KR102153923B1 - Wireless communication control device performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in three-dimensional space and operating method thereof - Google Patents

Abstract

The present invention proposes a wireless communication control apparatus and an operation method thereof for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space. Accordingly, it it possible to prevent signal eavesdropping by a third party and improve diversity gain at the receiving side in a wireless sensor network.

Description

A wireless communication control device that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a 3D space, and its operation method {WIRELESS COMMUNICATION CONTROL DEVICE PERFORMING SIGNAL TRANSMISSION PROCESSING BASED ON ANALOG COOPERATIVE BEAMFORMING THROUGH COMMUNICATION NODES DISTRIBUTED IN THREE-DIMENSIONAL SPACE AND OPERATING METHOD THEREOF}

The present invention relates to a wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a 3D space, and a method of operating the same.

Recently, as technologies such as the Internet of Things have developed, interest in wireless sensor networks is increasing.

The wireless sensor network is being used in various fields such as logistics, distribution, environmental monitoring, and home automation because it can acquire sensing data through various sensors and provide it to the manager.

Since the wireless sensor network is used for acquisition and transmission of sensing data in factories and military fields, it is necessary to maintain a high level of security. However, due to the characteristics of the wireless network, the possibility of signal eavesdropping by a third party in the process of transmitting data to the data receiving side cannot be excluded.

As a method to block eavesdropping by a third party, a method of encrypting and transmitting data may be considered, but since the communication nodes used in the wireless sensor network are not of high performance, an encryption protocol for data encryption is applied. It may not be suitable for

In this regard, beamforming may be considered as a method for blocking eavesdropping by a third party. Beamforming refers to a technology that allows data to be transmitted only to a specific data receiving side, and a beamforming vector is usually transmitted to the data receiving side after precoding the signal to be transmitted using a predetermined beamforming vector in the data transmitting side. Since transmission data can be recovered only from the data receiving side sharing the data, it can be effectively used to block eavesdropping by a third party.

In addition, the introduction of an analog cooperative beamforming method may be considered as a method for improving the diversity gain of the data receiving side in the wireless sensor network. If the network is configured so that a plurality of communication nodes constituting the wireless sensor network transmit data to the data receiving side through cooperative beamforming, it is possible to block the possibility of eavesdropping by a third party due to beamforming to the data receiving side, and multiple communication nodes It is possible to achieve a high diversity gain at the data receiving side due to the cooperative communication between them.

Therefore, it is necessary to study the signal transmission processing technology of the analog cooperative beamforming method using a plurality of communication nodes constituting the network in the wireless sensor network, and in addition to the method of selecting the optimal communication nodes to participate in the cooperative beamforming. Research is needed.

The present invention proposes a wireless communication control apparatus and an operating method for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space, thereby eavesdropping a signal by a third party in a wireless sensor network. It is intended to support to improve the diversity gain of the receiving side while preventing this.

According to an embodiment of the present invention, a wireless communication control device that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space is n (n is a natural number of 3 or more) constituting a wireless sensor network. ) Communication nodes-the n communication nodes are distributed in a preset three-dimensional first space-an identification number storage unit in which a unique identification number is stored, and the first sensing data is transmitted to the first signal receiving device. When a transmission event to be transmitted occurs, k (k is 2) for transmitting the first sensing data to the first signal receiving apparatus among the n communication nodes based on analog cooperative beamforming. The k communication nodes are identified based on the unique identification numbers of the k communication nodes when the communication node selection unit for selecting communication nodes and the k communication nodes are selected. and a control command signal transmission unit for transmitting a control command signal instructing the k communication nodes to cooperatively transmit the first sensing data to the first signal receiving apparatus based on analog cooperative beamforming.

