WO2023021626A1

WO2023021626A1 - Wireless access network device, wireless communication device, method and recording medium

Info

Publication number: WO2023021626A1
Application number: PCT/JP2021/030241
Authority: WO
Inventors: 真明谷尾; 一志村岡; 直人石井
Original assignee: 日本電気株式会社
Priority date: 2021-08-18
Filing date: 2021-08-18
Publication date: 2023-02-23
Also published as: JPWO2023021626A1

Abstract

[Problem] To transmit or receive information in order to improve transmission between two communication devices. [Solution] First wireless access network devices (810, 3210) obtain information about transmission between the first wireless access network devices and second wireless access network devices (820, 3220), and transmit the information about transmission to the second wireless access network devices. The second wireless access network devices receive the information about transmission, and execute processing pertaining to communication with the first wireless access network devices by using said information about transmission.

Description

RADIO ACCESS NETWORK DEVICE, WIRELESS COMMUNICATION DEVICE, METHOD AND RECORDING MEDIUM

The present disclosure relates to a radio access network device, radio communication device, method and recording medium.

In the field of wireless communication, technology development is progressing to achieve high-speed communication in order to cope with the increase in traffic. In order to achieve high-speed communication, a wireless communication device usually needs to be equipped with a high-speed and high-precision DAC (Digital-to-Analog Converter). However, there is a problem that the power consumption of such a device increases.

To solve this problem, delta-sigma modulation may be used (see, for example, Patent Document 1, Non-Patent Document 1, and Non-Patent Document 2). Delta-sigma modulation is a process of converting an analog signal as an input signal into a quantized signal (pulse train). Delta-sigma modulation can reduce the resolution requirements of the DAC (potentially down to 1 bit). Thereby, the power consumption of the wireless communication device can be reduced.

On the other hand, in radio communication devices, a configuration is known in which a plurality of functions of a radio access network device are divided into two physically separated communication devices. For example, a base station is divided into a Base Band Unit (BBU) and a Remote Unit (RU). The RU may also be called RRU (Remote Radio Unit), RRH (Remote Radio Head), or RAU (Remote Antenna Unit). The BBU and RU are connected via a communication path (for example, optical fiber). In this configuration, RoF (Radio over Fiber) technology is used for signal transmission between the BBU and RU.

In recent years, systems using delta-sigma modulation and RoF technology have been studied (see, for example, Non-Patent Document 3). Hereinafter, in such a system, a pulse train output by delta-sigma modulation is transmitted from the BBU to the RU via an optical fiber. In this case, the RU restores the pulse train to the original analog signal before delta-sigma modulation, for example through an analog bandpass filter (BPF). Since the RU does not need to be equipped with a DAC, the power consumption of the RU can be reduced.

International Publication No. 2016/103981

By the way, as described in Non-Patent Document 1, it is known that in a configuration using delta-sigma modulation, a phenomenon called spectrum leakage occurs due to waveform distortion. Here, the spectrum leak is a phenomenon in which signal components in bands around the desired frequency band (that is, bands other than the desired frequency band) occur. The quality of the signal output from the RU is degraded due to spectrum leakage. In order to suppress the above distortion, it is required to exchange appropriate information between the two communication devices (BBU and RU in this example).

This disclosure provides techniques for sending or receiving information to improve transmission between two communication devices.

In one or more embodiments, a first radio access network device is provided that performs processing for a first physical layer. The first radio access network device is between the first radio access network device and a second radio access network device that performs processing related to a second physical layer higher than the first physical layer. an obtaining unit for obtaining information about transmission; and a transmitting unit for transmitting said information about said transmission to said second radio access network device.

In one or more embodiments, a second radio access network device is provided that performs processing for a second physical layer above the first physical layer. The second radio access network device includes: a first radio access network device that performs processing related to the first physical layer; and a receiving unit that receives information related to transmission between the second radio access network device. and a processing unit that performs processing related to communication with the first radio access network device using the information related to the transmission.

In one or more embodiments, a wireless communication device is provided. The radio communication device includes a first radio access network device that performs processing related to a first physical layer and a second radio access network device that performs processing related to a second physical layer higher than the first physical layer. And prepare. The first radio access network device obtains information regarding transmissions between the first radio access network device and the second radio access network device, and transmits the information regarding the transmissions to the second radio access network device. Send to a network device. The second radio access network device receives the information regarding the transmission and uses the information regarding the transmission to perform processing relating to communication with the first radio access network device.

In one or more embodiments, a method is provided in a first radio access network device that performs processing for a first physical layer. The method obtains information about transmissions between the first radio access network device and a second radio access network device performing processing on a second physical layer above the first physical layer. and sending said information regarding said transmission to said second radio access network device.

In one or more embodiments, a method is provided in a second radio access network device for processing for a second physical layer above the first physical layer. The method comprises: receiving information regarding a transmission between a first radio access network device performing processing for the first physical layer and the second radio access network device; using to perform processing related to communication with the first radio access network device.

In one or more embodiments, a computer-readable non-transitory recording medium is provided. The non-temporary recording medium includes a first radio access network device that performs processing related to a first physical layer and a second radio access network device that performs processing related to a second physical layer higher than the first physical layer. A program is recorded which causes a processor to obtain information regarding transmissions to and from a network device and to transmit said information regarding said transmissions to said second radio access network device.

In one or more embodiments, a computer-readable non-transitory recording medium is provided. The non-temporary recording medium includes a first radio access network device that performs processing related to a first physical layer and a second radio access network device that performs processing related to a second physical layer higher than the first physical layer. recording a program for causing a processor to receive information regarding transmission to and from a network device and to perform processing regarding communication with said first radio access network device using said information regarding said transmission; are doing.

According to the above arrangement, it is possible to send or receive information for improving the transmission between two devices (the first radio access network device and the second radio access network device). Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.

1 is a diagram showing a schematic configuration of a wireless communication device according to a first embodiment; FIG. 4 is a diagram showing the configuration of a delta-sigma modulation section according to the first embodiment; FIG. 3 is a diagram showing the configuration of a neural network processing unit according to the first embodiment; FIG. 3 is a diagram showing the configuration of a neural network learning unit according to the first embodiment; FIG. 4 is a diagram showing the configuration of a modulating section according to the first embodiment; FIG. It is a figure explaining the flow of construction|assembly of the transmission model which concerns on 1st Embodiment. 4 is a flow chart showing the flow of processing of the delta-sigma modulation device according to the first embodiment; It is a figure which shows an example of a concrete structure of the radio|wireless communication apparatus which concerns on 1st Embodiment. It is a figure which shows the hardware constitutions of the 1st apparatus based on 1st Embodiment. It is a figure which shows the hardware constitutions of the 2nd apparatus based on 1st Embodiment. 4 is a sequence diagram showing the flow of processing of the wireless communication device according to the first embodiment; FIG. FIG. 11 is a diagram showing a configuration of a delta-sigma modulation section according to a modification; It is a figure which shows the structure of the 1st neural network which concerns on a modification. It is a figure which shows the structure of the 1st neural network which concerns on a modification. 9 is a flow chart showing the flow of processing of a delta-sigma modulation device according to a modification; It is a figure which shows the structure of the neural network learning part which concerns on a modification. FIG. 7 is a diagram showing the configuration of a wireless communication device according to a second embodiment; FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the second embodiment; FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the modification; FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the modification; FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the modification; FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the modification; FIG. 10 is a diagram showing the configuration of a radio communication device according to a modification; FIG. 10 is a diagram showing the configuration of a radio communication device according to a modification; FIG. 11 is a diagram showing the configuration of a wireless communication device according to a third embodiment; FIG. FIG. 12 is a diagram showing the configuration of a wireless communication device according to a fourth embodiment; FIG. FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the fourth embodiment; FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the modification; FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the modification; FIG. 12 is a sequence diagram showing the flow of processing of the wireless communication device according to the modification; FIG. 10 is a diagram showing the configuration of a radio communication device according to a modification; FIG. 10 is a diagram showing the configuration of a radio communication device according to a modification; FIG. 12 is a diagram showing the configuration of a wireless communication device according to a fifth embodiment; FIG. 12 is a diagram showing the configuration of a first radio access network device according to the fifth embodiment; FIG. 12 is a diagram showing the configuration of a second radio access network device according to the fifth embodiment; FIG. 14 is a flow chart showing the flow of processing of the first radio access network device according to the fifth embodiment; FIG. FIG. 14 is a flow chart showing the flow of processing of the second radio access network device according to the fifth embodiment; FIG. 1 is an example of a system using delta-sigma modulation and RoF technology; 1 is an example of a system using delta-sigma modulation and RoF technology;

One or more embodiments are described below with reference to the accompanying drawings. In the present specification and drawings, elements that can be described in the same manner are denoted by the same reference numerals, thereby omitting redundant description.

