Apparatus and method of control traffic
The traffic volume control device optimizes traffic signal control through clustering and normalization, addressing biased data issues in conventional methods to enhance traffic efficiency.
Patent Information
- Application Number
- KR1020230187971
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2023-12-21
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2043-12-21
AI Technical Summary
Conventional traffic volume collection methods are manual and limited in survey periods, leading to biased data and inefficient traffic control plans, exacerbated by inadequate signal planning on urban roads.
A traffic volume control device and method that utilizes a processor to collect and analyze traffic volume by direction, generate a traffic characteristic value table, perform clustering, and create a traffic volume control plan by normalizing and optimizing traffic signal control based on Euclidean distances and silhouette scores.
Establishes a traffic volume control plan that reflects traffic characteristics by time period and direction, reducing congestion by optimizing traffic signal control plans.
Smart Images

Figure 112023143661156-PAT00041_ABST
Abstract
Description
Technology Field
[0001] The embodiments relate to a traffic volume control device and method. Background Technology
[0002] Domestic traffic congestion and the costs incurred due to it are increasing every year. One of the main causes of reduced traffic efficiency on major urban roads is inadequate signal planning.
[0003] Conventional traffic volume collection methods were recorded manually and had limited survey periods, resulting in biased data. Establishing traffic control plans using such biased data leads to inefficiency.
[0004] The recent introduction of the smart signal operation market and the advancement of traffic volume detection technology have made it possible to calculate traffic volume by turning direction, laying the groundwork for establishing efficient traffic volume control plans. means of solving the problem
[0005] In a device for controlling traffic volume at an intersection movable in one or more directions of movement, a traffic volume control device according to one embodiment comprises a processor and a memory storing instructions executable by said processor, wherein the processor receives traffic volume by direction of movement per unit time, generates a traffic characteristic value table based on said traffic volume by direction of movement, and generates a traffic volume control plan by performing clustering on said traffic characteristic value table.
[0006] The above traffic volume by direction of movement includes traffic volume corresponding to the vehicle's entry direction, exit direction, and combination of the entry direction and the exit direction according to the above unit time, and the processor can generate the traffic characteristic value table by sorting the traffic volume by direction of movement for the above unit time according to the day of the week, hour, or minute.
[0007] The processor can generate normalized traffic characteristic values by normalizing the traffic characteristic value table based on the total traffic volume for the unit time, and generate the traffic volume control plan by performing clustering based on the normalized traffic characteristic values.
[0008] The processor can generate multiple clusters by randomly selecting a predetermined number of objects from the normalized traffic characteristic values to generate multiple initial cluster centers, and by clustering the remaining values of the traffic characteristic values based on the Euclidean distance between the remaining values of the traffic characteristic values and the multiple initial cluster centers.
[0009] The processor can calculate the centers of the plurality of clusters and update the plurality of clusters based on the centers of the plurality of clusters.
[0010] The processor can calculate a silhouette score based on the smallest distance between the average distance to an object within one of the plurality of clusters and the average distance to a cluster to which the object does not belong among the plurality of clusters, determine the number of target clusters based on the silhouette score, and generate clusters equal to the number of target clusters.
[0011] The processor can calculate the silhouette score based on the result of comparing the average distance and the smallest distance and the value obtained by dividing the average distance by the smallest distance, and determine the number of clusters with the highest silhouette score as the number of target clusters.
[0012] The processor can calculate the silhouette score while increasing the number of clusters from the minimum number of clusters up to the maximum number of traffic signal control plans.
[0013] The processor can generate a plurality of clusters by performing clustering based on the traffic characteristic value table, and generate a traffic volume control plan by assigning a traffic signal control plan corresponding to the plurality of clusters.
[0014] A method for controlling traffic volume at an intersection movable in one or more directions of movement, wherein a traffic volume control method according to one embodiment comprises the steps of receiving traffic volume by direction of movement for a unit time, generating a traffic characteristic value table based on the traffic volume by direction of movement, and generating a traffic volume control plan by performing clustering on the traffic characteristic value table. Effects of the invention
[0015] The embodiments can establish a traffic volume plan and provide a traffic volume control plan that reflects traffic characteristics by time period.
