KR102309714B1 - Traffic simulation method based on parallel processing and appratus therefor - Google Patents

Abstract

A parallel processing-based traffic simulation method and an apparatus therefor according to an embodiment of the present invention are provided. In the traffic simulation method according to an embodiment of the present invention, the number of first vehicles capable of moving from a first link to a second link that is a next link among a plurality of links divided to have the same characteristics is determined, and the a first step of transmitting the determined first number of vehicles to the second link through a connection cell located between the links; a second step of acquiring a second number of vehicles that can be accommodated in the second link through the connection cell; and a third step of simulating moving a vehicle corresponding to the second number of vehicles among the vehicles corresponding to the first number of vehicles to the second link through the connection cell, wherein the first step, the first Step 2 and the third step are allocated as threads to each of a plurality of cores included in a GPU (Graphic Processing Unit) of the traffic simulation apparatus in correspondence with each of the plurality of links, and the allocated threads include: Each of the plurality of cores is executed in parallel at least simultaneously.

Description

TRAFFIC SIMULATION METHOD BASED ON PARALLEL PROCESSING AND APPRATUS THEREFOR

The present invention relates to a parallel processing-based traffic simulation method and an apparatus therefor.

Recently, various traffic problems such as traffic jams, traffic accidents, traffic environments, and traffic services are occurring due to the explosion of driving vehicles due to the continuous increase in vehicles. In order to solve such a traffic problem, a traffic simulation device that models a real traffic flow by road or a traffic situation such as vehicle movement and performs it virtually is attracting attention.

In general, a traffic simulation device simulates a vehicle flow or a vehicle movement by road according to at least one scenario using road traffic big data collected through a high pass, a smart traffic card system, and the like.

However, since the traffic simulation apparatus has to sequentially process a large amount of data for traffic simulation, there is a problem in that time and resources required for data processing increase.

Accordingly, there is a need for a method and apparatus for efficiently and quickly performing traffic simulation while minimizing time and resources required for traffic simulation.

An object of the present invention is to provide a parallel processing-based traffic simulation method and an apparatus therefor.

Specifically, the problem to be solved by the present invention is to provide a parallel processing-based traffic simulation method and an apparatus therefor in order to efficiently and quickly perform traffic simulation while minimizing time and resources required for traffic simulation.

The problems of the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the above-described problems, a parallel processing-based traffic simulation method and an apparatus therefor are provided. In the traffic simulation method according to an embodiment of the present invention, the number of first vehicles capable of moving from a first link to a second link that is a next link among a plurality of links divided to have the same characteristics is determined, and the a first step of transmitting the determined first number of vehicles to the second link through a connection cell located between the links; a second step of acquiring a second number of vehicles that can be accommodated in the second link through the connection cell; and a third step of simulating moving a vehicle corresponding to the second number of vehicles among the vehicles corresponding to the first number of vehicles to the second link through the connection cell, wherein the first step, the first Step 2 and the third step are allocated as threads to each of a plurality of cores included in a GPU (Graphic Processing Unit) of the traffic simulation apparatus in correspondence with each of the plurality of links, and the allocated threads include: Each of the plurality of cores is executed in parallel at least simultaneously.

In the traffic simulation method according to an embodiment of the present invention, the number of first vehicles capable of moving from a first link to a second link that is a next link among a plurality of links divided to have the same characteristics is determined, and the a first step of transmitting the determined first number of vehicles to the second link through a connection cell located between the links; a second step of acquiring vehicle data including a vehicle speed of the second link, a vehicle density, and a second number of vehicles that can be accommodated in each of a plurality of cells constituting the second link through the connection cell; and a third step of simulating moving a vehicle corresponding to the second number of vehicles among the vehicles corresponding to the first number of vehicles to the second link through the connection cell, wherein the first step, the first a fourth step of predicting a second number of vehicles that can be accommodated in the second link using the vehicle data in a next simulation operation after steps 2 and 3 are performed; and a fifth step of simulating moving a vehicle corresponding to the predicted second number of vehicles to the second link through the connection cell, wherein the fourth and fifth steps are performed for a preset number of times. do.

Traffic simulation apparatus according to an embodiment of the present invention, a storage unit for storing data; and a control unit connected to the storage unit and configured to perform the traffic simulation using simulation element data, road network data, and traffic demand data used for traffic simulation, wherein the control unit comprises a GPU (Graphic Processing Unit) is configured to include, and the GPU is configured to include a plurality of cores, and a first core among the plurality of cores is configured to include a road in a first link among a plurality of links divided to have the same characteristics. A first operation of determining the number of first vehicles capable of moving to a second link, which is the next link, and transferring the determined number of first vehicles to the second link through a connection cell located between the links, the connection cell a second operation of obtaining the second number of vehicles acceptable in the second link through and the first operation, the second operation, and the third operation are allocated as a thread to each of the plurality of cores in correspondence with each of the plurality of links, and the allocation The threads are executed in parallel at least simultaneously on each of the plurality of cores.

Traffic simulation apparatus according to an embodiment of the present invention, a storage unit for storing data; and a control unit connected to the storage unit and configured to perform the traffic simulation using simulation element data, road network data, and traffic demand data used for traffic simulation, wherein the control unit comprises a GPU (Graphic Processing Unit) is configured to include, and the GPU is configured to include a plurality of cores, and a first core among the plurality of cores is configured to include a road in a first link among a plurality of links divided to have the same characteristics. A first operation of determining the number of first vehicles capable of moving to a second link, which is the next link, and transferring the determined number of first vehicles to the second link through a connection cell located between the links, the connection cell a second operation of acquiring vehicle data including the vehicle speed of the second link, the vehicle density, and the second number of vehicles that can be accommodated in each of a plurality of cells constituting the next link; and perform a third operation of moving a vehicle corresponding to the second number of vehicles among corresponding vehicles to the next link through the connection cell, and the first operation, the second operation, and the third operation are performed After this, the controller performs a fourth operation of predicting the second number of vehicles that can be accommodated in the second link using the vehicle data in the next simulation operation, and assigning a vehicle corresponding to the predicted second number of vehicles to the connection cell and to perform a fourth operation simulating to move to the second link through

The details of other embodiments are included in the detailed description and drawings.

The present invention can provide a parallel processing-based traffic simulation method and apparatus therefor that efficiently and quickly perform traffic simulation while minimizing time and resources required for traffic simulation.

The effect according to the present invention is not limited by the contents exemplified above, and more various effects are included in the present invention.

1 is a block diagram of a traffic simulation apparatus according to an embodiment of the present invention.
2 is a schematic diagram of a control unit according to an embodiment of the present invention.
3A, 3B, 3C and 3D are exemplary views for explaining a parallel processing-based traffic simulation method according to an embodiment of the present invention.
4 is an exemplary view for explaining a method of performing a traffic simulation using a buffer in the traffic simulation apparatus according to an embodiment of the present invention.
5 is an exemplary diagram for explaining a method of performing vehicle movement between links constituting an intersection in the traffic simulation apparatus according to an embodiment of the present invention.
6 is a flowchart illustrating a method of performing parallel processing-based traffic simulation in a traffic simulation apparatus according to an embodiment of the present invention.
7 is a flowchart illustrating a method of performing vehicle movement between links in a traffic simulation apparatus according to an embodiment of the present invention.
8 is a flowchart illustrating a method of performing vehicle movement between links in a traffic simulation apparatus according to another embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. In connection with the description of the drawings, like reference numerals may be used for like components.

