Traffic flow prediction device, traffic flow prediction method and program

Abstract

To provide a technology that makes it possible to highly precisely simulate a traffic flow while suppressing a decrease in processing time.SOLUTION: A traffic flow prediction system includes: a speed acquisition unit that acquires a first speed which is a statistic of a vehicle speed at which a vehicle travels in a predetermined block; a traffic volume acquisition unit that acquires a first traffic volume of the vehicle which has entered the predetermined block; a traffic density acquisition unit that acquires a first traffic density of the predetermined block at a first time instant; and a simulation execution unit that predicts a second traffic density of the predetermined block at a second time instant succeeding the first time instant on the basis of the first traffic density, first speed, and first traffic volume.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a traffic flow prediction device, a traffic flow prediction method, and a program. [Background technology]

[0002] In recent years, various techniques have become known for simulating traffic flow based on sensor data collected by sensors.

[0003] For example, Patent Document 1 discloses a technology for constructing a multi-input, multi-output block module in which independent blocks are arranged in parallel for each lane, and providing each block with an attribute that describes regulations (such as route regulations or vehicle-specific regulations). This technology provides a routine for selectively moving only vehicles that satisfy the regulations from multiple upstream blocks to downstream blocks adjacent to those multiple blocks. This makes it possible to represent lane changes and traffic regulations for vehicles between adjacent upstream and downstream blocks (see, for example, paragraph 0016).

[0004] Furthermore, Non-Patent Document 1 discloses a technology for switching the traffic flow simulation model used in the section where traffic disturbance occurs or in the buffer section located upstream of the section where traffic disturbance occurs from a macro simulation model to a micro simulation model when a traffic disturbance occurs (for example, Figure 2 "Outline flow of integrated traffic flow simulation model").

[0005] Furthermore, Non-Patent Document 2 discloses a technique in which the simulation models at the beginning and end of a congested section are microsimulation models, and the simulation models at positions other than the beginning and end of the congested section are macrosimulation models, thereby improving processing speed and accuracy. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent No. 2826083 [Non-patent literature]

[0007] [Non-Patent Document 1] Masashi Okaue and Masashi Okushima, "Basic Study on Real-time Traffic Flow Simulation of Expressways in Case of Traffic Disasters", Journal of the Japan Society of Civil Engineers, Vol. D3 (Civil Engineering Planning), 2011, Vol. 67, No. 5, I_1071-I_1078 [Non-patent document 2] Toru Takahashi, Kazunori Abe, Hideki Fujii, Keiji Ikata, Masaki Matsudaira, “Development of a Dynamic Hybrid Traffic Flow Simulation Model and Its Verification Using Actual Expressway Data”, 2021, Transactions of the Japan Society for Simulation Technology, Vol. 13, No. 1, pp. 37-47 Summary of the Invention [Problem to be solved by the invention]

[0008] However, it is desirable to provide a technology that enables traffic flow simulation with high accuracy while suppressing a decrease in processing time. [Means for solving the problem]

[0009] In order to solve the above problem, according to one aspect of the present invention, a first speed, which is a statistic of the speed of a vehicle traveling through a predetermined block, is acquired. thing and obtain a first traffic volume of vehicles that have flowed into the predetermined block. thing and obtain a first traffic density of the predetermined block at a first time. thing the first traffic density, and the first speed. Mixing results with predetermined free stream velocity and and predicting a second traffic density of the predetermined block at a second time later than the first time based on the first traffic volume. thing and, Computer-implemented traffic flow prediction method is provided. In order to solve the above problem, according to another aspect of the present invention, there is provided a traffic flow prediction method executed by a computer, comprising: acquiring a first speed, which is a statistic of the speed of vehicles traveling through a specified block; acquiring a first traffic volume of vehicles entering the specified block; acquiring a first traffic density of the specified block at a first time; predicting a second traffic density of the specified block at a second time after the first time based on the first traffic density, the first speed, and the first traffic volume; and, if the second traffic density is equal to or lower than a specified traffic density, predicting the second speed, which is a statistic of the speed of vehicles traveling through the specified block during a period corresponding to the second time, based on a relational expression indicating the relationship between traffic density and vehicle speed that has been generated in advance. In addition, according to another aspect of the present invention to solve the above problem, there is provided a traffic flow prediction method executed by a computer, comprising: acquiring a first speed, which is a statistic of the speed of vehicles traveling through a specified block; acquiring a first traffic volume of vehicles entering the specified block; acquiring a first traffic density of the specified block at a first time; predicting a second traffic density of the specified block at a second time after the first time based on the first traffic density, the first speed, and the first traffic volume; and, if the second traffic density exceeds the specified traffic density, predicting the second speed, which is a statistic of the speed of vehicles traveling through the specified block during a period corresponding to the second time, based on the traffic density and traffic volume of the specified block during a period prior to the period corresponding to the first time and the second traffic density.

[0011] Predicting the second traffic density includes: The second traffic density is predicted further based on a ratio of the number of lanes available for traffic to the total number of lanes in the predetermined block. Including Good too.

[0012] Predicting the second traffic density includes: Based on the first traffic density and the first speed, a traffic volume of vehicles flowing into a downstream block of the predetermined block is predicted as a downstream block traffic volume, and based on the downstream block traffic volume, the first traffic volume, and the first traffic density, the second traffic density is predicted. Including Good too.

[0013] Predicting the second traffic density includes: The second traffic density is predicted based on a difference between the downstream block traffic volume and the first traffic volume, the length of the predetermined block, the time interval between the first time and the second time, and the first traffic density. Including Good too.

[0014] In addition, according to another aspect of the present invention to solve the above problem, there is provided a traffic flow prediction method executed by a computer, comprising: acquiring a first speed, which is a statistical quantity of vehicle speeds traveling through a specified block; acquiring a first traffic volume of vehicles entering the specified block; acquiring a first traffic density of the specified block at a first time; and, if a multiplication result of a predetermined maximum traffic volume and a ratio of the number of passable lanes to the total number of lanes in the specified block is smaller than the traffic volume based on the multiplication result of the first traffic density and the first speed, predicting a second traffic density of the specified block at a second time after the first time based on the multiplication result, the first traffic volume, and the first traffic density.

[0015] In order to solve the above problem, according to another aspect of the present invention, there is provided a traffic flow prediction method executed by a computer, comprising: acquiring a first speed, which is a statistic of vehicle speeds traveling through a specified block; acquiring a first traffic volume of vehicles that have entered the specified block; acquiring a first traffic density of the specified block at a first time; and, if a first multiplication result of a difference between a predetermined maximum traffic density and the first traffic density and a ratio of the number of passable lanes to the total number of lanes in the specified block and a predetermined congestion wave propagation speed is smaller than the traffic volume based on the multiplication result of the first traffic density and the first speed, predicting a second traffic density of the specified block at a second time after the first time based on the second multiplication result, the first traffic volume, and the first traffic density.

[0019] Traffic flow prediction method predicts a second traffic volume of vehicles entering the predetermined block based on a traffic volume of vehicles entering the predetermined block in a period prior to a period corresponding to the first time. thing may also be provided.

[0020] A program for causing a computer to execute the traffic flow prediction method is provided Good .

