Control device, wireless communication system, control method, and program
The control device and method improve communication quality by removing intrinsic components from beam sweep information, addressing prediction accuracy and processing load issues in high-frequency wireless systems with obstructions.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- NIPPON TELEGRAPH & TELEPHONE CORP
- Filing Date
- 2024-12-09
- Publication Date
- 2026-06-19
AI Technical Summary
Existing predictive control methods using beam sweeping in high-frequency wireless communication systems face decreased prediction accuracy and increased processing load due to the use of all available information and large feature vectors, especially when obstructions are present.
A control device and method that removes predetermined intrinsic components from beam sweep information to extract relevant features, using eigencomponents other than main components for improved prediction accuracy and reduced processing load.
Enables high-quality communication without increasing processing load, even with obstructions, by enhancing prediction accuracy through selective feature extraction and dimensionality reduction in machine learning.
Smart Images
Figure 2026100443000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a control device, a wireless communication system, a control method, and a program.
Background Art
[0002] In systems such as 5G (5th Generation), high-frequency bands in the millimeter-wave band are used. In future wireless communication systems such as 6G (6th Generation), in order to achieve further higher speed and larger capacity of communication, the use of high-frequency bands capable of securing a wider bandwidth is being considered (see Non-Patent Document 1).
[0003] Note that since high-frequency bands have large propagation losses, high directivity, and low permeability, the influence of deterioration of communication quality due to obstacles existing between wireless communication devices becomes significant (see Non-Patent Document 2). As a method for avoiding deterioration of communication quality, prediction of communication quality and the like using communication radio wave sensing using beam sweeping without using an external sensing device has been proposed, and it has been studied to efficiently improve communication quality while suppressing an increase in the size and cost of wireless communication devices (see Non-Patent Document 3).
Prior Art Documents
Non-Patent Documents
[0004]
Non-Patent Document 1
Non-Patent Document 2
Non-Patent Document 3
[0005] When performing predictive control using sensing based on information such as received power obtainable during beam sweeping as described in Non-Patent Document 3, the prediction accuracy may decrease if all information is used, depending on the target of prediction. Furthermore, as the number of beams used in beam sweeping increases, the size of the feature vector used in machine learning increases, and the load on the amount of learning required for convergence of machine learning increases.
[0006] In view of the above circumstances, the present invention aims to provide a control device, a wireless communication system, a control method, and a program that enable the second wireless communication device to perform communication with good communication quality without increasing the processing load, even when an obstruction exists between the first wireless communication device and the second wireless communication device. [Means for solving the problem]
[0007] One aspect of the present invention is a control device comprising a control unit that controls the first wireless communication device or the second wireless communication device based on a beam sweep information obtained by removing a predetermined intrinsic component from a plurality of intrinsic components included in beam sweep information received by the second wireless communication device, based on a reference signal transmitted from the first wireless communication device to the second wireless communication device using a plurality of beams.
[0008] Furthermore, one aspect of the present invention is a wireless communication system comprising a first wireless communication device, a second wireless communication device, and a control device, wherein the first wireless communication device transmits a reference signal to the second wireless communication device using a plurality of beams, the second wireless communication device generates beam sweep information based on the reference signal transmitted from the first wireless communication device and transmits it to the control device, and the control device controls the first wireless communication device or the second wireless communication device based on beam sweep information obtained by removing a predetermined intrinsic component from a plurality of intrinsic components included in the beam sweep information received by the second wireless communication device.
[0009] Furthermore, one aspect of the present invention is a control method for controlling the first wireless communication device or the second wireless communication device based on a beam sweep information obtained by removing a predetermined intrinsic component from a plurality of intrinsic components included in beam sweep information received by the second wireless communication device, based on a reference signal transmitted from the first wireless communication device to the second wireless communication device using a plurality of beams.
