance cameras, key vehicle GPS and other static data on the highway network, entrances and exits, interchanges, pile sections, tunnels, service areas, etc., and converts the sensor data into usable traffic flow indicator data.

[0047] (ii) Based on the highway network and spatial information, the pile ends are divided and the time scale is determined.

[0048] According to the locations of sensors such as toll booths, gantry ETC, and surveillance cameras, the road is divided into multiple equal-length segments. The length of the segment is L, and the length L of each segment should not be too large. The road name and segment are used as the horizontal and vertical coordinate axes to establish a spatial coordinate system T1, i.e., the spatial relationship layer.

[0049] According to the length L of the pile segment, a large time period T and a small time period t are set (the size of the time period can be adjusted as needed). In order to effectively analyze the time relevance of the data, the setting of the large time period T and the small time period t should not be too different. The small time period t and the large time period T are used as the horizontal and vertical axes respectively to establish a time coordinate system T2, that is, a time relationship layer. The large and small time periods in the coordinate system T2 can be parameterized according to the time relevance of the road data to realize the analysis of the road traffic flow characteristics under various time periods. When the large and small time periods are modified, the data changes in the time coordinate system T2 under each spatial dimension are realized by changing the address. In this embodiment, the length of the pile segment of the Guangdong-Guangxi Expressway from K0+000 to K3+000 is set to 500m, the large and small time periods T are weeks, and t is days.

[0050] In this application, the data model uses large and small time periods to perform similarity analysis on the data between months in a year, between weeks in a month, and every day in a week; the time period is adjusted based on the time correlation requirements, and the data at different time scales are unified into the time relationship model and correlation analysis is performed. The size of the time period can be adjusted according to the needs of data correlation analysis. When the size of the time period changes, the data storage location needs to be changed accordingly. The specific method is to use the storage address of the speed-vehicle number model to represent the speed-vehicle number model, store the storage address in the time model, and after modifying the size of the time period in the time model, you only need to modify the storage address at different times.

[0051] (3) Simplify the traffic flow index data into a speed-vehicle number model, store it in different time and space dimensions, and establish it as a basic data model.

[0052] The high-dimensional vector constructed by traffic flow index data is simplified into speed and its corresponding vehicle number data; the average speed of each vehicle is counted, and the basic data coordinate system T3 is established with the average speed and the number of vehicles as the horizontal and vertical axes, and the basic data coordinate system T3 is stored at each discrete point of the time coordinate system T2 to represent the speed and corresponding vehicle number data of a certain road section at a certain time. The time coordinate system T2 is stored at each discrete point of the space coordinate system T1 to establish a basic data model to represent the traffic flow data of a certain road section at each time.

[0053] In this embodiment, the data of various IoT monitoring devices such as toll booths, gantry ETC, surveillance cameras, key vehicle GPS, etc. are converted into vehicle speed data and statistically analyzed, as shown in the following table:

[0054]

[0055] For example, the vehicle speed data statistics of the first day of the first week at the section K0+500 to K1+000 of the Guangdong-Guangxi Expressway are {A1, A2, A3, A4, A5, A6, A7, A8} = {1, 72, 144, 286, 197, 136, 39, 3}. Based on the statistical speed data of each vehicle, a speed-vehicle number model of each section at different times is established. The speed-vehicle number model of the section K0+500 to K1+000 of the first day of the first week is as follows: Figure 2 shown.

[0056] like Figure 3 and Figure 4 As shown, the space model and the time model are established according to the pile segment length L, the large time period T, and the small time period t, and are divided into a space relationship layer and a time relationship layer respectively, wherein the time model is stored in the space model as a node. Figure 3 At the middle address point p1, the horizontal axis road is now the Liangguang Expressway, the vertical axis pile section is the K0+500 to K1+000 pile section, and p1 represents the storage address of the time relationship layer model at the K0+500 to K1+000 pile section of the Liangguang Expressway; similarly, Figure 4 The address q2 in the middle represents the storage address of the speed-vehicle number model of the first Monday of the Liangguang Expressway from K0+500 to K1+000.

[0057] (iv) Calculate the flow rate and density at different times and spaces based on the speed-vehicle number model and conduct statistics to construct an actual flow density model and an optimization theoretical model.