[0016] The embodiments can provide a traffic volume control plan that reflects traffic volume demand varying by vehicle direction of travel.
[0017] In addition, various effects that can be identified directly or indirectly through this document may be provided. Brief explanation of the drawing
[0018] FIG. 1 shows a schematic block diagram of a traffic volume control device according to one embodiment. Figure 2 shows the process of generating a traffic volume control plan for the traffic volume control device illustrated in Figure 1. Figure 3 shows an example of traffic volume by direction of travel. Figure 4 shows an example of an intersection that can move in one or more directions of movement. Figure 5 shows an example of distinguishing the direction of movement. Figure 6 shows another example of distinguishing the direction of movement. Figure 7 shows an example of a traffic characteristic value table. Figure 8 shows an example of a normalized traffic characteristic value. Figure 9 shows an example of pseudo code for performing a clustering operation. Figure 10 shows an example of a traffic volume control plan. Figure 11 shows another example of normalized traffic characteristic values. Figure 12 shows an example of silhouette scores according to the number of clusters. Figure 13 shows an example of a traffic volume control plan generated based on the number of target clusters. FIG. 14 is an example of a drawing to explain the correction operation when there is a difference in the ratio of movement flow by direction. This is another example of a drawing to explain the correction operation when there is a difference in the directional flow rate of Fig. 15. Figure 16 shows an example of a traffic volume control plan generated by considering the flow rate by direction. FIGS. 17 to 19 show examples of the performance of a traffic volume control device. FIG. 20 shows the flow of operation of the traffic volume control device illustrated in FIG. 1. Specific details for implementing the invention
[0019] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, actual implementations are not limited to the specific embodiments disclosed, and the scope of this specification includes modifications, equivalents, or substitutions included in the technical concept described by the embodiments.
[0020] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.
[0021] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between.
[0022] Singular expressions include plural expressions unless the context clearly indicates otherwise. In this document, phrases such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “at least one of A, B, or C” may each include any one of the items listed together with the corresponding phrase, or all possible combinations thereof. In this specification, terms such as “comprising” or “having” are intended to designate the existence of the described feature, number, step, action, component, part, or combination thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.
[0023] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.
[0024] As used herein, the term "module" may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).
[0025] As used in this document, the term "part" refers to a software or hardware component, such as an FPGA or ASIC, that performs certain roles. However, "part" is not limited to software or hardware. "Part" may be configured to reside in an addressable storage medium or configured to operate one or more processors. For example, "part" may include components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." Furthermore, components and "parts" may be implemented to operate one or more CPUs within a device or secure multimedia card. Additionally, '~part' may include one or more processors.
[0026] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are given the same reference numeral regardless of the drawing number, and redundant descriptions thereof will be omitted.
[0028] FIG. 1 shows a schematic block diagram of a traffic volume control device according to one embodiment.
[0029] Referring to FIG. 1, the traffic volume control device (10) can control the traffic volume of a road used by vehicles. The traffic volume control device (10) can control the traffic volume by generating a traffic volume control plan. The traffic volume control device (10) can reduce traffic congestion and facilitate the flow of vehicles by optimally controlling traffic signals.
[0030] The traffic volume control device (10) can generate a traffic volume control plan to control the traffic volume of an intersection that is movable in one or more directions of movement.
[0031] A traffic volume control plan may include a Time-Of-Day (TOD) traffic signal plan. A traffic volume control plan may include a fixed signal control plan composed of multiple TOD traffic signal plans included over a day. Each TOD traffic signal plan may include a signal cycle length set differently depending on the traffic volume.
[0032] The traffic volume control device (10) can generate a traffic volume control plan by utilizing data mining. The traffic volume control device (10) can generate an optimal traffic volume control plan that reflects traffic characteristics by time period by utilizing clustering technology.
[0033] The traffic volume control device (10) can generate a traffic volume control plan by reflecting the traffic volume demand according to the direction of the intersection. The traffic volume control device (10) can collect detailed time-based traffic volume data and generate a traffic volume control plan based on the time-based traffic volume data.