The description is given in the following order.
1. Outline of embodiment 2 . First embodiment 2-1. Schematic Configuration of Wireless Communication Device 2-2. Configuration of delta-sigma modulation unit 2-3. Configuration of Neural Network Processing Unit 2-4. Outline of configuration of neural network learning unit 2-5. Configuration of communication path 2-6. Configuration of bandpass filter 2-7. Configuration of modulation unit 2-8. Specific Configuration of Neural Network Learning Unit 2-9. Flow of processing of delta-sigma modulator 2-10. Specific configuration example of wireless communication device 2-11. Configuration of first device 2-12. Configuration of second device 2-13. Flow of processing of wireless communication device 2-14. Modification 3. Second Embodiment 3-1. Schematic Configuration of Wireless Communication Device 3-2. Configuration of first device 3-3. Configuration of second device 3-4. Outline of processing flow of wireless communication device 3-5. Flow of processing of wireless communication device 3-6. Modification 4. Third Embodiment 4-1. Schematic Configuration of Wireless Communication Device 4-2. Configuration of first device 4-3. Configuration of second device 5 . Fourth Embodiment 5-1. Schematic Configuration of Wireless Communication Device 5-2. Configuration of first device 5-3. Configuration of second device 5-4. Flow of processing of wireless communication device 5-5. Modification 6. Fifth Embodiment 6-1. Configuration of Wireless Communication Device 6-2. Flow of processing of wireless communication device 6-3. Modification

<<1. Outline of Embodiment>>
SUMMARY One or more embodiments are summarized below.

(1) Technical Problem FIG. 38 is an example of a system using delta-sigma modulation and RoF technology. The system comprises a first device 3710 and a second device 3720 . First device 3710 and second device 3720 are connected via optical fiber 3730 .

A first device 3710 includes an O/E converter (Optic-Electric converter) 3711 , a bandpass filter (BPF) 3712 , an amplifier 3713 and an antenna 3714 . The second device 3720 comprises a delta-sigma modulator 3721 and an E/O converter (Electric-Optic converter) 3722 .

An analog signal 3741 as an input signal is converted into a quantized signal (pulse train) 3742 through a delta-sigma modulator 3721 . The delta-sigma modulation section 3721 has a general configuration of one input and one output, and the quantized signal (pulse train) is fed back inside the delta-sigma modulation section 3721 . The pulse train 3742 is converted into an optical signal through the E/O converter 3722 . Optical signals are transmitted over optical fiber 3730 . After that, the optical signal is converted into an electrical signal 3743 through the O/E converter 3711 . Electrical signal 3743 is converted through BPF 3712 to original analog signal 3745 before delta-sigma modulation. Analog signal 3745 is amplified using amplifier 3713 . The amplified analog signal is output from antenna 3714 .

In the system of FIG. 38, ideal delta-sigma modulation is performed. No distortion occurs in the pulse train 3742 during the transmission process of the pulse train 3742 . As a result, no spectrum leak occurs.

FIG. 39 is an example of a system using delta-sigma modulation and RoF technology. In this system, distortion occurs in the pulse train 3742 during the transmission process of the pulse train 3742 . For example, distortion occurs as the optical signal passes through the optical fiber 3730 . Such distortion is referred to as "optical transmission distortion". A pulse train 3810 represents a state in which optical transmission distortion has occurred.

Furthermore, distortion also occurs when the power reflection between the O/E converter 3711 and the BPF 3712 is large. Such distortion is referred to as "electrical transmission distortion". Pulse train 3820 represents a state in which electrical transmission distortion has occurred. Hereinafter, optical transmission distortion and electrical transmission distortion are collectively referred to as "transmission distortion".

As a result, the transmission distortion affects the frequency components of the analog signal 3830 output via the BPF 3712. Specifically, the above spectrum leak occurs. This degrades the signal to noise ratio of analog signal 3830 . Thus, there is a problem that the signal quality deteriorates due to transmission distortion.

In order to solve the above problems, an arrangement is required to send or receive appropriate information to improve the transmission between the two devices (the first device 3710 and the second device 3720).

(2) Technical Features In one or more embodiments, a wireless communication device comprises a first radio access network device and a second radio access network device. The first radio access network device is a device that performs processing related to the first physical layer. The second radio access network device is a device that performs processing related to a second physical layer higher than the first physical layer. Here, the first and second physical layers are the first layer (lowest layer) among multiple layers forming the communication protocol implemented in the first radio access network device and the second radio access network device. ) can be considered to be included in

The first radio access network device comprises: an obtaining unit for obtaining information about transmission between the first radio access network device and the second radio access network device; and transmitting information about the transmission to the second radio access network device. and a transmitter for transmitting.

The second radio access network device includes a receiving unit that receives information about transmission, and a processing unit that uses the information about transmission to perform processing related to communication with the first radio access network device.

The above configuration has the following effects. The first radio access network device sends (feeds back) information regarding the transmission to the second radio access network device. The second radio access network device can use the information regarding the transmission to improve the transmission between the two devices (the first radio access network device and the second radio access network device).

<<2. First Embodiment>>
Next, the first embodiment and its modification will be described with reference to FIGS. 1 to 16. FIG.

<2-1. Schematic Configuration of Wireless Communication Device>
FIG. 1 is a diagram showing a schematic configuration of a wireless communication device 100. As shown in FIG. Wireless communication device 100 is a device conforming to the technical specifications of 3GPP (Third Generation Partnership Project). Specifically, the wireless communication device 100 may be a device conforming to the technical specifications of 5G (5th Generation). Of course, wireless communication device 100 is not limited to this example.

A wireless communication device 100 includes a delta-sigma modulation device 110 and a transmission path 120 . Radio communication apparatus 100 converts the signal output by delta-sigma modulation apparatus 110 into a radio signal via transmission path 120 and transmits the radio signal to terminal apparatus 190 .

The delta-sigma modulation device 110 includes a delta-sigma modulation section 111, a neural network processing section 112, and a neural network learning section 113. Hereinafter, the neural network processing unit 112 is referred to as "NN processing unit 112". The neural network learning unit 113 is called "NN learning unit 113".

The transmission path 120 includes a communication path 130 and a transmission section 140 . Communication path 130 connects delta-sigma modulation section 111 and transmission section 140 . The transmitter 140 includes an antenna 141 , a bandpass filter (BPF) 142 , an amplifier 143 and a modulator 144 .

The delta-sigma modulation unit 111 performs delta-sigma modulation on an analog signal as an external input signal and outputs a quantized signal (1-bit pulse train). The quantized signal is sent to BPF 142 via communication path 130 . The BPF 142 performs bandpass processing (hereinafter referred to as “BPF processing”) for passing only a desired frequency band on the quantized signal. The quantized signal is converted to an analog signal through BPF 142 . That is, the quantized signal is restored to the original analog signal before delta-sigma modulation. Amplifier 143 amplifies the analog signal. Antenna 141 outputs the amplified analog signal. Thus, the transmission section 140 has a function of transmitting a signal toward the terminal device 190 .

Note that the amplified analog signal is also output to the modulation section 144 . Modulation section 144 performs modulation processing on the analog signal and outputs the modulated analog signal to NN learning section 113 . Thus, the transmitter 140 also has a function of transmitting (that is, feeding back) the signal generated through the transmission process of the quantized signal output from the delta-sigma modulator 111 to the delta-sigma modulator 110 .

Hereinafter, the analog signal input to the delta-sigma modulation section 111 will be referred to as a "first signal". Furthermore, the quantized signal output by the delta-sigma modulating section 111 is referred to as a "second signal". Further, a signal generated through the transmission process of the second signal and fed back to the NN learning unit 113 is referred to as a "third signal". In other words, the third signal is a signal generated in the course of the second signal being transmitted over transmission path 120 . The third signal may contain information about transmission distortions induced in transmission path 120 . Accordingly, the third signal is used to feed back information about transmission distortions that have occurred in transmission path 120 .

The NN processing unit 112 includes a first neural network 300 that operates according to predetermined parameters (see FIG. 3). Hereinafter, the first neural network 300 will be referred to as "first NN 300". The parameters of the first NN 300 are referred to as "first parameters".

The NN learning unit 113 receives the second signal and the third signal as input signals. NN learning section 113 calculates the first parameter using the second signal and the third signal. NN learning section 113 transmits the calculated first parameter to NN processing section 112 .

The NN processing unit 112 receives the first parameter from the NN learning unit 113 . The NN processing unit 112 updates the first parameter of the first NN 300 to the received first parameter (that is, the first parameter calculated by the NN learning unit 113).

The NN processing unit 112 receives the second signal as an input signal. The NN processing unit 112 uses the second signal to output an approximate value (analog signal) of the signal generated through at least part of the transmission process of the second signal through the first NN 300 . Hereinafter, this approximation will be referred to as the "fourth signal". NN processing section 112 can use the fourth signal to feed back, to delta-sigma modulation section 111, information about the transmission distortion that occurs in the process of transmitting the second signal.

The delta-sigma modulation section 111 receives the first signal and the fourth signal as input signals. Delta-sigma modulation section 111 performs delta-sigma modulation on the first signal using the fourth signal, and outputs the second signal.

Generally, the 1-input 1-output configuration described in FIG. 38 (that is, the delta-sigma modulation section 3721 in which the quantized signal is directly fed back) is called delta-sigma modulation. In contrast, in one or more embodiments of the present disclosure, the second signal is not directly fed back as the fourth signal, and the second and fourth signals have NN processing unit 112 between them. separated by an interposition. The delta-sigma modulation unit 111 receives the first signal and the fourth signal as input signals and outputs the second signal, that is, has a two-input one-output configuration. In one or more embodiments of the present disclosure, for convenience, such a two-input, one-output configuration is defined as delta-sigma modulation. The NN processing unit 112 has a feedback function. One or more embodiments are characterized in that the first parameter in the NN processing unit 112 is updated by the NN learning unit 113 .