In this document, expressions such as "has," "may have," "includes," or "may include" refer to the presence of a corresponding characteristic (eg, a numerical value, function, operation, or component such as a part). and does not exclude the presence of additional features.

In this document, expressions such as "A or B," "at least one of A and/and B," or "one or more of A or/and B" may include all possible combinations of the items listed together. . For example, "A or B," "at least one of A and B," or "at least one of A or B" means (1) includes at least one A, (2) includes at least one B; Or (3) it may refer to all cases including both at least one A and at least one B.

As used herein, expressions such as "first," "second," "first," or "second," may modify various elements, regardless of order and/or importance, and refer to one element. It is used only to distinguish it from other components, and does not limit the components. For example, the first user equipment and the second user equipment may represent different user equipment regardless of order or importance. For example, without departing from the scope of rights described in this document, the first component may be named as the second component, and similarly, the second component may also be renamed as the first component.

A component (eg, a first component) is "coupled with/to (operatively or communicatively)" to another component (eg, a second component) When referring to "connected to", it will be understood that the certain element may be directly connected to the other element or may be connected through another element (eg, a third element). On the other hand, when it is said that a component (eg, a first component) is "directly connected" or "directly connected" to another component (eg, a second component), the component and the It may be understood that other components (eg, a third component) do not exist between other components.

As used herein, the expression "configured to (or configured to)" depends on the context, for example, "suitable for," "having the capacity to ," "designed to," "adapted to," "made to," or "capable of." The term “configured (or configured to)” may not necessarily mean only “specifically designed to” in hardware. Instead, in some circumstances, the expression “a device configured to” may mean that the device is “capable of” with other devices or parts. For example, the phrase “a processor configured (or configured to perform) A, B, and C” refers to a dedicated processor (eg, an embedded processor) for performing the operations, or by executing one or more software programs stored in a memory device. , may mean a generic-purpose processor (eg, a CPU or an application processor) capable of performing corresponding operations.

Terms used in this document are only used to describe specific embodiments, and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly dictates otherwise. Terms used herein, including technical or scientific terms, may have the same meanings as commonly understood by one of ordinary skill in the art described in this document. Among the terms used in this document, terms defined in a general dictionary may be interpreted with the same or similar meaning as the meaning in the context of the related art, and unless explicitly defined in this document, ideal or excessively formal meanings is not interpreted as In some cases, even terms defined in this document cannot be construed to exclude embodiments of this document.

Each feature of the various embodiments of the present invention may be partially or wholly combined or combined with each other, and technically various interlocking and driving are possible, as will be fully understood by those skilled in the art, and each embodiment may be independently implemented with respect to each other, It may be possible to implement together in a related relationship.

In this specification, a road is divided into a plurality of links having the same characteristics, and the links are divided into lanes and sections indicating the length of the links in the road direction.

In the present specification, a cell is a sub-unit consisting of a link, a section, and a lane, and is a criterion for evaluating vehicle movement, vehicle speed and density on a road, and the like.

In the present specification, a connection cell is a unit connecting a link and a link, and serves to distribute vehicles between links based on road-specific connection data and traffic signal data of the link. Here, the connection data for each road may include information on a next link connected in a link, and the traffic signal data may include information on a traffic signal between links.

In the present specification, a source is a space stored before a vehicle enters a link, and may correspond to a space such as a parking lot, a building, and the like. A vehicle is created in the source every simulation cycle, and a vehicle existing in the source may enter the link depending on whether the link is accepted or not. The vehicle created in the source may have a driving start time, a driving route, and a target lane range.

In the present specification, a sink is a space to which a vehicle that has finished driving advances, and information about the vehicle that has been driven may be stored.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of a traffic simulation apparatus according to an embodiment of the present invention.

Referring to FIG. 1 , a traffic simulation device 100 is a device for simulating a vehicle flow between links divided into a plurality of roads, and includes a communication unit 110 , a display unit 120 , a storage unit 130 , and a control unit. (140). For example, the traffic simulation apparatus 100 may be a computing device such as a personal computer (PC), a notebook computer, or a tablet PC, but is not limited thereto, and various devices capable of performing traffic simulation may be used.

The traffic simulation device 100 includes vehicle data for a road (eg, vehicle speed, density, driving direction, etc.), link data (eg, number of links, size of links, etc.) and connection cell data (eg, between links). Vehicle flow between links can be simulated based on simulation element data including road-specific connection data and traffic signal data).

First, the communication unit 110 connects the traffic simulation device 100 to enable communication with an external device. For example, the communication unit 110 may be connected to an external device using wired/wireless communication to transmit/receive various data.

The display unit 120 may display various contents (eg, text, image, video, icon, banner or symbol, etc.) to the user. Specifically, the display unit 120 may display an interface screen indicating a traffic simulation result.

In various embodiments, the display unit 120 may include a touch screen, for example, a touch, a gesture, a proximity, a drag, and a swipe using an electronic pen or a part of the user's body. A swipe or hovering input may be received.

The storage unit 130 may store various data used to simulate a vehicle flow between links. In particular, the storage unit 130 may store simulation element data including vehicle data for each road, link data, and connection cell data used for traffic simulation.

In various embodiments, the storage unit 130 may include a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory (eg, SD or XD). memory, etc.), Random Access Memory (RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM) , a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. The traffic simulation apparatus 100 may operate in relation to a web storage that performs a storage function of the storage unit 130 on the Internet.

The controller 140 is operatively connected to the communication unit 110 , the display unit 120 , and the storage unit 130 , and may perform various commands for simulating a vehicle flow between links.

The controller 140 may perform a vehicle movement simulation operation between a plurality of links in which roads are divided to have the same characteristics by using simulation element data used for traffic simulation.

To this end, the control unit 140 may include a first processing unit 150 and a second processing unit 160 .

The first processing unit 150 may generate simulation element data, road network data, and traffic demand data for traffic simulation according to at least one traffic scenario based on the road traffic big data. For example, the first processing unit 150 may be a central processing unit (CPU), but is not limited thereto. Here, the road traffic big data is data representing the actual road configuration, driving direction, traffic signal, vehicle demand, traffic condition, and the like, and may be periodically collected. In addition, the simulation element data includes vehicle data including vehicle speed, density, and driving direction for traffic simulation, link data including the number and size of links, and road-specific connection data and traffic signal data between links. It may include the included connection cell data. The road network data may represent links, connection cells, sources, and sinks constituting a road for traffic simulation, and the traffic demand data may represent a route of a vehicle for simulation based on the road network. At least one traffic scenario may be pre-stored or may be variously set for traffic simulation, but is not limited thereto.

