KR20190020479A - Apparatus for processing data in tactical data link system - Google Patents

Abstract

The present invention relates to data processing technique of a tactical data link system. A data processing apparatus connected to a parallel processing apparatus having the n number of blocks may comprise: a data cleaning unit cleaning tactical data to be data necessary for a correlation operation; and a parallel processing unit dividing some cleaned data of the data cleaning unit into the n number of groups corresponding to the n number of blocks, allocating the n number of groups to the n number of blocks, and returning a result of the correlation operation from the parallel processing apparatus.

Description

TECHNICAL FIELD [0001] The present invention relates to a tactical data link system, a tactical data link system,

The present invention relates to a tactical data link system and a data processing technique performed in a tactical data link system.

In a weapon system that utilizes tactical information through tactical data links that are operated in various ways, in order to provide the tactical situation information of the player to the operator, the tactical data of the friendly and enemy forces reported by the detection system is tracked Taking care of it.

Systems that manage tactical data adhere to the inherent communication rules defined by standard rules or systems such as Link-16, Link-11, ISDL, and Link-K. In a system in which such various types of tactical data link communication are operated together, a system in which tactical data is integratedly managed needs to receive and receive heterogeneous tactical data from a plurality of sources and to manage them in an integrated manner.

A system for managing wakes in a variety of tactical data link operating environments should be operated so that even if the same wake is detected by multiple tactical data link environments, it can be recognized as a single wake rather than a plurality of wake. Perform track correlation operations. The Cartesian Compare Matching operation is a technique for determining whether a number of detected tactical walks are indeed monolithic by analyzing whether each of the two trajectories reported has similar position, course, speed and altitude attributes at a particular point in time.

In the conventional tactical data link system, since the track comparison and comparison operations are performed in a sequential manner, the system load can be increased with hundreds of millions of comparison and matching operations on average.

Korean Registered Patent No. 10-1659485 (Registered on September 19, 2016)

In the embodiment of the present invention, a data processing technique of a tactical data link system that can reduce the system load at the time of comparison and coincidence calculation of the tactical data of the navigation unit is proposed.

According to an embodiment of the present invention, there is provided a data processing apparatus connected to a parallel processing apparatus having n blocks, the data processing apparatus comprising: a data refining unit for refining tactical data into data necessary for a comparison operation; And a parallel processing unit for dividing a part of the refinement data of the data refinement unit into n groups corresponding to the n blocks and allocating them to the n blocks and returning the result of the comparison matching operation from the parallel processing unit The data processing apparatus of the tactical data link system can be provided.

Here, the parallel processing unit allocates another part of the purified data to the global memory of the parallel processing apparatus, and returns the result of the comparison and matching operation of the part of the purified data and the other part of the purified data from the global memory The portion of the refinement data is local data, and the other portion of the refinement data is remote data.

In addition, the data refinement unit may check the validity of the local data and the remote data.

The apparatus may further include a preprocessor for correcting an error between the local data and the remote data, the validity of which is checked.

The data preprocessing unit may correct at least one of a geodetic error, an altitude error, a detection azimuth, a distance error, and a position error of the local data and the remote data.

In addition, the tactical data may include a tactical track.

According to an embodiment of the present invention, there is provided a parallel processing apparatus for performing a comparative matching operation between local data and remote data of a tactical data link system in units of n blocks; And allocating the local data to the n blocks corresponding to the n blocks and allocating the remote data to the global memory of the parallel processing device, And a data processing unit for receiving a result from the global memory.

Here, the tactical data link system may include: a local relay for receiving the local data at a first time point; And the parallel processing unit is connected to a remote repeater for receiving the remote data at the first time point, and the parallel processing unit compares the local data with the remote data, and if the data is generated from the same node, It can be judged from the data.

Also, the parallel processing apparatus may compare at least one of latitude, longitude, speed, course, and altitude included in the local data and the remote data.

According to the embodiment of the present invention, the tactical data link system divides received tactical data into groups corresponding to the parallel processing blocks and assigns them to the parallel processing apparatus, thereby reducing the system load Can be greatly reduced.

