Wireless communication system, communication device, and communication control method

Abstract

According to the present invention, a reception-side communication device performs machine-learning on the state of a wireless signal, and executes compensation for the wireless signal on the basis of the learned result. In addition, the reception-side communication device evaluates the communication quality of the wireless signal by using a prescribed evaluation function, and transmits feedback information indicating the partial derivative or difference of the evaluation function to a transmission-side communication device. The transmission-side communication device performs machine-learning on the state of a wireless signal, and executes compensation for the wireless signal on the basis of the learned result. The transmission-side communication device updates weights applied to the machine-learning on the basis of the partial derivative or difference of the evaluation function. The transmission-side communication device and the reception-side communication device determine the degree of weight update according to the partial derivative or difference of the evaluation function indicated by the feedback information.

Description

Wireless communication system, communication device, and communication control method

[0001] This disclosure relates to a wireless communication system, communication device, and communication control method that address compensation for characteristics resulting from device imperfections.

[0002] Wireless devices used in mobile communications and other applications often have imperfections (device defects). Therefore, methods have been proposed to compensate for characteristics resulting from such imperfections.

[0003] For example, a method has been proposed to use a deep neural network (DNN) to simultaneously compensate for the nonlinearity of an amplification circuit (PA) and the imbalance between the common-mode and orthogonal components (I, Q) of a wireless signal (IQ imbalance) (Non-Patent Document 1). Furthermore, methods have also been proposed to use DNNs to compensate for and detect characteristics caused by receiver imperfections, and to simultaneously compensate for the IQ imbalance and channel characteristics of a transceiver (Non-Patent Documents 2 and 3).

[0004] Y. Wu, U. Gustavsson, A. G. I. Amat, and H. Wymeersch, “Low Complexity Joint Impairment Mitigation of I / Q Modulator and PA Using Neural Networks,” in IEEE Journal on Selected Areas in Communications, vol. 40, no. 1, pp. 54 64, Jan. 2022S. Anand, A. K. Singh, and P. Kumar, “A BBL Net based OFDM Signal Detection in the Presence of RF Impairments,” 2023 National Conference on Communications (NCC), Guwahati, India, 2023S. G. Neelam and P. R. Sahu, “Joint Compensation of TX / RX IQ Imbalance and Channel Parameters for OTSM Systems,” in IEEE Communications Letters, vol. 27, no. 3, pp. 976 980, March 2023

[0005] By compensating the characteristics for each communication device such as a wireless device using the method as described above, the communication quality can be improved. However, although such a compensation method can optimize the wireless link alone, it is difficult to optimize the characteristics for the entire communication network. Therefore, if the compensation for each wireless device is executed separately and independently, it may result in over-compensation for the entire communication network, and problems such as an increase in the power consumption of digital / analog processing may occur.

[0006] Considering such a situation, it is desirable to optimize the compensation level for each communication device in consideration of the required communication quality for the entire communication network according to the required quality index (for example, the evaluation index based on KPI: Key Performance Indicator).

[0007] Therefore, the following disclosure is made in light of these circumstances and aims to provide a wireless communication system, communication device, and communication control method that can optimize the compensation level for each communication device, taking into account the required communication quality across the entire communication network, according to the required quality indicators.

[0008] One aspect of the present disclosure is a wireless communication system (wireless communication system 10) including a transmitting communication device (e.g., a wireless base station 100) and a receiving communication device (e.g., a terminal 200), wherein the receiving communication device includes a signal receiving unit (wireless communication unit 110) that receives a wireless signal from the transmitting communication device, a receiving learning unit (receiving learning unit 120) that performs machine learning on the state of the wireless signal, a receiving compensation unit (receiving compensation unit 130) that performs compensation on the wireless signal based on the learning results by the receiving learning unit, and a feedback information transmitting unit (feedback information transmitting unit) that evaluates the communication quality of the wireless signal using a predetermined evaluation function and transmits feedback information indicating the partial derivative or difference of the evaluation function to the transmitting communication device. The transmitting communication device comprises a transmitting learning unit (transmitting learning unit 220) that learns the state of the wireless signal by machine learning, a transmitting compensation unit (transmitting compensation unit 230) that performs compensation on the wireless signal based on the learning results by the transmitting learning unit, and a feedback information receiving unit (feedback information receiving unit 240) that receives the feedback information and updates the weights applied to the machine learning by the transmitting learning unit based on the partial derivative or difference of the evaluation function, wherein the transmitting learning unit and the receiving learning unit determine the degree of weight update applied to the machine learning according to the partial derivative or difference of the evaluation function indicated by the feedback information.

[0009] Figure 1 is an overall schematic diagram of the wireless communication system 10. Figure 2 is a diagram showing an example configuration of wireless equipment (transmitter and receiver) corresponding to characteristic compensation. Figure 3 is a diagram showing a general example configuration of DNN. Figure 4 is a functional block configuration diagram of the receiver communication device (RX). Figure 5 is a functional block configuration diagram of the transmitter communication device (TX). Figure 6 is an overall network configuration diagram including communication equipment related to updating DNN weights in DL. Figure 7 is a sequence diagram related to updating DNN weights in DL. Figure 8 is a diagram showing an example of the hardware configuration of the wireless base station 100 and terminal 200.

[0010] The embodiments will be described below with reference to the drawings. Note that identical or similar reference numerals are used to denote the same functions and components, and their descriptions will be omitted as appropriate.