[0010] Furthermore, one aspect of the present invention is a program that causes the computer of a control device to control the first wireless communication device or the second wireless communication device based on a beam sweep information obtained by removing a predetermined intrinsic component from a plurality of intrinsic components included in beam sweep information received by the second wireless communication device, based on a reference signal transmitted from the first wireless communication device to the second wireless communication device using a plurality of beams. [Effects of the Invention]
[0011] The present invention makes it possible for the second wireless communication device to perform high-quality communication without increasing the processing load, even when there is an obstruction between the first wireless communication device and the second wireless communication device. [Brief explanation of the drawing]
[0012] [Figure 1] This figure illustrates an overview of a wireless communication system according to an embodiment of the present invention. [Figure 2] This figure illustrates the generation of a feature extraction matrix according to an embodiment of the present invention. [Figure 3] This is a schematic block diagram showing the configuration of a wireless communication device and a control device according to an embodiment of the present invention. [Figure 4] This flowchart shows the processing of a wireless communication device and control device according to an embodiment of the present invention. [Figure 5] This is a sequence diagram showing the processing performed in a wireless communication system according to an embodiment of the present invention. [Modes for carrying out the invention]
[0013] Embodiments of the present invention will be described below with reference to the drawings. Note that the embodiments described below are merely examples, and the present invention is not limited to the embodiments described below.
[0014] Figure 1 is a diagram illustrating the outline of a wireless communication system 100 according to an embodiment of the present invention. The wireless communication system 100 comprises wireless communication devices 10a and 10b (also referred to as the first wireless communication device and the second wireless communication device), a control device 20, and a counter wireless communication device 30 (also referred to as the second wireless communication device and the first wireless communication device). In this embodiment of the present invention, the case in which there are two wireless communication devices (i.e., wireless communication devices 10a and 10b) is described, but the number of wireless communication devices is not limited to two, and may be three or more. In Figure 1, a shielding object 40 exists between the counter wireless communication device 30 and the wireless communication device 10a.
[0015] The wireless communication devices 10a and 10b are attached to a building (e.g., a utility pole) and perform wireless communication with the opposing wireless communication device 30. The wireless communication device 10a performs beamforming by controlling the phase and / or amplitude of a plurality of antenna elements included in the wireless communication device 10a. The wireless communication device 10a performs a beam sweep in which it sweeps while changing the formed beam. Also, when the wireless communication device 10a performs a beam sweep, it receives feedback as beam sweep information from the opposing wireless communication device 30 regarding information when a reference signal is transmitted with each beam.
[0016] Information that the wireless communication device 10a acquires as beam sweep information during a beam sweep includes received signal strength, signal-to-noise power ratio, communication distance, reception timing, propagation path information (CSI, Channel State Information), and the like. Then, the wireless communication device 10a estimates or predicts a propagation environment such as shielding or reflection and future communication quality using the beam sweep information fed back from the opposing wireless communication device 30, which is information when a reference signal is transmitted with each of a plurality of beams.
[0017] When the wireless communication device 10a estimates or predicts future communication quality, it may use machine learning or may create a database in advance and search from that database. When using machine learning, the beam sweep information x received by the wireless communication devices 10a and 10b k is transformed using a component limiting matrix described later, and by performing machine learning as described later using the transformed matrix, a learning model M1 is obtained. Note that since the configuration of the wireless communication device 10b is the same as that of the wireless communication device 10a, the description of the wireless communication device 10b is omitted.
[0018] In an embodiment of the present invention, in the estimation or prediction of future communication quality performed by the wireless communication device 10a, feature quantity extraction described later is performed from the beam sweep information fed back from the opposing wireless communication device 30 according to the event to be predicted.
[0019] The control device 20 performs control to switch the wireless communication device 10a or 10b to which the opposing wireless communication device 30 is connected, or selects a beam to be used for data communication, using information on propagation environments such as estimated or predicted shielding and reflection, and future communication quality.
[0020] Here, the case where the wireless communication device 10a performs estimation or prediction is described, but it is not limited thereto, and the control device 20 may perform the process of estimating or predicting future communication quality. Also, here, the case where the wireless communication device 10a (or the wireless communication device 10b) and the control device 20 are provided separately is described, but it is not limited thereto, and the wireless communication device 10a (or the wireless communication device 10b) and the control device 20 may be configured as one device.