In addition, the operating method of the wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space according to an embodiment of the present invention is n ( n is a natural number of 3 or more) communication nodes-the n communication nodes are distributed in a preset three-dimensional first space-maintaining an identification number storage unit in which a unique identification number of is stored, a first signal When a transmission event in which first sensing data must be transmitted to a receiving device occurs, the first sensing data is transmitted to the first signal receiving device among the n communication nodes based on analog cooperative beamforming. Selecting k communication nodes for transmission (k is a natural number of 2 or more and less than n), and when the k communication nodes are selected, the k communication nodes based on the unique identification numbers of the k communication nodes And transmitting a control command signal instructing the k communication nodes to cooperatively transmit the first sensing data to the first signal receiving apparatus based on analog cooperative beamforming after identifying them.

The present invention proposes a wireless communication control apparatus and an operating method for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space, thereby eavesdropping a signal by a third party in a wireless sensor network. At the same time, the diversity gain of the receiving side can be improved.

1 is a diagram illustrating a structure of a wireless communication control apparatus that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a 3D space according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating an operation of a wireless communication control apparatus that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a 3D space according to an embodiment of the present invention.
3 is a flowchart illustrating a method of operating a wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. This description is not intended to limit the present invention to a specific embodiment, it is to be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention. While describing each drawing, similar reference numerals have been used for similar components, and unless otherwise defined, all terms used in the present specification including technical or scientific terms refer to common knowledge in the technical field to which the present invention belongs. It has the same meaning as commonly understood by someone who has it.

In this document, when a part "includes" a certain component, it means that other components may be further included rather than excluding other components unless otherwise stated. In addition, in various embodiments of the present invention, each component, functional blocks or means may be composed of one or more sub-components, and the electrical, electronic, and mechanical functions performed by each component are electronic. A circuit, an integrated circuit, and an application specific integrated circuit (ASIC) may be implemented with various known devices or mechanical elements, and may be implemented separately or two or more may be integrated into one.

On the other hand, the blocks of the attached block diagram and the steps in the flowchart are computer program instructions that are mounted on a processor or memory of equipment capable of processing data such as a general-purpose computer, a special-purpose computer, a portable notebook computer, and a network computer to perform specified functions. It can be interpreted as meaning. Since these computer program instructions can be stored in a memory provided in a computer device or in a memory readable by a computer, the functions described in the blocks in the block diagram or in the steps in the flowchart are produced as a product containing the instruction means to perform this. It could be. In addition, each block or each step may represent a module, segment, or part of code including one or more executable instructions for executing the specified logical function(s). In addition, it should be noted that in some alternative embodiments, functions mentioned in blocks or steps may be executed in a different order. For example, two blocks or steps shown in succession may be performed substantially simultaneously or may be performed in reverse order, and in some cases, some blocks or steps may be omitted.

1 is a diagram illustrating a structure of a wireless communication control apparatus that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a 3D space according to an embodiment of the present invention.

Referring to FIG. 1, a wireless communication control apparatus 110 according to the present invention includes an identification number storage unit 111, a communication node selection unit 112, and a control command signal transmission unit 113.

The identification number storage unit 111 stores unique identification numbers of n (n is a natural number of 3 or more) communication nodes constituting the wireless sensor network.

Here, the n communication nodes are distributed on a first three-dimensional space set in advance.

In this case, according to an embodiment of the present invention, the three-dimensional first space is a three-dimensional spherical space having a radius of a preset length, and the n communication nodes are a three-dimensional Gaussian distribution in the three-dimensional spherical space ( Gaussian Distribution).

In relation to this, FIG. 2 is a conceptual diagram illustrating a state in which the n communication nodes are distributed in a three-dimensional spherical space.

As illustrated in FIG. 2, the n communication nodes may be distributed in a three-dimensional spherical space having a radius of a preset length, and at this time, the distribution of the n communication nodes in the three-dimensional spherical space Can follow a three-dimensional Gaussian distribution.

In connection, a point indicated by reference numeral 211 denotes one communication node among n communication nodes, and the positions of each communication node may be expressed in a three-dimensional spherical coordinate system.

Further, a point indicated by reference numeral 212 represents a signal receiving device that receives sensing data through a wireless sensor network, and the position of the signal receiving device may also be expressed in a three-dimensional spherical coordinate system.