[0034] The traffic volume control device (10) can generate a traffic volume control plan that reflects traffic characteristics by time period by utilizing clustering technology based on traffic volume data collected through smart intersections and similar traffic volume collection devices. The traffic volume control device (10) can generate a traffic volume control plan by deriving time groups with similar turning directions or traffic characteristics by direction of movement through clustering technology.
[0035] The traffic volume control device (10) can be implemented as a printed circuit board (PCB) such as a motherboard, an integrated circuit (IC), or a system on chip (SoC). The traffic volume control device (10) can be implemented including an application processor.
[0036] Additionally, the traffic control device (10) can be implemented to be linked with a PC (personal computer), data server, kiosk, or portable device.
[0037] Portable devices can be implemented as laptop computers, mobile phones, smartphones, tablet PCs, mobile internet devices (MID), personal digital assistants (PDA), enterprise digital assistants (EDA), digital still cameras, digital video cameras, portable multimedia players (PMP), personal navigation devices (PND), handheld game consoles, e-books, or smart devices. Smart devices can be implemented as smart watches, smart bands, or smart rings.
[0038] The traffic volume control device (10) includes a processor (100) and a memory (200).
[0039] The processor (100) may include a receiving interface. The processor (100) may receive data from an external source or from memory (200). The processor (100) may store the received data or generated data in memory (200).
[0040] The processor (100) can process data stored in memory (200). The processor (100) can execute computer-readable code (e.g., software) stored in memory (200) and instructions triggered by the processor (100).
[0041] The processor (100) may be a data processing device implemented in hardware having a circuit having a physical structure for executing desired operations. For example, the desired operations may include code or instructions included in a program.
[0042] For example, a data processing device implemented in hardware may include a microprocessor, a central processing unit, a processor core, a multi-core processor, a multiprocessor, an Application-Specific Integrated Circuit (ASIC), and a Field Programmable Gate Array (FPGA).
[0043] The processor (100) can receive traffic volume by direction of movement for a unit of time. The traffic volume by direction of movement may include traffic volume corresponding to the vehicle's entry direction, exit direction, and / or combination of the entry direction and exit direction for a unit of time.
[0044] The processor (100) can generate a traffic characteristic value table based on traffic volume by direction of travel. The processor (100) can generate a traffic characteristic value table by sorting the traffic volume by direction of travel for a unit of time according to the day of the week, hour, and / or minute.
[0045] The processor (100) can generate a traffic volume control plan by performing clustering on a traffic characteristic value table.
[0046] The processor (100) can generate normalized traffic characteristic values by normalizing a traffic characteristic value table based on the total traffic volume per unit time. The processor (100) can generate a traffic volume control plan by performing clustering based on the normalized traffic characteristic values.
[0047] The processor (100) can generate multiple initial cluster centers by randomly selecting a predetermined number of objects from normalized traffic characteristic values.
[0048] The processor (100) can generate multiple clusters by clustering the remaining values of traffic characteristic values based on the Euclidean distance between the remaining values of the traffic characteristic values and the multiple initial cluster centers.
[0049] The processor (100) can calculate the centers of multiple clusters. The processor (100) can update multiple clusters based on the centers of multiple clusters.
[0050] The processor (100) can calculate a silhouette score based on the smallest distance between the average distance to an object in one of the multiple clusters and the average distance to a cluster to which the object does not belong among the multiple clusters.
[0051] The processor (100) can determine the number of target clusters based on the silhouette score. The processor (100) can generate clusters equal to the number of target clusters.
[0052] The processor (100) can calculate a silhouette score based on the result of comparing the average distance and the smallest distance and the value obtained by dividing the average distance by the smallest distance.
[0053] The processor (100) can determine the number of clusters with the highest silhouette score as the target number of clusters. The processor (100) can calculate the silhouette score while increasing the number of clusters from the minimum number of clusters up to the maximum number of traffic signal control plans. For example, the minimum number of clusters may be 2.
[0054] The processor (100) can generate multiple clusters by performing clustering based on a traffic characteristic value table. The processor (100) can generate a traffic volume control plan by assigning a traffic signal control plan corresponding to the multiple clusters.
[0055] The memory (200) may store data for operations performed by the processor (100) or the results of operations of the processor (100). The memory (200) may store instructions (or programs) executable by the processor (100). For example, the instructions may include instructions for executing operations of the processor (100) and / or operations of each component of the processor (100).