[0021] A traffic flow prediction device, wherein the computer functions as the traffic flow prediction device by executing the program. is provided Good . [Effects of the Invention]

[0022] As described above, the present invention provides a technique that enables traffic flow simulation with high accuracy while suppressing a decrease in processing time. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a diagram illustrating an example of a functional configuration of a traffic flow prediction device according to an embodiment of the present invention. [Figure 2] 5A and 5B are diagrams illustrating examples of various common parameters stored in a common parameter storage unit. [Figure 3] FIG. 10 is a diagram illustrating an example of free flow data stored by a free flow data storage unit. [Figure 4] FIG. 4 is a diagram illustrating an example of probe data stored in a probe data storage unit. [Figure 5] FIG. 1 is a diagram showing a set of traffic density (K) and speed (V) and a KV relational expression. [Figure 6] 10 is a flowchart illustrating an example of a KV parameter creation process executed by a KV parameter creation unit. [Figure 7] 10 is a diagram for explaining an example of calculation of the passing time at a measurement point of a vehicle that has arrived at an estimation point; FIG. [Figure 8] 10 is a diagram for explaining an example of calculating the traffic volume at an estimation point from the traffic volume at a measurement point; FIG. [Figure 9] 10 is a flowchart illustrating an example of a traffic density calculation process executed by a traffic density calculation unit. [Figure 10] This is a diagram showing the traffic volume, speed, and traffic density corresponding to each of three consecutive cells. [Figure 11] FIG. 10 is a diagram for explaining the overall flow of a simulation. [Figure 12] FIG. 10 is a diagram showing a simulation result in a comparative example. [Figure 13]FIG. 3 is a diagram showing a first simulation result by the traffic flow prediction device according to the embodiment of the present invention. [Figure 14] FIG. 10 is a diagram showing a second simulation result by the traffic flow prediction device according to the embodiment of the present invention. [Figure 15] FIG. [Figure 16] 1 is a diagram illustrating a hardware configuration of an information processing device as an example of a traffic flow prediction device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant explanations will be omitted.

[0025] Furthermore, in this specification and drawings, multiple components having substantially the same functional configuration may be distinguished by adding different numbers after the same reference numeral. However, if there is no particular need to distinguish between multiple components having substantially the same functional configuration, only the same reference numeral will be used. Furthermore, similar components in different embodiments may be distinguished by adding different letters after the same reference numeral. However, if there is no particular need to distinguish between similar components in different embodiments, only the same reference numeral will be used.

[0026] (0. Overview) First, an outline of the embodiment of the present invention will be described.

[0027] In recent years, various techniques have been known for simulating traffic flow based on sensor data collected by sensors, such as the technique disclosed in Patent Document 1, the technique disclosed in Non-Patent Document 1, and the technique disclosed in Non-Patent Document 2, as described above.

[0028] However, Patent Document 1 does not disclose how to calculate the traffic density of a block of lanes that remain passable when some lanes are blocked due to traffic restrictions (including traffic restrictions due to an accident, etc.). Furthermore, Patent Document 1 does not disclose how to calculate the traffic density of each lane block located downstream from the lane block where traffic restrictions are in place. In other words, the technology disclosed in Patent Document 1 cannot perform a highly accurate traffic flow simulation when traffic restrictions are in place.

[0029] Furthermore, in the techniques disclosed in Non-Patent Document 1 and Non-Patent Document 2, the processing time increases as the section in which the microsimulation is performed becomes longer. Non-Patent Document 2 reports that the processing time for macrosimulation in a simulation of a total length of 4 km is 0.121 seconds, while the processing speed for microsimulation is 25.045 seconds (Fig. 11: Comparison of calculation times). Therefore, in actual operation on large-scale expressways, it is desirable to perform processing using only macrosimulation.

[0030] Therefore, this specification mainly describes a technology that enables highly accurate traffic flow simulation while suppressing a decrease in processing time. More specifically, this specification describes a technology that enables highly accurate traffic flow simulation while suppressing a decrease in processing time by performing processing only by macro-simulation even when traffic restrictions are in place.

[0031] The outline of the embodiment of the present invention has been described above.

[0032] (1. Details of the embodiment) First, details of the embodiment of the present invention will be described.

[0033] (1-1. Configuration of the traffic flow prediction device) First, a configuration example of a traffic flow prediction device 1 according to an embodiment of the present invention will be described. Fig. 1 is a diagram showing a functional configuration example of a traffic flow prediction device 1 according to an embodiment of the present invention.

[0034] Referring to FIG. 1, vehicles M1 to M3 are shown as examples of vehicles traveling on a road. Referring further to FIG. 1, vehicles M1 and M2 are traveling in the far lane (vehicle M1 is traveling following vehicle M2), and vehicle M3 is traveling in the near lane in the opposite direction to vehicles M1 and M2 in the far lane. As described above, the embodiment of the present invention mainly assumes that the road is made up of multiple lanes, but the road may also be made up of a single lane. Each of vehicles M1 to M3 is equipped with an on-board device. Note that lane can also be referred to as "lane."

[0035] A traffic flow prediction device 1 according to an embodiment of the present invention includes an event data storage unit 120, a driving history data storage unit 121, a probe data storage unit 122, a free flow data storage unit 123, a traffic volume data storage unit 124, a KV parameter storage unit 125, a common parameter storage unit 126, a traffic density data storage unit 127, and a predicted traffic volume data storage unit 128. The traffic flow prediction device 1 according to an embodiment of the present invention also includes an event input unit 150, a statistical processing unit 131, a traffic volume calculation unit 133, and a processing unit 140. The processing unit 140 includes a KV parameter creation unit 141, a traffic density calculation unit 142, a traffic volume prediction unit 143, and a simulation execution unit 144.

[0036] The driving history data storage unit 121 is connected to the probe antenna 112, and the free flow data storage unit 123 is connected to the free flow antenna 114.

[0037] The statistical processing unit 131, the traffic volume calculation unit 133, and the processing unit 140 include an arithmetic unit such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), and their functions can be realized by the arithmetic unit expanding a program stored in a ROM (Read Only Memory) into a RAM and executing it. In this case, a computer-readable recording medium on which the program is recorded can also be provided.

[0038] Alternatively, the statistical processing unit 131, the traffic volume calculation unit 133, and the processing unit 140 may be configured by dedicated hardware or may be configured by a combination of multiple pieces of hardware. Data necessary for calculations by the calculation device is stored as appropriate in a storage unit (not shown).

[0039] The event data storage unit 120, the driving history data storage unit 121, the probe data storage unit 122, the free flow data storage unit 123, the traffic volume data storage unit 124, the KV parameter storage unit 125, the common parameter storage unit 126, the traffic density data storage unit 127, and the predicted traffic volume data storage unit 128 are stored in a storage unit (not shown). Such a storage unit may be configured by a memory such as a RAM (Random Access Memory), a hard disk drive, or a flash memory.

[0040] (Common parameter storage unit 126) Various common parameters are stored in advance in the common parameter storage unit 126. Examples of the common parameters will now be described with reference to FIG.

[0041] FIG. 2 is a diagram showing examples of various common parameters stored in the common parameter storage unit 126. As shown in FIG.

[0042] 2, the common parameter storage unit 126 stores, as examples of common parameters, a driving history time range 711, a driving history location range 712, a simulation execution time interval 721, and a simulation execution cell range 722. Furthermore, the common parameter storage unit 126 stores, as examples of common parameters, a congestion flow determination speed 741, a maximum traffic volume 742, a maximum traffic density 743, a free flow speed 744, and a congestion wave propagation speed 745.

[0043] (Event input unit 150) The event input unit 150 receives input from the user of information for specifying a section where vehicle passage is restricted (hereinafter also referred to as a "restricted section") and information regarding lanes where vehicles are not permitted to pass in the restricted section (for example, the number of lanes where vehicles are not permitted to pass). Note that the reason why vehicle passage is restricted is not particularly limited. For example, the reason why vehicle passage is restricted may be the occurrence of an accident, the presence of an obstacle on the road, scheduled construction work, etc.

[0044] For example, the event input unit 150 may be configured with an input device such as a mouse or a keyboard. However, the event input unit 150 may also be configured with other input devices. For example, the event input unit 150 may be configured with a touch panel or buttons.

[0045] For example, assume that the user inputs information specifying the measurement starting point "Point A" and the distance "24 km" from the measurement starting point "Point A." In this case, for example, if the simulation execution cell width 722 is "200 m," the 120th section from the measurement starting point (24 km / 200 m =) is specified as the restricted section.