1 is a conceptual diagram illustrating an exemplary comparative match operation performed in a tactical data link system.
2 is an exemplary illustration of a tactical data link for illustrating a tactical data link system according to an embodiment of the present invention.
3 is a block diagram of a tactical data link system in accordance with an embodiment of the present invention.
4 is a conceptual diagram illustrating an example of local data group allocation performed by a data processing apparatus of a tactical data link system according to an embodiment of the present invention.
5 is a detailed block diagram of the data refinement unit 100 of FIG.
FIG. 6 is a detailed block diagram of the preprocessing unit 110 of FIG.
7 is a detailed block diagram of the operation unit 200 of FIG.
8 is a diagram schematically illustrating a core architecture of a CPU (Control Processing Unit) of a sequential calculation method and a GPU (Graphics Processing Unit) of a parallel computing method.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention, and the manner of achieving them, will be apparent from and elucidated with reference to the embodiments described hereinafter in conjunction with the accompanying drawings. It should be understood, however, that the invention is not limited to the disclosed embodiments, but may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, To fully disclose the scope of the invention to a person skilled in the art, and the scope of the invention is only defined by the claims.

In describing embodiments of the present invention, a detailed description of well-known functions or constructions will be omitted unless otherwise described in order to describe embodiments of the present invention. The following terms are defined in consideration of the functions in the embodiments of the present invention, which may vary depending on the intention of the user, the intention or the custom of the operator. Therefore, the definition should be based on the contents throughout this specification.

In the conventional tactical data link system such as the Master Control and Report Center (MCRC) and the Korean Naval Tactical Data System (KNTDS), local data managed by the tactical data link and data received via the third tactical data link And an algorithm for comparing remote data in a sequential manner is applied.

1 is a conceptual diagram illustrating an exemplary comparative match operation performed in a tactical data link system.

As shown in FIG. 1, when it is assumed that M local data is received and N remote data is received, a comparison matching operation between local data # 1 and N remote data is sequentially performed, and then local data # 2 and N It is possible to discriminate whether or not a single wakeup is performed by sequentially performing comparison and matching operations between the remote data.

In a tactical data link environment in which tactical data (local data and remote data) have a small capacity but do not require a large load on the system but require tens or thousands of trajectory management, an average of hundreds of millions of comparative matching operations are sequentially , The load for the apparatus for comparing and matching operations, for example, the CPU, is increased, and the occupancy rate can be greatly increased. Excessive CPU utilization can also have an adverse effect on the thread behavior of other processes.

The embodiment of the present invention divides the tactical data received by the tactical data link system into groups corresponding to the parallel processing blocks and allocates them to the blocks of the parallel processing apparatus so that the system load And to provide a technology that can be reduced.

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

2 is an exemplary illustration of a tactical data link for illustrating a tactical data link system according to an embodiment of the present invention.

2, the tactical data link includes a tactical data link system 1, a local repeater b and a remote repeater group b-1 to bn connected to the tactical data link system 1, And a node group (a-1, a-2) connected to the local repeater b and / or the remote repeater group b-1 to bn.

The tactical data transmitted from any one of the node groups a-1 to a-2, for example, node 1 (a-1) can be provided to the tactical data link system 1 via the local repeater b have. In this case, the tactical data can be named as local data managed in the tactical data link system 1. [

The tactical data transmitted from the node 1 (a-1) is transmitted to the tactical data link system 1 (b-1) via any one of the remote repeater groups b-1 to bn, ). ≪ / RTI > In this case, the tactical data can be named as remote data that is not managed in the tactical data link system 1. [

Since the tactical data provided to the tactical data link system 1 through the local repeater b and the remote repeater 1 (b-1) is data transmitted from the node 1 (a-1) And the remote data provided through the remote repeater 1 (b-1) can be determined as the tactical data having the same wake. As described above, the determination as to whether or not the tactical data are identical can be performed by the comparison matching operation.

1, the tactical data is refined and allocated to the parallel processing blocks so that the comparison matching operations can be processed in parallel through the data processing process. .