When a transmission event for transmitting the first sensing data to the first signal receiving device occurs, the communication node selection unit 112 analogizes the first sensing data to the first signal receiving device among the n communication nodes. K (k is a natural number greater than or equal to 2 and less than n) communication nodes for transmission based on cooperative beamforming (Analog Cooperative Beamforming) are selected.

When the k communication nodes are selected, the control command signal transmission unit 113 identifies the k communication nodes based on the unique identification numbers of the k communication nodes, and then performs the first sensing to the k communication nodes. A control command signal instructing to cooperatively transmit data to the first signal receiving device based on analog cooperative beamforming is transmitted.

In this case, according to an embodiment of the present invention, the wireless communication control device 110 may be configured to select a communication node to transmit sensing data by using machine learning-based artificial intelligence technology. In this regard, wireless communication control The apparatus 110 is a component for performing machine learning, and may further include a training set storage unit 114, a calculation matrix generation unit 115, a probability value calculation unit 116, and a learning execution unit 117.

In the training set storage unit 114, three-dimensional coordinates for each of a plurality of signal receiving sides set in advance and a unique identification number of a communication node preset as corresponding to each of the plurality of signal receiving sides are provided as a training set for machine learning. It is stored as data.

Here, the communication node corresponding to each of the plurality of signal receiving sides is a communication node selected from among the n communication nodes, and when a signal is transmitted to each of the plurality of signal receiving sides based on beamforming, It refers to a communication node that has been confirmed by a pre-test as having the maximum signal to noise ratio (SNR) at each signal receiving side. For example, when the n communication nodes transmit signals based on beamforming to a receiving side having three-dimensional coordinates of'(a1, b1, c1)', communication with a unique identification number of'identification number 1' If the SNR at the node is measured at the maximum, the manager can associate a communication node with a unique identification number of'Identification number 1'to a receiving side having a three-dimensional coordinate of'(a1, b1, c1)'. In this way, the administrator can configure training set data for machine learning by matching the unique identification number of the corresponding communication node for each of the plurality of signal receiving sides through several experiments.

In consideration of this point, data may be stored in the training set storage unit 114 as shown in Table 1 below.

Training set Multiple signals To the receiving parties 3D coordinates for Unique identification number of the corresponding communication node Set 1 (a1, b1, c1) Identification number 1 Set 2 (a2, b2, c2) Identification number 2 Set 3 (a3, b3, c3) Identification number 3 ... ... ...

The arithmetic matrix generator 115 generates a 1 x 3 matrix corresponding to each of the plurality of signal receiving sides based on the three-dimensional coordinates of each of the plurality of signal receiving sides, and the plurality of signal receiving sides A 1x3 matrix corresponding to each is sequentially multiplied by at least one weight matrix to generate a 1xn arithmetic matrix corresponding to each of the plurality of signal receiving sides.

For example, when it is assumed that there are 100 of the plurality of signal receiving sides, the arithmetic matrix generating unit 115 corresponds to 1 corresponding to each of the 100 signal receiving sides based on the three-dimensional coordinates for each of the 100 signal receiving sides. You can create an x 3 matrix. Relatedly, if there is a signal receiving side having three-dimensional coordinates of'(a1, b1, c1)', the arithmetic matrix generator 115 is 1 called'[a1 b1 c1]' for the signal receiving side. You can create an x 3 matrix.

In this case, when the at least one weighting matrix includes a weighting matrix 1 having a size of 3 x 4 and a weighting matrix 2 having a size of 4 xn, the calculation matrix generator 115 includes 100 1 x 3 matrices. Each of the weight matrices 1 and 2 may be sequentially multiplied to generate 100 1xn arithmetic matrices corresponding to each of 100 signal receiving sides. In this case, components constituting the weight matrixes 1 and 2 may be configured randomly. Although to be described later, components constituting the weight matrices 1 and 2 are determined through machine learning.

The probability value calculator 116 applies a preset activation function for calculating a probability value to n components included in a 1 xn computation matrix corresponding to each of the plurality of signal receiving sides, Calculate n probability values in each of them.