[0011] (1) Figure 1 is an overall schematic diagram of the wireless communication system 10 according to this embodiment. As shown in Figure 1, the wireless communication system 10 includes a wireless base station 100, a terminal 200, and a relay station 300. The wireless communication system 10 is, for example, a wireless communication system that conforms to 5G New Radio (NR), which is standardized by the 3rd Generation Partnership Project (3GPP: registered trademark). The wireless communication system 10 may also be a wireless communication system that conforms to a method called Beyond 5G, 5G Evolution, or 6G. Alternatively, the wireless communication system 10 does not necessarily have to be a wireless communication system that conforms to the 3GPP technical standards, and may utilize other wireless communication technologies, including short-range wireless communication technology.

[0012] The radio base station 100 can perform wireless communication with the terminal 200. The radio base station 100 is one of the components of a radio access network (RAN) and may be called Node B, etc. (in the case of 3GPP). Alternatively, the radio base station 100 may be called an access point (AP), etc. The terminal 200 may be called User Equipment (UE), etc. (in the case of 3GPP), or may be called a host or device, etc.

[0013] The wireless base station 100 may be connected to the terminal 200 via a relay station 300. The relay station 300 (RS) relays communication between the wireless base station 100 and the terminal 200. The relay station 300 may also be called a repeater, smart repeater, IRS (Intelligent Reflecting Surface), RIS (Reconfigurable Intelligent Surface), etc. The relay station 300 may also be an IAB node in accordance with Integrated Access and Backhaul (IAB) as defined in 3GPP.

[0014] The wireless base station 100 may form a macrocell C1 having broad coverage. The relay station 300 may form a picocell C2 (which may also be called a microcell) having narrower coverage compared to the macrocell C1.

[0015] The wireless communication system 10 is equipped with a function to compensate for characteristics caused by imperfections (device defects) in wireless devices such as the wireless base station 100, terminal 200, and relay station 300. Figure 2 shows an example configuration of wireless devices (transmitter and receiver) that support characteristic compensation. The transmitting wireless device (TX) and the receiving wireless device (RX) may perform compensation for individual imperfections in each wireless device.

[0016] For example, a radio transceiver (TX) can compensate for IQ imbalances in the radio frequency (RF) circuit and nonlinearities in the amplifier circuit (PA) using DPD (Digital Pre-Distortion). IQ imbalance can refer to an imbalance between the common-mode and quadrature components (I, Q) of the radio signal. A radio transceiver (RX) can compensate for IQ imbalances in the RF circuit, etc.

[0017] Furthermore, artificial intelligence / machine learning models (AI / ML Models), such as deep neural networks (DNNs), may be used for such compensation. Figure 3 shows a typical configuration example of a DNN. As shown in Figure 3, a DNN may have an input layer, a hidden layer, and an output layer. The input layer is the layer that receives the input data. The hidden layer is the layer that processes the input data and extracts features. The output layer is the layer that interprets the processed data and generates the final output.

[0018] The radio (TX) and radio (RX) may be equipped with a DPD or Detector incorporating such a DNN. Each radio can perform more appropriate characteristic compensation by having the DNN learn the state of the radio signal (which may be interpreted as the state of the radio) such as the nonlinearity of the PA and IQ imbalance.

[0019] By using this method, communication quality can be improved by compensating for the characteristics of each communication device, such as the wireless base station 100, terminal 200, and relay station 300. Furthermore, in the wireless communication system 10, it is possible to optimize the characteristics of the entire communication network, not just the wireless link itself using the conventional method of compensating for individual communication devices.

[0020] Furthermore, the wireless communication system 10 can optimize the compensation level for each communication device, taking into account the required communication quality across the entire communication network, according to the required quality indicators (e.g., evaluation indicators based on KPIs: Key Performance Indicators). Specifically, the wireless communication system 10 can evaluate the communication quality of wireless signals using an evaluation function based on KPIs and determine the compensation level for each communication device. This enables distributed processing (learning) across multiple communication devices, allowing for optimization of the compensation level for the characteristics of the entire communication network while avoiding overcompensation.

[0021] (2) Functional Block Configuration of the Wireless Communication System Next, the functional block configuration of the wireless communication system 10 will be described. Specifically, the functional block configuration of the transmitting communication device and the receiving communication device will be described.

[0022] The wireless base station 100, terminal 200, and relay station 300 may constitute a transmitting communication device or a receiving communication device when they support an uplink (UL) or downlink (DL).

[0023] (2.1) Receiver-side communication device Figure 4 is a functional block diagram of the receiver-side communication device (RX). As shown in Figure 4, the receiver-side communication device comprises a wireless communication unit 110, a receiver-side learning unit 120, a receiver-side compensation unit 130, and a feedback information transmission unit 140.

[0024] The wireless communication unit 110 performs wireless communication with the transmitting communication device (TX). For example, the wireless communication unit 110 can send and receive wireless signals with the transmitting communication device in accordance with 3GPP specifications. In this way, the wireless communication unit 110 may receive wireless signals from the transmitting communication device. In this embodiment, the wireless communication unit 110 may constitute a signal receiving unit.

[0025] The receiving-side learning unit 120 learns the state of the wireless signal using machine learning. Specifically, the receiving-side learning unit 120 can learn the state of the wireless signal (which may be a radio or communication device) using an AI / ML Model. More specifically, the target of learning by the DNN may be characteristics caused by device damage (such as IQ imbalance), or the communication quality of the wireless signal. This communication quality may include, for example, the bit error rate (BER), RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), SINR (Signal-to-Interference plus Noise power Ratio), throughput, etc.

[0026] The receiving learning unit 120 may determine the degree of weight update applied to machine learning according to the partial derivative or difference of the evaluation function indicated by the feedback information transmitted by the feedback information transmission unit 140. Specifically, the receiving learning unit 120 may increase or decrease the weight update level according to the said partial derivative or difference (details will be described later).