[0056] The memory (200) can be implemented as a volatile memory device or a non-volatile memory device.
[0057] Volatile memory devices can be implemented as DRAM (dynamic random access memory), SRAM (static random access memory), T-RAM (thyristor RAM), Z-RAM (zero capacitor RAM), or TTRAM (Twin Transistor RAM).
[0058] Non-volatile memory devices can be implemented as EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, MRAM (Magnetic RAM), Spin-Transfer Torque (STT)-MRAM, Conductive Bridging RAM (CBRAM), FeRAM (Ferroelectric RAM), PRAM (Phase change RAM), Resistive RAM (RRAM), Nanotube RRAM, Polymer RAM (PoRAM), Nano Floating Gate Memory (NFGM), holographic memory, Molecular Electronic Memory Device, or Insulator Resistance Change Memory.
[0060] Figure 2 shows the process of generating a traffic volume control plan for the traffic volume control device illustrated in Figure 1.
[0061] Referring to FIG. 2, a processor (e.g., processor (100) of FIG. 1) can receive traffic volume by direction of movement per unit time (traffic volume by direction of movement per unit time (210)). The processor (100) can process the received traffic volume by direction of movement (220).
[0062] The processor (100) can generate a traffic characteristic value table (230) by processing traffic volume by direction of movement.
[0063] The processor (100) can normalize the traffic characteristic value table (230) (240). The processor (100) can generate normalized traffic characteristic values by normalizing the traffic characteristic value table (230).
[0064] The processor (100) can perform clustering on normalized traffic characteristic values (250). For example, the clustering may include K-means clustering.
[0065] The processor (100) can generate a traffic volume control plan (e.g., TOD plan) based on the maximum number of traffic signal control plans (e.g., maximum number of TOD plans). The processor (100) can generate a TOD plan (270) by performing clustering on normalized traffic characteristic values based on the maximum number of TOD plans (260).
[0066] The processor (100) may consider traffic volume according to the entry and exit directions together to sufficiently reflect the turning characteristics within the intersection. To reduce bias according to the scale of traffic volume during clustering, the processor (100) may use a traffic characteristic value table converted into a ratio by normalizing it. The processor (100) may use normalized traffic volume for the entire time period to reflect the scale of traffic volume on the same influence road.
[0067] The processor (100) can determine the optimal number of clusters. The optimal number of clusters can be derived by repeatedly performing clustering while varying the value of K, which is the number of clusters, within a certain range.
[0068] The processor (100) can estimate time clusters with similar characteristics by considering traffic volume by direction of travel and total traffic volume to generate a signal traffic volume control plan that considers traffic demand characteristics.
[0069] The processor (100) can be used to ensure that the length of each display within the TOD is proportional to the traffic volume ratios for different traffic flow directions according to the TOD plan.
[0071] Hereinafter, the operation of FIG. 2 will be explained in detail with reference to FIG. 3 to FIG. 10.
[0073] Figure 3 shows an example of traffic volume by direction of travel, and Figure 4 shows an example of an intersection traversable in one or more directions of travel.
[0074] Referring to FIGS. 3 and 4, a processor (e.g., processor (100) of FIG. 1) may receive traffic volume (310) by direction of movement for a unit of time. The traffic volume (310) by direction of movement may receive as input the traffic volume (unit, time, or lane) by turn or direction of movement (or flow direction) for a single intersection. For example, the unit of time may be 10 minutes or 30 minutes.
[0075] The processor (100) can assign a number according to the direction of movement, as in the example of FIG. 4. The processor (100) can assign a number according to the direction of movement to include information about the direction of entry and / or exit of the vehicle.
[0077] Figure 5 shows one example of a movement flow direction classification, and Figure 6 shows another example of a movement flow direction classification.
[0078] Referring to FIGS. 5 and 6, a processor (e.g., processor (100) of FIG. 1) can collect traffic volume by direction of travel. The processor (100) can calculate traffic volume (510) by direction of travel per unit time.