FIG. 3 is a block diagram of a tactical data link system suitable for tactical data refinement and parallel processing according to an embodiment of the present invention, wherein a tactical data link system according to an embodiment of the present invention includes a data processing device 10 and a parallel processing device 20).

First, the data processing apparatus 10 may include a data processing unit 100, a preprocessing unit 110, and a parallel processing unit 120.

The data refinement unit 100 may refine the local data received through the local repeater b and the remote data received through the remote repeater groups b-1 to b-n to the data necessary for the comparison matching operation. For example, the tactical data, which is a tactical navigation unit, may include various data such as motility data, identification data, and armed data. Of these data, the data required for the comparison coincidence operation may be mobility data and identification data, It is necessary to refine. At the same time, the data refinement unit 100 can check the validity of the local data and the remote data according to the field and the transmission / reception rule, and filter the data with the possibility of error. Here, the validity check can be performed in accordance with, for example, the protocol of the Interface Control Document (ICD) or the tactical data link standard document. Also, the data refinement unit 100 can convert the validated local data and remote data into a common format.

The preprocessing unit 110 can correct the error between the local data and the remote data converted into the common format through the data refinement unit 100. [ The error corrected through the preprocessing unit 110 may be, for example, an error of at least one of geodetic error, altitude, detection orientation, distance, and position of local data and remote data.

The parallel processing unit 120 may divide the error-corrected local data through the preprocessing unit 110 into a plurality of groups corresponding to a plurality of blocks of the parallel processing unit 20 and allocate them to a plurality of blocks. In FIG. 3, data provided from the parallel processing unit 120 to the operation unit 200 of the parallel processing unit 20 may be a local data group. Here, the block of the parallel processing device 20 means a core responsible for the operation of the parallel processing device 20, and the block of the parallel processing device 20 is a local data The number of groups may correspond to the number of cores of the parallel processor 20. [

FIG. 4 is a conceptual diagram illustrating the local data group allocation performed by the parallel processing unit 120 as an example.

4, the parallel processing unit 120 can set a local data group obtained by dividing the local data received by the tactical data link system 1 by the number of blocks (cores) of the parallel processing device 20. [ For example, assuming that 10,000 local data are received in the tactical data link system 1, and the number of blocks (cores) of the parallel processing apparatus performing the comparison matching operation of the local data is 100, the parallel processing unit 120 may divide 10,000 local data into 100 local data groups corresponding to the number of blocks of the parallel processing unit 20. [

A local data group to be divided by the parallel processing unit 120 may be assigned to each block of the parallel processing unit 20 and each of the blocks of the parallel processing unit 20 may be provided with respective local data set as a local data group You can perform a compare match operation on a thread-by-thread basis.

3, the parallel processing unit 120 may allocate the error-corrected remote data to the parallel processing unit 20 through the preprocessing unit 110, And the operation result can be returned from the parallel processing device 20. [ The comparison matching operation performed in the parallel processing unit 20 means a comparison matching operation between the local data and the remote data.

The parallel processing unit 20 may include a computing unit 200, a first global memory 210, and a second global memory 220.

The operation unit 200 may perform a comparison match operation on a block-by-block basis with respect to local data of a local data group provided from the parallel processing unit 10 and remote data to be loaded in the first global memory 210 described later. The arithmetic unit 200 may include each block in the parallel processor 20 of FIG. 4, and each block may include a separate memory (not shown) such that a plurality of threads (100 threads in the case of FIG. 4) (Not shown). Here, the separate memory may include, for example, a shared memory, a local memory, and the like.

The first global memory 210 may load remote data provided from the parallel processing unit 120 of the data processing apparatus 10. [ The remote data stored in the first global memory 210 may be used for the comparison matching operation of the operation unit 200.

The second global memory 220 may temporarily store the comparison result of the comparison operation of the calculation unit 200. [ The comparison result data temporarily stored in the second global memory 220 may be returned to the parallel processing unit 120 of the data processing apparatus 10. [

The first global memory 210 and the second global memory 220 may include, for example, RAM (Random Access Memory).

FIG. 5 is a detailed block diagram of the data refining unit 100 of FIG. 3, and includes an Ethernet / serial communication unit 101, a message decoding unit 102, a message encoding unit 103, ).