[0027] The network topology (such as the cell configuration and the presence or absence of relay stations 300 shown in Figure 1) and the DNN models in each communication device may be assumed to be known. The DNN models implemented (and used) in each communication device may be the same or different. The initial values ​​of the weights (W) of the DNN models in each communication device can be determined by known techniques. Furthermore, the DNN models may be located within the communication device or in another location within the wireless communication system 10.

[0028] The receiver-side compensation unit 130 performs compensation for the radio signal based on the learning results from the receiver-side learning unit 120. Specifically, the receiver-side compensation unit 130 may perform compensation such as IQ imbalance based on the learning results of the state of the radio signal (radio or communication device) using a DNN. For example, based on the learning results, the receiver-side compensation unit 130 may adjust parameters related to demodulation (IQ DeMod.) to reduce the IQ imbalance of the receiver-side RF circuit.

[0029] In this embodiment, learning may be interpreted as updating the DNN weights using an evaluation function. Compensation may also be interpreted as using the DNN to mitigate the effects of imperfections in the transmitted and received signals.

[0030] The feedback information transmission unit 140 evaluates the communication quality of the wireless signal using a predetermined evaluation function and transmits information (feedback information) indicating parameters related to the evaluation function to the transmitting communication device. Specifically, the feedback information transmission unit 140 may transmit feedback information indicating the partial derivative or difference of the evaluation function to the transmitting communication device. The partial derivative of the evaluation function may be interpreted as the slope of a straight line on a plane represented by the evaluation function, and the difference of the evaluation function may be interpreted, for example, as the difference between the output result and the previous output result using the evaluation function used in the transmitting communication device and the receiving communication device, respectively.

[0031] The evaluation function may be interpreted as evaluating the communication quality of the wireless signals transmitted and received by the wireless communication unit 110. The feedback information transmission unit 140 may use an evaluation function that includes parameters defined by one or more quality indicators required for the entire communication network.

[0032] Multiple quality metrics can be presented as KPIs. Examples of KPIs include communication quality metrics such as out-of-band radiation, in-band interference, channel equalization accuracy, EVM (Error Vector Magnitude), and bit error rate (BER).

[0033] The term "communication network" may refer to the communication network formed by the entire wireless communication system 10, or it may refer to a cell formed by a specific wireless base station 100 (or relay station 300).

[0034] The arguments of the evaluation function (parameters of the evaluation function) may be the weights of the DNN, but in practice, it is also possible to define an evaluation function as an evaluation index that is weighted and added together by the KPIs calculated from the compensation results after compensating the transmitted and received signals using a DNN with weights.

[0035] Strictly speaking, although the weights are not input into the evaluation function, the evaluation index can change depending on the weights. For example, when compensating for the nonlinearity of the PA in the transmitted signal with DPD, the following operation may be performed in general.

[0036] (i) Check the output signal of the PA, calculate the out-of-band radiation level and the in-band interference level, and use them as evaluation indices for training the DNN.

[0037] (ii) Use the evaluation index to update the DNN weights for DPD (this may be called training).

[0038] (iii) The transmitted signal is compensated using the weight-updated DNN and input to the PA (this may be called compensation).

[0039] (iv) Next, the evaluation index is calculated using the output signal of the PA, and the learning and compensation process is repeated.

[0040] The feedback information transmission unit 140 may use an evaluation function that includes weights applied to machine learning as parameters. Specifically, the feedback information transmission unit 140 may use an evaluation function that includes weights applied to the DNN. Specific examples of the evaluation function will be described later.

[0041] (2.2) Transmission-side communication device FIG. 5 is a functional block configuration diagram of a transmission-side communication device (TX). As shown in FIG. 5, the transmission-side communication device includes a wireless communication unit 210, a transmission-side learning unit 220, a transmission-side compensation unit 230, and a feedback information reception unit 240.

[0042] The wireless communication unit 210 performs wireless communication with the reception-side communication device (RX). For example, the wireless communication unit 210 can transmit and receive wireless signals conforming to the 3GPP specifications with the reception-side communication device. Thus, the wireless communication unit 210 may transmit a wireless signal to the reception-side communication device.

[0043] The transmission-side learning unit 220 performs machine learning on the state of the wireless signal. Specifically, similar to the reception-side learning unit 120, the transmission-side learning unit 220 can learn the state of a wireless signal (which may be a wireless device or a communication device) using an AI / ML Model.

[0044] The transmission-side learning unit 220 may update the weights applied to the machine learning in the transmission-side learning unit 220 based on the feedback information received by the feedback information reception unit 240 from the reception-side communication device. Specifically, the transmission-side learning unit 220 may update the weights applied to the DNN based on the partial derivative or difference of the evaluation function included in the feedback information. Also, in updating the weights applied to the machine learning (weights of the DNN), the transmission-side learning unit 220 may set a positive fraction not exceeding a predetermined value as the learning rate of the evaluation function. Specifically, the transmission-side learning unit 220 may update the weights of the DNN by applying the learning rate (ρ) of the evaluation function.

[0045] The learning rate is preferably a positive infinitesimal value. Specifically, the learning rate is preferably a tiny positive value close to zero (0). While setting the learning rate to such a value, among them, a larger learning rate is more likely to follow the fluctuations of the transmission situation, and a smaller learning rate contributes to stable learning. For example, the learning rate can be set to about 0.0005 to 0.001.