In this case, according to an embodiment of the present invention, the activation function may be a softmax function that converts n values into a probability value between 0 and 1 according to the operation of Equation 1 below.

Here, f _i is a probability value calculated on the i-th value of n values, x _i is the i-th value of n values, x _k is the k-th value of n values, and e is a natural constant. The sum of n probability values calculated by Equation 1 is 1.

In relation to the above, as in the above-described example, when it is assumed that a 1xn calculation matrix corresponding to each of the 100 signal receiving sides is generated by the calculation matrix generator 115, the probability value calculation unit 116 receives 100 signals. By applying the softmax function according to Equation 1 to n components included in the calculation matrix of each of the sides, n probability values corresponding to each of the 100 signal receiving sides may be calculated.

When the n probability values of each of the plurality of signal receiving sides are calculated, the learning performing unit 117 uses the n probability values calculated by each of the plurality of signal receiving sides to be unique identification numbers of the n communication nodes. Is matched one by one, and the probability value matched with the unique identification number of the communication node selected as corresponding to each of the plurality of signal receiving sides among n probability values calculated by each of the plurality of signal receiving sides is the maximum. If possible, the at least one weight matrix is machine-learned.

In relation to the above, it is assumed that weight matrices 1 and 2 are present as the at least one weight matrix, and n probability values corresponding to each of the 100 signal receiving sides are calculated by the probability value calculator 116. If it is, the learning performing unit 117 may match n probability values with unique identification numbers of n communication nodes one by one for each of the 100 signal receiving sides. In this case, the learning performing unit 117 may match the n probability values calculated by each signal receiving side and the unique identification numbers of n communication nodes one by one in a predetermined order.

Then, the learning performing unit 117 checks the unique identification number of the communication node corresponding to the training set data for each of the 100 signal receiving sides, and training at each signal receiving side among n probability values at each signal receiving side. The weight matrices 1 and 2 may be machine-learned so that the probability value matching the unique identification number of the communication node corresponding to the set is maximized.

For example, when it is assumed that the training set data is configured as shown in Table 1, the learning performing unit 117 is used to identify'identification' among n probability values for the receiving side having three-dimensional coordinates of'(a1, b1, c1)'. The weight matrices 1 and 2 may be machine-learned so that the probability value matched with the number 1'becomes maximum. In this way, the learning performing unit 117 may repeat the process of machine learning the weight matrices 1 and 2 for each of the 100 signal receiving sides.

In this way, when a transmission event for transmitting the first sensing data to the first signal receiving device occurs after machine learning for the at least one weight matrix is completed, the communication node selection unit 112 performs the first Transmitting the first sensing data to the first signal receiving device among the n communication nodes based on the three-dimensional coordinates of the signal receiving device and at least one weight matrix on which the machine learning has been completed, based on analog cooperative beamforming For the k (k is a natural number greater than or equal to 2 and less than n) communication nodes may be selected.

In this case, according to an embodiment of the present invention, the communication node selection unit 112 is a specific configuration for selecting a communication node based on at least one weight matrix on which the machine learning has been completed, and the coordinate checking unit 118 and the matrix An operation unit 119, a probability value selection unit 120, and a selection processing unit 121 may be included.

When a transmission event for transmitting the first sensing data to the first signal receiving device occurs, the coordinate checking unit 118 checks the three-dimensional coordinates of the first signal receiving device.

The matrix operation unit 119 generates a 1 x 3 matrix corresponding to the first signal reception device based on the three-dimensional coordinates of the first signal reception device, and generates a 1 x 3 matrix corresponding to the first signal reception device. At least one weight matrix on which the machine learning has been completed is serially multiplied to generate a 1 xn arithmetic matrix corresponding to the first signal receiving apparatus.

The probability value selection unit 120 applies the activation function for calculating a probability value to n components included in a 1 xn calculation matrix corresponding to the first signal reception device, After calculating n probability values, matching the n probability values for the first signal receiving device with unique identification numbers of the n communication nodes one by one, the size of the n probability values for the first signal receiving device is Select k probability values in the largest order.