The second processing unit 160 may simultaneously perform at least a parallel vehicle movement simulation operation between links in correspondence to each of the plurality of links. For example, the second processing unit 160 may be a graphic processing unit (GPU), but is not limited thereto.

The second processing unit 160 includes a plurality of cores, and a vehicle movement simulation operation between links may be assigned to each of the plurality of cores as threads. In this way, the threads allocated to each of the plurality of cores may be executed in parallel at least simultaneously. For example, a vehicle movement simulation operation for the i-th link may be performed by the i-th core 162 , and a vehicle movement simulation operation for the i+1-th link may be performed by the i+1-th core 164 ( i>0, i is a natural number).

Hereinafter, a simulation operation of vehicle movement between links performed in each of the i-th core 162 corresponding to the i-th link and the i+1-th core 164 corresponding to the i+1-th link will be described.

The i-th core 162 determines the first number of vehicles that can move from the i-th link to the next link, i+1-th link, and the i+1-th core 164 performs vehicle movement simulation on the i+1-th link. ) may transmit the determined first vehicle number. Here, the first number of vehicles may be the number of vehicles located in the last cell of the i-th link.

In general, there may be a link cell between the link and a connection cell that regulates the flow of vehicles between the links. Such a connection cell includes road-specific connection data indicating information on the next link connected from a specific link and traffic signal data indicating whether a vehicle moves when a vehicle moves between links. can In other words, since the movement of a vehicle between a link and a link is made through a connection cell, a vehicle existing in the last cell of the i-th link does not move directly to the first cell of the i+1-th link. That is, the i-th core 162 checks the next link to which a vehicle existing in the last cell of the i-th link should move using the connection data for each road through the connection cell, and determines whether the vehicle moves using the traffic signal data. By checking, you can perform vehicle movement between links.

In this case, the i-th core 162 may transmit the first data representing the first number of vehicles to the i+1-th core 164 through the connection cell. For example, the i-th core 162 copies the first data to the connection cell, and the first data copied to the connection cell is a virtual cell of the i+1-th link by the i+1-th core 164 . cell) can be added. Here, the virtual cell is a cell for temporarily storing data, and may be located in front of the first cell and behind the last cell of the link.

Subsequently, the i-th core 162 may obtain the second number of vehicles acceptable in the i+1-th link from the i+1-th core 164 . Here, the second number of vehicles is determined by the i+1th core 164 and may be the number of vehicles that can be accommodated in the first cell of the i+1th link. In other words, the acceptable vehicle may be the number of vehicles capable of moving from the virtual cell of the i+1-th link to the first cell of the i+1-th link. In this case, the i+1th core 164 may copy the second data indicating the second number of vehicles to the connection cell, and the i-th core 162 may bring the copied second data to the connection cell.

The i-th core 162 may simulate moving a vehicle corresponding to the acquired second vehicle number among vehicles corresponding to the first vehicle number to the i+1-th link. Specifically, the i-th core 162 may move a vehicle corresponding to the second number of vehicles among the vehicles located in the last cell of the i-th link to a virtual cell located behind the last cell of the i-th link. In other words, the i-th core 162 may copy identification data (eg, ID) of a vehicle corresponding to the second number of vehicles to the virtual cell. For example, when the second number of vehicles is one, if 18 vehicles exist in the last cell, the i-th core 162 may copy vehicle identification data of one of them to the virtual cell.

The i-th core 162 may move the vehicle moving to the virtual cell to the connection cell, and the vehicle may move to the i+1-th link through the connection cell. In other words, the vehicle identification data may be copied to the connection cell, and the vehicle identification data copied to the connection cell may be added to the first cell of the i+1-th link.

Through this, according to the present invention, since each of the GPU cores simultaneously performs the above-described operations corresponding to each link in parallel, it is possible to reduce the time and resources required to perform the traffic simulation, thereby improving the traffic simulation performance.

In various embodiments, the i-th core 162 performs a vehicle movement simulation operation between links by omitting some of the above-described operations, thereby partially omitting a plurality of operations performed by each core, thereby omitting some of the resources and time required to perform a traffic simulation. can be minimized.

To this end, the i-th core 162 obtains the second number of vehicles acceptable in the first cell of the i+1-th link from the above-described i+1-th core 164, but instead of acquiring the vehicle speed and vehicle density of the i+1-th link. and vehicle data including the number of vehicles that can be accommodated in each of a plurality of cells included in the i+1th link.

Specifically, the i-th core 162 determines the first number of vehicles that can move from the i-th link to the next link, i+1-th link, and transmits the determined first vehicle number to the i+1-th core 164, Vehicle data of the i+1th link may be obtained from the i+1th core 164 . For example, when the number of cells included in the i+1th link is 4, vehicle data includes the average vehicle speed in the i+1th link, the average vehicle density, and a virtual cell located in front of the first cell, which is the first cell. The number of vehicles capable of moving from each of the cell, the second cell, and the third cell to the next cell may be included.

The i-th core 162 transfers a vehicle corresponding to the number of vehicles that can move from the virtual cell of the i+1-th link to the first cell (ie, the second number of vehicles) among the vehicles corresponding to the first number of vehicles through i+ through the connection cell. The transfer is performed to the first core 164 , and the i+1-th core 164 may move the transferred vehicle to the first cell of the i+1-th link. In other words, the i-th core 162 copies vehicle identification data corresponding to the second number of vehicles to the connection cell, and the i+1-th core 164 copies the vehicle identification data copied to the connection cell to the i+1-th vehicle identification data. You can add it to the first cell of the link.

Thereafter, the i-th core 162 transfers the above-described first vehicle number to the next link for the next vehicle movement simulation, and uses the vehicle data obtained in advance without the need to perform the operation of obtaining the second vehicle number from the next link Thus, it is possible to predict the number of second vehicles that can be accommodated in the first cell of the next link.

Specifically, the i-th core 162 predicts the second number of vehicles acceptable in the first cell of the i+1-th link by using the vehicle data of the i+1-th link obtained in the previous process, and A vehicle corresponding to the predicted second number of vehicles among the corresponding vehicles may be moved to the connection cell. In other words, the i-th core 162 uses the average vehicle speed, the average vehicle density, and the number of vehicles that can move from the first cell to the second cell of the i+1-th link in the last cell of the i-th link. The number of vehicles capable of moving to the first cell of the +1-th link (ie, the number of second vehicles) may be predicted.

The vehicle moving to the connection cell can move to the first cell of the i+1-th link by the i+1-th core 164 , and since the moving vehicle corresponds to the predicted number of second vehicles, the first cell of the i+1-th link There may be a difference from the number of second vehicles that can actually be accommodated in . In this case, since the moved vehicle cannot move to the i-th link again, the i+1-th core 164 moves the remaining vehicles except for the actual number of second vehicles to the virtual cell located in front of the first cell of the i+1-th link, The corresponding virtual cell may be used as a buffer.