[0046] The transmission-side learning unit 220 may determine the degree of weight update applied to machine learning according to the partial derivative or difference of the evaluation function indicated by the feedback information received by the feedback information receiving unit 240. Specifically, the transmission-side learning unit 220 may increase or decrease the weight update level according to the partial derivative or difference.

[0047] The transmission-side compensation unit 230 performs compensation for the radio signal based on the learning result by the transmission-side learning unit 220. Specifically, similar to the reception-side compensation unit 130, the transmission-side compensation unit 230 may perform compensation such as IQ imbalance based on the learning result of the state of the radio signal (radio device or communication device) using DNN.

[0048] The feedback information receiving unit 240 receives feedback information from the reception-side communication device and updates the weight applied to the machine learning by the transmission-side learning unit 220 based on the partial derivative or difference of the evaluation function. Specifically, the feedback information receiving unit 240 may instruct the transmission-side learning unit 220 to update the weight of the DNN used in the transmission-side learning unit 220 according to the partial derivative or difference.

[0049] The feedback information receiving unit 240 may use an evaluation function including parameters defined by one or more quality indicators required for the entire communication network. Specifically, similar to the feedback information transmission unit 140, the feedback information receiving unit 240 may use an evaluation function including parameters defined by the communication quality indicated as the KPI.

[0050] Furthermore, the feedback information receiving unit 240 may use an evaluation function that includes weights applied to machine learning as parameters. Specifically, the feedback information receiving unit 240 may use an evaluation function that includes weights applied to DNNs. Specific examples of evaluation functions will be described later.

[0051] (3) Operation of the Wireless Communication System Next, the operation of the wireless communication system 10 will be described. Specifically, an example of operation that optimizes the compensation level for each communication device, taking into account the required communication quality for the entire wireless communication system 10 (communication network), according to the required quality indicators will be described.

[0052] (3.1) Operation Overview The following are the prerequisites and initial settings for the operation aimed at optimizing the compensation level for each communication device.

[0053] The network topology and the DNN models used by each communication device (wireless base station 100, terminal 200, and relay station 300) are known.

[0054] The DNN models used by each communication device may be different (the DNN models used by each communication device do not have to be the same).

[0055] The initial values ​​of the weights (W) of the DNN model used by each communication device are determined using known techniques.

[0056] The procedure for optimizing the compensation level for each communication device in the wireless communication system 10 is generally as follows:

[0057] (i) The receiving communication device performs learning about the state of the wireless signal, etc., and feeds back the partial derivative or difference of the evaluation function to the transmitting communication device.

[0058] (ii) If a relay station is involved, the relay station performs learning about the state of the radio signal and feeds back the partial derivative or difference of the evaluation function to the transmitting communication device.

[0059] (iii) The transmitting communication device performs learning about the state of the radio signal, etc. The transmitting communication device also updates the DNN weights applied to the learning based on the partial derivative or difference of the feedbacked evaluation function (if necessary).

[0060] (iv) Repeat steps (i) through (iii).

[0061] Furthermore, as described above, the wireless communication system 10 optimizes characteristic compensation by considering multiple KPIs, such as the communication characteristics of the entire communication network. The importance given to each KPI in each communication device is not necessarily the same, and different KPIs may be applied. Examples of KPIs include, as mentioned above, out-of-band radiation, in-band interference, channel equalization accuracy, EVM (Error Vector Magnitude), and bit error rate (BER).

[0062] Thus, in the wireless communication system 10, distributed learning is possible among communication devices, and the evaluation function for communication quality can be set to a combination of multiple KPIs depending on the state of the communication device. This makes it possible to optimize characteristic compensation across the entire communication network according to the set KPIs.

[0063] (3.2) Example of Operation In order to evaluate the communication quality (transmission and reception quality) in a communication network, the evaluation function may be defined by combining multiple KPIs. For example, the evaluation function may be defined as follows:

[0064] Evaluation function at terminal k (receiving station):

[0065]

[0066] Evaluation function at relay station r:

[0067]

[0068] Evaluation function at wireless base station b (transmitting station):

[0069]

[0070] Here, the meaning of each parameter is as follows:

[0071]

[0072]

[0073] The sign of the function is set so that it can be learned using the steepest descent method, and the absolute value may be designed according to the importance of the KPI.

[0074] Using such an evaluation function, the wireless communication system 10 may repeat the procedures (i) to (iii) described above. Alternatively, only (i) and (ii) may be repeated, or only (i) may be repeated. Furthermore, parameter updates may be performed only at specific terminals.

[0075] When the partial derivative (slope) of the evaluation function is fed back, the weight update of the DNN may be performed according to the following formula.

[0076]

[0077] Furthermore, when the difference in the evaluation function is fed back, the DNN weight update may be performed according to the following formula.

[0078]

[0079] Note that the weights may be updated using the steep descent method. The meaning of each parameter is as follows:

[0080]

[0081] The learning rate is a small positive value and needs to be designed appropriately. Specifically, the learning rate (ρ) is preferably a small positive value close to zero (0). A large learning rate is more likely to follow fluctuations in transmission conditions, while a small learning rate contributes to stable learning.

[0082] (3.3) Specific Operation Example in Downlink (DL) Figure 6 is a diagram of the entire network configuration including communication equipment related to updating DNN weights in DL. Figure 7 is a sequence diagram related to updating DNN weights in DL.

[0083] As shown in Figures 6 and 7, this example describes a scenario in which communication is performed on link ABD between base station A (where appropriate, abbreviated as base station) A, relay station B, and terminal D (Step 1), communication is performed on link AF between base station A and terminal F (Step 2), and then communication is performed on link ACH between base station A, relay station C, and terminal H (Step 3).