[0021] Also, a plurality of wireless communication devices may be connected to the control device 20, and the control device 20 may perform cooperative control. Also, based on the result of estimating or predicting the future communication quality described above, the wireless communication device 10a or 10b to which the opposing wireless communication device 30 is connected may be switched. Also, based on the result of estimating or predicting the future communication quality described above, beam directivity control by beamforming or reduction of the beam search range may be performed.
[0022] When the wireless communication device 10a or 10b predicts the shielding of the communication path between the wireless communication device 10a or 10b and the opposing wireless communication device 30, the main component in the main beam direction is removed from the beam sweep information by the method described later, and machine learning is performed centering on the eigencomponents other than the main beam direction that contribute highly to the prediction of shielding, whereby the estimation and prediction accuracy can be improved. Here, the case where machine learning is performed using the beam sweep information including eigencomponents other than predetermined eigencomponents by removing main components such as the first eigenvalue and upper eigenvalues (for example, the first to third eigenvalues) as predetermined eigencomponents from the beam sweep information is described. Note that the eigencomponents are eigenvectors or eigenvalues.
[0023] Next, a method for extracting features from beam sweep information according to an embodiment of the present invention will be described. When the wireless communication device 10a (or wireless communication device 10b) periodically performs beam sweeps and makes predictions using past N beam sweep information, the data X used for machine learning can be expressed as shown in equation (1) below.
[0024]
number
[0025] Here, the k-th vector x k As shown in equation (2) below, the elements of the beam sweep using the number of beams M are the information for each beam (received signal strength, signal-to-noise power ratio, communication distance, reception timing, propagation path information (CSI), etc.). M is an integer of 2 or more. k is an integer from 1 to N. N is an integer of 2 or more.
[0026]
number
[0027] Furthermore, the variance-covariance matrix Σ can be expressed as shown in equation (3) below.
[0028]
number
[0029] However, in equation (3) above, the relationship in equation (4) below holds true.
[0030]
number
[0031] By performing eigenvalue decomposition on the variance-covariance matrix Σ shown in equation (3) above, the variance-covariance matrix Σ can be expressed as shown in equation (5) below, using a matrix Λ whose diagonal elements are the eigenvalues and a matrix U whose column vectors are the eigenvectors.
[0032]
number
[0033] Next, as shown in Figure 2, a feature extraction matrix is obtained by extracting only the eigenvectors corresponding to n eigenvalues from a matrix U whose column vectors are eigenvectors.
[0034]
number
[0035] The following is generated. In the embodiment of the present invention, n eigenvalues are selected depending on the target to be estimated or predicted. For example, when predicting a decrease in communication quality due to shielding of the communication path between wireless communication devices 10a and 10b and the opposing wireless communication device 30, the eigenvectors corresponding to the top m eigenvalues are deleted, and the above-described feature extraction matrix is generated such that the reflected wave components other than the main beam direction, which contribute highly to the prediction of shielding, are central.
[0036] The value of m is determined according to the number of beams, beam width, and the time of the prediction target. For example, when predicting changes in reception quality in communication between wireless communication devices 10a and 10b and the opposing wireless communication device 30, eigenvectors corresponding to the top n eigenvalues are extracted, and the feature extraction matrix described above is generated such that the eigencomponents in the main beam direction, which contributes highly to the prediction, and the reflected wave direction, which has high power, are central. The value of n is determined according to the number of beams, beam width, and the time of the prediction target.
[0037] Feature vectors generated using the feature extraction matrix described above.
[0038]
number
[0039] A matrix of the same thing
[0040]
number
[0041] This is used in machine learning. As a result, features can be extracted from beam sweep information according to the target and conditions, thereby improving prediction accuracy. In addition, by reducing the dimensionality of the input in machine learning, the learning load, such as the amount of learning required for convergence of machine learning, can be reduced.
[0042] Figure 3 is a schematic block diagram showing the configuration of the wireless communication device 10a and control device 20 according to an embodiment of the present invention. Note that the configuration of the wireless communication device 10b is the same as that of the wireless communication device 10a, and therefore its description is omitted.