The operation of predicting the second number of vehicles may be performed by a number that is one less than the number of acquired vehicle data. In other words, the i-th core 162 may predict the second number of vehicles using vehicle data by a number that is one less than the number of cells included in the i+1-th link. For example, if the i+1th link includes 4 cells, the i-th core 162 predicts the second number of vehicles using the average vehicle speed, average vehicle density, and the number of vehicles that can move from the first cell to the second cell, , predict a second number of vehicles using the average vehicle speed, average vehicle density, and the number of vehicles that can move from the second cell to the third cell for the next vehicle movement, and then the average vehicle speed, average vehicle density and third cell for the next vehicle movement. A total of three prediction operations may be performed, such as the operation of predicting the second number of vehicles by using the number of vehicles that can move from to the fourth cell.

As such, when the operation of predicting the number of second vehicles by one less than the number of cells included in the i+1-th link is completed, the i-th core 162 determines the first number of vehicles for the next vehicle movement simulation. and transfer the determined first number of vehicles to the i+1th core 164 through the connection cell, and obtain vehicle data for each cell from the i+1th core 164 again. have.

As described above, the operation of predicting the second number of vehicles may be performed using the average vehicle speed, the average vehicle density, and the number of acceptable vehicles obtained in the past for each cell, but is not limited thereto, and the second number of vehicles is not limited thereto. Various methods such as machine learning, deep learning, and the like may be used to predict .

In various embodiments, the vehicle stored in the buffer may move to the first cell of the i+1-th link whenever the number of vehicles that can be accommodated in the first cell of the i+1-th link exceeds '0'.

In various embodiments, when the number of vehicles stored in the buffer exceeds a preset threshold, vehicle identification data stored in the buffer may be deleted starting with the oldest data.

As described above, the present invention predicts the second number of vehicles acceptable in the next link based on vehicle data obtained from the next link, thereby transferring the first number of vehicles to the next link and obtaining the second number of vehicles from the next link. This is omitted so that resources and time required for this can be reduced.

In various embodiments, the controller 140 may display an interface screen indicating a traffic simulation result through the display unit 120 . The interface screen displayed through the display unit 120 may include at least one graphic object representing a traffic flow between links.

Hereinafter, the control unit 140 including the first processing unit 142 and the second processing unit 144 will be described in detail with reference to FIG. 2 .

2 is a schematic diagram of a control unit according to an embodiment of the present invention.

Referring to FIG. 2 , the control unit 200 includes a CPU 210 and a GPU 220 . In the presented embodiment, the control unit 200 , the CPU 210 , and the GPU 220 may refer to the control unit 140 , the first processing unit 142 , and the second processing unit 144 of FIG. 1 .

The CPU 210 includes a simulation element generator 212 , and the GPU 220 includes a resource updater 222 , a lane change unit 224 , and a vehicle estimator 226 .

The simulation element generator 212 generates simulation element data used for traffic simulation based on road traffic big data.

Specifically, the simulation element generator 212 may generate simulation element data including vehicle data, link data, and connection cell data using road traffic big data, and may generate road network data and traffic demand data. The data generated in this way may be used as input data for traffic simulation.

The resource updater 222 resets the simulation road (eg, link, connection cell, source, and sink) based on the simulation element data, road network data, and traffic demand data, and introduces a simulation vehicle into the reset simulation road. can do it This process may be performed at regular intervals of the simulation.

When the vehicle inside the cell moves to another cell, the lane change unit 224 may perform a lane change essential for a route change and a selective lane change to a high speed lane for fast driving.

The vehicle follower 226 calculates the amount of vehicle movement between cells, calculates the actual movement amount of the vehicle in consideration of traffic signals and intersections, and checks whether the vehicle located in the cell can move according to the calculated actual movement amount. have. Also, the vehicle follower 226 may update vehicle data (eg, vehicle identification data, next link identification data, target lane data, etc.) for each cell.

Specifically, the vehicle follower 226 receives the number of vehicles desired to move from an arbitrary cell (eg, a sending cell) to a next cell (eg, a receiving cell) in the driving direction, and the reception cell. According to the number of vehicles and road characteristics, the amount of vehicle movement between cells can be calculated as the minimum value of the number of vehicles that can be moved during the simulation time unit. The vehicle follower 226 may calculate the actual number of movable vehicles (eg, effective vehicle movement amount) of the vehicle located in the cell in consideration of road connection behavior and traffic signals within the intersection.

The vehicle follower 226 checks whether the leading vehicle in the vehicle queue in the cell can move according to the effective vehicle movement amount, updates the number of vehicles per cell based on the effective vehicle movement amount per cell, and according to whether movement is possible Inter-cell vehicle data can be updated.

The vehicle follower 226 may perform the vehicle movement simulation between the links described above in FIG. 1 . For example, when the vehicle moves between links, the vehicle follower 226 determines the first number of vehicles that can move in the last cell of a specific link, and transmits the determined number of first vehicles to the next link through the connection cell, and the next link. may obtain an acceptable second number of vehicles, and transfer the vehicle corresponding to the second number of vehicles corresponding to the first number to the next link through the connection cell.

In addition, as described above, the vehicle follower 266 acquires vehicle data including the vehicle speed of the next link, the vehicle density, and the second number of vehicles that can be accommodated in each of a plurality of cells constituting the next link, and performs the following simulation operation The vehicle corresponding to the predicted second number of vehicles after predicting the second number of vehicles by using the obtained vehicle data without the need to determine the first number of vehicles and obtain the second number of vehicles from the next link. By transferring ? to the next link, it is also possible to perform vehicle movement between links.

As described above, the present invention simultaneously processes the operations corresponding to each link in parallel, thereby reducing the time and resources required for the traffic simulation, increasing the processing speed, and performing efficient traffic simulation.

Hereinafter, when the type of road is a straight road, a traffic simulation operation of the traffic simulation apparatus 100 will be described in detail with reference to FIGS. 3A, 3B, 3C, and 3D.

3A, 3B, 3C and 3D are exemplary views for explaining a parallel processing-based traffic simulation method according to an embodiment of the present invention. In the presented embodiment, the i-th core 162 of FIG. 1 performs an operation corresponding to the i-th link 400 , and the i+1-th core 164 performs an operation corresponding to the i+1-th link 330 . can be done

Referring to FIG. 3A , the i-th link 300 includes the first to fourth cells, and the virtual cell 302 is located in front of the first cell, which is the first cell, and the virtual cell ( 304) exist.

Subsequently, the i+1-th link 330 includes the first to fourth cells, the virtual cell 332 is located in front of the first cell, which is the first cell, and the virtual cell 334 is located behind the fourth cell, which is the last cell. this exists

In addition, a connection cell (cc) 350 exists between the i-th link 300 and the i+1-th link 330 , and data between the i-th link 300 and the i+1-th link 330 is It can move through a connection cell.

Specifically, when performing the vehicle simulation, the i-th core 162 transmits data (numVeh[4]) indicating the number of vehicles located in the fourth cell 306 of the i-th link 300 to the connection cell for vehicle movement. (350) can be copied. The i+1th core 164 may add the data copied to the connection cell 350 to the virtual cell 332 of the i+1th link 330 .