And, when the k probability values are selected, the selection processing unit 121 selects the k communication nodes whose unique identification numbers are matched to the k probability values among the n communication nodes to the first signal receiving device. 1 Select a communication node for transmitting sensing data based on cooperative analog beamforming.

For example, when the three-dimensional coordinates according to the first signal receiving device are'(k1, k2, k3)', the matrix calculator 119 generates a 1 x 3 matrix called'[k1 k2 k3]', The 1 x 3 matrix may be serially multiplied by the at least one weight matrix on which machine learning has been completed to generate a 1 x n arithmetic matrix.

Then, the probability value selection unit 120 may calculate n probability values by applying a softmax function such as Equation 1 to n components included in the 1 x n computation matrix, and n probability values. For values, the unique identification numbers of the n communication nodes may be sequentially matched one by one.

Thereafter, the probability value selecting unit 120 may select k probability values in the order of the largest size among the n probability values.

In this way, when k probability values are selected, the selection processing unit 121 selects k communication nodes with unique identification numbers matched to the k probability values among the n communication nodes as communication nodes for performing signal transmission. I can.

Eventually, the wireless communication control device 110 according to the present invention checks the communication node identified as having an optimal SNR for predetermined signal receiving sides, configures it as a training set, and performs machine learning based on the training set. By learning the weight matrix for selecting the communication node, and selecting the optimal communication nodes to participate in the cooperative beamforming among the communication nodes existing in the wireless sensor network based on the machine learning-completed weight matrix, cooperation in the wireless sensor network You can increase the efficiency of communication.

3 is a flowchart illustrating a method of operating a wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space according to an embodiment of the present invention.

In step S310, a unique identification number of n (n is a natural number of 3 or more) communication nodes constituting the wireless sensor network (the n communication nodes are distributed in a preset three-dimensional first space) is stored. Maintain the stored identification number.

In step S320, when a transmission event in which the first sensing data needs to be transmitted to the first signal receiving device occurs, the first sensing data is transmitted to the first signal receiving device among the n communication nodes. K (k is a natural number of 2 or more and is less than n) for transmission based on.

In step S330, when the k communication nodes are selected, the k communication nodes are identified based on the unique identification numbers of the k communication nodes, and the first sensing data is transmitted to the k communication nodes. 1 Transmits a control command signal instructing to transmit cooperatively based on analog cooperative beamforming to the signal receiving device.

In this case, according to an embodiment of the present invention, the first three-dimensional space is a three-dimensional spherical space having a radius of a preset length, and the n communication nodes are based on a three-dimensional Gaussian distribution within the three-dimensional spherical space. May be distributed along the lines.

In addition, according to an embodiment of the present invention, the method of operating the wireless communication control device includes a three-dimensional coordinate for each of a plurality of preset signal receiving sides and a preset communication corresponding to each of the plurality of signal receiving sides. Node (a communication node corresponding to each of the plurality of signal receiving sides is a communication node selected from among the n communication nodes, and when a signal is transmitted to each of the plurality of signal receiving sides based on beamforming, Maintaining a training set storage unit in which a unique identification number of each signal receiving side has a maximum SNR and is identified by a pre-test) as training set data for machine learning, the plurality of A 1 x 3 matrix corresponding to each of the plurality of signal reception sides is generated based on the three-dimensional coordinates of each of the signal reception sides, and at least one in a 1 x 3 matrix corresponding to each of the plurality of signal reception sides Generating a 1xn arithmetic matrix corresponding to each of the plurality of signal receiving sides by serially multiplying the weight matrix of, n number of calculation matrices included in the 1xn arithmetic matrix corresponding to each of the plurality of signal receiving sides Computing n probability values at each of the plurality of signal receiving sides by applying a preset activation function for calculating a probability value for the components, and n probability values at each of the plurality of signal receiving sides When calculated, the n probability values calculated by each of the plurality of signal receiving sides are matched one by one with the unique identification numbers of the n communication nodes, and among the n probability values calculated by each of the plurality of signal receiving sides, the The method may further include machine learning the at least one weight matrix such that a probability value matched with a unique identification number of a communication node selected to correspond to each of the plurality of signal receiving sides is maximized.