[0079] The processor (100) can calculate traffic volume (510) by direction of movement by analyzing the results of capturing vehicles moving at an intersection using one or more cameras. The processor (100) can distinguish the direction of rotation or movement of vehicles by detecting the direction of exit of vehicles using cameras for each direction of entry.
[0080] The processor (100) can calculate traffic volume (610) by direction of movement by assigning intersection entry and / or exit section numbers and distinguishing the direction of turning or movement of vehicles based on the assigned numbers.
[0081] The processor (100) can calculate traffic volume by direction of travel and total traffic volume according to the day, hour, or minute. The unit of traffic volume by direction of travel (510 or 610) may be the number of vehicles per lane per unit time.
[0083] Figure 7 shows an example of a traffic characteristic value table, and Figure 8 shows an example of a normalized traffic characteristic value.
[0084] Referring to FIGS. 7 and FIGS. 8, a processor (e.g., processor (100) of FIG. 1) can generate a traffic characteristic value table (710) based on traffic volume by direction of travel.
[0085] The processor (100) can calculate traffic volume based on a unit of time. The unit of time can be set based on a day of the week, an hour, or a minute. If there are no lane divisions at the intersection, the processor (100) can calculate traffic volume by direction of travel based on the number of vehicles per unit of time. The processor (100) can calculate traffic volume by direction of travel by distinguishing between weekdays, Saturdays, and Sundays.
[0086] In the case of traffic volume collected over several periods, the processor (100) may use the average value of the traffic volume. The processor (100) may calculate the total traffic volume by summing the traffic volume by direction of travel and reflect it in the traffic characteristic value table (710).
[0087] The processor (100) can create one or more clusters by clustering time zones that have similar traffic characteristics by direction of travel. When the processor (100) performs clustering on times that have similar traffic characteristics, it can perform normalization on the traffic characteristic value table (710) to reduce the impact of the traffic volume scale.
[0088] If the traffic characteristic value table (710) is used as is, even time periods showing the same traffic volume ratio by direction of travel may be recognized as time periods with different characteristics due to differences in the scale of traffic volume.
[0089] To prevent this, the processor (100) has traffic volume by direction of travel ( ) Total traffic volume for the corresponding time ( The proportion of ( in ) It can be converted into ). The processor (100) can calculate the ratio as in mathematical formula 1.
[0091]
[0093] Here, represents the direction of movement, It can represent the number of directions of movement. The ratio of normalized traffic characteristic values by direction of movement can have a value between 0 and 1.
[0094] The processor (100) can normalize the total traffic volume to between 0 and 1 by considering that the magnitude of the traffic volume will be reflected when calculating the signal cycle per TOD thereafter. The processor (100) can normalize the total traffic volume as in Equation 2.
[0096]
[0098] Here, is time It refers to the total traffic volume, is time It can mean the normalized total traffic volume. is the set of total traffic volumes by time period ( It can mean ).
[0099] The normalized total traffic volume can have a level equivalent to the ratio of traffic characteristics by direction of travel. In clustering, the normalized traffic characteristic values can have a similar degree of influence to the ratio for each direction of travel when calculating distance similarity.
[0101] Figure 9 shows an example of pseudo code for performing clustering operations, and Figure 10 shows an example of a traffic volume control plan.
[0102] Referring to FIGS. 9 and 10, a processor (e.g., processor (100) of FIG. 1) can generate a traffic volume control plan by performing clustering based on normalized traffic characteristic values. The traffic volume control plan may include multiple TOD plans.
[0103] The processor (100) has a normalized traffic characteristic value and a maximum number of traffic signal control plans (e.g., maximum number of TOD plans, ) can be used as input for clustering (e.g., D in Fig. 9). Clustering may include K-means clustering.
[0104] The processor (100) can generate multiple initial cluster centers by randomly selecting a predetermined number of objects from normalized traffic characteristic values. The processor (100) can randomly select K objects (e.g., times having traffic characteristic values) from input data (e.g., normalized traffic characteristic values) and set them as the centers of the initial clusters.
[0105] The processor (100) can generate multiple clusters by clustering the remaining values of traffic characteristic values based on the Euclidean distance between the remaining values of the traffic characteristic values and the multiple initial cluster centers.