5, the Ethernet / serial communication unit 101 serves to receive local data from the local repeater b and remote data from the remote repeater groups b-1 to bn via Ethernet or serial .

The message decoding unit 102 may perform field conversion on local data and remote data received through the Ethernet / serial communication unit 101. [ For example, the message decoding unit 102 may perform field conversion by checking validity of local data and remote data according to a protocol of an interlocking control document (ICD) or a standard document of a tactical data link.

The message encoding unit 103 may perform an inverse function of the message decoding unit 102. Since the message encoding unit 103 can use a well-known encoding method, a detailed description thereof will be omitted.

The common format management unit 104 may convert the field values of the local data and the remote data effectively converted through the message decoding unit 102 into a common format.

FIG. 6 is a detailed block diagram of the preprocessing unit 110 of FIG. 3 and includes a geodesic error correction unit 111, a sensor error correction unit 112, a data processing error correction unit 113, . ≪ / RTI >

As shown in Fig. 6, the geodesic error correcting unit 111 can correct a geodesic error with respect to the latitude and longitude and altitude of local data received through the local repeater (b), for example.

The sensor error correction unit 112 corrects the mechanical / logical altitude and detection orientation of sensors included in any node, for example, node 1 (a-1), from the local data received from the local repeater b, The error can be corrected.

The data processing error correcting unit 113 can correct the error due to the coordinate conversion, the error between the time of the comparison coincidence time and the detection (reception) time, and the like. The data processing error correcting unit 113 can correct the error by, for example, applying extrapolation.

The remote node error correcting unit 114 corrects the position information of the remote node transmitting the remote data to the tactical data link system 1 through the remote repeater group b-1 to bn, for example, Can be corrected. The local data and the remote data can be corrected for errors through respective error functions of the preprocessing unit 110. At this time, the correction functions of the respective correction units 111 to 114 are supplied to the parallel processing unit 120 through the kernel ) Function and may be allocated to each block of the parallel processing unit 20 on a thread basis.

3 is a detailed block diagram of the calculating unit 200 of FIG. 3, and includes a comparison matching parameter managing unit 201, a comparison matching condition managing unit 202, a position testing unit 203, a speed testing unit 204, An altitude testing unit 206 and an Identification Friend or Foe (IFF) / Ship In Frames (SIF) code testing unit 207.

As shown in Fig. 7, the comparison coincidence parameter managing unit 201 can manage the parameters for the comparison coincidence operation. The parameters for this comparison matching operation may include at least one of geodetic error, altitude error, detected azimuth, distance error, and position error, for example, .

The comparison-match-condition-management unit 202 can manage the case of excluding from the comparison-match operation item in order to prevent unnecessary comparison-match operation. In the case where the tactical trajectory category is different, the quality of the tactical trajectory is less than a certain level, and the tactical trajectory is different from the actual state and the simulation state, for example, may be excluded from the comparison match operation item.

The position test section 203, the speed test section 204, the azimuth test section 205, and the altitude test section 206 may be configured with algorithms that are self-defined by a standard algorithm or system of the tactical data link, The parameter to be used may be input through the comparison matching parameter management unit 201. [

The IFF / SIF code testing unit 207 can be used as an option in the system in which the assumption is made that the identification code values can be compared and matched only in the condition that they are the same or compatible.

The functions of the test units 203 to 207 are converted into kernel functions through the parallel processing unit 120 and allocated to the respective blocks of the parallel processing unit 20 as threads, 1 global memory 210 so that each kernel function can be used simultaneously.

8 is a diagram schematically illustrating a core architecture of a CPU (Control Processing Unit) of a sequential calculation method and a GPU (Graphics Processing Unit) of a parallel computing method.

The CPU can currently accommodate up to 8 cores, and requires developers' expertise to run threads and synchronize data for each core. On the other hand, GPUs are built with hundreds of cores, so they are optimized for parallel processing of data, and can be controlled directly by devices using core-specific arithmetic units, global memory of memories and devices, Has the advantage of being able to. Also, there is an advantage that the parallel processing apparatus is logically managed as a two-dimensional or three-dimensional grid / block / thread, and is mapped with the index of the parallelized data, thereby facilitating simultaneous processing.