Referring to FIG. 3B , the i-th core 162 performs vehicle tracking on the i-th link 300 , and the i+1-th core 164 performs vehicle tracking on the i+1-th link 330 . Thus, it is possible to determine the number of vehicles that can move from each link to the next. When performing such vehicle tracking, the i-th link 300 includes a virtual cell 302 and first to fourth cells, and the i+1-th link 330 includes a virtual cell 332 and first to fourth cells. It may include a fourth cell.

Specifically, the i-th core 162 determines the number of vehicles that can move from each cell of the i-th link 300 to the next cell, and the i+1-th core 164 determines the number of vehicles that can move from each cell to the next cell. can In other words, the i-th core 162 is the number of vehicles that can move from the virtual cell 302 to the first cell of the i-th link 300 (numCF[0]), and the number of vehicles that can move from the first cell to the second cell (numCF). [1]), the number of vehicles that can move from the second cell to the third cell (numCF[2]), and the number of vehicles that can move from the third cell to the fourth cell 306 (numCF[3]) may be determined. The i+1th core 164 is the number of vehicles (numCF[0]) that can move from the virtual cell 332 of the i+1th link 330 to the first cell 336, and the first in the first cell 336. The number of vehicles that can move to cell 2 (numCF[1]), the number of vehicles that can move from the second cell to the third cell (numCF[2]), and the number of vehicles that can move from the third cell to the fourth cell (numCF[3]) can decide

The i+1th core 164 transmits data representing the number of vehicles (numCF[0]) 340 that can move from the virtual cell 332 of the i+1th link 330 to the first cell 336 to the connection cell. (350) can be copied.

The i-th core 162 uses the data copied to the connection cell 350 from the fourth cell 306, which is the last cell of the i-th link 300 , to the first cell 336 of the i+1-th link 330 . The number of vehicles that can move (numCF[4]) 310 may be updated.

The i-th core 162 includes vehicle identification data (vehCF[1], vehCF[2], vehCF[3], vehCF[4]) corresponding to the number of vehicles that can move to the next cell among vehicles located in each cell as shown in FIG. 3C . ) can be updated. Thereafter, the i-th core 162 identifies a vehicle corresponding to the number of vehicles capable of moving from the fourth cell 306 to the first cell 336 of the i+1-th link 330 among vehicles located in the fourth cell 306 . The data (vehCF[4]) 308 may be copied to the virtual cell 304 , and the vehicle identification data copied to the virtual cell 304 may be copied to the connection cell 350 as shown in FIG. 3D .

Referring to FIG. 3D , the i+1th core 164 may add the vehicle identification data copied to the connection cell 350 to the first cell 336 that is the first cell of the i+1th link 330 .

As described above, in the present invention, each of a plurality of cores simultaneously and parallelly processes operations corresponding to each link, thereby reducing time and resources required for traffic simulation, increasing processing speed, and performing efficient traffic simulation. .

Hereinafter, a method of performing a traffic simulation using a buffer in the traffic simulation apparatus 100 will be described in detail with reference to FIG. 4 .

4 is an exemplary view for explaining a method of performing a traffic simulation using a buffer in the traffic simulation apparatus according to an embodiment of the present invention. In the presented embodiment, the i-th core 162 of FIG. 1 performs an operation corresponding to the i-th link 400 , and the i+1-th core 164 performs an operation corresponding to the i+1-th link 430 . can be done

Referring to FIG. 4 , the i-th link 400 includes four cells s1, s2, s3, and s4, and the buffer 402 may be located in front of the first cell s1, which is the first cell. Subsequently, the i+1-th link 430 includes four cells s1, s2, s3, and s4, and the buffer 434 may be located in front of the first cell s1, 432, which is the first cell. . Also, a connection cell (cc) 450 may exist between the i-th link 400 and the i+1-th link 430 .

Referring to FIG. 4A , the i-th core 162 transmits data indicating the number of vehicles located in the last cell (s4) 404 of the i-th link 400 to the connection cell (cc) 450 . After copying, the i+1th core 164 may add data representing the number of vehicles copied to the connection cell (cc) 450 to the first cell s1 of the i+1th link 430 .

The i-th core 162 performs vehicle tracking for each of the four cells of the i-th link 400 to include the vehicle speed, vehicle density, and the number of vehicles capable of moving from each cell to the next cell of the i-th link 400 . Vehicle data can be obtained. The i+1-th core 164 performs vehicle tracking for each of the four cells of the i+1-th link 430 to obtain the vehicle speed, vehicle density, and movement from each cell to the next cell of the i+1-th link 430 . Vehicle data including the number of possible vehicles may be obtained.

Referring to (b) of FIG. 4 , the i+1th link 430 copies the vehicle data of the i+1th link 430 to the connection cell (cc) 450, and the i-th core 162 is The vehicle data copied to the connection cell (cc) 450 may be imported.

Referring to (c) of FIG. 4 , the i-th core 162 is accommodated in the first cell (s1) 432 of the i+1-th link 430 using the vehicle data of the i+1-th link 430 . You can check the number of possible vehicles. The i-th core 162 copies identification data of a vehicle corresponding to the number of vehicles located in the last cell (s4) 404 of the i-th link to the connection cell (cc) 450, i+1 The 1st core 164 may add the vehicle identification data copied to the connection cell (cc) 450 to the 1st cell (s1) 432 of the i+1th link 430 .

For the next vehicle movement simulation, the i-th core 162 determines the number of vehicles that can be accommodated in the first cell (s1) 432 of the i+1-th link 430 using the vehicle data obtained in (b) of FIG. 4 . predictable.

Referring to (d) of FIG. 4 , the i-th core 162 transmits vehicle identification data corresponding to the predicted number of vehicles among the vehicles located in the last cell (s4) 404 of the i-th link to the connection cell (cc). (450) can be copied. Prediction of the number of vehicles may be performed based on an average vehicle speed, an average vehicle density, and an acceptable number of vehicles, but is not limited thereto. The i+1th core 164 adds the vehicle identification data copied to the connection cell (cc) 450 to the buffer 434 located in front of the first cell (s1) 432 of the i+1th link 430 can do.

Referring to (e) of FIG. 4 , the i+1th core 164 checks the number of vehicles that can actually be accommodated in the first cell s1 432 , and vehicle identification data stored in the buffer 434 with the checked number of vehicles If it is greater than or equal to the number of vehicles corresponding to , the vehicle identification data stored in the buffer 434 may be added to the first cell (s1) 432 of the i+1th link 430 . If the number of confirmed vehicles is smaller than the number of vehicles corresponding to the vehicle identification data stored in the buffer 434 , the i+1th core 164 performs vehicle identification data corresponding to the number of vehicle identification data stored in the buffer 434 . is added to the first cell (s1) 432 of the i+1th link 430 , and the remaining vehicle identification data may be queued in the buffer 434 .