[0084] Link ABD communication: Base station A transmits data (user data or control data) to relay station B via radio signal, and relay station B forwards the data to terminal D via radio signal. Terminal D then calculates an evaluation function and feeds back information about the evaluation function (partial derivative or difference) to relay station B and base station A. Base station A and relay station B update the weights of their respective DNNs.

[0085] Link AF communication: Base station A transmits to terminal F. Terminal F calculates an evaluation function and feeds back the information of the evaluation function to base station A, and base station A updates the weights of its DNN.

[0086] Link ACH: Base station A transmits to relay station C, and relay station C forwards the received signal to terminal H. Terminal H then calculates an evaluation function and feeds back the information of the evaluation function to relay station C and base station A, and base station A and relay station C update the weights of their respective DNNs.

[0087] Furthermore, communication within the wireless communication system 10 (communication network) may be performed randomly, and each time, the relevant base station (or relay station) and terminal may update the DNN weights.

[0088] For each base station (or relay station) and terminal, KPIs may be set as follows: For base stations, out-of-band radiation and in-band interference may be set as KPIs. For relay stations, out-of-band radiation, in-band interference, and channel equalization accuracy may be set as KPIs. For terminals, channel equalization accuracy, EVM, and BER may be set as KPIs.

[0089] Furthermore, the learning rate (ρ) may be set as follows, for example:

[0090]

[0091] According to the example operation described above, the receiving communication device can learn about the state of the radio signal and feed back the partial derivative or difference of the evaluation function to the transmitting communication device. The transmitting communication device also learns about the state of the radio signal and can update the DNN weights based on the fed-back partial derivative or difference of the evaluation function. By each communication device performing these operations, the compensation for characteristics caused by device damage can be optimized for the entire wireless communication system 10 (communication network).

[0092] This ensures that the overcompensation of the entire communication network, which can occur when compensation is performed separately and independently for each communication device, and the increased power consumption of digital / analog processing, are reliably avoided.

[0093] Furthermore, the wireless communication system 10 can evaluate the communication quality of wireless signals using an evaluation function based on KPIs. This makes it possible to optimize the compensation level for each communication device, taking into account the required communication quality across the entire communication network, according to the required quality indicators.

[0094] Furthermore, the wireless communication system 10 can use an evaluation function that includes weights applied to machine learning as parameters. Each communication device can also update the DNN weights based on feedback information (partial derivative or difference of the evaluation function). Moreover, when updating these weights, each communication device can set a positive decimal value less than or equal to a predetermined value as the learning rate of the evaluation function. Therefore, a more appropriate compensation level can be determined according to the state of each communication device.

[0095] (4) Other Embodiments Although embodiments have been described above, it will be obvious to those skilled in the art that the embodiments are not limited to those described and that various modifications and improvements are possible.

[0096] For example, in the embodiment described above, the wireless communication system 10 included a relay station 300, but the relay station 300 is not essential. In other words, the wireless communication system 10 may consist of a wireless base station 100 and a terminal 200.

[0097] Furthermore, the evaluation function shown in the example is just one example, and the parameters included in the evaluation function may be changed as appropriate.

[0098] In the above description, configure, activate, update, indicate, enable, specify, and select may be interpreted as interchangeable. Similarly, link, associate, correspond, and map may be interpreted as interchangeable, and allocate, assign, monitor, and map may also be interpreted as interchangeable.

[0099] Furthermore, "specific," "dedicated," "UE specific," and "UE individual" may be interpreted interchangeably. Similarly, "common," "shared," "group-common," "UE common," and "UE shared" may be interpreted interchangeably.

[0100] In this disclosure, terms such as “precoding,” “precoder,” “weight (precoding weight),” “quasi-co-location (QCL),” “transmission configuration indication state (TCI state),” “spatial relation,” “spatial domain filter,” “transmit power,” “phase rotation,” “antenna port,” “antenna port group,” “layer,” “number of layers,” “rank,” “resource,” “resource set,” “resource group,” “beam,” “beam width,” “beam angle,” “antenna,” “antenna element,” and “panel” may be used interchangeably.

[0101] Furthermore, the block diagrams (Figures 4 and 5) used in the description of the embodiments above show functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Moreover, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining the one or more devices with software.

[0102] Functions include, but are not limited to, judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In any case, as mentioned above, the method of implementation is not particularly limited.

[0103] Furthermore, the aforementioned wireless base station 100 and terminal 200 (the device) may function as a computer that processes the wireless communication method of this disclosure. Figure 8 shows an example of the hardware configuration of the device. The relay station 300 may have a similar configuration. As shown in Figure 8, the device may be configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, and bus 1007.

[0104] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the device may include one or more of the devices shown in the diagram, or it may be configured to omit some of the devices.

[0105] Each functional block of the device (see Figures 4 and 5) is implemented by any hardware element of the computer device, or a combination of such hardware elements.

[0106] Furthermore, each function in the device is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

[0107] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may consist of a central processing unit (CPU) that includes interfaces with peripheral devices, control units, arithmetic units, registers, and so on.

[0108] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. Moreover, the above-mentioned various processes may be executed by one processor 1001, or by two or more processors 1001 simultaneously or sequentially. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0109] Memory 1002 is a computer-readable recording medium and may consist of at least one of the following: Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), Random Access Memory (RAM), etc. Memory 1002 may also be called a register, cache, main memory, etc. Memory 1002 can store a program (program code), software module, etc., that can execute a method according to one embodiment of this disclosure.

[0110] Storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a Compact Disc ROM (CD-ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., Compact Disc, Digital Multipurpose Disc, Blu-ray® Disc), a smart card, flash memory (e.g., a card, stick, key drive), a floppy® disk, a magnetic strip, etc. Storage 1003 may also be called an auxiliary storage device. The recording medium described above may also be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0111] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc.