[0106] The processor (100) can assign the remaining objects, excluding the object that formed the initial cluster center, to the nearest cluster center through Euclidean distance.
[0107] The processor (100) can calculate the centers of multiple clusters and update the multiple clusters based on the centers of the multiple clusters. The processor (100) can update the cluster centers using the average value of the object clusters. The processor (100) can reassign objects to the updated cluster centers and repeat the cluster assignment until there is no change in the cluster assignment.
[0108] The processor (100) can determine the number of clusters by calculating a silhouette score. The processor (100) can calculate the silhouette score while increasing the number of clusters from the minimum number of clusters up to the maximum number of traffic signal control plans.
[0109] The processor (100) is from 2 until By repeating the cluster generation process described above while increasing by 1, the optimal number of clusters is and Time clusters can be generated based on.
[0110] The processor (100) set the initial value of K to 2, but according to the embodiment You can adjust the initial value together with.
[0111] The processor (100) can determine the number of clusters with the highest silhouette score as the number of target clusters. The processor (100) determines the highest silhouette score (Silhouette score, The number of clusters K having the mean of is the optimal number of clusters ( )forming It can be decided as.
[0112] The processor (100) can calculate the silhouette score as in mathematical formula 3.
[0114]
[0116] Here, represents the average distance (dissimilarity) with objects within the same cluster (or, the average distance with objects within a single cluster), and is an object It can mean the smallest average distance among other clusters to which it does not belong (or, the smallest average distance among clusters to which the object does not belong).
[0117] The processor (100) can generate multiple clusters and assign a cluster number to each cluster. The processor (100) can assign a TOD plan corresponding to each cluster.
[0118] The processor (100) can generate a traffic volume control plan such as the example in FIG. 10 by assigning TODs suitable for multiple clusters. The traffic volume control plan may include a TOD plan table.
[0120] Hereinafter, with reference to FIGS. 11 to 19, an embodiment for generating a traffic volume control plan will be described.
[0122] Figure 11 shows another example of normalized traffic characteristic values, Figure 12 shows an example of silhouette scores according to the number of clusters, and Figure 13 shows an example of a traffic volume control plan generated based on the number of target clusters.
[0123] Referring to FIGS. 11 through 13, a processor (e.g., processor (100) of FIG. 1) can generate normalized traffic characteristics (1110) as described with reference to FIGS. 7 and FIG. 8.
[0124] The processor (100) can use normalized traffic characteristic values as input data for clustering operations, and calculate a silhouette score based on the number of clusters as described above, and determine 6 as the optimal number of clusters (or target number of clusters) as shown in the example of FIG. 12.
[0125] The processor (100) can generate multiple clusters by performing clustering as described in FIG. 9. An example in FIG. 13 may show the result of clustering 144 time zones (3×24×2) at 30-minute intervals for weekdays, Saturdays, and Sundays into 6 time groups (TOD).
[0126] In the example of Fig. 13, the cluster number for each time period can be indicated as the TOD plan number.
[0128] FIGS. 14 and 15 are examples of drawings for explaining correction operations when there is a difference in the directional flow rate, and FIG. 16 shows an example of a traffic volume control plan generated by considering the directional flow rate.
[0129] Referring to FIGS. 14 through 16, a processor (e.g., the processor (100) of FIG. 1) can calculate additional signal indicators, such as signal cycles or display lengths, by taking into account traffic characteristic values for each TOD.
[0130] A phase refers to allowing traffic flow in a specific direction for a specific time (phase length (seconds)) within an intersection signal cycle, and the direction of traffic flow for each phase can be determined in advance.
[0131] The processor (100) may consider the ratio of the direction of movement belonging to each display to assign the signal display length based on the ratio of the direction of movement according to the TOD. The processor (100) may calculate the display length as in Equation 4.
[0133]
[0135] Here, TOD direction from It refers to the display length of the row, TOD direction from It refers to the turnover rate of the row, TOD It can mean the appropriate signal period at.
[0136] The processor (100) has an appropriate cycle value for each TOD ( To calculate ) the Webster signal cycle calculation methodology can be used. If the processor (100) is given two or more displays for the same direction within one cycle, it can divide the traffic volume ratio by direction of travel by that number.