<2-2. Configuration of delta-sigma modulation section>
There are two types of devices that implement the delta-sigma modulation unit 111: a bandpass type (see Non-Patent Document 1) and a low-pass type (see Non-Patent Document 2). The delta-sigma modulation unit 111 of this example is a band-pass type device, and is implemented with reference to Non-Patent Document 1.

FIG. 2 is a diagram showing an example of the configuration of the delta-sigma modulation section 111. As shown in FIG. Delta-sigma modulation section 111 includes upconverter 210 , loop filter 220 , and quantizer 230 .

The first signal is a baseband signal and includes an in-phase component signal (hereinafter referred to as "I signal") and a quadrature component signal (hereinafter referred to as "Q signal").

The upconverter 210 is a 2-input, 1-output component. Upconverter 210 receives the I and Q signals as input signals. Upconverter 210 upconverts the first signal (I signal and Q signal) to a desired frequency (target frequency) f0.

The upconverter 210 includes a first multiplier 211a, a second multiplier 211b, and an adder 212. The first multiplier 211 a multiplies the I signal by cos ωt and outputs the multiplication result to the adder 212 . The second multiplier 211 b multiplies the Q signal by −sinωt and outputs the multiplication result to the adder 212 . Here, "cos()" is a cosine function and "sin()" is a sine function (same below). Furthermore, ω=2×π×f0.

The adder 212 adds the multiplication result of the first multiplier 211a and the multiplication result of the second multiplier 211b, and outputs the addition result.

The loop filter 220 is a 2-input, 1-output element. Loop filter 220 receives as input signals the output of upconverter 210 and the fourth signal. The loop filter 220 performs processing for suppressing transmission distortion contained in the feedback component (that is, the fourth signal) of the input signal.

The loop filter 220 includes a first adder 221a, a second adder 221b, and a transfer function processing section 222.

The first adder 221 a adds the output of the upconverter 210 (the output of the adder 212 ) and the fourth signal, and outputs the addition result to the transfer function processing section 222 . Here, the output of the first adder 221a is the difference between the output of the upconverter 210 and the fourth signal. In other words, the output of the first adder 221a may contain transmission distortion components that occur during the transmission process of the second signal.

The transfer function processing unit 222 applies a transfer function to the output of the first adder 221a to suppress (or to cancel). The transfer function is a function that determines the characteristics of the delta-sigma modulation in this example, and is determined based on the desired signal transfer function, noise transfer function, and the like.

The second adder 221 b adds the output of the upconverter 210 and the output of the transfer function processing section 222 and outputs the addition result to the quantizer 230 .

In this way, loop filter 220 uses the output of upconverter 210 and the fourth signal to generate a signal (analog signal).

Quantizer 230 is a 1-bit quantizer. The quantizer 230 quantizes the output of the loop filter 220 (output of the second adder 221b) with 1 bit and outputs a second signal (1-bit pulse train).

In this way, delta-sigma modulation section 111 uses the fourth signal to calculate a component for suppressing at least part of the transmission distortion that occurs in the process of transmitting the second signal, and converts the calculated component into the second signal. reflected in the signal.

In another example, the loop filter 220 may omit the second adder 221b. In this case, the output of transfer function processing section 222 is input to quantizer 230 . The output of transfer function processing section 222 includes the output of upconverter 210 and a component for suppressing at least part of the transmission distortion that occurs in the process of transmitting the second signal.

<2-3. Configuration of Neural Network Processing Unit>
FIG. 3 is a diagram showing an example of the configuration of the NN processing unit 112. As shown in FIG. NN processing unit 112 includes a first NN 300 . The first NN 300 receives the second signal as an input signal and outputs a fourth signal.

In this example, the fourth signal is an approximation (estimate) of the signal generated while the second signal passes through part of the transmission path 120 . More specifically, the fourth signal is an approximation (estimate) of the signal generated in the course of the second signal passing through communication path 130 , BPF 142 and amplifier 143 . In other words, the fourth signal is an approximation (estimate) of the radio signal output from antenna 141 .

Therefore, the fourth signal contains an approximation of at least part of the transmission distortion that occurs through the transmission process of the second signal. Specifically, the fourth signal includes an approximation of at least a portion of the transmission distortion that the second signal experiences as it passes through communication path 130 , BPF 142 and amplifier 143 .

The first NN 300 operates according to the first parameters. The first parameters include, for example, weights and biases. For example, let the function f in equation (1) below be the activation function in the neural network, where x is the input, w is the weight, and b is the bias.
f(wx+b) (1)

The first NN 300 comprises an input layer 310 , an intermediate layer 320 and an output layer 330 . The intermediate layer 320 is one layer.

The input layer 310 includes a node 310a into which the current value of the second signal is input. Additionally, the input layer 310 further includes a node 310b into which the past value of the second signal is input. Note that "D" represents delay. The output layer 330 is a linear layer with no activation functions. A first parameter is reflected in the intermediate layer 320 . The output layer 330 outputs the sum of the outputs of the multiple nodes of the intermediate layer 320 as a fourth signal.

The configuration of the first NN 300 is not limited to the configuration of FIG. Various commonly used neural networks may be applied to this embodiment. For example, the intermediate layer 320 of the first NN 300 may have multiple layers. That is, a multilayer neural network may be adopted as the first NN 300 .

The NN processing unit 112 receives the first parameter from the NN learning unit 113 . The NN processing unit 112 updates the first parameter of the first NN 300 to the received first parameter. That is, the NN processing unit 112 updates the first parameter according to the state of the transmission path 120 . Therefore, the NN processing unit 112 can reflect at least part of the transmission distortion that occurs in the current state of the transmission path 120 in the fourth signal.

<2-4. Outline of Configuration of Neural Network Learning Unit>
FIG. 4 is a diagram showing an example of the configuration of the NN learning unit 113. As shown in FIG. NN learning section 113 includes transmission model 410 , error calculation section 420 , and parameter calculation section 430 .

The transmission model 410 is a component that models at least part of the transmission process of the second signal. In this example, transmission model 410 is a component that models transmission path 120 . Transmission model 410 uses the second signal to output an approximation (estimate) of the third signal.

The transmission model 410 includes a second neural network 600 operating according to predetermined parameters (see FIG. 6). The second neural network 600 is hereinafter referred to as the "second NN 600". The parameters of the second NN 600 are referred to as "second parameters". The second parameter, like the first parameter, includes weights and biases.

The error calculator 420 receives the output of the transmission model 410 (approximate value of the third signal) and the third signal (output of the modulator 144 in this example) as input signals. Error calculator 420 calculates the error (difference) between the output of transmission model 410 and the third signal. Hereinafter, this error will be referred to as the "approximation error". Error calculator 420 outputs the approximation error to parameter calculator 430 .

The parameter calculator 430 calculates the first parameter and the second parameter using the approximation error. Parameter calculator 430 transmits the calculated first parameter to NN processor 112 . Furthermore, the parameter calculator 430 updates the second parameter of the second NN 600 to the calculated second parameter.

Thus, the NN learning unit 113 learns the current state of the transmission path 120 using the second signal and the third signal. That is, the NN learning unit 113 calculates the first parameter and the second parameter according to the current state of the transmission path 120. FIG. NN learning section 113 can reflect at least part of the transmission distortion that occurs in the current state of transmission path 120 in first NN 300 and second NN 600 .

<2-5. Configuration of Communication Path>
The communication path 130 includes one or both of an electrical transmission line (eg, metal wire) that transmits electrical signals and an optical transmission line (eg, optical fiber) that transmits optical signals.

Note that the communication path 130 includes one or more of an E/O converter that converts an electrical signal into an optical signal, an O/E converter that converts an optical signal into an electrical signal, a bandpass filter, a frequency converter, and the like. may include a combination of

<2-6. Configuration of Bandpass Filter>
BPF 142 performs BPF processing on the output of communication path 130 . Here, the desired frequency band is a band from f0-fα to f0+fα. fα is an arbitrary frequency.

The BPF 142 may be composed of analog elements. BPF 142 may be an LC filter or an RLC filter. An LC filter is a filter based on a combination of inductors (L) and capacitors (C). An RLC filter is a filter based on a combination of resistors (R), inductors (L) and capacitors (C).

<2-7. Configuration of Modulation Unit>
FIG. 5 is a diagram showing an example of the configuration of the modulating section 144. As shown in FIG. Modulation section 144 down-converts the output of amplifier 143 by a direct conversion method and outputs the down-converted signal as a third signal.

The modulating section 144 includes a first modulating section 500a and a second modulating section 500b.

The first modulating section 500a includes a first multiplier 510a, a first low-pass filter (LPF) 520a, and a first A/D converter (ADC) 530a.

The first multiplier 510a multiplies the output of the amplifier 143 by cosωt and outputs the multiplication result to the first LPF 520a. where ω=2×π×f0. The first LPF 520a performs low-pass filtering on the output of the first multiplier 510a and outputs the execution result to the first ADC 530a. The first ADC 530a converts the output of the first LPF 520a into a digital signal, thereby outputting a digital I signal.

The second modulation section 500b includes a second multiplier 510b, a second low-pass filter (LPF) 520b, and a second A/D converter (ADC) 530b.