[0046] The total number of lanes for each section may be stored in advance by the event data storage unit 120. For example, assume that the user inputs "1" as the number of lanes on which vehicles cannot travel in a restricted section with a total number of lanes of "3." In this case, the ratio of the number of passable lanes to the total number of lanes in the restricted section can be calculated as follows: (total number of lanes - number of passable lanes) / total number of lanes = (3 - 1) / 3 = "2 / 3."

[0047] Information for specifying the restricted section received from the user by the event input unit 150, and information regarding lanes on which vehicles cannot travel in the restricted section (e.g., the number of lanes on which vehicles cannot travel) are output to the event data storage unit 120.

[0048] (Free Flow Antenna 114) The free flow antenna 114 functions as an example of a vehicle detection unit that detects vehicles traveling at various positions on a road. That is, in the embodiment of the present invention, it is mainly assumed that the vehicle detection unit includes the free flow antenna 114. As a result, an ETC free flow antenna of an already established ETC (Electronic Toll Collection) system can be used as the vehicle detection unit, eliminating the need to provide a new vehicle detection unit. However, instead of the free flow antenna 114, another vehicle detection unit (for example, a vehicle detector, an infrared sensor, or an ultrasonic sensor) may be used.

[0049] More specifically, the free flow antenna 114 detects vehicles in real time by receiving vehicle identification information (vehicle ID) from the vehicle through communication with an on-board unit mounted on the vehicle. In the embodiment of the present invention, a case where an ETC on-board unit is used is mainly assumed as an example of the on-board unit. Note that the free flow antenna 114 may be compatible with multiple versions of ETC on-board units, while the probe antenna 112, which will be described later, may be compatible only with a specific version of ETC on-board unit. In other words, the free flow antenna 114 can detect more vehicles than the probe antenna 112.

[0050] Note that the "positions" on the road where a vehicle is detected by the free flow antenna 114 are not particularly limited as long as they are vehicle positions that can be detected by the vehicle detection unit. Hereinafter, each position on the road where a vehicle can be detected by the free flow antenna 114 may be simply referred to as a "free flow antenna position."

[0051] When the free flow antenna 114 detects a vehicle in real time by receiving a vehicle ID through communication with an on-board device mounted on the vehicle, it outputs the vehicle detection result (hereinafter also referred to as "free flow data") in real time to the free flow data storage unit 123. The vehicle detection result output in real time from the free flow antenna 114 to the free flow data storage unit 123 can then be used in real time by the traffic volume calculation unit 133.

[0052] Here, "real-time" can mean any short period of time between when a vehicle arrives at the free flow antenna position and when the traffic conditions on the road change. If a vehicle is detected at this time, some action can be taken according to the traffic conditions at the time the vehicle is detected before the traffic conditions on the road change.

[0053] FIG. 3 is a diagram showing an example of free flow data stored by the free flow data storage unit 123. As shown in FIG. 3, the free flow data is made up of a "vehicle ID" and a "passing time" associated with each other. The "vehicle ID" is vehicle identification information received from the vehicle through communication between the free flow antenna 114 and an onboard device mounted on the vehicle. The "passing time" is the time when the vehicle ID is received from the vehicle by the free flow antenna 114, and may correspond to the time when the vehicle passed the free flow antenna position.

[0054] (Traffic volume calculation unit 133) The traffic volume calculation unit 133 acquires the detection results (free flow data) of vehicles traveling through the free flow antenna position from the free flow data storage unit 123 (FIG. 3). Then, based on the free flow data (vehicle IDs and passing times), the traffic volume calculation unit 133 calculates the number of vehicles that pass the free flow antenna position per preset unit time (the number of vehicle IDs detected per unit time by the free flow antenna 114) as the traffic volume at the free flow antenna position. The traffic volume calculation by the traffic volume calculation unit 133 may be repeatedly performed for each unit time.

[0055] It should be noted that not all vehicles that pass the free flow antenna position are necessarily equipped with an on-board unit capable of communicating with the free flow antenna 114. In other words, not all vehicles that pass the free flow antenna position are necessarily detected by the free flow antenna 114. Therefore, if the ratio of vehicles equipped with on-board units capable of communicating with the free flow antenna 114 to the total number of vehicles (including vehicles that do not have on-board units capable of communicating with the free flow antenna 114) is set in advance as the "on-board unit installation ratio," and the number of vehicles detected by the free flow antenna 114 is set as the "number of detected vehicles," it is desirable for the traffic volume calculation unit 133 to more accurately estimate the traffic volume at the free flow antenna position using the following formula (1):

[0056] (Estimated traffic volume) = (Number of detected vehicles) ÷ (Proportion of vehicles equipped with on-board devices) (1)

[0057] However, such estimation may be omitted in cases where there is a sufficient prevalence of in-vehicle devices capable of communicating with the free flow antenna 114. The traffic volume estimated by the traffic volume calculation unit 133, the measurement time which is the end of the time corresponding to that traffic volume, and the free flow antenna position corresponding to that traffic volume are output to the traffic volume data storage unit 124 as traffic volume data corresponding to each free flow antenna position every time the traffic volume is estimated.

[0058] (Probe antenna 112) The probe antenna 112 functions as an example of a driving history data acquisition unit that acquires driving history data of a vehicle. That is, in the embodiment of the present invention, it is mainly assumed that the driving history data acquisition unit includes the probe antenna 112. This allows the ETC probe antenna of an already established ETC system to be used as the driving history data acquisition unit, eliminating the need to provide a new driving history data acquisition unit. However, instead of the probe antenna 112, another driving history data acquisition unit (for example, a mobile base station) may be used.

[0059] More specifically, when the probe antenna 112 acquires driving history data from the vehicle through communication with an on-board device mounted on the vehicle, the probe antenna 112 outputs the acquired driving history data to the driving history data storage unit 121. The driving history data output from the probe antenna 112 to the driving history data storage unit 121 can then be used by the statistical processing unit 131.

[0060] The driving history data includes the speed of each vehicle traveling on each section (between kilometer posts) on the road for each driving history point width 712 (for example, 100 m) for each driving history time width 711 (for example, 1 minute), and the collection time, which is the time when the speed was collected by the probe antenna 112.

[0061] (Statistical processing unit 131) The statistical processing unit 131 acquires the driving history data from the driving history data storage unit 121, performs statistical processing on the driving history data, and outputs the driving history data after the statistical processing as probe data to the probe data storage unit 122. The probe data output from the statistical processing unit 131 to the probe data storage unit 122 can then be used by the KV parameter creation unit 141.

[0062] For example, the statistical processing unit 131 performs a predetermined statistical process (for example, averaging process) on the speeds of one or more vehicles that traveled in each section (between kilometer posts) on the road in each travel history point width 712 for each travel history time width 711. This provides statistics of the vehicle speeds in each section on the road for each travel history time width 711. An example of the averaging process is a process of taking a harmonic mean.

[0063] Fig. 4 is a diagram showing an example of probe data stored by the probe data storage unit 122. As shown in Fig. 4, the probe data is made up of "passing time," "kilometer post," "speed," and "collection time" associated with each other.

[0064] The "passing time" is the time when the vehicle passes a distance marker (kilometer post) from the start point of the road. A "kilometer post" is a distance marker from the start point of the road.

[0065] "Speed" is a statistic (e.g., average speed) of one or more vehicle speeds traveling along each section (between kilometer posts) on the road for each travel history time span 711 (between passing times). For example, "Speed: 80 km / h" is a statistic of the speed of one or more vehicles traveling from "Kilopost: 100" to "Kilopost: 100.1" between "Passing Time: 10:23 AM, January 1, 2019" and "10:24 AM, January 1, 2019."

[0066] The "collection time" is the time when the vehicle speed is collected by the probe antenna 112.