[0112] The communication device 1004 may be configured to include, for example, a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0113] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0114] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0115] Furthermore, the device may include hardware such as a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (PLD), and a field-programmable gate array (FPGA), and some or all of each functional block may be implemented by such hardware. For example, processor 1001 may be implemented using at least one of these hardware components.

[0116] Furthermore, notification of information is not limited to the embodiments described herein and may be carried out by other means. For example, notification of information may be carried out by physical layer signaling (e.g., Downlink Control Information (DCI), Uplink Control Information (UCI)), upper layer signaling (e.g., RRC signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB), System Information Block (SIB))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.

[0117] Each aspect / embodiment described herein may be applied to at least one of the following: Long Term Evolution (LTE), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (where x is, for example, an integer or decimal), Future Radio Access (FRA), New Radio (NR), W-CDMA®, GSM®, CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth®, and other appropriate systems, as well as next-generation systems extended based thereon. Furthermore, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G).

[0118] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0119] The specific operations described in this disclosure as being performed by a base station may, in some cases, be performed by its upper node. In a network consisting of one or more network nodes having a base station, it is clear that various operations performed for communication with a terminal can be performed by the base station and at least one other network node (for example, an MME or S-GW, but not limited to these). Although the above example illustrates the case where there is one other network node besides the base station, it may also be a combination of multiple other network nodes (for example, an MME and an S-GW).

[0120] Information and signals (such as data) can be output from a higher layer (or lower layer) to a lower layer (or higher layer). Input and output may occur via multiple network nodes.

[0121] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be sent to other devices.

[0122] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0123] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0124] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0125] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or Digital Subscriber Line (DSL)) and wireless technologies (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0126] The information, signals, etc. described in this disclosure may be represented using any of the various different technologies. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0127] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc.

[0128] The terms “system” and “network” as used in this disclosure are interchangeable.

[0129] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or corresponding other information. For example, wireless resources may be indicated by an index.

[0130] The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Since various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, the various names assigned to these various channels and information elements are not restrictive in any way.

[0131] In this disclosure, terms such as "Base Station (BS)," "wireless base station," "fixed station," "NodeB," "eNodeB (eNB)," "gNodeB (gNB)," "access point," "transmission point," "reception point," "transmission / reception point," "cell," "sector," "cell group," "carrier," and "component carrier" may be used interchangeably. Base stations may also be referred to by terms such as macrocell, small cell, femtocell, and picocell.

[0132] A base station can house one or more (e.g., three) cells (also called sectors). If a base station houses multiple cells, the entire coverage area of ​​the base station can be divided into multiple smaller areas, each of which can also be provided with communication services by a base station subsystem (e.g., a small indoor base station (Remote Radio Head: RRH)).

[0133] The terms "cell" or "sector" refer to a portion or all of the coverage area of ​​at least one of the base stations and base station subsystems that provide communication services in this coverage.

[0134] In this disclosure, the transmission of information by a base station to a terminal may be interpreted as the base station instructing the terminal to perform control or operation based on the information.

[0135] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

[0136] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term.

[0137] At least one of the base station and the mobile station may be called a transmitting device, a receiving device, a communication device, etc. At least one of the base station and the mobile station may also be a device mounted on a mobile body, the mobile body itself, etc. The mobile body refers to a movable object, and its speed of movement is arbitrary. This also includes the case when the mobile body is stationary. The mobile body includes, but is not limited to, vehicles, transport vehicles, automobiles, motorcycles, bicycles, connected cars, excavators, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, handcarts, rickshaws, ships and other watercraft, airplanes, rockets, satellites, drones (registered trademark), multicopters, quadcopters, balloons, and items mounted on them. The mobile body may also be a mobile body that moves autonomously based on operation commands. It may be a vehicle (e.g., a car, an airplane, etc.), an unmanned mobile body (e.g., a drone, an autonomous vehicle, etc.), or a robot (manned or unmanned). Furthermore, at least one of the base station and the mobile station may include devices that do not necessarily move during communication operations. For example, at least one of the base station and the mobile station may be an IoT (Internet of Things) device such as a sensor.

[0138] Furthermore, the term "base station" in this disclosure may be interpreted as "mobile station" (user terminal, hereinafter the same). For example, the various aspects / embodiments of this disclosure may be applied to a configuration in which communication between a base station and a mobile station is replaced with communication between multiple mobile stations (which may be called, for example, Device-to-Device (D2D), Vehicle-to-Everything (V2X), etc.). In this case, the mobile station may have the functions that a base station has. Also, terms such as "uplink" and "downlink" may be interpreted as terms corresponding to terminal-to-terminal communication (for example, "side"). For example, uplink channel, downlink channel, etc. may be interpreted as side channel (or side link).

[0139] Similarly, the term "mobile station" in this disclosure may be interpreted as "base station." In this case, the base station may be configured to have the functions that a mobile station has.

[0140] A wireless frame may consist of one or more frames in the time domain. Each of these one or more frames in the time domain may be called a subframe. A subframe may further consist of one or more slots in the time domain. A subframe may have a fixed time length (e.g., 1 ms) that is independent of numerology.

[0141] Numerology may be communication parameters applied to at least one of the transmission and reception of a signal or channel. Numerology may include, for example, at least one of the following: subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), number of symbols per TTI, radio frame configuration, specific filtering processes performed by the transceiver in the frequency domain, and specific windowing processes performed by the transceiver in the time domain.