[0043] The wireless communication device 10a comprises a transmission unit 11, a signal processing unit 12, a beam control unit 13, and a transceiver unit 14. The transmission unit 11 transmits signals to higher-level devices 60 and control devices 20 and 70 on the network 50. The signal processing unit 12 performs signal processing related to wireless communication. Here, we describe the case where the wireless communication device 10a has the configuration shown in Figure 3, but it is not limited to this. The wireless communication device 10a may have a configuration in which the signal processing unit 12 is divided into separate devices, such as the CU (Central Unit), DU (Distributed Unit), and RU (Radio Unit) in 5G NR (New Radio), or it may be integrated into wireless communication devices 10a, 10b, and control devices 20, etc.
[0044] The beam control unit 13 controls the beam being formed. The transmitting / receiving unit 14 performs beamforming and signal transmission / reception processing, controlling the phase and / or amplitude of the signal, via antennas 15-1 to 15-P. P is an integer of 2 or more.
[0045] The control device 20 shown in Figure 3 comprises a transmission unit 21, a signal processing unit 22, a storage unit 23, an estimation / prediction unit 24, and a control unit 25. The transmission unit 21 transmits signals to the upper-level device 60, wireless communication devices 10a, 10b, and another control device 70 on the network 50. The signal processing unit 22 performs signal processing related to wireless communication. The storage unit 23 stores learning models and databases generated by the estimation / prediction unit 24 through machine learning, based on feedback of beam sweep information from the opposing wireless communication device 30.
[0046] The estimation / prediction unit 24 generates a learning model and database held by the memory unit 23 using data from which features have been extracted using a feature extraction method from beam sweep information fed back from the opposing wireless communication device 30. Then, the estimation / prediction unit 24 uses this learning model and database to estimate or predict propagation environments such as shielding and reflection, future communication quality, etc., according to the purpose of control.
[0047] The control unit 25 performs actions such as issuing beam sweep instructions to the wireless communication device 10a or 10b based on the estimation or prediction results of the estimation / prediction unit 24, and switching the wireless communication device 10a or 10b to which the opposing wireless communication device 30 is connected. Note that the control unit 25, estimation / prediction unit 24, and storage unit 23 may be provided in the wireless communication devices 10a and 10b, respectively, instead of the control device 20.
[0048] Figure 4 is a flowchart showing the processing of a wireless communication device 10a and a control device 20 according to an embodiment of the present invention. First, the transmission unit 11 of the wireless communication device 10a transmits a reference signal to the opposing wireless communication device 30 using beam sweep (step S101). Next, the transmission unit 11 of the wireless communication device 10a receives beam sweep information such as the received signal strength in each beam, the signal-to-noise power ratio, the timestamp at the time of reception, the timestamp at the time of transmission, and propagation path information (CSI) as feedback from the opposing wireless communication device 30 based on the reference signal transmitted in step S101 (step S102).
[0049] The beam sweep information fed back from the opposing wireless communication device 30 to the wireless communication device 10a is stored in the memory unit 23 of the control device 20 (step S103). Next, based on the learning model and time-series data held in the memory unit 23, the estimation / prediction unit 24 of the control device 20 estimates or predicts the propagation environment, such as shielding and reflection, and future communication quality using machine learning (step S104).
[0050] The learning model is generated from data from which features have been extracted according to the embodiment of the present invention, during a learning period for machine learning, either before or during the operation of the wireless communication system 100 according to the embodiment of the present invention.
[0051] The control unit 25 determines the need for control based on the estimated or predicted results (step S105). For example, the control unit 25 determines in step S105 that control is necessary if it is predicted that after a certain time, the line of sight between the wireless communication device 10a or 10b and the opposing wireless communication device 30 will be blocked due to fixed or variable shielding, or if it is predicted that the received signal strength or signal-to-noise power ratio after a certain time will fall below a predetermined value, or if the difference between the predicted received signal strength or signal-to-noise power ratio after a certain time and the predicted received signal strength or signal-to-noise power ratio after a certain time when connected to another wireless communication device exceeds a predetermined value.