The second multiplier 510b multiplies the output of the amplifier 143 by -sinωt and outputs the multiplication result to the second LPF 520b. The second LPF 520b performs low-pass filtering on the output of the second multiplier 510b and outputs the execution result to the second ADC 530b. The second ADC 530b converts the output of the second LPF 520b into a digital signal, thereby outputting a digital Q signal.

Therefore, the third signal includes a digital I signal and a digital Q signal. The third signal is input to NN learning section 113 .

<2-8. Specific Configuration of Neural Network Learning Unit>
Next, a specific configuration of NN learning section 113 will be described. First, the configuration of the transmission model 410 will be described. FIG. 6 is an example of the flow of constructing the transmission model 410 .

As shown in the upper part of FIG. 6, the transmission path 120 includes a communication path 130, a BPF 142, an amplifier 143, and a modulation section 144. Now assume that amplifier 143 does not have strong nonlinearity, ie amplifier 143 has strong linearity. Since the BPF 142 also has linearity, the position of the BPF 142 and the position of the amplifier 143 can be interchanged as shown in the middle part of FIG. That is, the configuration of the upper transmission path 120 can be approximated by the middle transmission path 120'. This allows the communication path 130 and the amplifier 143 to be modeled together.

The communication path 130 and amplifier 143 are collectively modeled by the second NN 600. The second NN 600 outputs an approximation (estimate) of the signal generated through part of the transmission process of the second signal. Specifically, second NN 600 outputs an approximation of the signal generated in the course of the second signal passing through communication path 130 and amplifier 143 .

The BPF 142 is modeled by a digital filter 610. Digital filter 610 may be, for example, FIR (Finite impulse response).

The modulation section 144 is modeled by a digital downconverter 620 . Digital downconverter 620 has the same functions/properties as modulator 144 . Accordingly, the digital downconverter 620 downconverts the output of the digital filter 610 to output a digital I signal and a digital Q signal.

Next, the approximation error calculated by the error calculator 420 will be described. The approximation error represents the error between the approximation of the third signal (output of transmission model 410) and the actual third signal (output of modulator 144).

At the time when the wireless communication device 100 is activated, the transmission distortion information generated in the transmission path 120 is not reflected in the second NN 600, so the transmission model 410 outputs the second signal as it is. On the other hand, the actual third signal includes transmission distortion caused during the transmission process of the second signal. As the magnitude of transmission distortion (hereinafter referred to as "distortion amount") increases, the approximation error increases. If the approximation error is large, this means that the information about the transmission distortion currently occurring in the transmission path 120 cannot be reflected in the first NN 300 and the second NN 600, and therefore the transmission distortion cannot be suppressed. means. On the other hand, even after information about transmission distortion occurring in transmission path 120 is reflected in second NN 600, the amount of distortion changes over time. Therefore, when the approximation error is large, it also means that the difference (error) between the amount of distortion included in the output of the transmission model 410 and the amount of distortion included in the actual third signal is large. Therefore, the approximation error is a value related to the amount of distortion that occurred during the transmission process of the second signal.

If the approximation error is small, this means that the output of transmission model 410 is close to the actual third signal. That is, this means that the information about the transmission distortion currently occurring in the transmission path 120 can be reflected in the first NN 300 and the second NN 600, and therefore the transmission distortion can be suppressed.

The error calculator 420 calculates a first difference between the I signal output by the transmission model 410 and the I signal included in the third signal. Since the I signal has a real component, the first difference has a real component. Furthermore, error calculator 420 calculates a second difference between the Q signal output by transmission model 410 and the Q signal included in the third signal. Since the Q signal is the imaginary component, the second difference is the imaginary component.

The error calculator 420 calculates an approximation error based on the first difference and the second difference. For example, the approximation error may be a complex number represented by a first difference that is a real component and a second difference that is an imaginary component. According to another example, the approximation error may be the larger of the absolute value of the first difference and the absolute value of the second difference. The approximation error may be calculated by one of the known calculation methods so long as it represents the error between the output of transmission model 410 and the actual third signal.

The parameter calculator 430 uses the approximation error and the internal parameters of the transmission model 410 to calculate the first parameter and the second parameter. The internal parameters of transmission model 410 may include second parameters of second NN 600 and output values of at least one node within second NN 600 . In another example, the internal parameters of transmission model 410 may further include filter coefficients of digital filter 610 and sine and cosine waves in digital downconverter 620 . The parameter calculator 430 calculates the first parameter and the second parameter so as to reduce the approximation error. For example, the parameter calculator 430 calculates the first parameter and the second parameter such that at least one of the absolute value of the first difference and the absolute value of the second difference is small.

<2-9. Flow of Processing of Delta-Sigma Modulator>
Next, referring to FIG. 7, the processing flow of the delta-sigma modulation device 110 will be described. FIG. 7 is a flow chart showing an example of the processing flow of the delta-sigma modulation device 110. As shown in FIG.

When radio communication apparatus 100 is activated (or radio communication apparatus 100 is reset), delta-sigma modulation section 111 performs delta-sigma modulation on a first signal as an external input signal to generate a second signal. signal is output (701).

The NN learning unit 113 uses the second signal and the third signal to calculate the first parameter and the second parameter (702). NN learning section 113 transmits the calculated first parameter to NN processing section 112 .

The NN processing unit 112 updates the first parameter of the first NN 300 to the first parameter calculated by the NN learning unit 113. Furthermore, the NN learning unit 113 updates the second parameter of the second NN 600 in the transmission model 410 to the calculated second parameter (703).

The NN processing unit 112 outputs a fourth signal through the first NN 300 using the second signal (704).

The delta-sigma modulation unit 111 performs delta-sigma modulation on the first signal using the fourth signal and outputs the second signal (705).

After that, the processes of steps 702 to 705 are repeatedly executed.

The above configuration has the following effects. The delta-sigma modulator 110 receives, as a third signal to be fed back, information about transmission distortion that occurred in the transmission process (transmission path 120) of the second signal. Delta-sigma modulator 110 calculates an approximation error using the second signal and the third signal, and calculates the first parameter and the second parameter using the approximation error. The delta-sigma modulator 110 updates the first parameter of the first NN 300 to the calculated first parameter, and updates the second parameter of the second NN 600 to the calculated second parameter. do. Thereby, information on transmission distortion occurring in the transmission path 120 is reflected in the first NN 300 and the second NN 600 . Delta-sigma modulator 110 performs delta-sigma modulation on the first signal using the fourth signal (output of first NN 300). As a result, the delta-sigma modulator 110 can pass the signal component of the target frequency f0 and perform noise shaping to move the noise in the vicinity of the frequency f0 out of the band.

The delta-sigma modulation device 110 can suppress transmission distortion that occurs in the process of transmitting the second signal by the feedback processing as described above. Therefore, the delta-sigma modulation device 110 can suppress spectrum leak. The delta-sigma modulator 110 is capable of high quality signal transmission.

<2-10. Specific Configuration Example of Wireless Communication Device>
Next, a specific configuration of the wireless communication device will be described with reference to FIGS. 8 to 10. FIG. FIG. 8 is an example of a specific configuration of wireless communication device 800 . Constituent elements that have already been described are denoted by the same reference numerals, and detailed description thereof will be omitted.

A wireless communication device 800 is a node of a radio access network (RAN). In this example, wireless communication device 800 is a base station. The wireless communication device 800 performs wireless communication with the terminal device 190 located within its coverage area.

A wireless communication device 800 includes multiple devices (or multiple nodes). Specifically, wireless communication device 800 comprises a first device 810 and a second device 820 . The first device 810 is a node of the radio access network and may be referred to as "first radio access network device". The second device 820 is a node of the radio access network and may be referred to as "second radio access network device".

The first device 810 performs processing related to the first physical layer. In this example, the processing for the first physical layer includes BPF processing and amplification processing.

The second device 820 performs processing related to the second physical layer, which is higher than the first physical layer. In this example, the processing for the second physical layer includes delta-sigma modulation. It should be noted that the first and second physical layers are included in the first layer (lowest layer) of the multiple layers forming the communication protocol implemented in the first device 810 and the second device 820. You can catch it.

The first device 810 and the second device 820 are connected via the first communication path 131 . Second device 820 transmits a second signal to first device 810 via first communication path 131 .

The first device 810 and the second device 820 are connected via the second communication path 132 . First device 810 transmits information regarding transmissions between first device 810 and second device 820 to second device 820 via second communication path 132 . Hereinafter, the information related to transmission is referred to as "transmission-related information".

In this example, the transmission-related information is information about transmission of the second signal transmitted from the second device 820 to the first device 810 . Specifically, the transmission-related information is the third signal (that is, the output of the modulating section 144) generated in the process of transmitting the second signal. The third signal contains information about transmission distortion caused during the transmission process of the second signal.

<2-11. Configuration of the first device>
A first device 810 includes an antenna 141 , a BPF 142 , an amplifier 143 , a modulator 144 and an information transmitter 145 . Information transmitter 145 controls communication with second device 820 via second communication path 132 . Specifically, the information transmission unit 145 controls transmission of transmission-related information.

FIG. 9 is a diagram showing an example of the hardware configuration of the first device 810. As shown in FIG. The first device 810 comprises a communication interface 910 , a storage section 920 and a processing section 930 .