In this case, in step S320, when a transmission event in which the first sensing data must be transmitted to the first signal receiving device occurs, the three-dimensional coordinates of the first signal receiving device and at least one weight on which the machine learning is completed Based on the matrix, the k communication nodes for transmitting the first sensing data to the first signal receiving apparatus from among the n communication nodes based on analog cooperative beamforming are selected.

At this time, according to an embodiment of the present invention, in step S320, when a transmission event for transmitting the first sensing data to the first signal receiving device occurs, the three-dimensional coordinates of the first signal receiving device are determined. The step of confirming, generating a 1 x 3 matrix corresponding to the first signal reception device based on the three-dimensional coordinates of the first signal reception device, and the machine in a 1 x 3 matrix corresponding to the first signal reception device Generating a 1xn arithmetic matrix corresponding to the first signal reception device by serially multiplying at least one weight matrix on which training has been completed, n included in the 1xn arithmetic matrix corresponding to the first signal reception device N probability values for the first signal receiving device are calculated by applying the activation function for calculating probability values for the components, and n probability values for the first signal receiving device are calculated for the n communication nodes. After matching the unique identification numbers of each one by one, selecting k probability values in the order of the largest size among n probability values for the first signal receiving device, and when the k probability values are selected, the n communication nodes Among them, selecting k communication nodes whose unique identification numbers are matched to the k probability values as communication nodes for transmitting the first sensing data to the first signal receiving apparatus based on analog cooperative beamforming. can do.

In this case, according to an embodiment of the present invention, the activation function may be a softmax function that converts n values into a probability value between 0 and 1 according to the operation of Equation 1 above.

In the above, an operation method of a wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space according to an embodiment of the present invention has been described with reference to FIG. 3. . Here, an operating method of the wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space according to an embodiment of the present invention is described with reference to FIGS. 1 and 2. Since it may correspond to the configuration of the operation of the wireless communication control device 110 that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in the described 3D space, a more detailed description thereof will be omitted. I will do it.

In accordance with an embodiment of the present invention, a method of operating a wireless communication control apparatus that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space is stored for execution through combination with a computer. It may be implemented as a computer program stored in a medium.

In addition, a method of operating a wireless communication control apparatus that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space according to an embodiment of the present invention may be performed through various computer means. It may be implemented in the form of a program command 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 medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those produced by a compiler but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, in the present invention, specific matters such as specific components, etc., and limited embodiments and drawings have been described, but this is provided only to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , If a person of ordinary skill in the field to which the present invention belongs, various modifications and variations are possible from these descriptions.

Therefore, the spirit of the present invention is limited to the described embodiments and should not be defined, and all things that are equivalent or equivalent to the claims as well as the claims to be described later fall within the scope of the spirit of the present invention. .

110: A wireless communication control device that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a 3D space
111: identification number storage unit 112: communication node selection unit
113: control command signal transmission unit 114: training set storage unit
115: calculation matrix generator 116: probability value calculator
117: learning execution unit 118: coordinate checking unit
119: matrix operation unit 120: probability value selection unit
121: selection processing unit

Claims (12)