[0052] If it is determined in step S105 that control is necessary, the control unit 25 performs control based on the estimation or prediction results performed in step S104 (step S106). For example, in step S106, the control unit 25 performs control to switch between the wireless communication devices 10a or 10b to which the opposing wireless communication device 30 is connected, or control to select the beam to be used for data communication from among multiple beams.
[0053] Regarding the control for switching the wireless communication device 10a or 10b to which the opposing wireless communication device 30 is connected, for example, the wireless communication device 10a or 10b that is predicted to have the highest communication quality with the opposing wireless communication device 30 after a specific time may be switched to be the connection target, or the wireless communication device 10a or 10b that is predicted to have a clear line of sight after a specific time may be switched to be the connection target.
[0054] Regarding the control for selecting the beam to be used for data communication from among multiple beams, for example, the control unit 25 may select the beam in the direction in which the communication quality is expected to be highest after a specific time, or it may select the beam in the direction in which a clear line of sight is expected to be secured after a specific time. Then, the transmission unit 21 of the control device 20 performs data communication with the opposing wireless communication device 30 connected to the wireless communication device 10a or 10b (step S107).
[0055] If it is determined in step S105 that control is not necessary, the control unit 25 will proceed to step S107 without performing the process in step S106. After the process in step S107 is performed, the process in step S101 will be performed again.
[0056] Figure 5 is a sequence diagram showing the processing performed in a wireless communication system 100 according to an embodiment of the present invention. In the sequence diagram shown in Figure 5, the wireless communication system 100, which includes wireless communication devices 10a, 10b and a control device 20, switches the destination wireless communication devices 10a and 10b to which the opposing wireless communication device 30 is connected based on the estimation or prediction of future communication quality. Specifically, the sequence diagram shown in Figure 5 shows the case in which the opposing wireless communication device 30 switches its destination to wireless communication device 10b and performs communication, based on the estimation or prediction of future communication quality, from a state in which it is connected to wireless communication device 10a and performing communication.
[0057] In the sequence diagram shown in Figure 5, the wireless communication device 10a communicates with the control device 20 (step S201) while simultaneously communicating with the opposing wireless communication device 30 (step S202). Next, the control device 20 transmits a measurement instruction control signal to the opposing wireless communication device 30 via the wireless communication device 10a at regular intervals (step S203) (step S204).
[0058] Upon receiving the measurement instruction control signal in step S204, the opposing wireless communication device 30 performs the measurement using the reference signal according to the received measurement instruction control signal. Wireless communication device 10a transmits a reference signal to the opposing wireless communication device 30 while performing a beam sweep to change the beam over time (steps S205-1 to 205-N). Wireless communication device 10b also transmits a reference signal to the opposing wireless communication device 30 while performing a beam sweep to change the beam over time (steps S206-1 to 206-N).
[0059] At this time, as shown in the sequence diagram in Figure 5, beam sweeps may be performed separately over time between multiple wireless communication devices 10a and 10b, or the frequency on which the reference signal is superimposed may be separated, or beam sweeps may be performed simultaneously between multiple wireless communication devices 10a and 10b using orthogonal signals.
[0060] The opposing wireless communication device 30 calculates the received signal strength, signal-to-noise power ratio, reception timestamp, propagation path information (CSI), etc. for each beam from the reference signal received in steps S205-1 to S205-N, adds a transmission timestamp, and transmits it to the wireless communication device 10a as a report signal including beam sweep information (step S207).
[0061] Furthermore, wireless communication devices 10a and 10b may specify the feedback timing for each beam of the opposing wireless communication device 30 and sweep the received beam to receive the report signal, similar to the beam sweep during reference signal transmission. Alternatively, the opposing wireless communication device 30 may aggregate the feedback information for each beam and transmit at the feedback timing of the beam with the highest received signal strength.