A communication interface 910 is an interface for communication with other devices. Communication interface 910 includes antenna 141 for wireless communication. Further, the communication interface 910 includes connection terminals, connection circuitry, etc. for communicating with the second device 820 via the first communication path 131 . The communication interface 910 includes connection terminals, connection circuitry, etc. for communicating with the second device 820 via the second communication path 132 .

The storage unit 920 includes volatile memory and nonvolatile memory. Volatile memory may include, for example, random access memory (RAM). The non-volatile memory may include, for example, one or more of ROM (Read Only Memory), HDD (Hard Disk Drive) and SSD (Solid State Drive). The non-volatile memory stores program code (instructions) for implementing one or more functions of the first device 810 .

The processing unit 930 includes one or more processors. The one or more processors may include, for example, one or more of a CPU (Central Processing Unit), an MPU (Micro Processing Unit), and a microcontroller. The processing unit 930 implements one or more functions of the first device 810 by executing program codes (instructions) stored in the storage unit 920 .

The processing unit 930 may include one or more analog elements and/or analog circuits. Processing unit 930 may implement one or more functions of first device 810 using one or more analog elements and/or analog circuits. In this specification, the expression "A and/or B" should be interpreted as "A or B" or "A and B."

<2-12. Configuration of the second device>
The second device 820 comprises a delta-sigma modulation section 111 , an NN processing section 112 and an NN learning section 113 .

FIG. 10 is a diagram showing an example of the hardware configuration of the second device 820. As shown in FIG. The second device 820 comprises a communication interface 1010 , a storage section 1020 and a processing section 1030 .

A communication interface 1010 is an interface for communication with other devices. The communication interface 1010 includes connection terminals, connection circuits, etc. for communicating with the first device 810 via the first communication path 131 . The communication interface 1010 includes connection terminals, connection circuitry, etc. for communicating with the first device 810 via the second communication path 132 .

The communication interface 1010 may include connection terminals, connection circuits, and the like for communicating with nodes (not shown) of the core network. Additionally, communication interface 1010 may include an antenna for wirelessly communicating with first device 810 .

The storage unit 1020 includes volatile memory and nonvolatile memory. Volatile memory may include, for example, RAM. Non-volatile memory may include, for example, one or more of ROM, HDD and SSD. The non-volatile memory stores program code (instructions) for implementing one or more functions of the second device 820 .

The processing unit 1030 includes one or more processors. The one or more processors may include, for example, one or more of a CPU, MPU and microcontroller. The processing unit 1030 implements one or more functions of the second device 820 by executing program codes (instructions) stored in the storage unit 1020 .

The processing unit 1030 may include one or more analog elements and/or analog circuits. The processing unit 1030 may implement one or more functions of the second device 820 using one or more analog elements and/or analog circuits.

<2-13. Flow of Processing of Wireless Communication Device>
Next, referring to FIG. 11, the processing flow of wireless communication apparatus 800 will be described. FIG. 11 is a sequence diagram showing an example of the flow of processing by wireless communication apparatus 800. As shown in FIG.

The second device 820 executes the process of step 701 in FIG. 7 (1101). Accordingly, second device 820 transmits a second signal to first device 810 .

The first device 810 receives the second signal. After that, the first device 810 (the information transmitting unit 145 in this example) transmits the transmission-related information (the third signal in this example) to the second device 820 (1102).

The second device 820 receives the transmission-related information and executes the processing of steps 702 to 704 in FIG. 7 (1103).

The second device 820 executes the process of step 705 in FIG. 7 (1104). Accordingly, second device 820 transmits a second signal to first device 810 . After that, the processing of steps 1102 to 1104 is repeatedly executed.

It should be noted that the information transmitting section 145 of the first device 810 may transmit transmission-related information to the second device 820 according to a predetermined rule. The information transmitter 145 may periodically (ie, at predetermined time intervals) transmit the transmission-related information to the second device 820 . The information transmitter 145 may aperiodically transmit transmission-related information to the second device 820 .

The above configuration has the following effects. The first device 810 can feed back transmission related information to the second device 820 . The second device 820 can receive the transmission-related information and perform appropriate processing for transmission distortion caused during the transmission process of the second signal. For example, the second device 820 updates the first parameter of the first NN 300 with transmission related information. This allows second device 820 to transmit to first device 810 a second signal containing a component for suppressing transmission distortion. Therefore, the transmission between the two devices (the first device 810 and the second device 820) can be improved.

<2-14. Variation>
The technology according to the present disclosure is not limited to the above-described embodiments.

(1) First Modification The delta-sigma modulation section 111 may be a low-pass type device. FIG. 12 is a diagram showing an example of the configuration of the delta-sigma modulation section 111. As shown in FIG. Hereinafter, the I signal included in the first signal is referred to as "first I signal". A Q signal included in the first signal is referred to as a "first Q signal".

Delta-sigma modulation section 111 includes down converter 1210, first loop filter 1220, second loop filter 1230, first quantizer 1240, second quantizer 1250, and up converter 1260. Prepare.

The downconverter 1210 includes a first multiplier 1211a and a second multiplier 1211b.

The first multiplier 1211a multiplies the fourth signal by cosωt to generate the I component of the fourth signal. where ω=2×π×f0. Hereinafter, the I component generated from the fourth signal will be referred to as the "second I signal". First multiplier 1211 a outputs the second I signal to first loop filter 1220 .

The second multiplier 1211b multiplies the fourth signal by -sinωt to generate the Q component of the fourth signal. Hereinafter, the Q component generated from the fourth signal will be referred to as the "second Q signal". Second multiplier 1211 b outputs the second Q signal to second loop filter 1230 .

Thus, downconverter 1210 downconverts the fourth signal into a second I signal and a second Q signal.

When the sampling rate of the signal is set to 1/4 times the target frequency f0, that is, f0/4, the signal example of cosωt is [1, 0, −1, 0, 1, . The signal train of sinωt is [0, −1, 0, 1, 0, . . . ]. The symbol "/" here represents division. This simplifies the multiplication process described above. This modification may include such processing.

The first loop filter 1220 performs processing for suppressing transmission distortion included in the feedback component (that is, the second I signal). Specifically, the first loop filter 1220 uses the first I signal and the second I signal to reduce at least one of the transmission distortions that occur in the transmission process of the second signal (that is, the transmission path 120). outputs a signal that includes a first component for suppressing the part.

The first loop filter 1220 includes a first adder 1221a, a second adder 1221b, and a transfer function processing section 1222.

The first adder 1221a adds the first I signal and the second I signal. The first adder 1221 a outputs the addition result to the transfer function processing section 1222 . Here, the output of the first adder 1221a is the difference between the first I signal and the second I signal. In other words, the output of the first adder 1221a contains part of the transmission distortion component that occurs during the transmission process of the second signal.

The transfer function processing unit 1222 applies a transfer function to the output of the first adder 1221a and outputs a first component for suppressing at least part of the transmission distortion that occurs in the transmission path 120. The transfer function is a function that determines the characteristics of the delta-sigma modulation in this example, and is determined based on the desired signal transfer function, noise transfer function, and the like.

The second adder 1221 b adds the first I signal and the output of the transfer function processing section 1222 and outputs the addition result to the first quantizer 1240 .

The first quantizer 1240 is a 1-bit quantizer. First quantizer 1240 quantizes the output of second adder 1221 b by 1 bit and outputs a first quantized signal to upconverter 1260 .

The second loop filter 1230 performs processing for suppressing transmission distortion included in the feedback component (that is, the second Q signal). Specifically, the second loop filter 1230 uses the first Q signal and the second Q signal to reduce at least one of the transmission distortions that occur in the transmission process of the second signal (that is, the transmission path 120). outputs a signal containing a second component for suppressing the part.

The second loop filter 1230 includes a first adder 1231a, a second adder 1231b, and a transfer function processing section 1232.

The first adder 1231a adds the first Q signal and the second Q signal. The first adder 1231 a outputs the addition result to the transfer function processing section 1232 . Here, the output of the first adder 1231a is the difference between the first Q signal and the second Q signal. In other words, the output of the first adder 1231a contains part of the transmission distortion component that occurs in the transmission process of the second signal.

The transfer function processing unit 1232 applies a transfer function to the output of the first adder 1231a and outputs a second component for suppressing at least part of the transmission distortion that occurs in the transmission path 120. The transfer function is the function that determines the characteristics of the delta-sigma modulation in this example, and is determined based on the desired signal transfer function and noise transfer function.

The second adder 1231 b adds the first Q signal and the output of the transfer function processing section 1232 and outputs the addition result to the second quantizer 1250 .

The second quantizer 1250 is a 1-bit quantizer. Second quantizer 1250 quantizes the output of second adder 1231 b by 1 bit and outputs a second quantized signal to upconverter 1260 .

The upconverter 1260 is a 2-input, 1-output component. Upconverter 1260 comprises a first multiplier 1261 a , a second multiplier 1261 b and an adder 1262 .

The first multiplier 1261 a multiplies the first quantized signal by cos ωt and outputs the multiplication result to the adder 1262 .

The second multiplier 1261 b multiplies the second quantized signal by -sinωt and outputs the multiplication result to the adder 1262 .

The adder 1262 adds the output of the first multiplier 1261a and the output of the second multiplier 1261b to output a second signal. Thus, upconverter 1260 upconverts the first quantized signal and the second quantized signal to output a second signal.