N (n is a natural number of 3 or more) communication nodes constituting the wireless sensor network-the n communication nodes are distributed in a pre-set three-dimensional first space-an identification number in which a unique identification number of is stored part;
3D coordinates for each of a plurality of preset signal receiving sides and a communication node preset to correspond to each of the plurality of signal receiving sides- A communication node corresponding to each of the plurality of signal receiving sides includes the n communication As a communication node selected from among nodes, when transmitting signals based on beamforming to each of the plurality of signal receiving sides, each signal receiving side has the maximum signal to noise ratio (SNR). Means a communication node identified by-a training set storage unit in which a unique identification number of is stored as training set data for machine learning;
A 1 x 3 matrix corresponding to each of the plurality of signal reception sides is generated based on 3D coordinates for each of the plurality of signal reception sides, and a 1 x 3 matrix corresponding to each of the plurality of signal reception sides An arithmetic matrix generator for generating a 1xn arithmetic matrix corresponding to each of the plurality of signal receiving sides by serially multiplying at least one weight matrix by;
N probabilities at each of the plurality of signal receiving sides by applying a preset activation function for calculating a probability value to n components included in a 1 xn calculation matrix corresponding to each of the plurality of signal receiving sides A probability value calculating unit for calculating values;
When n probability values at each of the plurality of signal receiving sides are calculated, the n probability values calculated at each of the plurality of signal receiving sides are matched one by one with unique identification numbers of the n communication nodes, and the plurality of The at least one weight matrix so that the probability value matched with the unique identification number of the communication node selected as corresponding to each of the plurality of signal receiving sides among n probability values calculated by each of the signal receiving sides of Learning execution unit for machine learning;
When a transmission event for transmitting the first sensing data to the first signal receiving device occurs, the n communication nodes based on the three-dimensional coordinates of the first signal receiving device and at least one weight matrix on which the machine learning has been completed Communication for selecting k (k is a natural number greater than or equal to 2 and less than n) communication nodes for transmitting the first sensing data to the first signal receiving device based on analog cooperative beamforming. Node selector; And
When the k communication nodes are selected, the k communication nodes are identified based on the unique identification numbers of the k communication nodes, and the first sensing data is transmitted to the k communication nodes. A control command signal transmission unit that transmits a control command signal instructing to transmit cooperatively based on analog cooperative beamforming.
A wireless communication control device that performs signal transmission processing based on cooperative analog beamforming through communication nodes distributed in a 3D space including a. The method of claim 1,
The three-dimensional first space is a three-dimensional spherical space having a radius of a preset length, and the n communication nodes are a three-dimensional space distributed according to a three-dimensional Gaussian distribution within the three-dimensional spherical space. A wireless communication control device that performs signal transmission processing based on analog cooperative beamforming through communication nodes distributed over the phases. delete The method of claim 1,
The communication node selection unit
A coordinate check unit configured to check 3D coordinates of the first signal receiving device when a transmission event in which the first sensing data is to be transmitted to the first signal receiving device occurs;
At least a 1 x 3 matrix corresponding to the first signal reception device is generated based on the three-dimensional coordinates of the first signal reception device, and the machine learning is completed in a 1 x 3 matrix corresponding to the first signal reception device. A matrix calculator configured to sequentially multiply one weight matrix to generate a 1 xn calculation matrix corresponding to the first signal reception device;
Computing n probability values for the first signal receiving apparatus by applying the activation function for calculating probability values to n components included in a 1 x n computation matrix corresponding to the first signal receiving apparatus, After matching the n probability values for the first signal reception device with the unique identification numbers of the n communication nodes one by one, k probability values of the n probability values for the first signal reception device in the order of the largest A probability value selection unit to select; And
When the k probability values are selected, the k communication nodes matched with the unique identification number to the k probability values among the n communication nodes are analog cooperative beamforming the first sensing data to the first signal receiving device. Select processing unit to select as a communication node for transmission based on
A wireless communication control device that performs signal transmission processing based on cooperative analog beamforming through communication nodes distributed in a 3D space including a. The method of claim 4,
The activation function is
Performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space, which is a softmax function that converts n values into probability values between 0 and 1 according to the operation of Equation 1 below. Wireless communication control device.
[Equation 1]