[0062] If the control device 20 is located outside the wireless communication device 10a, the report signal is further transmitted from the wireless communication device 10a to the control device 20 (step S208). Based on the beam sweep information fed back from the opposing wireless communication device 30, the control device 20 performs feature extraction processing according to the embodiment of the present invention and inputs it into the stored learning model. As a result, the estimation / prediction unit 24 of the control device 20 estimates or predicts the propagation environment such as shielding and reflection, and the future communication quality (step S209).
[0063] The control device 20 determines the switching of the connection destination of the opposing wireless communication device 30 based on the results estimated or predicted in step S209 (step S210). Following the switching decision, the control device 20 transmits control signals to the current connection destination wireless communication device 10a and the switching destination wireless communication device 10b (steps S211, S212). At this point, if there is any data that has not been transmitted from the wireless communication device 10a to the opposing wireless communication device 30 due to the switching, the wireless communication device 10a transfers that data to the switching destination wireless communication device 10b (step S213).
[0064] Next, the control device 20 transmits a switching instruction control signal to the opposing wireless communication device 30 via the wireless communication device 10a (steps S214, S215). As a result, the opposing wireless communication device 30 performs the switching process to the wireless communication device 10a.
[0065] The opposing wireless communication device 30 performs synchronization and connection establishment processing with the wireless communication device 10b according to the switching instruction control signal received in step S215 (step S216). As a result, the opposing wireless communication device 30 can switch the connection destination from wireless communication device 10a to wireless communication device 10b and continue communication (step S217).
[0066] Furthermore, once synchronization and connection are established between the wireless communication device 10b and the opposing wireless communication device 30 in step S216, communication also begins between the wireless communication device 10b and the control device 20 (steps S218, S219).
[0067] In the explanation so far, we have described a case where the base stations, wireless communication devices 10a and 10b, perform a beam sweep and control the wireless communication devices 10a, 10b and the opposing wireless communication device 30 based on feedback information from the terminal, the invention is not limited to this, and embodiments of the present invention can be applied in the same way even if the downlink and uplink of the communication are reversed. In other words, the terminal, opposing wireless communication device 30, can also perform a beam sweep and estimate or predict the propagation environment such as shielding and reflection, as well as the future communication quality, based on feedback information from the base stations, wireless communication devices 10a and 10b, and control the wireless communication devices 10a, 10b and the opposing wireless communication device 30 based on the results of the estimation or prediction.
[0068] In an embodiment of the present invention, the control device 20 includes a control unit 25 that controls the wireless communication devices 10a, 10b or the opposing wireless communication device 30 based on a reference signal transmitted from the wireless communication devices 10a, 10b to the opposing wireless communication device 30 using multiple beams, and based on beam sweep information obtained by removing a predetermined intrinsic component (main component) from the multiple intrinsic components included in the beam sweep information received by the opposing wireless communication device 30.
[0069] The control device 20 further includes a storage unit 23 that stores in advance a learning model generated by machine learning of multiple beam sweep information relating to a predetermined intrinsic component (principal component) among multiple intrinsic components. The control unit 25 then controls the wireless communication devices 10a, 10b and the opposing wireless communication device 30 based on the beam sweep information and the learning model stored in the storage unit 23.
[0070] The control device 20, with this configuration, can extract appropriate features from beam sweep information according to the target and conditions of the prediction, thereby improving the prediction accuracy of control using prediction and improving wireless communication quality. Furthermore, by reducing the dimensionality of the input in machine learning through feature extraction, the amount of training required can be suppressed, and the cost of machine learning can be reduced.
[0071] Generally, for sensing information including beam sweep information, the principal components are analyzed and extracted. However, depending on the target of prediction, features that contribute to the prediction may appear in intrinsic components other than the principal components. Therefore, in the embodiments of the present invention, control based on features that contribute to the prediction can be realized without knowing information such as the selected beam direction or the direction of arrival of the direct wave related to the principal components.