[0067] (KV parameter creation unit 141) The KV parameter creation unit 141 acquires the speed and end time for a predetermined period for each free flow antenna position from the probe data storage unit 122. Furthermore, the KV parameter creation unit 141 acquires traffic volume data (traffic volume and passing time) for a predetermined period for each free flow antenna position from the traffic volume data storage unit 124.

[0068] The KV parameter creation unit 141 creates parameters indicating the correspondence between traffic density (K) and speed (V) (in the example below, an approximate formula) for each free flow antenna position using machine learning based on the traffic volume and passing time for a predetermined period, and the speed and measurement time for the predetermined period.

[0069] More specifically, the KV parameter creation unit 141 associates traffic volume (Q) and speed (V) corresponding to the same time and the same free flow antenna position, and then calculates the traffic density (K) for each associated traffic volume (Q) and speed (V) using the following equation (2).

[0070] K = Q × 1 / (V × 60) (2)

[0071] where K indicates traffic density (vehicles / km), Q indicates traffic volume (vehicles / min), and V indicates speed (km / hour). The KV parameter creation unit 141 approximates a pair of corresponding traffic density (K) and speed (V) using a predetermined relationship, and creates the parameters of the approximation equation (KV relational equation) obtained by the approximation as KV parameters.

[0072] Here, it is assumed that the KV parameter creation unit 141 creates parameters of an approximation equation corresponding to a congestion flow. More specifically, it is assumed that the KV parameter creation unit 141 creates parameters of a KV relational equation corresponding to a congestion flow by approximating, in a predetermined relationship, a pair of a speed (V) equal to or less than a congestion flow determination speed 741 (for example, 55 km / h on a highway) and a traffic density (K) corresponding to that speed (V). For example, the KV relational equation corresponding to a congestion flow may be an exponential function expressed by the following equation (3):

[0073] V = a × exp(-b × K) (3)

[0074] where K indicates traffic density (vehicles / km), V indicates speed (km / hour), and a and b are KV parameters. In this specification, congested flow is used as a concept that is included in jammed flow, and can refer to a state in which the speed is greater than a certain value even in jammed flow.

[0075] Fig. 5 is a diagram showing pairs of traffic density (K) and speed (V) and the KV relational expression. In the example shown in Fig. 5, the horizontal axis represents traffic density (K) and the vertical axis represents speed (V). In the KV diagram, each pair of traffic density (K) and speed (V) associated with each other is plotted as a point. Also, Fig. 5 shows an exponential function indicating the KV relational expression obtained by approximating these pairs.

[0076] The KV parameter creating unit 141 stores the created KV parameters in the KV parameter storage unit 125. Typically, the predetermined period may be one month. However, the predetermined period is not limited to one month. For example, the predetermined period may be one day.

[0077] 6 is a flowchart showing an example of KV parameter creation processing executed by the KV parameter creation unit 141. First, the KV parameter creation unit 141 acquires the speed and passing time for each free flow antenna position for a predetermined period from the probe data storage unit 122 (S11). The KV parameter creation unit 141 also acquires traffic volume data (traffic volume and measurement time) for each free flow antenna position for a predetermined period from the traffic volume data storage unit 124 (S12).

[0078] The KV parameter creation unit 141 associates the traffic volume (Q) and speed (V) corresponding to the same time and the same free flow antenna position, and then calculates the traffic density (K) for each associated traffic volume (Q) and speed (V) (S13).

[0079] The KV parameter creation unit 141 creates parameters of a KV relational equation that indicates the relationship between traffic density (K) and speed (V) through machine learning (S14). More specifically, the KV parameter creation unit 141 approximates a pair of corresponding traffic density (K) and speed (V) with a predetermined relationship (for example, an exponential function), and creates the parameters of the KV relational equation obtained by the approximation as KV parameters. Here, it is assumed that the KV parameter creation unit 141 creates parameters of an approximation equation that corresponds to a traffic congestion flow.

[0080] The KV parameter creating unit 141 stores the created KV parameters in the KV parameter storage unit 125 (S15).

[0081] (Traffic density calculation unit 142) The traffic density calculation unit 142 acquires the speed and unit time for each section from the current time to a predetermined set time ago (for example, one hour ago) at a preset simulation execution time interval 721 (for example, every five minutes) from the probe data storage unit 122. In addition, the traffic density calculation unit 142 acquires traffic volume data (traffic volume and unit time) for each free flow antenna position from the traffic volume data storage unit 124 at the simulation execution time interval 721 from the current time to a predetermined set time ago.

[0082] The traffic density calculation unit 142 calculates the traffic density in each section based on at least the speed in each section. Here, the traffic density in each section may be calculated in any specific manner.

[0083] For example, the traffic density calculation unit 142 may acquire KV parameters from the KV parameter storage unit 125 and calculate the traffic density in a target section (first section) on a road based on the speed in the target section and the KV relational equation defined by the KV parameters.

[0084] More specifically, the traffic density calculation unit 142 may calculate the traffic density in a section that is a congested flow, i.e., a target section where the speed is equal to or less than the congested flow determination speed 741 (threshold value), based on the speed in the target section and the KV relational equation.

[0085] Furthermore, the traffic density calculation unit 142 may set a point on a road corresponding to a target section (second section) as an estimated point, and calculate the traffic density in the target section based on the traffic volume at the estimated point and the speed in the target section. For example, the estimated point may be the starting point of the target section.

[0086] More specifically, the traffic density calculation unit 142 may calculate the traffic density in a target section where the speed exceeds the congested flow determination speed 741 based on the traffic volume at the estimation point and the speed in the target section. For example, the traffic density calculation unit 142 may calculate the traffic volume at the estimation point based on the traffic volume at the measurement point calculated by the traffic volume calculation unit 133 and the speed for each section from the measurement point to the target section. For example, the measurement point may be a free flow antenna position upstream from the target section (e.g., the free flow antenna position closest upstream from the target section).

[0087] An example of a method for calculating the traffic density in a target section based on the traffic volume at an estimation point and the speed in the target section will be described with reference to FIGS.

[0088] FIG. 7 is a diagram illustrating an example of calculating the passing time at a measurement point of a vehicle that has arrived at an estimated point. In the example shown in FIG. 7, the horizontal axis represents distance on the road (the right direction is the downstream direction on the road), and the horizontal axis represents time (the downward direction is the direction of elapsed time). The speed corresponding to a section (between kilometer posts) and unit time (between passing times) in the driving history data is indicated by the darkness of the color within the rectangle (space-time range) corresponding to that section and unit time. In this example, the darker the color within the rectangle, the lower the speed.

[0089] The traffic density calculation unit 142 calculates a trajectory from the estimated point and the time at the estimated point, upstream and in the past, to the measurement point, based on the speed corresponding to each section and time. More specifically, the traffic density calculation unit 142 calculates a trajectory from the estimated point and the time at the estimated point, such that the trajectory moves within the rectangle along a straight line with a slope corresponding to the speed corresponding to each section and time, and moves between adjacent rectangles at the boundaries of the rectangles.

[0090] As a result, the traffic density calculation unit 142 can obtain the time at which the trajectory arrives at the measurement point as the passing time at the measurement point. Referring to Figure 7, the trajectories of two vehicles are depicted. Here, the traffic volume between the arrival times of the two vehicles at the estimated point and the traffic volume between the passing times of the two vehicles at the measurement point can be considered to be the same.

[0091] 8 is a diagram for explaining an example of calculating the traffic volume at the estimation point from the traffic volume at the measurement point. Referring to FIG. 8, the traffic volume Q between the arrival times at the estimation point and the traffic volume Q between the passing times at the measurement point are shown. Here, the traffic volume between the passing times at the measurement point is stored in the traffic volume data storage unit 124. Therefore, the traffic density calculation unit 142 can acquire the traffic volume Q between the passing times at the measurement point from the traffic volume data storage unit 124.