For the next vehicle movement simulation, the operations in FIGS. 4(d) and 4(e) may be performed by one less than the number of cells of the i+1th link 430, and when these operations are completed, The operations of (a), (b), (c), (d), and (e) of FIG. 4 may be performed.

As described above, in the present invention, by reducing the amount of data processed by each core, the processing speed of each core can be increased, and efficient traffic simulation can be performed.

Hereinafter, when the type of road is an intersection, a traffic simulation operation of the traffic simulation apparatus 100 will be described in detail with reference to FIG. 5 .

5 is an exemplary diagram for explaining a method of performing vehicle movement between links constituting an intersection in the traffic simulation apparatus according to an embodiment of the present invention. In the presented embodiment, vehicle movement between four links (eg, the first link, the second link, the fourth link, and the sixth link) among the links constituting the intersection will be described. In addition, in the presented embodiment, the first core operates in correspondence to the first link, the second core operates in correspondence to the second link, the fourth core operates in correspondence to the fourth link, and the sixth link corresponds to the sixth link. It will be described that the sixth core is operating.

Referring to FIG. 5 , each link consists of four lanes (first lane, second lane, third lane, and fourth lane) and four cells, and virtual cells exist in front of the first cell and behind the last cell. For example, the first link 500 consists of four lanes and four cells, such as a first lane 502, a second lane 504, a third lane 506, and a fourth lane 508; A virtual cell 512 exists in front of the first cell 510 , and a virtual cell 516 exists behind the last cell 514 . In addition, a connection cell (cc) 570 is positioned between the link and the link to control the flow of vehicles between the links.

A vehicle included in the last cell corresponding to the first lane 502 of the first link 500 moves to the sixth link 560, which is the next link according to the driving direction of the intersection, and corresponds to the second lane 504 Thus, the vehicle included in the last cell moves to the fourth link 540 , and the vehicle included in the last cell moves to the fourth link 540 in response to the third lane 506 , and the fourth lane 508 . In response, the vehicle included in the last cell may move to at least one of the second link 520 and the fourth link 540 . As such, the data for the next link may be stored in the connection cell 570 as a 3 (eg, the number of next links movable according to the driving direction)×4 (eg, the number of lanes) matrix 572 .

The first core performing an operation on the first link 500 includes a first number of vehicles (numVeh[4][0]) that can move in the last cell corresponding to the first lane 502 (eg, three); The first number of vehicles movable in the last cell corresponding to the second lane 504 (numVeh[4][1]) (eg, two), the first movable vehicle in the last cell corresponding to the third lane 506 . The number of vehicles (numVeh[4][2]) (eg, 3) and the first number of movable vehicles (numVeh[4][3]) in the last cell corresponding to the fourth lane 508 (eg, 2) and at least one of 1) can be determined. Such an operation may be performed according to each link.

The first core may copy the determined first number of movable vehicles per lane to the connection cell 570, and the copied number of vehicles per lane may be added to a virtual cell corresponding to each of the following links. Here, the copied number of first vehicles per lane may be copied to the connection cell 570 as a 3x4 matrix 574 .

For example, the first number of vehicles (eg, three) determined to correspond to the first lane 502 of the first link 500 is added to the virtual cell corresponding to the first lane of the sixth link 560 and , the first number of vehicles (eg, two) determined in response to the second lane 504 is added to the virtual cell corresponding to the second lane of the fourth link 540 , and is added to the virtual cell corresponding to the third lane 506 . The determined first number of vehicles (eg, three) is added to the virtual cell corresponding to the third lane of the fourth link 540 , and the second link ( The first number of vehicles (eg, two) that can move to 520 is added to a virtual cell corresponding to the fourth lane of the second link 520 , and the first number of vehicles that can move to the fourth link 540 (eg, two) is : 1 unit) may be added to the virtual cell corresponding to the fourth lane of the fourth link 540 .

Each of the first core, the second core, the fourth core and the sixth core performs vehicle tracking for the virtual cell, the first cell, the second cell and the third cell of each link, and the second vehicle acceptable in each link number can be determined. In other words, the first core determines the number of vehicles (numCF[0][0], numCF[0][1], numCF[0]) that can move from the virtual cell 512 to the first cell 510 in correspondence with each lane. [2], numCF[0][3]), the number of vehicles that can move from the first cell 510 to the second cell (numCF[1][0], numCF[1][1], numCF[1][2] ], numCF[1][3]), the number of vehicles that can move from cell 2 to cell 3 (numCF[2][0], numCF[2][1], numCF[2][2], numCF[2] ][3]), the number of vehicles that can move from the third cell to the fourth cell 514 (numCF[3][0], numCF[3][1], numCF[3][2], numCF[3] [3]) can be determined. The second core, the fourth core, and the sixth core may also perform the same operation as the operation performed by the first core.

For example, the number of vehicles capable of moving from the virtual cell corresponding to the first lane of the sixth link 560 to the first cell (ie, the first cell) (numCF[0][0] of the sixth link 560) is 3, the number of vehicles that can move from the virtual cell corresponding to the second lane of the fourth link 540 to the first cell (numCF[0][1] of the fourth link 540) is 2, The number of vehicles that can move from the virtual cell corresponding to the third lane of the 4 link 540 to the first cell (numCF[0][2] of the fourth link 540) is two, and the The number of vehicles that can move from the virtual cell corresponding to the fourth lane to the first cell (numCF[0][3] of the second link 520) is one, and the number of vehicles corresponding to the fourth lane of the fourth link 540 is one. It is assumed that the number of vehicles that can move from the virtual cell to the first cell (numCF[0][3] of the fourth link 540) is one.

In this case, the second number of vehicles that can be accommodated for each lane of the second link 520 , the fourth link 540 , and the sixth link 560 are copied to the connection cell 570 , and the second number copied to the connection cell 570 . 2 The number of vehicles is the number of vehicles (numCF[4][0], numCF[4][1], numCF[4) that can move from the fourth cell 514 of the first link 500 to the next movable link for each lane. ][2], numCF[4][3]). Here, the second number of vehicles that can be accommodated corresponding to each lane of each copied link may be copied to the connection cell 570 as a 3x4 matrix 576 .