When the sampling rate of the signal is set to 1/4 times the desired frequency f0, that is, f0/4, the signal example of cosωt is [1, 0, −1, 0, 1, . The signal train of sinωt is [0, −1, 0, 1, 0, . . . ]. The symbol "/" here represents division. This simplifies the multiplication process described above. Furthermore, since the output of the first quantizer 1240 and the output of the second quantizer 1250 are binarized signal instances (ie, either 1 or -1), the output of the adder 1262 is The output is also a binarized signal example. The processing of upconverter 1260 does not impair the quantization of the signal. This modification may include such processing.

The above configuration has the following effects. A fourth signal (output of first NN 300 ) is fed back to first loop filter 1220 and second loop filter 1230 via downconverter 1210 . As a result, the delta-sigma modulation unit 111 can pass the signal component of the target frequency f0 and perform noise shaping to shift noise in the vicinity of the frequency f0 out of the band.

Note that in the first loop filter 1220, the second adder 1221b may be omitted. In this case, the output of transfer function processing section 1222 is input to first quantizer 1240 . The transfer function in transfer function processor 1222 is set such that the output of transfer function processor 1222 includes the first I signal and the first component.

In the second loop filter 1230, the second adder 1231b may be omitted. In this case, the output of transfer function processing section 1232 is input to second quantizer 1250 . The transfer function in transfer function processor 1232 is set such that the output of transfer function processor 1232 includes the first Q signal and the second component.

(2) Second Modification The first NN 300 may be configured to output an approximation of the signal generated through part of the transmission path 120 . As an example, first NN 300 outputs an approximation of the signal generated by the second signal passing through communication path 130 . With this configuration, at least part of the transmission distortion that occurs in transmission path 120 can be suppressed.

(3) Third Modification The first NN 300 is not limited to the above example. FIG. 13 is a diagram showing an example of the configuration of the first NN 300. As shown in FIG.

The input layer 310 may include

nodes

310c and 310d to which the results of logic operations of two nodes in the input layer 310 are input. For example, logical operations may include logical AND (AND) and exclusive OR (XOR), and the like. Note that the input layer 310 may include a node to which a logical operation between a first result of the logical operation of two nodes and a second result of the logical operation of the two nodes is input. That is, the input layer 310 may include nodes to which results of logic operations of two or more nodes in the input layer 310 are input.

The above configuration has the following effects. The first NN 300 can efficiently generate nonlinear distortion such as inter-symbol interference that occurs while the second signal passes through the transmission path 120 . The accuracy of the fourth signal output by the first NN 300 is improved.

FIG. 14 is a diagram showing an example of the configuration of the first NN300. Node 310 a may have an output line (connection line) through which the current value of the second signal is output to output layer 330 without going through intermediate layer 320 .

The above configuration has the following effects. No weight is applied to the current value of the second signal because the current value of the second signal does not pass through the hidden layer 320 . The first NN 300 can efficiently reflect the residual from the current input value in the fourth signal. The accuracy of the fourth signal output by the first NN 300 is improved.

Note that the first NN 300 may be a combination of the configurations described above. Input layer 310 includes at least a node into which the current value of the second signal is input. The input layer 310 includes a node to which the past value of the second signal is input, a node to which the result of logical operation of two or more nodes in the input layer 310 is input, and a current value of the second signal. and a node having an output line that outputs to the output layer 330 without going through the intermediate layer 320 . Additionally, the first NN 300 may include various known structures.

(4) Fourth Modification The processing flow of the delta-sigma modulation device 110 is not limited to the above example. FIG. 15 is a flow chart showing an example of the processing flow of the delta-sigma modulation device 110. As shown in FIG. The flowchart in FIG. 15 is a flowchart in which step 1501 is added to the flowchart in FIG.

After step 701, the NN learning unit 113 determines whether or not a predetermined first condition is satisfied (1501). If the first condition is satisfied, the delta-sigma modulation device 110 executes the processing of

steps

702 and 703 . Accordingly, the first parameter of the first NN 300 and the second parameter of the second NN 600 are updated.

If the first condition is not satisfied, the delta-sigma modulation device 110 does not execute the processing of step 702 and the processing of step 703. That is, the first parameter of the first NN 300 and the second parameter of the second NN 600 are not updated.

The first condition is that the approximation error is larger than a predetermined first magnitude. Specifically, when the approximation error is the larger one of the absolute value of the first difference and the absolute value of the second difference, the first condition is that the approximation error is greater than a predetermined first threshold value Th1. may also be a condition that is large. When the approximation error is represented by a complex number, the first condition may be a condition regarding the absolute value of the complex number (that is, the distance from the origin on the complex number plane). The first condition may be that the absolute value of the approximation error (distance from the origin) is greater than a predetermined first distance threshold. In another example, the first condition may include a condition for the first difference and a condition for the second difference. For example, when the absolute value of the first difference exceeds a predetermined first real component threshold and/or the absolute value of the second difference exceeds a predetermined first imaginary component threshold, the NN learning unit 113 It may be determined that the first condition is satisfied.

The state of the transmission path 120 changes from moment to moment. The delta-sigma modulator 110 modulates the first parameter of the first NN 300 and the second parameter of the second NN 600 according to the current state of the transmission path 120 by using the first condition as described above. can be updated.

As described above, if the approximation error is large, this means that the output of the transmission model 410 (the approximation of the third signal) is far from the actual third signal. This means that the accuracy of the output of the transmission model 410 is low and the accuracy of the fourth signal output by the first NN 300 is also low. Therefore, it is highly necessary to reflect the current state of the transmission path 120 (in particular, information on transmission distortion) to the first NN 300 and the second NN 600 . Therefore, when the first condition is satisfied, the NN learning unit 113 determines “Yes” in step 1501 . Then, the delta-sigma modulation device 110 executes the processing of

steps

702 and 703 .

On the other hand, if the approximation error is small, this means that the output of transmission model 410 is close to the actual third signal. Therefore, the need to update the first parameter of the first NN 300 and the second parameter of the second NN 600 is low. Therefore, NN learning section 113 determines “No” in step 1501 . Delta-sigma modulator 110 then proceeds to step 704 .

The above configuration has the following effects. The delta-sigma modulator 110 executes the processing of

steps

702 and 703 only when it is highly necessary to reflect the current state of the transmission path 120 on the first NN 300 and the second NN 600 . Since the delta-sigma modulation device 110 does not execute the processing of

steps

702 and 703 in unnecessary situations, the processing load on the delta-sigma modulation device 110 can be suppressed.

After the first condition is satisfied, the delta-sigma modulation device 110 may repeatedly execute the processing of

steps

702 and 703 until a predetermined second condition is satisfied. Specifically, the parameter calculator 430 continues the process of calculating the first parameter and the second parameter until the second condition is satisfied. Parameter calculator 430 continues the process of updating the second parameter of second NN 600 until the second condition is satisfied. The NN processing unit 112 continues the process of updating the first parameter of the first NN 300 until the second condition is satisfied.

The second condition is that the approximation error is smaller than a predetermined second magnitude. The second magnitude is less than the first magnitude. Specifically, when the approximation error is the larger one of the absolute value of the first difference and the absolute value of the second difference, the second condition is that the approximation error is greater than the predetermined second threshold Th2. may also be a condition that is small. The second threshold Th2 is smaller than the first threshold Th1. If the approximation error is represented by a complex number, the second condition may be a condition regarding the absolute value of the complex number (that is, the distance from the origin on the complex number plane). The second condition may be that the absolute value of the approximation error (distance from the origin) is smaller than a predetermined second distance threshold. The second distance threshold is less than the first distance threshold. In another example, the second condition may include a condition for the first difference and a condition for the second difference. For example, when the absolute value of the first difference is below a predetermined second real component threshold and/or the absolute value of the second difference is below a predetermined second imaginary component threshold, the NN learning unit 113 It may be determined that condition 2 is established. For example, the second real component threshold is less than the first real component threshold. The second imaginary component threshold is less than the first imaginary component threshold.

(5) Fifth Modification The configuration of the NN learning unit 113 is not limited to the above example. FIG. 16 is a diagram showing an example of the configuration of the NN learning unit 113. As shown in FIG.

NN learning section 113 further includes delay adjustment section 1610 and gain adjustment section 1620 .

The delay adjusting section 1610 receives the second signal as an input signal. Delay adjustment section 1610 delays the second signal so that the timing at which the output of transmission model 410 is input to error calculation section 420 and the timing at which the third signal is input to error calculation section 420 are synchronized. Let

The gain adjustment section 1620 receives the third signal as an input signal. Gain adjustment section 1620 multiplies the third signal by the gain. Specifically, gain adjustment section 1620 regards the third signal as a complex number, and multiplies each of the I and Q signals included in the third signal by the complex gain.

The delay value in delay adjustment section 1610 and the complex gain in gain adjustment section 1620 are set so that the approximation error output from error calculation section 420 is minimized.

(6) Sixth Modification The modulation section 144 may down-convert the output of the amplifier 143 by a superheterodyne method and output an IF signal.

(7) Seventh Modification The modulation section 144 in the transmission path 120 may be omitted. In this configuration, digital downconverter 620 in transmission model 410 is omitted. Error calculator 420 calculates an approximation error between the output of transmission model 410 and the third signal (the output of amplifier 143 in this example).