Inexpensive graphics card models that are more common on desktops than modern CPUs can achieve at least five times the computation speed. In particular, the parallel processing device is a peripheral device, which is easy to upgrade or add through the interface such as PCI-Express without replacing the main board, thus it is very cost effective and cost effective in system performance upgrade .

On the other hand, the data processing apparatus 10 according to the embodiment of the present invention is different from a general GPU in that it is made on-board with a chip dedicated for calculation, It is expected to be able to maximize its functionality by developing and installing it in the form of appliances, and applying parallel processing kernel functions such as comparison comparison in the form of firmware.

As described above, according to the embodiment of the present invention, the received tactical data is divided into groups corresponding to the parallel processing blocks and assigned to the parallel processing units, thereby enabling the system load This is an implementation that greatly reduces.

In the meantime, each block of the accompanying block diagrams and combinations of steps of the flowchart may be performed by computer program instructions. These computer program instructions may be loaded into a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, so that the instructions, which may be executed by a processor of a computer or other programmable data processing apparatus, Thereby creating means for performing functions.

These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner, It is also possible to produce manufacturing items containing instruction means for performing the functions described in each block of the block diagram.

Computer program instructions may also be loaded onto a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible that the instructions that perform possible data processing equipment provide steps for executing the functions described in each block of the block diagram.

Also, each block may represent a portion of a module, segment, or code that includes at least one or more executable instructions for executing the specified logical function (s). It should also be noted that in some alternative embodiments, the functions mentioned in the blocks may occur out of order. For example, two blocks shown in succession may actually be executed substantially concurrently, or the blocks may sometimes be performed in reverse order according to the corresponding function.

1: Tactical Data Link System
10: Data processing device
100: Data refining section
110:
120: parallel processor
20: Parallel processing device
200:
210: first global memory
220: second global memory

Claims (9)

A data processing apparatus in connection with a parallel processing apparatus having n blocks,
A data refining unit for refining the tactical data into data necessary for a comparison correlation operation; And
And a parallel processing unit that divides part of the refinement data of the data refinement unit into n groups corresponding to the n blocks and allocates the same to the n blocks and returns the result of the comparison matching operation from the parallel processing unit
Data processing device of a tactical data link system. The method according to claim 1,
The parallel processing unit includes:
Allocating another portion of the refinement data to the global memory of the parallel processing device,
A result of comparison and coarse calculation of the part of the tablet data and the other part of the tablet data is returned from the global memory,
Wherein the portion of the tablet data is local data and the other portion of the tablet data is remote data
Data processing device of a tactical data link system. 3. The method of claim 2,
The data-
And validating the local data and the remote data
Data processing device of a tactical data link system. The method of claim 3,
And a preprocessing unit for correcting an error between the local data and the remote data,
Data processing device of a tactical data link system. 5. The method of claim 4,
The data pre-
Correcting at least one of a geodetic error, an altitude error, a detection azimuth, a distance error, and a position error of the local data and the remote data
Data processing device of a tactical data link system. The method according to claim 1,
The tactical data may include a tactical track,
Data processing device of a tactical data link system. A parallel processor for performing a comparison matching operation between local data and remote data of the tactical data link system in units of n blocks; And
Dividing the local data into n groups corresponding to the n blocks and assigning the local data to the n blocks, allocating the remote data to the global memory of the parallel processing device, And a data processing device for receiving a result from the global memory
Tactical data link system. 8. The method of claim 7,
The tactical data link system comprises:
A local repeater for receiving the local data at a first point in time; And
Wherein the first remote controller is connected to a remote repeater for receiving the remote data at the first point in time,
The parallel processing apparatus includes:
If the local data and the remote data are compared and the data is generated from the same node, the local data and the remote data are determined as a single data
Tactical data link system. 9. The method of claim 8,
The parallel processing apparatus compares the local data with at least one of latitude, longitude, speed, course, and altitude included in the remote data
Tactical data link system.

Images