[0092] The traffic density calculation unit 142 can calculate the traffic volume at the estimation point from the traffic volume Q between the passing times at the measurement point by the ratio of the arrival time difference at the estimation point to the passing time difference at the measurement point. For example, if the passing time difference at the measurement point is t1 and the arrival time difference at the estimation point is t2, the traffic density calculation unit 142 can calculate the traffic volume at the estimation point by multiplying the traffic volume Q between the passing times at the measurement point by t1 / t2. Hereinafter, this method of calculating the traffic volume at the estimation point from the traffic volume at the measurement point is also referred to as a traffic volume calculation method using "vehicle tracking."

[0093] 9 is a flowchart showing an example of a traffic density calculation process executed by the traffic density calculation unit 142. First, the traffic density calculation unit 142 acquires the speed and passage time for each section from the current time to a predetermined set time before during a preset simulation execution time interval 721 from the probe data storage unit 122 (S21).

[0094] Furthermore, the traffic density calculation unit 142 acquires traffic volume data (traffic volume and measurement time) for each free flow antenna position from the current time to a predetermined set time ago during the simulation execution time interval 721 from the traffic volume data storage unit 124 (S22). The traffic density calculation unit 142 determines whether the speed in the target section is equal to or less than the congestion flow speed, i.e., the congestion flow determination speed 741 (S23).

[0095] If the speed in the target section is the congestion flow speed (i.e., a speed that is equal to or lower than the congestion flow determination speed 741) ("YES" in S23), the traffic density calculation unit 142 calculates the traffic density in the target section based on the speed in the target section and the KV relational equation (S24).

[0096] On the other hand, if the speed in the target section is the free flow speed (i.e., a speed higher than the congested flow determination speed 741) ("NO" in S23), the traffic density calculation unit 142 calculates the traffic volume at the measurement point by vehicle tracking, and calculates the traffic density in the target section based on the calculated traffic volume at the measurement point and the speed of each section from the measurement point to the target section (S25). The traffic density calculation unit 142 outputs traffic density data, in which the traffic volume measurement time, section, and traffic density are associated, to the traffic density data storage unit 127.

[0097] (Traffic Volume Prediction Unit 143) The traffic volume prediction unit 143 can calculate the traffic volume of vehicles flowing into each cell by setting an estimation point at the starting point of a block (hereinafter also referred to as a "cell") that constitutes a road and performing a process for calculating the traffic volume at the estimation point by vehicle tracking (i.e., based on the traffic volume at the measurement point and the speed for each section from the measurement point to the cell). For example, the traffic volume prediction unit 143 can calculate the traffic volume of vehicles flowing into each cell during the period corresponding to the start time (first traffic volume) by performing a process for calculating the traffic volume at the estimation point for the period from a unit time before the start time to the start time (hereinafter also referred to as a "period corresponding to the start time").

[0098] Here, the cell is represented as i (i is an integer satisfying 1≦i≦N), the start time is represented as t, and the traffic volume flowing into cell i is represented as Q i In this case, the traffic volume (vehicles / minute) flowing into cell i from cell i-1 during the period corresponding to the start time t is expressed as Q i That is, the traffic volume prediction unit 143 calculates the traffic volumes Q1(t) to Q2(t) of each cell in the period corresponding to the start time t. N (t) can be calculated.

[0099] The start time t may be a time designated by the user in advance or may be the current time, and the start point and end point may be positions designated by the user in advance.

[0100] The width of each cell is defined by the simulation execution cell width 722. Meanwhile, the width of each section is defined by the driving history point width 712. The width of each cell may be the same as the width of each section, or may be different from the width of each section. For example, the width of each section may be 100 m, while the width of each cell may be 500 m.

[0101] Furthermore, the traffic volume prediction unit 143 executes, for each cell, a process of predicting the traffic volume of vehicles that will flow into the cell in a period after the start time (second traffic volume). For example, the traffic volume of vehicles that have flowed into each cell in a period before the period corresponding to the start time has already been calculated by the traffic volume prediction unit 143. Therefore, the traffic volume prediction unit 143 executes, for each cell, a process of predicting the traffic volume of vehicles that will flow into the cell in a period after the start time, based on the traffic volume of vehicles that have flowed into the cell in a period before the period corresponding to the start time.

[0102] Here, the step time interval (minutes) of the simulation is expressed as Δt, and the end time is expressed as t+MΔt (M is the number of simulation runs). In this case, the traffic volume flowing into cell i during the period from the start time to the time Δt after the start time is Q i (t+Δt), and the traffic volume flowing into cell i during the period from the unit time before the end time to the end time is Q i In addition, if m is an integer satisfying 1≦m≦M, the traffic volume flowing into cell i in the mth period after the period corresponding to the start time t (hereinafter also referred to as "the period corresponding to time t+mΔt") is Q i It is expressed as (t+mΔt).

[0103] For example, the traffic volume prediction unit 143 predicts the traffic volume Q flowing into the cell i during the period corresponding to the time t+mΔt. i (t+mΔt) may be predicted based on the past traffic volume that flowed into the same cell as cell i at the same time and day of the week as time t+mΔt and the day of the week to which time t+mΔt belongs. As an example, the traffic volume prediction unit 143 performs a predetermined statistical process on the past traffic volume to predict the traffic volume Q flowing into cell i during the period corresponding to time t+mΔt. i (t+mΔt) may be predicted.

[0104] Here, the statistical processing may be processing to calculate a trimmed mean excluding the upper and lower limits of the past traffic volume (for example, a trimmed mean excluding the upper and lower 10%). Alternatively, the statistical processing may be processing to calculate a harmonic mean of the past traffic volume. At this time, the traffic volume prediction unit 143 calculates a harmonic mean of the past traffic volume by multiplying the traffic volume Q of the previous period by the past traffic volume. i The greater the similarity with (t+(m-1)Δt) (that is, the smaller the difference), the greater the weighting that may be applied when performing statistical processing.

[0105] The traffic volume prediction unit 143 calculates the traffic volume Q flowing into the cell i. i (t)~Q i (t+MΔt) is output to the predicted traffic volume data storage unit 128. The end time may be a time specified by the user, or may be a time when a predetermined time (for example, the product of the step time width Δt and the number of simulation executions M) has elapsed from the start time t.

[0106] (Simulation execution unit 144) The simulation execution unit 144 calculates the speeds V1 to V2 in the periods corresponding to time t+Δt to time t+MΔt, respectively. N , traffic density K1~K N First, the simulation execution unit 144 calculates the traffic volumes Q1(t) to Q N (t), speed V1(t)~V N (t), traffic density K1(t)~K N Get (t).

[0107] (Traffic volume Q1(t)~Q N (t)) The simulation execution unit 144 calculates the traffic volume Q1(t) to Q2(t) of vehicles that flow into a cell i (i is an integer satisfying 1≦i≦N) during a period corresponding to the start time t. N For example, the simulation execution unit 144 functions as a traffic volume acquisition unit that acquires the traffic volumes Q1(t) to Q(t) of vehicles that flow into the cell i during the period corresponding to the start time t, which are calculated by the traffic volume prediction unit 143. NGet (t).

[0108] (Speed ​​V1(t)~V N (t)) Furthermore, the simulation execution unit 144 calculates speeds V1(t) to V2(t) which are statistics of the speed of a vehicle traveling through a cell i (i is an integer satisfying 1≦i≦N) during a period corresponding to the start time t. N It functions as a speed acquisition unit that acquires (t) (km / hour) (first speed).

[0109] As an example, it is assumed that the travel history point width 712 is the same as the simulation execution cell width 722. In such a case, the simulation execution unit 144 acquires, from the probe data storage unit 122, speeds that are statistics of vehicle speeds that traveled in sections corresponding to cells 1 to N during the period corresponding to the start time t, and calculates the acquired speeds as speeds V1(t) to V N Just treat it as (t).