[0137] The processor (100) can correct the imbalance by considering the difference between the movement ratios when two or more movement directions are included in one display. The processor (100) can correct the imbalance based on the difference in the movement ratios.
[0138] For example, if the difference in the movement ratios exceeds 0.1, the processor (100) takes the average of the two ratios as the representative weight (or turnover rate) of the corresponding display. ) can be calculated. If the difference in the movement ratio is less than 0.1, the processor (100) calculates the maximum value of the two ratios as the representative weight (or turnover rate, of the corresponding display) It can be calculated as ).
[0139] The processor (100) can generate a traffic volume control plan (1610) based on the result of correcting the imbalance. An example of FIG. 16 is a signal cycle per TOD ( Display length based on ) and ratio by movement direction ( By calculating ), the traffic volume control plan (1610) created can be displayed.
[0141] FIGS. 17 to 19 show examples of the performance of a traffic volume control device.
[0142] Referring to FIGS. 17 to 19, a traffic volume control device (e.g., the traffic volume control device (10) of FIG. 1) can divide TODs using the traffic volume control plan generation method described above for nine intersections and calculate signal cycles and display lengths for each TOD.
[0143] Through traffic simulation, the average delay time per intersection was compared with the signal plan per TOD derived through the conventional TOD signal plan and the traffic volume control device (10).
[0144] The example in Fig. 17 shows the result of signal optimization for a single intersection during off-peak hours, the example in Fig. 18 shows the result of signal optimization for a single intersection during morning peak hours, and the example in Fig. 19 shows the result of signal optimization for a single intersection during afternoon peak hours.
[0145] As a result of evaluating performance by dividing it into off-peak (weekdays 1:00 PM to 2:00 PM), morning peak (weekdays 8:00 AM to 9:00 AM), and afternoon peak (weekdays 6:00 PM to 7:00 PM), when traffic volume control is performed by the traffic volume control device (10), a reduction in delay time can be confirmed at most intersections throughout the entire time period.
[0147] FIG. 20 shows the flow of operation of the traffic volume control device illustrated in FIG. 1.
[0148] Referring to FIG. 20, the processor (100) can receive traffic volume by direction of movement for a unit of time (2010). The traffic volume by direction of movement may include traffic volume corresponding to the vehicle's entry direction, exit direction, and / or combination of the entry direction and exit direction for a unit of time.
[0149] The processor (100) can generate a traffic characteristic value table based on traffic volume by direction of travel (2030). The processor (100) can generate a traffic characteristic value table by sorting the traffic volume by direction of travel for a unit of time according to the day of the week, hour, and / or minute.
[0150] The processor (100) can generate a traffic volume control plan by performing clustering on a traffic characteristic value table (2050).
[0151] The processor (100) can generate normalized traffic characteristic values by normalizing a traffic characteristic value table based on the total traffic volume per unit time. The processor (100) can generate a traffic volume control plan by performing clustering based on the normalized traffic characteristic values.
[0152] The processor (100) can generate multiple initial cluster centers by randomly selecting a predetermined number of objects from normalized traffic characteristic values.
[0153] The processor (100) can generate multiple clusters by clustering the remaining values of traffic characteristic values based on the Euclidean distance between the remaining values of the traffic characteristic values and the multiple initial cluster centers.
[0154] The processor (100) can calculate the centers of multiple clusters. The processor (100) can update multiple clusters based on the centers of multiple clusters.
[0155] The processor (100) can calculate a silhouette score based on the smallest distance between the average distance to an object in one of the multiple clusters and the average distance to a cluster to which the object does not belong among the multiple clusters.
[0156] The processor (100) can determine the number of target clusters based on the silhouette score. The processor (100) can generate clusters equal to the number of target clusters.
[0157] The processor (100) can calculate a silhouette score based on the result of comparing the average distance and the smallest distance and the value obtained by dividing the average distance by the smallest distance.
[0158] The processor (100) can determine the number of clusters with the highest silhouette score as the target number of clusters. The processor (100) can calculate the silhouette score while increasing the number of clusters from the minimum number of clusters up to the maximum number of traffic signal control plans. For example, the minimum number of clusters may be 2.