(8) Eighth Modified Example The configuration of the transmission model 410 is not limited to the above example. The configuration of transmission model 410 may be changed as appropriate according to the configuration of delta-sigma modulator 110 and the configuration of transmission path 120 . For example, commonly used digital distortion compensation techniques may be applied to the first signals (I and Q signals). The configuration of transmission model 410 may be modified accordingly.

The second NN 600 may be a neural network that models the entire transmission path 120.

If the modulation section 144 has a configuration that down-converts the output of the amplifier 143 by superheterodyne, the transmission model 410 may include components corresponding to this. Transmission model 410 may include components that output the IF signal from the output of digital filter 610 in a superheterodyne fashion.

Amplifier 143 may not be modeled as second NN 600 and amplifier 143 may be modeled separately. In another example, modeling of amplifier 143 may be omitted.

The second NN 600 may be a component that models part of the transmission path 120 . For example, the second NN600 may be a neural network that outputs the same signal (fourth signal) as the first NN300. That is, the second NN 600 may output an approximation of the signal generated by the second signal passing through the communication path 130 , BPF 142 and amplifier 143 .

The second NN 600 may have the same structure as the first NN 300. The second NN 600 comprises an input layer, at least one hidden layer and an output layer. The input layer includes at least a node into which the current value of the second signal is input. The input layer further includes a node to which the past value of the second signal is input, a node to which the result of a logical operation of two or more nodes in the input layer is input, and a current value of the second signal. and a node having an output line from which is output to the output layer without going through the intermediate layer.

<<3. Second Embodiment >>
Next, a second embodiment and modifications thereof will be described with reference to FIGS. 17 to 24. FIG. In addition, about 2nd Embodiment, the same code|symbol is attached|subjected to the same component as 1st Embodiment, and detailed description of those components is abbreviate|omitted.

<3-1. Schematic Configuration of Wireless Communication Device>
FIG. 17 is a diagram showing the configuration of wireless communication apparatus 1700. As shown in FIG. Wireless communication device 1700 comprises a first device 810 and a second device 820 .

The first communication path 131 includes an optical fiber 131a. The first communication path 131 includes an E/O converter 131b at the end of the optical fiber 131a on the second device 820 side. The E/O converter 131b converts an electrical signal into an optical signal. Further, the first communication path 131 includes an O/E converter 131c at the end of the optical fiber 131a on the first device 810 side. The O/E converter 131c converts the optical signal into an electrical signal.

The second communication path 132 includes an optical fiber 132a. The second communication path 132 includes an E/O converter 132b at the end of the optical fiber 132a on the second device 820 side. Further, the second communication path 132 includes an O/E converter 132c at the end of the optical fiber 132a on the first device 810 side.

<3-2. Configuration of the first device>
A first device 810 includes an antenna 141 , a BPF 142 , an amplifier 143 , a modulator 144 and an information transmitter 145 . Information transmitting unit 145 transmits the transmission-related information to second device 820 via second communication path 132 . The transmission-related information in this example is the third signal (output of the modulation section 144), as in the first embodiment.

<3-3. Configuration of the second device>
The second device 820 includes a delta-sigma modulation section 111 , an NN processing section 112 , an NN learning section 113 and an instruction transmission section 114 . Delta-sigma modulator 111 transmits the second signal to first device 810 via first communication path 131 . The instruction transmission unit 114 transmits instruction signals (initial instruction signal, first instruction signal, and second instruction signal), which will be described later, to the first device 810 via the first communication path 131 .

<3-4. Overview of Processing Flow of Wireless Communication Device>
Next, an outline of the processing flow of wireless communication apparatus 1700 will be described. Specifically, the flow of processing in which the first device 810 transmits transmission-related information to the second device 820 will be described.

The instruction transmission unit 114 determines whether or not the condition regarding the amount of distortion that occurred in the process of transmitting the second signal is satisfied. For example, the condition is the above first condition regarding the approximation error. The instruction transmission unit 114 transmits a first instruction signal to the first device 810 when the first condition is satisfied.

In this example, the first instruction signal is a signal that instructs the first device 810 to transmit transmission-related information to the second device 820 . The first indication signal contains information about the number of times Nk that the first device 810 sends the transmission related information to the second device 820 . Nk is an integer of 1 or more. Information transmitting section 145 transmits the transmission-related information to second device 820 in response to the first instruction signal.

The instruction transmission unit 114 determines whether or not the second condition regarding the approximation error is satisfied. The instruction transmission unit 114 transmits a second instruction signal to the first device 810 when the second condition is satisfied.

In this example, the second instruction signal is a signal that instructs the first device 810 to stop sending transmission-related information to the second device 820 . Information transmitting section 145 stops transmitting the transmission-related information in response to the second instruction signal.

<3-5. Flow of Processing of Wireless Communication Device>
Next, referring to FIG. 18, the processing flow of wireless communication apparatus 1700 will be described. FIG. 18 is a sequence diagram showing an example of the flow of processing by wireless communication apparatus 1700. As shown in FIG.

The instruction transmission unit 114 transmits an initial instruction signal to the first device 810 via the first communication path 131 (1801). The initial instruction signal is an instruction signal for causing the first device 810 to transmit the transmission-related information to the second device 820 only once.

The delta-sigma modulation unit 111 transmits the second signal to the first device 810 via the first communication path 131 (1802). The information transmitter 145 transmits transmission-related information (third signal in this example) to the second device 820 via the second communication path 132 (1803).

The second device 820 receives transmission-related information. The second device 820 (that is, the NN processing unit 112 and the NN learning unit 113) executes the processing of

steps

702 and 703 in FIG. 7 (1804). Hereinafter, a series of processes of

steps

702 and 703 are collectively referred to as "learning process". NN learning section 113 transmits the approximation error calculated in the process of step 702 to instruction transmitting section 114 .

The instruction transmission unit 114 uses the approximation error to determine whether the first condition is satisfied. In this example, the instruction transmission unit 114 determines that the first condition is satisfied (1805). Accordingly, the instruction transmitter 114 transmits the first instruction signal to the first device 810 via the first communication path 131 (1806).

The delta-sigma modulation unit 111 transmits the second signal to the first device 810 via the first communication path 131 (1807).

The information transmission unit 145 transmits transmission-related information to the second device 820 via the second communication path 132 in response to the first instruction signal (1808). This is the first transmission of the transmission-related information from the time when the first device 810 received the first instruction signal.

The second device 820 executes learning processing (1809). Each time second device 820 executes the learning process, instruction sending unit 114 determines whether the second condition is satisfied.

Transmission of the second signal, transmission of transmission-related information, and learning processing are repeatedly executed. This gradually reduces the approximation error.

The delta-sigma modulator 111 then transmits the second signal to the first device 810 via the first communication path 131 (1810).

The information transmitting unit 145 transmits transmission-related information to the second device 820 via the second communication path 132 (1811). This is the Nj-th transmission of the transmission-related information from when the first device 810 received the first instruction signal. Note that Nj<Nk.

The second device 820 executes learning processing (1812). The instruction transmission unit 114 determines that the second condition is satisfied (1813). Accordingly, the instruction transmitter 114 transmits the second instruction signal to the first device 810 via the first communication path 131 (1814). Information transmitting section 145 stops transmitting the transmission-related information in response to the second instruction signal.

After that, the instruction transmission unit 114 transmits an initial instruction signal to the first device 810 via the first communication path 131 each time a predetermined waiting time Tw elapses (1815).

When the information transmitting unit 145 transmits the transmission-related information Nk times after the first device 810 receives the first instruction signal, the information transmitting unit 145 stops transmitting the transmission-related information. The instruction transmitting unit 114 transmits an initial instruction signal to the first device 810 when a predetermined waiting time Tw has elapsed since the transmission-related information was received Nk times.

In another example, the second instruction signal may further include information on the waiting time Tw. In this configuration, the information transmitting section 145 transmits the transmission-related information to the second device 820 each time the waiting time Tw elapses. The instruction transmitting unit 114 determines whether or not the first condition is satisfied each time transmission-related information is received. The instruction transmission unit 114 transmits a first instruction signal to the first device 810 when the first condition is satisfied.

The above configuration has the following effects. If the first condition is satisfied (that is, if the approximation error is large), this means that the current state of the transmission path 120 (in particular, information on transmission distortion) can be reflected in the first NN 300 and the second NN 600. This means that the transmission distortion cannot be suppressed. Under such circumstances, the first device 810 feeds back transmission-related information to the second device 820 . The second device 820 can perform a learning process using the transmission related information to update the first parameter of the first NN 300 and the second parameter of the second NN 600 . As a result, transmission distortion that occurs in the process of transmitting the second signal can be suppressed. Furthermore, a distributed MIMO (Multiple Input Multiple Output) system that increases the number of simultaneous connections and transmission capacity can be realized.

<3-6. Variation>
The technology according to the present disclosure is not limited to the above-described embodiments.

(1) First Modification The first instruction signal is not limited to the above example. The first indication signal may include information about the period Tp with which the first device 810 sends transmission related information to the second device 820 . Information transmitting section 145 transmits transmission-related information to second device 820 every time period Tp elapses in response to the first instruction signal.

The period Tp may be k1 times the learning period. Here, k1 is an integer of 1 or more. The learning period is required from the time when the second device 820 receives the transmission-related information until the second device 820 updates the first parameter of the first NN 300 and the second parameter of the second NN 600. period.