The first core corresponds to the first lane of the sixth link 560 among vehicles (ie, vehicles corresponding to the first number of vehicles) located in the last cell corresponding to the first lane 502 of the first link 500 . A vehicle corresponding to the number of vehicles capable of moving to the first cell (numCF[4][0] of the first link 500) is moved to a virtual cell corresponding to the first lane 502 of the first link 500, and the corresponding A vehicle located in the virtual cell may be moved to the connection cell 570 . Subsequently, the first core determines the number of vehicles capable of moving to the first cell corresponding to the second lane of the fourth link 540 among vehicles located in the last cell corresponding to the second lane 504 of the first link 500 (first The vehicle corresponding to numCF[4][1]) of the link 500 is moved to the virtual cell corresponding to the second lane 504 of the first link 500, and the vehicle located in the virtual cell is moved to the connection cell 570 ) can be moved to Subsequently, the first core determines the number of vehicles capable of moving to the first cell corresponding to the third lane of the fourth link 540 among vehicles located in the last cell corresponding to the third lane 506 of the first link 500 (the first The vehicle corresponding to numCF[4][2]) of the link 500 is moved to the virtual cell corresponding to the third lane 506 of the first link 500 , and the vehicle is moved to the connection cell 570 . can In addition, the first core is the number of vehicles capable of moving to the first cell corresponding to the fourth lane of the second link 520 among vehicles located in the last cell corresponding to the fourth lane 508 of the first link 500 (first The number of vehicles corresponding to the numCF[4][3] of the link 500 and the number of vehicles capable of moving to the first cell corresponding to the fourth lane of the fourth link 540 (numCF[4][ of the first link 500 ) 3]) may be moved to a virtual cell corresponding to the fourth lane 508 of the first link 500 , and the corresponding vehicle may be moved to the connection cell 570 . In other words, identification data of the vehicle may be copied.

The vehicle moved to the connection cell 570 may move to the first cell of each link based on the traffic signal data. For example, three vehicles located in the last cell corresponding to the first lane 502 of the first link 500 move to the first cell corresponding to the first lane of the sixth link 560, and the first link ( Two vehicles located in the last cell corresponding to the second lane 504 of 500 may move to the first cell corresponding to the second lane of the fourth link 540 . Two vehicles located in the last cell corresponding to the third lane 506 of the first link 500 may move to the first cell corresponding to the third lane of the fourth link 540 . One vehicle located in the last cell corresponding to the fourth lane 508 of the first link 500 moves to the first cell corresponding to the fourth lane of the second link 520 and Another vehicle located in the last cell corresponding to the fourth lane 508 may move to the first cell corresponding to the fourth lane of the fourth link 540 .

As such, the present invention can perform more efficient traffic simulation in terms of time and cost.

6 is a flowchart illustrating a method of performing parallel processing-based traffic simulation in a traffic simulation apparatus according to an embodiment of the present invention. In the presented embodiment, the following operations may be performed by the controller 140 of FIG. 1 .

Referring to FIG. 6 , the traffic simulation apparatus 100 generates simulation element data, road network data, and traffic demand data for traffic simulation according to at least one traffic scenario based on road traffic big data ( S600 ).

The traffic simulation apparatus 100 performs an operation (S610) of performing a traffic simulation on the first link using the generated simulation element data, road network data, and traffic demand data (S610), ... and performing an operation ( S620 ) of performing a traffic simulation on the n-th link using the generated simulation element data, road network data, and traffic demand data simultaneously and in parallel (n>0, n is a natural number).

The traffic simulation apparatus 100 determines whether the number of simulations performed in this way is less than a preset maximum value (S630), and if the number of simulations performed is less than the maximum value, the traffic simulation operations S610 and S620 are continuously performed. do.

If the number of simulations performed is not less than (eg, equal to or greater than) the maximum value, the traffic simulation apparatus 100 outputs a traffic simulation result (S640). In other words, the controller 140 may display an interface screen representing the traffic simulation result through the display unit 120 .

7 is a flowchart illustrating a method of performing vehicle movement between links in a traffic simulation apparatus according to an embodiment of the present invention. In the presented embodiment, the following operation may be performed by the i-th core 162 of FIG. 1 . Hereinafter, for convenience, the i-th core 162 is described as the first core, the i-th link is described as the first link, the i+1-th core 164 is described as the second core, and the i+1-th link is described as the second core. Let it be described as the second link.

Referring to FIG. 7 , the first core determines the number of first vehicles that can move from a first link to a second link that is a next link among a plurality of links divided to have the same characteristics. is transmitted to the second link through a connection cell located between the links (S700). Specifically, the first core may copy the first data indicating the number of vehicles located in the last cell among the plurality of cells included in the first link to the connection cell. The first data copied to the connection cell may be added to a virtual cell located in front of the first cell of the second link. This operation may be performed by the second core.

The first core acquires the second number of vehicles that can be accommodated in the second link through the connection cell (S710). Specifically, each of the plurality of cores included in the GPU performs vehicle tracking in response to each of the plurality of links, and the first core is a virtual cell among a plurality of cells constituting the second link from the second link through the connection cell. Second data indicating the number of vehicles capable of moving to the first cell may be obtained.

The first core performs a simulation to move the vehicle corresponding to the second number of vehicles among the vehicles corresponding to the first number of vehicles to the second link through the connection cell ( S720 ). Specifically, the first core selects a vehicle corresponding to the number of vehicles capable of moving from the virtual cell of the second link to the first cell among the vehicles corresponding to the number of vehicles located in the last cell, and the first of the second link in the last cell of the first link. It can be updated with the number of vehicles that can move into the cell. Subsequently, the first core may move the vehicle corresponding to the updated number of vehicles to the second link through the connection cell. In other words, the first core may copy vehicle identification data corresponding to the updated number of vehicles to the connection cell, and the vehicle identification data copied to the connection cell may be added to the first cell of the second link.

These operations may be allocated as threads to each of a plurality of cores included in the GPU corresponding to each of the plurality of links, and the allocated threads may be executed in parallel at least simultaneously in each of the plurality of cores.

8 is a flowchart illustrating a method of performing vehicle movement between links in a traffic simulation apparatus according to another embodiment of the present invention. In the presented embodiment, the following operation may be performed by the i-th core 162 of FIG. 1 . Hereinafter, for convenience, the i-th core 162 is described as the first core, the i-th link is described as the first link, the i+1-th core 164 is described as the second core, and the i+1-th link is described as the second core. Let it be described as the second link.

Referring to FIG. 8 , the first core determines the number of first vehicles that can move from a first link to a second link that is a next link among a plurality of links divided to have the same characteristics. is transmitted to the second link through the connection cell located between the links (S800).

The first core acquires vehicle data including the vehicle speed of the second link, the vehicle density, and the number of second vehicles that can be accommodated in each of the plurality of cells constituting the second link through the connection cell ( S810 ). For example, if the second link consists of a virtual cell, a first cell, a second cell, a third cell, and a virtual cell, the first core may determine the average vehicle speed of the second link, the average vehicle density, and the virtual cell of the second link. Vehicle data including the number of vehicles that can move from the cell to the first cell, the number of vehicles that can move from the first cell to the second cell, and the number of vehicles that can move from the second cell to the third cell may be acquired.

The first core performs a simulation to move the vehicle corresponding to the second number of vehicles among the vehicles corresponding to the first number of vehicles to the second link through the connection cell (S820). Specifically, the first core updates the number of vehicles that can move from the virtual cell of the second link to the first cell to the number of vehicles that can move from the last cell of the first link to the first cell of the second link, and corresponds to the updated number of vehicles. The vehicle may be moved to the second link through the connection cell.