[0142] A slot may consist of one or more symbols in the time domain (such as Orthogonal Frequency Division Multiplexing (OFDM) symbols or Single Carrier Frequency Division Multiple Access (SC-FDMA) symbols). A slot may also be a time unit based on neurology.

[0143] A slot may include multiple mini-slots. Each mini-slot may consist of one or more symbols in the time domain. Mini-slots may also be called sub-slots. Mini-slots may consist of fewer symbols than a slot. A PDSCH (or PUSCH) transmitted in a time unit larger than a mini-slot may be called PDSCH (or PUSCH) mapping type A. A PDSCH (or PUSCH) transmitted using a mini-slot may be called PDSCH (or PUSCH) mapping type B.

[0144] Wireless frames, subframes, slots, minislots, and symbols all represent units of time when transmitting a signal. Different names may be used for each of these terms.

[0145] For example, one subframe may be called a transmission time interval (TTI), multiple consecutive subframes may be called a TTI, or one slot or one minislot may be called a TTI. In other words, at least one of a subframe and a TTI may be a subframe in existing LTE (1ms), a period shorter than 1ms (e.g., 1-13 symbols), or a period longer than 1ms. Note that the unit representing the TTI may be called a slot, minislot, etc., instead of a subframe.

[0146] Here, TTI refers to, for example, the smallest unit of time for scheduling in wireless communication. For example, in an LTE system, the base station schedules each user terminal to allocate wireless resources (such as the frequency bandwidth and transmission power available to each user terminal) in TTI units. However, the definition of TTI is not limited to this.

[0147] TTI may be a transmission time unit for channel-encoded data packets (transport blocks), code blocks, code words, etc., or it may be a processing unit for scheduling, link adaptation, etc. Note that when a TTI is given, the actual time interval (e.g., number of symbols) in which the transport block, code block, code word, etc. are mapped may be shorter than the given TTI.

[0148] Furthermore, if one slot or one mini-slot is referred to as TTI, then one or more TTIs (i.e., one or more slots or one or more mini-slots) may constitute the minimum time unit of scheduling. In addition, the number of slots (number of mini-slots) that constitute the minimum time unit of scheduling may be controlled.

[0149] A TTI with a time length of 1ms may also be called a normal TTI, long TTI, normal subframe, long subframe, slot, etc. A TTI shorter than a normal TTI may also be called a shortened TTI, short TTI, partial or fractional TTI, shortened subframe, short subframe, mini slot, sub slot, slot, etc.

[0150] Furthermore, long TTIs (e.g., normal TTIs, subframes, etc.) may be interpreted as TTIs with a time length exceeding 1 ms, and short TTIs (e.g., shortened TTIs, etc.) may be interpreted as TTIs with a TTI length less than that of a long TTI but 1 ms or more.

[0151] A resource block (RB) is a resource allocation unit in the time domain and frequency domain, and in the frequency domain, it may contain one or more consecutive subcarriers. The number of subcarriers in an RB may be the same regardless of the neurology, for example, 12. The number of subcarriers in an RB may be determined based on the neurology.

[0152] Furthermore, the time domain of RB may contain one or more symbols and may be the length of one slot, one minislot, one subframe, or one TTI. One TTI, one subframe, etc., may each consist of one or more resource blocks.

[0153] One or more RBs may also be called a Physical RB (PRB), Sub-Carrier Group (SCG), Resource Element Group (REG), PRB pair, RB pair, etc.

[0154] Furthermore, a resource block may consist of one or more resource elements (REs). For example, one RE may be a radio resource area comprising one subcarrier and one symbol.

[0155] A Bandwidth Part (BWP), also known as a partial bandwidth, may represent a subset of consecutive common resource blocks (RBs) for a given neurology in a given carrier. Here, the common RBs may be identified by an index of the RBs relative to the carrier's common reference point. PRBs may be defined and numbered within a given BWP.

[0156] A BWP may include BWPs for UL (UL BWP) and BWPs for DL ​​(DL BWP). One or more BWPs may be set within a single carrier for a UE.

[0157] At least one of the configured BWPs may be active, and the UE does not need to assume that it will send or receive a given signal / channel outside of the active BWP. In this disclosure, terms such as "cell" and "carrier" may be read as "BWP".

[0158] The structures described above, such as wireless frames, subframes, slots, minislots, and symbols, are merely illustrative. For example, the number of subframes included in a wireless frame, the number of slots per subframe or wireless frame, the number of minislots included in a slot, the number of symbols and RBs included in a slot or minislot, the number of subcarriers included in an RB, and the number of symbols, symbol length, and cyclic prefix (CP) length within a TTI can be varied in various ways.

[0159] The terms “connected,” “coupled,” and any variations thereof mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0160] The reference signal can also be abbreviated as Reference Signal (RS), and may be called a pilot depending on the applicable standard.

[0161] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0162] In the configuration of each of the above devices, "means" may be replaced with "part," "circuit," "device," etc.

[0163] Any reference to elements using designations such as “First,” “Second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the First and Second elements do not imply that only two elements may be employed therein, or that the First element must precede the Second element in any way.

[0164] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to be exclusive OR.