[0110] As another example, it is assumed that the driving history point width 712 and the simulation execution cell width 722 are different. In such a case, the simulation execution unit 144 may identify multiple sections corresponding to the cell. For example, if the driving history point width 712 is 100 (m) and the simulation execution cell width 722 is 500 (m), five sections corresponding to the cell may be identified.

[0111] Then, the simulation execution unit 144 acquires the speeds corresponding to each of the multiple sections in the period corresponding to the start time t from the probe data storage unit 122, and performs statistical processing (for example, harmonic speed) on the speeds corresponding to each of the multiple sections to obtain V1(t) to V N All you need to do is obtain (t).

[0112] (Traffic density K1(t)~KN(t)) Furthermore, the simulation execution unit 144 calculates traffic densities K1(t) to K2(t) of cells i (i is an integer satisfying 1≦i≦N) at the start time t (first time). NIt functions as a traffic density acquisition unit that acquires (t) (vehicles / km) (first traffic density).

[0113] As an example, it is assumed that the travel history point width 712 is the same as the simulation execution cell width 722. In such a case, the simulation execution unit 144 acquires the traffic density of the section corresponding to cells 1 to N at the measurement time that coincides with the start time t from the traffic density data storage unit 127, and converts the acquired traffic densities into traffic densities K1(t) to K N Just treat it as (t).

[0114] As another example, it is possible that the travel history point width 712 is different from the simulation execution cell width 722. In such a case, the simulation execution unit 144 may identify a plurality of sections corresponding to the cell.

[0115] Then, the simulation execution unit 144 acquires the traffic density corresponding to each of the plurality of sections in the period corresponding to the start time t from the probe data storage unit 122, and performs statistical processing (for example, arithmetic speed) on the traffic density corresponding to each of the plurality of sections to obtain K1(t) to K N All you need to do is obtain (t).

[0116] (simulation) The simulation execution unit 144 calculates traffic densities K1 to K2 corresponding to times t+Δt to t+MΔt, respectively. N , speed V1~V N Referring to FIG. 10, in cell i (i is an integer satisfying 1≦i≦N), the traffic density K i (t) and velocity V i (t) and traffic volume Q i (t) and traffic density K i (t+Δt) and velocity V i We will explain the method for predicting (t+Δt).

[0117] (Traffic density simulation) First, traffic density K iAn example of a method for predicting (t+Δt) will be described.

[0118] FIG. 10 is a diagram showing the traffic volume, speed, and traffic density corresponding to each of three consecutive cells. Referring to FIG. 10, cell (i-1), cell i, and cell (i+1) are shown from the upstream side to the downstream side of the road. Also, the traffic volume Q at time t is i-1 (t)~Q i+1 (t), velocity V i-1 (t)~V i+1 (t), traffic density K i-1 (t)~K i+1 (t) is shown.

[0119] The simulation execution unit 144 calculates the traffic density K i (t) and velocity V i (t) and traffic volume Q i (t) and the traffic density K at time t + Δt (second time) i Predict (t+Δt) (second traffic density).

[0120] With this configuration, the speed V i (t) is traffic density K i Since the free flow speed 744 is used to predict (t+Δt), traffic flow can be simulated with higher accuracy than when only the free flow speed 744, which is a predetermined fixed value, is used. Furthermore, with this configuration, prediction is performed only by macro simulation, so that a decrease in processing time can be suppressed.

[0121] Also, the speed V i Not only (t), but also the velocity V i The mixed result of (t) and the predetermined free flow speed 744 is the traffic density K i In other words, the simulation execution unit 144 may use the traffic density K i (t) and velocity V i (t) and the mixed results of the predetermined free flow speed 744 and the traffic volume Q i (t) and traffic density Ki (t+Δt) may be predicted.

[0122] With this configuration, the speed V i Considering both (t) and the free flow speed 744 as a predetermined fixed value, the traffic density K i Therefore, this configuration allows for more accurate simulation of traffic flow.

[0123] The simulation execution unit 144 may also calculate the ratio of the number of passable lanes to the total number of lanes in the restricted section based on the information for specifying the restricted section stored in the event data storage unit 120 and information on lanes on which vehicles cannot travel in the restricted section. Then, the simulation execution unit 144 calculates the ratio of the number of passable lanes to the total number of lanes in the restricted section and the traffic density K i (t) and velocity V i (t) and traffic volume Q i (t) and traffic density K i (t+Δt) may be predicted.

[0124] With this configuration, even if traffic restrictions occur, the traffic density K i Therefore, this configuration allows for more accurate simulation of traffic flow.

[0125] More specifically, the simulation execution unit 144 calculates the traffic density K i (t) and velocity V i Based on (t) and traffic volume Q i+1 (t) (backward block traffic volume) may be predicted. For example, traffic volume Q i+1 (t) is the traffic density K i (t) and velocity V i (t), and more specifically, it may be the first term of min() in the following equation (4). Then, the simulation execution unit 144 calculates the traffic volume Q i+1(t) and traffic volume Q i (t) and traffic density K i (t) and traffic density K i (t+Δt) may be predicted.

[0126] For example, traffic density K i (t) and velocity V i Based on (t) and traffic volume Q i+1 The equation for predicting (t) can be expressed by the following equation (4):

[0127] Q i+1 (t)=min{(α×V i (t)+(1-α)×u)×R×K i (t), R×Q max ,W×(R×(K max -K i+1 (t)))} (4)

[0128] where u is the predetermined free stream velocity 744. α is the velocity V i R is the ratio of the number of lanes that can be used to the total number of lanes in the restricted section. Q max is the predetermined maximum traffic volume of 742 (vehicles / minute). max is the predetermined maximum traffic density of 743 (vehicles / km). W is the predetermined congestion wave propagation speed of 14.5 (km / h), which is the propagation speed of the congestion wave transmitted from the wake cell.

[0129] As shown in equation (4), the simulation execution unit 144 calculates the traffic density K i (t) and velocity V i (t) (for example, the first term of min() in Equation (4)) and Q max × R. Then, the simulation execution unit 144 compares the traffic density K i (t) and velocity V i (t) is the traffic volume based on multiplication with Q max When ×R is small, Q max×R is traffic volume Q i+1 (t). The simulation execution unit 144 then calculates the traffic volume Q i+1 (t) and traffic volume Q i (t) and traffic density K i (t) and traffic density K i You can predict (t+Δt).

[0130] Furthermore, as shown in equation (4), the simulation execution unit 144 calculates the traffic density K i (t) and velocity V i (t) (for example, the first term of min() in Equation (4)) and W × (R × (K max -K i (t))) can be compared with R×(K max -K i (t)) may be an example of the first multiplication result. max -K i (t))) may be an example of the second multiplication result.

[0131] Then, the simulation execution unit 144 calculates the traffic density K i (t) and velocity V i (t) is the traffic volume based on multiplication with W × (R × (K max -K i When (t))) is small, W×(R×(K max -K i (t))) is traffic volume Q i+1 (t). The simulation execution unit 144 then calculates the traffic volume Q i+1 (t) and traffic volume Q i (t) and traffic density K i (t) and traffic density K i You can predict (t+Δt).

[0132] Also, for example, traffic volume Q i+1 (t) and traffic volume Q i (t) and traffic density K i (t) and traffic density K i The equation for predicting (t+Δt) can be expressed by the following equation (5).

[0133] K i (t+Δt)=K i (t)+Δt / Δx(Q i (t)-Q i+1 (t))···(5)

[0134] In equation (5), Δt is the simulation step time interval (minutes), and Δx is the simulation execution cell width of 722 (km), which is the length of the cell in the road travel direction.

[0135] As shown in equation (5), the simulation execution unit 144 calculates Q i (t)-Q i+1 (t), Δx, Δt, and K i (t) and based on K i You can predict (t+Δt).