[0058] Based on the basic data coordinate system T3, the flow q at this pile segment is calculated from the total number of vehicles, the density ρ is calculated from the number of vehicles and the pile segment length L, and the average speed v is calculated from the speed v and its corresponding number of vehicles. The flow density relationship coordinate system T4 is established with density ρ and flow q as the horizontal and vertical axes, and the flow and density at each time in the pile segment are represented in the form of scattered points in the flow density relationship coordinate system T4, which is used to represent the flow density correspondence distribution diagram of a pile segment of a certain road.

[0059] like Figure 5 As shown in the figure, the speed-vehicle number model is stored as a node in the corresponding spatiotemporal relationship layer. According to the speed-vehicle number model, the average speed at the pile segment is calculated:

[0060]

[0061] In the formula, the unit of average speed is km / h, the speed of each vehicle is taken as the middle value of the speed range, and low-speed and speeding vehicles are not counted.

[0062] According to the speed-vehicle number model, the flow rate at this pile section is calculated: The unit is vehicle / h, and the road section for the flow rate is the section at the center of the pile section.

[0063] According to the speed-vehicle number model, the density at the pile section is calculated as: ρ = q / L, in units of vehicles / km.

[0064] A scatter plot is drawn based on the calculated velocity density traffic flow index, and the Underwood flow-density model method is used in the flow-density relationship coordinate system T4 to draw a fitting curve of the flow-density relationship. The formula is:

[0065]

[0066] Where k is the density, u f is the free-running speed, k m It is the optimal density. It can be obtained that, in this embodiment, the average vehicle speed on the first Monday of the week at the section from K0+500 to K1+000 of the Liangguang Expressway is about 88.4 km / h; the flow is 878 vehicles / h; and the density is 1756 vehicles / km.

[0067] The actual traffic flow index is used to optimize the parameters of the relationship analysis model, and the fit between the Underwood flow density model and the actual traffic flow index is improved by adjusting the parameters in the Underwood flow density model. Figure 7 As shown in the figure, the optimized Underwood flow-density model has a free-flow speed of 80 km / h and an optimal density of 227 vehicles / km.

[0068] (V) Store the theoretical model of flow density in different spatial dimensions and verify it with the actual model.

[0069] The flow density relationship coordinate system T4 with the Underwood fitting curve is stored in the spatial coordinate system T1. The flow density relationship coordinate system T4 can be mutually verified with the basic data coordinate system T3. When the data in the flow density relationship coordinate system T4 deviates greatly from the actual data, it is specifically manifested as large deviations in the flow density data of multiple time dimensions of the same road segment. At this time, the parameters of the Underwood flow-density model should be modified according to the actual data to improve the fitting of the model. In addition to the case of large deviation from the actual data, the Underwood flow-density model should also be updated regularly.

[0070] In a specific embodiment, the density of a certain section of the Guangdong-Guangxi Expressway at a certain time is 400 vehicles / km. At this time, in the Underwood flow-density model, the theoretical flow rate should be 4000 vehicles / h. If the actual flow rate is 3892 vehicles / h, it is considered that the Underwood flow-density model has a high degree of fit with the actual traffic flow indicators. If the actual flow rate is 3203 vehicles / h, it is necessary to compare the actual flow rates at multiple time nodes to check the randomness of the data. If it is not accidental data, it is necessary to adjust the model parameters to improve the fit between the model and the actual traffic flow indicators.

[0071] Among them, the allowable error value between theoretical data and actual data should be defined according to the characteristics of road historical data.

[0072] The method of the present invention obtains highway traffic flow data based on the Internet of Things monitoring equipment, divides the pile sections based on the spatial information of the highway network, entrances and exits, determines the time scale, simplifies traffic indicators such as flow rate and density into a speed-vehicle number model, stores it in different time and space dimensions, and establishes a basic data model. The speed-vehicle number model calculates the flow and density in different time and space, and performs statistics, thereby constructing an actual flow density model and an Underwood flow density relationship theoretical model, and stores the actual flow density model and the relationship theoretical model in different spatial dimensions, and verifies them with the actual data. Among them, simplifying traffic flow indicators such as flow, speed, and density into a speed-vehicle number model, and storing the speed-vehicle number model in the time relationship layer improves the expression efficiency of the data, reflects the temporal and spatial correlation between data and the correlation between indicators, and efficiently expresses traffic flow data and indicators.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A unified expression method for highway traffic flow indicators based on spatiotemporal correlation, characterized in that: The specific steps include: S1. Obtain highway traffic flow index data based on IoT monitoring equipment; S2. Based on the highway network and spatial information, divide the pile ends and determine the time scale; S3. Simplify the traffic flow index data into a speed-vehicle number model, and store it in different time and space dimensions to establish a basic data model; S4. Calculate the flow and density at different times and spaces according to the speed-vehicle number model, and make statistics to build a practical flow density model and an optimization theoretical model; S5. Store the theoretical flow density model in different spatial dimensions and verify it with the actual model.