In the next simulation operation after operations S800, S810, and S820, the first core predicts the second number of vehicles that can be accommodated in the second link by using the vehicle data obtained in operation S810 without the need to perform operations S800 and S810. (S830). In this case, since the number of vehicles moving from the virtual cell of the second link to the first cell was used in the previous simulation step, the first core determines the average vehicle speed of the second link, the average vehicle density, and the number of vehicles that can move from the first cell to the second cell. , and the number of vehicles capable of moving from the second cell to the third cell may be used to predict the second number of vehicles that can be accommodated in the first cell of the second link.

The first core performs a simulation to move the vehicle corresponding to the predicted second number of vehicles to the second link through the connection cell ( S840 ). Specifically, a buffer capable of storing a vehicle may exist in front of the first cell of each of the plurality of links. In this case, the vehicle corresponding to the predicted second vehicle number is stored in the buffer, and if the predicted second vehicle number is equal to or smaller than the number of vehicles that can actually be accommodated in the first cell of the second link, the vehicle stored in the buffer is stored in the second link You can move to the first cell of

If the predicted number of second vehicles is greater than the number of vehicles that can actually be accommodated in the first cell of the second link, the vehicles corresponding to the actual number of vehicles stored in the buffer move to the first cell of the second link, and the remaining vehicles are stored in the buffer. can wait A vehicle waiting in the buffer may move to the first cell of the second link whenever there is an acceptable vehicle on the first link of the second link.

In addition, the above-described operation of predicting the second number of vehicles and moving the vehicle by the predicted second number of vehicles may be performed by one smaller number than the number of cells constituting the second link. For example, when the number of cells constituting the second link is four, the above-described operation may be performed three times, but is not limited thereto.

Through this, the present invention can provide a parallel processing-based traffic simulation method and apparatus therefor that efficiently and quickly perform traffic simulation while minimizing time and resources required for traffic simulation.

The apparatus and method according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination.

The program instructions recorded on the computer readable medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the computer software field. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - Includes magneto-optical media and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

Although the embodiments of the present invention have been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and various modifications may be made within the scope without departing from the technical spirit of the present invention. . Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100: traffic simulation device
110: communication department
120: display unit
130: storage
140: control unit
150: first processing unit
160: second processing unit

Claims (18)

delete delete delete delete As a traffic simulation method performed through a control unit of a traffic simulation device,
The first number of vehicles capable of moving from a first link to a second link that is a next link among a plurality of links divided to have the same characteristics is determined, and the determined first number of vehicles is used in connection cells located between the links. a first step of transmitting to the second link through a connection cell;
a second step of acquiring vehicle data including a vehicle speed of the second link, a vehicle density, and a second number of vehicles that can be accommodated in each of a plurality of cells constituting the second link through the connection cell; and
a third step of simulating to move a vehicle corresponding to the second number of vehicles among the vehicles corresponding to the first number of vehicles to the second link through the connection cell;
a fourth step of predicting a second number of vehicles that can be accommodated in the second link using the vehicle data in a next simulation operation after the first step, the second step, and the third step are performed; and
a fifth step of simulating to move a vehicle corresponding to the predicted second number of vehicles to the second link through the connection cell,
The fourth step and the fifth step are performed for a preset number of times, a parallel processing-based traffic simulation method. According to claim 5, wherein the first to the fifth step,
Allocated as a thread to each of a plurality of cores included in a GPU (Graphic Processing Unit) of the traffic simulation device in correspondence to each of the plurality of links,
The allocated thread is executed at least simultaneously in parallel in each of the plurality of cores, a parallel processing-based traffic simulation method. According to claim 5, wherein the preset number of times,
A parallel processing-based traffic simulation method corresponding to a number that is one less than the number of a plurality of cells constituting the second link. The method of claim 5, wherein a buffer capable of storing a vehicle is located in front of the first cell of each of the plurality of links,
The vehicle corresponding to the predicted second number of vehicles is stored in the buffer,
If the predicted number of second vehicles is equal to or smaller than the number of vehicles that can actually be accommodated in the first cell of the second link, the vehicle stored in the buffer moves to the first cell of the second link,
If the predicted number of second vehicles is greater than the number of vehicles that can actually be accommodated in the first cell of the second link, the vehicle corresponding to the number of vehicles stored in the buffer that corresponds to the number of vehicles stored in the buffer moves to the first cell of the second link, A traffic simulation method based on parallel processing, in which the remaining vehicles wait in the buffer. The method of claim 8, wherein the vehicle waiting in the buffer,
A traffic simulation method based on parallel processing, which moves to the first cell of the second link whenever there is an acceptable vehicle in the first link of the second link. delete delete delete delete a storage unit for storing data; and
A control unit connected to the storage unit and configured to perform the traffic simulation using simulation element data, road network data, and traffic demand data used for traffic simulation,
The control unit is configured to include a GPU (Graphic Processing Unit),
The GPU is configured to include a plurality of cores,
A first core among the plurality of cores,
The first number of vehicles capable of moving from a first link to a second link that is a next link among a plurality of links divided to have the same characteristics is determined, and the determined first number of vehicles is used in connection cells located between the links. A first operation of transferring to the second link through a (connection cell),
a second operation of acquiring vehicle data including a vehicle speed, a vehicle density of the second link, and a second number of vehicles that can be accommodated in each of a plurality of cells constituting the next link through the connection cell;
and perform a third operation of moving a vehicle corresponding to the second number of vehicles among the vehicles corresponding to the first number of vehicles to the next link through the connection cell,
After the first operation, the second operation, and the third operation are performed, the controller may perform a fourth operation of predicting the number of second vehicles that can be accommodated in the second link by using the vehicle data in a next simulation operation; and
and perform a fifth operation of simulating moving a vehicle corresponding to the predicted second number of vehicles to the second link through the connection cell,
The fourth operation and the fifth operation are performed for a preset number of times, a parallel processing-based traffic simulation apparatus. 15. The method of claim 14, wherein the first to the fifth operation,
is assigned as a thread to each of the plurality of cores corresponding to each of the plurality of links;
The allocated thread is executed at least simultaneously in parallel in each of the plurality of cores, a parallel processing-based traffic simulation device. 15. The method of claim 14, wherein the preset number of times,
A parallel processing-based traffic simulation device corresponding to a number that is one less than the number of cells constituting the second link. The method according to claim 14, wherein a buffer capable of storing a vehicle is located in front of the first cell of each of the plurality of links,
The vehicle corresponding to the predicted second number of vehicles is stored in the buffer,
If the predicted number of second vehicles is equal to or smaller than the number of vehicles that can actually be accommodated in the first cell of the second link, the vehicle stored in the buffer moves to the first cell of the second link,
If the predicted number of second vehicles is greater than the number of vehicles that can actually be accommodated in the first cell of the second link, the vehicle corresponding to the number of vehicles stored in the buffer that corresponds to the number of vehicles stored in the buffer moves to the first cell of the second link, The rest of the vehicles wait in the buffer, a parallel processing-based traffic simulation device. The method of claim 17, wherein the vehicle waiting in the buffer,
A traffic simulation apparatus based on parallel processing, which moves to the first cell of the second link whenever there is an acceptable vehicle in the first link of the second link.

Images