[0159] The processor (100) can generate multiple clusters by performing clustering based on a traffic characteristic value table. The processor (100) can generate a traffic volume control plan by assigning a traffic signal control plan corresponding to the multiple clusters.
[0161] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.
[0162] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave in order to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on computer-readable recording media.
[0163] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may store program instructions, data files, data structures, etc., either alone or in combination, and the program instructions recorded on the medium may be those specifically designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.
[0164] The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.
[0165] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based thereon. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.
[0166] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.
Claims
Claim 1 A traffic volume control device for controlling traffic volume at an intersection movable in one or more directions of movement, comprising: a processor; and a memory for storing instructions executable by the processor, wherein the processor receives traffic volume by direction of movement for a unit time, generates a traffic characteristic value table based on the traffic volume by direction of movement, and generates a traffic volume control plan by performing clustering on the traffic characteristic value table, wherein the traffic volume by direction of movement includes traffic volume corresponding to the entry direction, exit direction, and combination of the entry direction and the exit direction of a vehicle according to the unit time, and wherein the processor calculates the traffic volume by direction of movement by assigning an intersection entry and exit section number of the vehicle and distinguishing the turning of the vehicle based on the number, and generates the traffic volume control plan using the turning rate from the first direction to the second direction of the intersection as a weight. Claim 2 A traffic volume control device according to claim 1, wherein the processor generates the traffic characteristic value table by sorting the traffic volume by direction of movement for the unit time according to the day of the week, hour, or minute. Claim 3 A traffic volume control device according to claim 1, wherein the processor generates normalized traffic characteristic values by normalizing the traffic characteristic value table based on the total traffic volume for the unit time, and generates the traffic volume control plan by performing clustering based on the normalized traffic characteristic values. Claim 4 A traffic volume control device according to paragraph 3, wherein the processor generates a plurality of initial cluster centers by randomly selecting a predetermined number of objects from the normalized traffic characteristic values, and generates a plurality of clusters by clustering the remainder values of the traffic characteristic values based on the Euclidean distance between the remainder values of the traffic characteristic values and the plurality of initial cluster centers. Claim 5 In paragraph 4, the processor calculates the center of the plurality of clusters and updates the plurality of clusters based on the center of the plurality of clusters, a traffic volume control device. Claim 6 A traffic volume control device according to claim 4, wherein the processor calculates a silhouette score based on the smallest distance between an object within one of the plurality of clusters and the average distance to a cluster to which the object does not belong among the plurality of clusters, determines the number of target clusters based on the silhouette score, and generates clusters equal to the number of target clusters. Claim 7 A traffic volume control device according to claim 6, wherein the processor calculates the silhouette score based on the result of comparing the average distance and the smallest distance and the value obtained by dividing the average distance by the smallest distance, and determines the number of clusters in the case where the silhouette score is highest as the number of target clusters. Claim 8 In paragraph 6, the processor calculates the silhouette score while increasing the number of clusters from the minimum number of clusters to the maximum number of traffic signal control plans, a traffic volume control device. Claim 9 A traffic volume control device according to claim 1, wherein the processor generates a plurality of clusters by performing clustering based on the traffic characteristic value table and generates the traffic volume control plan by assigning a traffic signal control plan corresponding to the plurality of clusters. Claim 10 A method for controlling traffic volume at an intersection movable in one or more directions of movement, comprising: receiving traffic volume by direction of movement for a unit time; generating a traffic characteristic value table based on the traffic volume by direction of movement; and generating a traffic volume control plan by performing clustering on the traffic characteristic value table, wherein the traffic volume by direction of movement includes traffic volume corresponding to the entry direction, exit direction, and combination of the entry direction and the exit direction of a vehicle according to the unit time, and the step of generating the traffic characteristic value table includes: assigning an intersection entry and exit section number of the vehicle; and calculating the traffic volume by direction of movement by distinguishing the turning of the vehicle based on the number, and the step of generating the traffic volume control plan includes generating the traffic volume control plan using the turning rate from the first direction to the second direction of the intersection as a weight.
Citation Information
Patent Citations
Method and apparatus for classifying traffic pattern
KR1020220092293A
Device for controlling traffic signal
KR102166283B1