Here, f _i is a probability value calculated for the i-th value of n values, x _i is the i-th value of n values, x _k is the k-th value of n values, and e is a natural constant. N (n is a natural number of 3 or more) communication nodes constituting the wireless sensor network-the n communication nodes are distributed in a pre-set three-dimensional first space-an identification number in which a unique identification number of is stored Maintaining wealth;
3D coordinates for each of a plurality of preset signal receiving sides and a communication node preset to correspond to each of the plurality of signal receiving sides- A communication node corresponding to each of the plurality of signal receiving sides includes the n communication As a communication node selected from among nodes, when transmitting signals based on beamforming to each of the plurality of signal receiving sides, each signal receiving side has the maximum signal to noise ratio (SNR). Maintaining a training set storage unit in which the unique identification number of is stored as training set data for machine learning;
A 1 x 3 matrix corresponding to each of the plurality of signal reception sides is generated based on 3D coordinates for each of the plurality of signal reception sides, and a 1 x 3 matrix corresponding to each of the plurality of signal reception sides Generating a 1xn arithmetic matrix corresponding to each of the plurality of signal receiving sides by serially multiplying at least one weight matrix by;
N probabilities at each of the plurality of signal receiving sides by applying a preset activation function for calculating a probability value to n components included in a 1 xn calculation matrix corresponding to each of the plurality of signal receiving sides Calculating values;
When n probability values at each of the plurality of signal receiving sides are calculated, the n probability values calculated at each of the plurality of signal receiving sides are matched one by one with unique identification numbers of the n communication nodes, and the plurality of The at least one weight matrix so that the probability value matched with the unique identification number of the communication node selected as corresponding to each of the plurality of signal receiving sides among n probability values calculated by each of the signal receiving sides of Machine learning the machine;
When a transmission event for transmitting the first sensing data to the first signal receiving device occurs, the n communication nodes based on the three-dimensional coordinates of the first signal receiving device and at least one weight matrix on which the machine learning has been completed Selecting k (k is a natural number greater than or equal to 2 and less than n) communication nodes for transmitting the first sensing data to the first signal receiving apparatus based on analog cooperative beamforming ; And
When the k communication nodes are selected, the k communication nodes are identified based on the unique identification numbers of the k communication nodes, and the first sensing data is transmitted to the k communication nodes. Transmitting a control command signal instructing to transmit cooperatively based on cooperative analog beamforming
A method of operating a wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a 3D space including a. The method of claim 6,
The three-dimensional first space is a three-dimensional spherical space having a radius of a preset length, and the n communication nodes are a three-dimensional space distributed according to a three-dimensional Gaussian distribution within the three-dimensional spherical space. A method of operating a wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in the image. delete The method of claim 6,
The step of selecting the communication nodes
When a transmission event in which the first sensing data is to be transmitted to the first signal receiving device occurs, checking the three-dimensional coordinates of the first signal receiving device;
At least a 1 x 3 matrix corresponding to the first signal reception device is generated based on the three-dimensional coordinates of the first signal reception device, and the machine learning is completed in a 1 x 3 matrix corresponding to the first signal reception device. Generating a 1xn arithmetic matrix corresponding to the first signal receiving apparatus by concatenatingly multiplying one weight matrix;
Computing n probability values for the first signal receiving apparatus by applying the activation function for calculating probability values to n components included in a 1 x n computation matrix corresponding to the first signal receiving apparatus, After matching the n probability values for the first signal reception device with the unique identification numbers of the n communication nodes one by one, k probability values of the n probability values for the first signal reception device in the order of the largest Selecting; And
When the k probability values are selected, the k communication nodes matched with the unique identification number to the k probability values among the n communication nodes are analog cooperative beamforming the first sensing data to the first signal receiving device. Selecting as a communication node for transmission based on
A method of operating a wireless communication control apparatus for performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a 3D space including a. The method of claim 9,
The activation function is
Performing signal transmission processing based on analog cooperative beamforming through communication nodes distributed in a three-dimensional space, which is a softmax function that converts n values into probability values between 0 and 1 according to the operation of Equation 1 below. A method of operating a wireless communication control device.
[Equation 1]

Here, f _i is a probability value calculated for the i-th value of n values, x _i is the i-th value of n values, x _k is the k-th value of n values, and e is a natural constant. A computer-readable recording medium recording a computer program for executing the method of any one of claims 6, 7, 9, or 10 through a combination with a computer. A computer program stored in a storage medium for executing the method of any one of claims 6, 7, 9 or 10 through a combination with a computer.

Images