2. The unified expression method of highway traffic flow index based on time-space correlation according to claim 1 is characterized in that: In step S2, the specific operations are: S21. Divide each road into multiple equal-length pile segments, the length of the pile segment is L, set the large time period T and the small time period t according to the length of the pile segment, and adjust the size of the time period as needed; S22. Using the road name and pile segment as the horizontal and vertical coordinate axes, establish a spatial coordinate system T1, i.e., a spatial relationship layer; S23. According to the pile segment length L, a large time period T and a small time period t are set. In order to effectively analyze the time correlation of the data, the small time period t and the large time period T are used as the horizontal and vertical axes respectively to establish a time coordinate system T2, i.e., a time relationship layer.

3. The unified expression method of highway traffic flow index based on time-space correlation according to claim 2 is characterized in that: In step S3, the specific steps are: S31. Simplifying the high-dimensional vector constructed by the traffic flow index data into speed and its corresponding vehicle number data; S32. Based on the statistical data of vehicle speed, establish the speed of each pile segment at different times - the number of vehicles model; S33. The time coordinate system T2 is stored at each discrete point of the space coordinate system T1, and is established as a basic data model to represent the traffic flow data of a certain section of a certain road at different times.

4. The unified expression method of highway traffic flow index based on time-space correlation according to claim 3 is characterized in that: The steps of establishing the speed-vehicle number model in step S32 are: counting the average speed of each vehicle, and establishing a basic data coordinate system T3 with the average speed and the number of vehicles as the horizontal and vertical coordinate axes, and storing the basic data coordinate system T3 at each discrete point of the time coordinate system T2 to represent the speed and corresponding vehicle number data of a certain section of a certain road at a certain time.

5. The unified expression method of highway traffic flow index based on time-space correlation according to claim 4 is characterized in that: In step S4, based on the basic data coordinate system T3, the flow rate q at this pile section is calculated from the total number of vehicles, the density ρ is calculated from the number of vehicles and the pile section length L, and the average speed is calculated from the speed v and its corresponding number of vehicles. The flow density relationship coordinate system T4 is established with density ρ and flow q as the horizontal and vertical axes, and the flow and density at each time in the pile segment are expressed in the form of scattered points in the flow density relationship coordinate system T4 to represent the flow density correspondence distribution diagram of a pile segment of a certain road.

6. The unified expression method of highway traffic flow index based on time-space correlation according to claim 5 is characterized in that: In step S4, the specific operations include: S41. Store the speed-vehicle number model as a node in its corresponding spatiotemporal relationship layer. S42. According to the speed-vehicle number model, the average speed at the pile section is calculated: In the formula, the unit of average speed is km / h, the speed of each vehicle is taken as the middle value of the speed range, and low-speed and speeding vehicles are not counted; S43. According to the speed-vehicle number model, the flow rate at the pile section is calculated: The unit is vehicle / h, and the road section taken for the flow rate is the section at the center of the pile section; S44. According to the speed-vehicle number model, the density at the pile section is calculated: ρ = q / L, in units of vehicles / km; S45. Draw a scatter plot based on the calculated velocity density traffic flow index, and draw a fitting curve of the flow-density relationship using the Underwood flow-density model method in the flow-density relationship coordinate system T4, the formula of which is: Where k is the density, u f is the free-running speed, k m is the optimal density; S46. Use actual traffic flow indicators to optimize the parameters of the relationship analysis model, and improve the fit between the Underwood flow density model and the actual traffic flow indicators by adjusting the parameters in the Underwood flow density model.

7. The unified expression method of highway traffic flow index based on time-space correlation according to claim 6 is characterized in that: The specific operation of step S5 is: storing the flow density relationship coordinate system T4 with the Underwood fitting curve into the spatial coordinate system T1. The flow density relationship coordinate system T4 can be mutually verified with the basic data coordinate system T3. When the data in the flow density relationship coordinate system T4 deviates greatly from the actual data, it is specifically manifested as large deviations in the flow density data of multiple time dimensions of the same road pile section. At this time, the parameters of the Underwood flow density model should be modified according to the actual data to improve the fitting of the model. In addition to the case of large deviation from the actual data, the Underwood flow density model should also be updated regularly.

Images