[0136] (Speed ​​simulation) Next, referring to Figure 10, the velocity V i An example of a method for predicting (t+Δt) will be described.

[0137] The simulation execution unit 144 calculates the traffic density K i Based on (t+Δt), the velocity V i Predict (t+Δt) (second velocity).

[0138] The simulation execution unit 144 calculates the traffic density K i If (t+Δt) is less than a predetermined traffic density, the KV relationship defined by the KV parameter and the traffic density K i (t+Δt) and based on the velocity V i The predetermined traffic density may be a traffic density corresponding to the congested flow determination speed 741 (threshold value) in the KV relational expression defined by the KV parameters.

[0139] On the other hand, the simulation execution unit 144 calculates the traffic density K iIf (t+Δt) exceeds a predetermined traffic density, the traffic density K i (t-pΔt) (where p is an integer greater than or equal to 1) and traffic volume Q i (t-pΔt) and traffic density K i (t) and velocity V i (t+Δt) may be predicted.

[0140] More specifically, the simulation execution unit 144 calculates the traffic density K i Of (t-pΔt), traffic density K i (t) and the traffic density close to (i.e., traffic density K i By performing a predetermined statistical process on the traffic density (whose difference with (t) is smaller than a predetermined difference), the traffic density after statistical processing is calculated, and the traffic density after statistical processing and traffic volume Q i Based on (t-pΔt) and equation (2), the velocity V i (t+Δt) may be predicted.

[0141] Here, the statistical processing may be processing to calculate a trimmed mean excluding the upper and lower limits of the traffic density (for example, a trimmed mean excluding the upper and lower 10%). Alternatively, the statistical processing may be processing to calculate a median.

[0142] (Overall flow of the simulation) Next, the overall flow of the simulation will be described with reference to FIG.

[0143] 11 is a diagram for explaining the overall flow of the simulation. Referring to FIG. 11, traffic volumes Q1 to Q2 corresponding to times t to t+MΔt, respectively, are n ,traffic density K1~K N , speed V1~V N is shown.

[0144] Here, the traffic volume Q1 to Q2 for the period corresponding to time t is nhave already been calculated by the traffic volume calculation unit 133, and are the traffic volumes Q1 to Q2 for the periods corresponding to the times t+Δt to t+MΔt, respectively. n has been predicted by the traffic volume prediction unit 143. In addition, the traffic densities K1(t) to K n (t) has already been calculated by the traffic density calculation unit 142. Furthermore, the speeds V1(t) to V n (t) has already been calculated by the statistical processing unit 131.

[0145] In this state, the simulation execution unit 144 may predict the traffic volume Q2(t) based on the traffic density K1(t), the traffic density K2(t), and the speed V1(t) using the above formula (4).The simulation execution unit 144 may then predict the traffic density K1(t+Δt) based on the predicted traffic volume Q2(t), the traffic volume Q1(t), and the traffic density K1(t) using the above formula (5).

[0146] Furthermore, when the traffic density K1(t+Δt) is equal to or less than a predetermined traffic density, the simulation executing unit 144 may predict the speed V1(t+Δt) based on the KV relational expression defined by the KV parameters and the traffic density K1(t+Δt). On the other hand, when the traffic density K1(t+Δt) exceeds the predetermined traffic density, the simulation executing unit 144 may predict the speed V1(t+Δt) based on the traffic density K1 and traffic volume Q1 for a period prior to the period corresponding to time t, and the traffic density K1(t).

[0147] This allows traffic density K1(t+Δt) and speed V1(t+Δt) to be predicted. Traffic density K1(t+Δt) and speed V1(t+Δt) can be used to predict traffic density K1(t+2Δt) and speed V1(t+2Δt).

[0148] The traffic density K1 and speed V1 corresponding to time t+2Δt to time t+MΔt can be predicted by repeating the same prediction. Similarly, the traffic densities K2 to K3 corresponding to time t+Δt to time t+MΔt can be predicted by repeating the same prediction for cells 2 to n. n , speed V2~V n can be predicted.

[0149] Fig. 12 is a diagram showing simulation results in a comparative example. Fig. 13 is a diagram showing first simulation results by the traffic flow prediction device 1 according to an embodiment of the present invention. Fig. 14 is a diagram showing second simulation results by the traffic flow prediction device 1 according to an embodiment of the present invention. Fig. 15 is a diagram showing actual measurement results. In the results shown in Figs. 12 to 15, the vertical axis indicates time, the horizontal axis indicates distance from the starting point, and the magnitude of the speed corresponding to the time and distance is indicated by lighter color.

[0150] In the comparative example shown in Fig. 12, only the free flow speed u, which is a predetermined fixed value, is used as the speed V to predict the traffic density K, and the ratio R of the number of passable lanes to the total number of lanes in the restricted section is not used to predict the traffic density K. Therefore, in the comparative example shown in Fig. 12, only natural congestion due to traffic concentration is expressed as a decrease in speed, and the comparative example shown in Fig. 12 is significantly different from the actual measurement results shown in Fig. 15.

[0151] On the other hand, the first simulation result by the traffic flow prediction device 1 according to the embodiment of the present invention shown in Fig. 13 is a result in which the ratio R of the number of passable lanes to the total number of lanes in the restricted section is used to predict the traffic density K. Therefore, the first simulation result shown in Fig. 13 expresses not only natural congestion due to traffic concentration but also congestion due to lane restrictions as a decrease in speed, and it can be seen that the first simulation result shown in Fig. 13 is close to the actual measurement result shown in Fig. 15.

[0152] The second simulation result by the traffic flow prediction device 1 according to the embodiment of the present invention shown in Fig. 14 is a result in which not only the ratio R of the number of passable lanes to the total number of lanes in the restricted section is used to predict the traffic density K, but also a mixed result of the statistics of the actually measured speeds and a predetermined free flow speed is used to predict the traffic density. In other words, this is a result in which the above equation (4) is used to predict the traffic density. Therefore, the second simulation result shown in Fig. 14 more accurately expresses congestion as a decrease in speed, and it can be seen that the second simulation result shown in Fig. 14 is much closer to the actual measurement result shown in Fig. 15.

[0153] The configuration example of the traffic flow prediction device 1 according to the embodiment of the present invention has been described above.

[0154] (1-2. Effects) As described above, the traffic flow prediction device 1 according to the embodiment of the present invention includes a speed acquisition unit that acquires a first speed, which is a statistical quantity of the speed of vehicles traveling through a predetermined block. The traffic flow prediction device 1 also includes a traffic volume acquisition unit that acquires a first traffic volume of vehicles that have flowed into the predetermined block.

[0155] Furthermore, the traffic flow prediction device 1 includes a traffic density acquisition unit that acquires a first traffic density of the predetermined block at a first time. The traffic flow prediction device 1 also includes a simulation execution unit that predicts a second traffic density of the predetermined block at a second time that is later than the first time, based on the first traffic density, the first speed, and the first traffic volume.

[0156] This configuration allows traffic density to be predicted taking into account the statistics of actually measured speeds. This makes it possible to simulate traffic flow with high accuracy. Furthermore, this configuration does not require the use of a microsimulation model, which can prevent a decrease in processing time.

[0157] The simulation execution unit may also predict traffic density based on the ratio of the number of passable lanes to the total number of lanes in a given block. With this configuration, even when traffic restrictions are imposed, it is possible to suppress a decrease in processing time and simulate traffic flow with high accuracy.

[0158] The use of the technology according to the embodiment of the present invention has the effect of enabling a traffic flow simulation to be performed in a short time when nighttime construction restrictions are in place. Furthermore, the use of the technology according to the embodiment of the present invention has the effect of enabling an easy calculation of the construction restriction time that will cause the least disruption to traffic flow.

[0159] The effects achieved by the traffic flow prediction device 1 according to the embodiment of the present invention have been described above.