[0165] In this disclosure, if articles are added through translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0166] The terms “determining” and “determining” as used in this disclosure may encompass a wide variety of actions. “Determining” and “determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” and “determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having "judgmented" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having "judgmented" or "decided" about some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0167] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0168] (Note) The above disclosure may be expressed as follows: The first feature is a wireless communication system including a transmitting communication device and a receiving communication device, wherein the receiving communication device comprises a signal receiving unit that receives a wireless signal from the transmitting communication device, a receiving learning unit that learns the state of the wireless signal, a receiving compensation unit that performs compensation for the wireless signal based on the learning results by the receiving learning unit, and a feedback information transmitting unit that evaluates the communication quality of the wireless signal using a predetermined evaluation function and transmits feedback information indicating the partial derivative or difference of the evaluation function to the transmitting communication device, wherein the transmitting communication device comprises a transmitting learning unit that learns the state of the wireless signal, a transmitting compensation unit that performs compensation for the wireless signal based on the learning results by the transmitting learning unit, and a feedback information receiving unit that receives the feedback information and updates the weights applied to the machine learning by the transmitting learning unit based on the partial derivative or difference of the evaluation function, wherein the transmitting learning unit and the receiving learning unit determine the degree of the weight update according to the partial derivative or difference of the evaluation function indicated by the feedback information.

[0169] The second feature is that, in the first feature, the feedback information transmission unit and the feedback information reception unit use the evaluation function which includes parameters defined by one or more quality indicators required for the entire communication network.

[0170] The third feature is that, in the first or second feature, the feedback information transmission unit and the feedback information reception unit use the evaluation function which includes the weight as a parameter.

[0171] The fourth feature is that, in the first to third features, the transmitting learning unit updates the weight based on the feedback information.

[0172] The fifth feature is that, in the first to fourth features, the transmitting learning unit sets a positive decimal value less than or equal to a predetermined value as the learning rate of the evaluation function when updating the weights.

[0173] 10 Wireless communication system 100 Wireless base station 110 Wireless communication unit 120 Receiver learning unit 130 Receiver compensation unit 140 Feedback information transmission unit 200 Terminal 210 Wireless communication unit 220 Transmitter learning unit 230 Transmitter compensation unit 240 Feedback information reception unit 300 Relay station 1001 Processor 1002 Memory 1003 Storage 1004 Communication device 1005 Input device 1006 Output device 1007 Bus

Claims

1. A wireless communication system comprising a transmitting communication device and a receiving communication device, wherein the receiving communication device comprises: a signal receiving unit that receives a wireless signal from the transmitting communication device; a receiving learning unit that performs machine learning on the state of the wireless signal; a receiving compensation unit that performs compensation on the wireless signal based on the learning results by the receiving learning unit; and a feedback information transmitting unit that evaluates the communication quality of the wireless signal using a predetermined evaluation function and transmits feedback information indicating the partial derivative or difference of the evaluation function to the transmitting communication device, wherein the transmitting communication device comprises: a transmitting learning unit that performs machine learning on the state of the wireless signal; a transmitting compensation unit that performs compensation on the wireless signal based on the learning results by the transmitting learning unit; and a feedback information receiving unit that receives the feedback information and updates the weights applied to the machine learning by the transmitting learning unit based on the partial derivative or difference of the evaluation function, wherein the transmitting learning unit and the receiving learning unit determine the degree of the weight update according to the partial derivative or difference of the evaluation function indicated by the feedback information.

2. The wireless communication system according to claim 1, wherein the feedback information transmitting unit and the feedback information receiving unit use the evaluation function which includes parameters defined by one or more quality indicators required for the entire communication network.

3. The wireless communication system according to claim 1, wherein the feedback information transmitting unit and the feedback information receiving unit use the evaluation function which includes the weight as a parameter.

4. The wireless communication system according to claim 3, wherein the transmitting learning unit updates the weight based on the feedback information.

5. The wireless communication system according to claim 4, wherein the transmitting learning unit sets a positive decimal value less than or equal to a predetermined value as the learning rate of the evaluation function when updating the weights.

6. A communication device comprising: a signal receiving unit that receives a wireless signal from a transmitting communication device; a receiving-side learning unit that performs machine learning on the state of the wireless signal; a receiving-side compensation unit that performs compensation on the wireless signal based on the learning results by the receiving-side learning unit; and a feedback information transmitting unit that evaluates the communication quality of the wireless signal using a predetermined evaluation function and transmits feedback information indicating the partial derivative or difference of the evaluation function to the transmitting communication device, wherein the receiving-side learning unit determines the degree of weight updating applied to the machine learning according to the partial derivative or difference of the evaluation function indicated by the feedback information.

7. A communication device comprising: a transmitting-side learning unit that learns the state of a wireless signal to a receiving-side communication device; a transmitting-side compensation unit that performs compensation for the wireless signal based on the learning results by the transmitting-side learning unit; and a feedback information receiving unit that evaluates the communication quality of the wireless signal using a predetermined evaluation function, receives feedback information indicating the partial derivative or difference of the evaluation function, and updates the weights applied to the machine learning by the transmitting-side learning unit based on the partial derivative or difference of the evaluation function, wherein the transmitting-side learning unit determines the degree of the weight update according to the partial derivative or difference of the evaluation function indicated by the feedback information.

8. A communication control method using a transmitting communication device and a receiving communication device, comprising the steps of: the receiving communication device receiving a radio signal from the transmitting communication device; the receiving communication device learning the state of the radio signal; the receiving communication device performing compensation for the radio signal based on the learning results; the receiving communication device evaluating the communication quality of the radio signal using a predetermined evaluation function and transmitting feedback information indicating the partial derivative or difference of the evaluation function to the transmitting communication device; the transmitting communication device learning the state of the radio signal; the transmitting communication device performing compensation for the radio signal based on the learning results; the transmitting communication device receiving the feedback information and updating weights applied to the machine learning based on the partial derivative or difference of the evaluation function; and the transmitting communication device and the receiving communication device determining the degree of the weight update according to the partial derivative or difference of the evaluation function indicated by the feedback information.

Images