[0072] Furthermore, at least some of the functions of each part of the wireless communication devices 10a, 10b, control device 20, and opposing wireless communication device 30 according to the embodiments of the present invention described above may be implemented by a computer. In that case, the functions may be implemented by recording a program for implementing these functions on a computer-readable recording medium, loading the program recorded on this recording medium into a computer system, and executing it. Here, "computer system" includes hardware such as an OS (Operating System) and peripheral devices. Furthermore, "computer-readable recording medium" refers to portable media such as flexible disks, magneto-optical disks, ROMs (Read Only Memory), CD-ROMs, and storage devices such as hard disks built into a computer system. Moreover, "computer-readable recording medium" may also include those that dynamically hold programs for a short period of time, such as communication lines used when transmitting programs via networks such as the Internet or communication lines such as telephone lines, and those that hold programs for a certain period of time, such as volatile memory inside a computer system that acts as a server or client in such cases. Furthermore, the above program may be for implementing some of the functions described above, or it may be a program that can implement the above functions in combination with a program already recorded in the computer system, or it may be implemented using a programmable logic device such as an FPGA.
[0073] While embodiments of this invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and includes designs and the like that do not depart from the spirit of this invention. [Industrial applicability]
[0074] The present invention can be applied to control devices, wireless communication systems, control methods, and programs that require the second wireless communication device to perform communication of good quality without increasing the processing load, even when an obstruction exists between the first wireless communication device and the second wireless communication device. [Explanation of symbols]
[0075] 10a, 10b... Wireless communication device, 11... Transmission unit, 12... Signal processing unit, 13... Beam control unit, 14... Transmit / receive unit, 20... Control device, 21... Transmission unit, 22... Signal processing unit, 23... Memory unit, 24... Estimation / prediction unit, 25... Control unit, 30... Opposite wireless communication device, 40... Shielding, 50... Network, 60... Higher-level device, 70... Control device, 100... Wireless communication system
Claims
1. The system includes a control unit that controls the first wireless communication device or the second wireless communication device based on a beam sweep information obtained by removing a predetermined intrinsic component from a plurality of intrinsic components included in beam sweep information received by the second wireless communication device, based on a reference signal transmitted from the first wireless communication device to the second wireless communication device using a plurality of beams. Control device.
2. The system further includes a storage unit that stores in advance a learning model generated by machine learning of a plurality of beam sweep information relating to a predetermined intrinsic component among the plurality of intrinsic components. The control unit controls the first wireless communication device or the second wireless communication device based on the beam sweep information and the learning model stored in the storage unit. The control device according to claim 1.
3. The control unit, Based on the learning model, if it is predicted that communication between the first wireless communication device and the second wireless communication device will be blocked, the communication destination of the second wireless communication device will be switched from the first wireless communication device to the third wireless communication device. The control device according to claim 2.
4. The control unit, Based on the learning model, if it is predicted that the received signal strength or signal-to-noise power ratio in communication between the first wireless communication device and the second wireless communication device will fall below a predetermined value, the communication destination of the second wireless communication device will be switched from the first wireless communication device to the third wireless communication device. The control device according to claim 2.
5. The control unit uses the main component of the main beam direction of the plurality of beams as the predetermined intrinsic component. The control device according to claim 1.
6. A wireless communication system comprising a first wireless communication device, a second wireless communication device, and a control device, The first wireless communication device transmits a reference signal to the second wireless communication device using multiple beams. The second wireless communication device generates beam sweep information based on the reference signal transmitted from the first wireless communication device and transmits it to the control device. The control device controls the first wireless communication device or the second wireless communication device based on beam sweep information obtained by removing a predetermined intrinsic component from among a plurality of intrinsic components included in the beam sweep information received by the second wireless communication device. Wireless communication system.
7. Based on a reference signal transmitted from the first wireless communication device to the second wireless communication device using multiple beams, the second wireless communication device controls either the first or the second wireless communication device based on beam sweep information obtained by removing a predetermined intrinsic component from among the multiple intrinsic components included in the beam sweep information received by the second wireless communication device. Control method.
8. In the control unit's computer, The first wireless communication device controls either the first or the second wireless communication device based on a beam sweep information obtained by removing a predetermined intrinsic component from a plurality of intrinsic components included in the beam sweep information received by the second wireless communication device, based on a reference signal transmitted from the first wireless communication device to the second wireless communication device using multiple beams. program.