[0160] (2. Hardware configuration example) Next, an example of the hardware configuration of the traffic flow prediction device 1 according to the embodiment of the present invention will be described.

[0161] Hereinafter, an example of the hardware configuration of the information processing device 900 will be described as an example of the hardware configuration of the traffic flow prediction device 1 according to the embodiment of the present invention. Note that the example of the hardware configuration of the information processing device 900 described below is merely one example of the hardware configuration of the traffic flow prediction device 1. Therefore, the hardware configuration of the traffic flow prediction device 1 may be such that unnecessary components are deleted from the hardware configuration of the information processing device 900 described below, or new components are added.

[0162] 16 is a diagram showing a hardware configuration of an information processing device 900 as an example of the traffic flow prediction device 1 according to an embodiment of the present invention. The information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external bus 906, an interface 907, an input device 908, an output device 909, a storage device 910, and a communication device 911.

[0163] The CPU 901 functions as an arithmetic processing unit and control unit, and controls the overall operation of the information processing device 900 in accordance with various programs. The CPU 901 may also be a microprocessor. The ROM 902 stores programs used by the CPU 901, calculation parameters, etc. The RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, etc. These are interconnected by a host bus 904 that is composed of a CPU bus, etc.

[0164] The host bus 904 is connected to an external bus 906, such as a PCI (Peripheral Component Interconnect / Interface) bus, via a bridge 905. It is not necessary to configure the host bus 904, bridge 905, and external bus 906 separately, and these functions may be implemented on a single bus.

[0165] The input device 908 is composed of input means such as a mouse, keyboard, touch panel, buttons, microphone, switches, and levers that allow the user to input information, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 901. By operating this input device 908, the user operating the information processing device 900 can input various data to the information processing device 900 and instruct the information processing device 900 to perform processing operations.

[0166] The output device 909 includes, for example, a display device such as a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, or a lamp, and an audio output device such as a speaker.

[0167] The storage device 910 is a device for storing data. The storage device 910 may include a storage medium, a recording device for recording data on the storage medium, a reading device for reading data from the storage medium, and a deletion device for deleting data recorded on the storage medium. The storage device 910 is configured, for example, with an HDD (Hard Disk Drive). This storage device 910 drives a hard disk and stores programs executed by the CPU 901 and various data.

[0168] The communication device 911 is, for example, a communication interface configured with a communication device for connecting to a network, etc. The communication device 911 may be compatible with either wireless communication or wired communication.

[0169] An example of the hardware configuration of the traffic flow prediction device 1 according to the embodiment of the present invention has been described above.

[0170] (3. Summary) Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to these examples. It is clear that a person skilled in the art to which the present invention pertains can conceive of various modifications and alterations within the scope of the technical ideas set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present invention.

[0171] In the above, the term "location" is used, but this term "location" can represent not only a single point but also a location having a certain range. Therefore, the term "location" can also be expressed as the term "section." [Explanation of symbols]

[0172] 1. Traffic flow prediction device 112 Probe Antenna 114 Free Flow Antenna 120 Event data storage unit 121 Driving history data storage unit 122 Probe data storage unit 123 Free Flow Data Storage Unit 124 Traffic volume data storage unit 125 KV parameter storage section 126 Common parameter storage unit 127 Traffic density data storage unit 128 Predicted traffic volume data storage unit 131 Statistical Processing Unit 133 Traffic Volume Calculation Department 140 Processing section 141 KV parameter creation section 142 Traffic density calculation section 143 Traffic Volume Prediction Department 144 Simulation Execution Unit 150 Event Input Unit

Claims

1. acquiring a first speed which is a statistic of vehicle speeds traveling through a predetermined block; acquiring a first traffic volume of vehicles that have flowed into the predetermined block; Obtaining a first traffic density of the predetermined block at a first time; predicting a second traffic density for the predetermined block at a second time later than the first time based on the first traffic density, a mixture of the first speed and a predetermined free flow speed, and the first traffic volume; A computer-implemented traffic flow prediction method comprising:

2. acquiring a first speed which is a statistic of vehicle speeds traveling through a predetermined block; acquiring a first traffic volume of vehicles that have flowed into the predetermined block; Obtaining a first traffic density of the predetermined block at a first time; predicting a second traffic density of the predetermined block at a second time later than the first time based on the first traffic density, the first speed, and the first traffic volume; If the second traffic density is equal to or less than a predetermined traffic density, predicting a second speed, which is a statistic of the speed of vehicles traveling in the predetermined block during a period corresponding to the second time, based on a relational expression indicating a relationship between traffic density and vehicle speed that has been generated in advance and the second traffic density; A computer-implemented traffic flow prediction method comprising:

3. acquiring a first speed which is a statistic of vehicle speeds traveling through a predetermined block; acquiring a first traffic volume of vehicles that have flowed into the predetermined block; Obtaining a first traffic density of the predetermined block at a first time; predicting a second traffic density of the predetermined block at a second time later than the first time based on the first traffic density, the first speed, and the first traffic volume; If the second traffic density exceeds a predetermined traffic density, predicting a second speed, which is a statistic of the speed of vehicles traveling through the predetermined block during the period corresponding to the second time, based on the traffic density and traffic volume of the predetermined block during the period prior to the period corresponding to the first time and the second traffic density; A computer-implemented traffic flow prediction method comprising:

4. Predicting the second traffic density includes predicting the second traffic density further based on a ratio of the number of passable lanes to the total number of lanes in the specified block. The traffic flow prediction method according to any one of claims 1 to 3.

5. Predicting the second traffic density includes predicting the traffic volume of vehicles flowing into a downstream block of the specified block as downstream block traffic volume based on the first traffic density and the first speed, and predicting the second traffic density based on the downstream block traffic volume, the first traffic volume, and the first traffic density. The traffic flow prediction method according to any one of claims 1 to 4.

6. Predicting the second traffic density includes predicting the second traffic density based on a difference between the downstream block traffic volume and the first traffic volume, the length of the specified block, the time interval between the first time and the second time, and the first traffic density. The traffic flow prediction method according to claim 5 .

7. acquiring a first speed which is a statistic of vehicle speeds traveling through a predetermined block; acquiring a first traffic volume of vehicles that have flowed into the predetermined block; Obtaining a first traffic density of the predetermined block at a first time; When a multiplication result of a predetermined maximum traffic volume and a ratio of the number of lanes that can be traveled to the total number of lanes in the specified block is smaller than a traffic volume based on the multiplication result of the first traffic density and the first speed, predicting a second traffic density in the specified block at a second time that is later than the first time based on the multiplication result, the first traffic volume, and the first traffic density; A computer-implemented traffic flow prediction method comprising:

8. acquiring a first speed which is a statistic of vehicle speeds traveling through a predetermined block; acquiring a first traffic volume of vehicles that have flowed into the predetermined block; Obtaining a first traffic density of the predetermined block at a first time; When a first multiplication result of a difference between a predetermined maximum traffic density and the first traffic density and a ratio of the number of passable lanes to the total number of lanes in the predetermined block by a predetermined congestion wave propagation speed is smaller than a traffic volume based on the multiplication result of the first traffic density and the first speed, predicting a second traffic density in the predetermined block at a second time later than the first time based on the second multiplication result, the first traffic volume, and the first traffic density; A computer-implemented traffic flow prediction method comprising:

9. The traffic flow prediction method includes: and predicting a second traffic volume of vehicles entering the predetermined block based on a traffic volume of vehicles entering the predetermined block in a period prior to a period corresponding to the first time. The traffic flow prediction method according to any one of claims 1 to 8.

10. A program that causes a computer to execute the traffic flow prediction method described in any one of claims 1 to 9.

11. A traffic flow prediction device, 11. The program according to claim 10, wherein the computer executes the program so that the computer functions as the traffic flow prediction device. Traffic flow prediction device.

Images