The period Tp may be defined by frames, subframes or slots defined on 3GPP. A frame is defined by multiple subframes. A subframe is defined by one or more slots. The period Tp may be defined as "k2 times the frame". Here, k2 is an integer of 1 or more. As an example, one frame is 10ms (milliseconds). The period Tp may be defined as "k3 times the subframe". Here, k3 is an integer of 1 or more. As an example, one subframe is 1 ms. The period Tp may be defined as "k4 times the slot". Here, k4 is an integer of 1 or more.

FIG. 19 is a sequence diagram showing an example of the processing flow of the wireless communication device 1700. As shown in FIG.

The instruction transmission unit 114 transmits the first instruction signal to the first device 810 (1901). Delta-sigma modulator 111 transmits the second signal to first device 810 (1902). The information transmitting unit 145 transmits transmission-related information (third signal in this example) to the second device 820 (1903). The second device 820 performs a learning process (1904). Delta-sigma modulator 111 then repeatedly transmits the second signal to first device 810 (1905).

A cycle Tp has passed since the information transmission unit 145 executed the process of step 1903 . The information transmitting unit 145 transmits transmission-related information to the second device 820 (1906). The second device 820 performs a learning process (1907). After that, the information transmitting section 145 transmits the transmission-related information to the second device 820 every time the cycle Tp elapses (1908).

The above configuration has the following effects. The first device 810 periodically feeds back transmission related information to the second device 820 . The second device 820 can periodically perform a learning process using the transmission related information to update the first parameter of the first NN 300 and the second parameter of the second NN 600 . As a result, transmission distortion that occurs in the process of transmitting the second signal can be suppressed.

(2) Second Modification Information transmitting unit 145 transmits transmission-related information to second device 820 when the conditions for transmission between first device 810 and second device 820 are met. good too. For example, the information transmitting section 145 may estimate the amount of distortion that occurred during the transmission process of the second signal based on the second signal. The information transmission unit 145 determines whether or not the third condition regarding the amount of distortion is satisfied. A third condition is that the distortion amount is greater than a predetermined magnitude. The information transmitting unit 145 transmits the transmission-related information to the second device 820 when the third condition is satisfied.

The amount of distortion may be estimated as follows. The information transmission unit 145 analyzes the frequency components of the second signal by executing Fourier transform processing or the like on the second signal. When the amount of distortion generated in the transmission process of the second signal is large, the frequency components outside the above-described desired frequency band (band from f0-fα to f0+fα) among the frequency components of the second signal are large. Considering this, the information transmitter 145 calculates the signal power of the band outside the desired frequency band.

The third condition may be a condition that the signal power in the band outside the desired frequency band is greater than the third threshold Th3. When the signal power of the band outside the desired frequency band is large, the information transmitting section 145 may determine that the distortion amount is larger than a predetermined magnitude.

The signal to be subjected to Fourier transform processing may be any one of the signals 1701 to 1703 shown in FIG.
A signal 1701 after passing through the first communication path 131 and before passing through the BPF 142
- Signal 1702 after passing through BPF 142 and before passing through amplifier 143
- Signal 1703 after passing through amplifier 143

FIG. 20 is a sequence diagram showing an example of the processing flow of the wireless communication device 1700. As shown in FIG.

The delta-sigma modulation unit 111 transmits the second signal to the first device 810 (2001). The information transmitting unit 145 estimates the amount of distortion as described above, and determines whether or not the third condition is satisfied (2002). In this example, the information transmitting unit 135 determines that the third condition is satisfied (2003). Accordingly, the information transmitting unit 145 transmits transmission-related information to the second device 820 (2004). The second device 820 performs a learning process (2005). The delta-sigma modulator 111 then repeatedly transmits the second signal to the first device 810 (2006).

After that, a first time Ta elapses from the time when the information transmission unit 145 executes the process of step 2002. The information transmitting unit 145 estimates the distortion amount as described above, and determines whether or not the third condition is satisfied (2007). In this way, the information transmitting section 145 estimates the distortion amount each time the first time Ta elapses. If the third condition is satisfied, the information transmitting section 145 transmits transmission related information to the second device 820 . On the other hand, if the third condition is not satisfied, the information transmitting section 145 does not transmit the transmission-related information to the second device 820 .

The above configuration has the following effects. The first device 810 feeds back the transmission-related information to the second device 820 when the third condition is met (ie, when the amount of distortion is relatively large). The first device 810 can feed back transmission-related information to the second device 820 in appropriate circumstances without a first indication signal from the second device 820 .

In another example, the information transmitting section 145 may estimate the amount of distortion each time the first device 810 receives the second signal.

(3) Third Modification The processing shown in FIG. 18 and the processing shown in FIG. 19 may be combined. FIG. 21 is a sequence diagram showing an example of the processing flow of wireless communication apparatus 1700. As shown in FIG.

Steps 2101 to 2107 in FIG. 21 and steps 1901 to 1907 in FIG. 19 are the same processing. Therefore, a detailed description of these steps is omitted. The information transmitting section 145 transmits transmission-related information to the second device 820 each time the period Tp elapses in response to the first instruction signal (2101) including information about the period Tp.

Every time the second device 820 executes the learning process, the instruction transmission unit 114 determines whether or not the first condition is satisfied.

After the second device 820 executes the learning process in step 2107, the instruction transmission unit 114 determines that the first condition is satisfied (2108). The instruction transmission unit 114 transmits a first instruction signal including information about the number of times Nk to the first device 810 (2109).

Steps 2110 to 2117 in FIG. 21 and steps 1807 to 1814 in FIG. 18 are the same processing. Therefore, a detailed description of these steps is omitted. In steps 2110 to 2117, the time interval at which the first device 810 transmits transmission-related information to the second device 820 is shorter than the period Tp.

After the instruction transmitting section 114 transmits the second instruction signal in step 2117, the instruction transmitting section 114 transmits to the first device 810 a first instruction signal including information about the period Tp. In response, the information transmitting section 145 transmits the transmission-related information to the second device 820 every time the cycle Tp elapses.

The above configuration has the following effects. When the first condition is met (that is, when the approximation error is large), the first device 810 feeds back the transmission-related information to the second device 820 at relatively short intervals. The second device 820 can quickly reflect the current state of the transmission path 120 to the first NN 300 and the second NN 600 . On the other hand, if the second condition is satisfied (that is, if the approximation error is small), the need to update the first parameter of the first NN 300 and the second parameter of the second NN 600 is low. Under such circumstances, the first device 810 feeds back transmission-related information to the second device 820 with a relatively long period Tp. The processing load on the second device 820 can be suppressed.

(4) Fourth Modification The processing shown in FIG. 18 and the processing shown in FIG. 20 may be combined. FIG. 22 is a sequence diagram showing an example of the processing flow of wireless communication apparatus 1700. As shown in FIG.

Steps 2201 to 2205 in FIG. 22 and steps 2001 to 2005 in FIG. 20 are the same processing. Therefore, a detailed description of these steps is omitted.

After the second device 820 executes the learning process in step 2205, the instruction transmission unit 114 determines that the first condition is satisfied (2206). The instruction transmission unit 114 transmits a first instruction signal including information about the number of times Nk to the first device 810 (2207).

Steps 2208 to 2215 in FIG. 22 and steps 1807 to 1814 in FIG. 18 are the same processing. Therefore, a detailed description of these steps is omitted. In steps 2208-2215, the first device 810 sends transmission-related information to the second device 820 each time the second device 820 sends a second signal to the first device 810. FIG. Therefore, the time interval for the first device 810 to send the transmission-related information to the second device 820 is relatively short.

After the instruction transmission unit 114 transmits the second instruction signal in step 2215, the delta-sigma modulation unit 111 transmits the second signal to the first device 810 (2216). The information transmitting unit 145 estimates the distortion amount as described above, and determines whether or not the third condition is satisfied (2217).

Every time the first device 810 receives the second signal, the information transmitting section 145 estimates the amount of distortion and determines whether the third condition is satisfied. If the third condition is satisfied, the information transmitting section 145 transmits transmission related information to the second device 820 . In this case, as described above, the instruction transmission unit 114 determines whether or not the first condition is satisfied.

On the other hand, if the third condition is not satisfied, the information transmitting section 145 does not transmit the transmission-related information to the second device 820 .

The above configuration has the following effects. In the first stage, the first device 810 feeds back transmission-related information to the second device 820 only when the third condition is met (ie, when the amount of distortion is relatively large). The second device 820 performs learning processing and determines whether the first condition is satisfied only when the first device 810 feeds back the transmission-related information. The processing load on the second device 820 can be suppressed.

Next, in the second stage, when the first condition is satisfied (that is, when the approximation error is large), the second device 820 sends the transmission-related information to the second device 820 at relatively short intervals. Instruct the first device 810 to feed back. In the second stage, the second device 820 can reflect the current state of the transmission path 120 (in particular, information on transmission distortion) to the first NN 300 and the second NN 600 in a relatively short cycle. .

(5) Fifth Modification The first device 810 and the second device 820 may be connected by one communication path (for example, one optical fiber). Transmission of the second signal may occur over an optical fiber and transmission of the transmission-related information may occur over the same optical fiber.

For example, the first device 810 and the second device 820 may be configured to communicate with each other using an optical wavelength division multiplexing scheme. Optical wavelength division multiplexing is a well-known technology, and is a method of transmitting optical signals with different wavelengths over one optical fiber.

The first device 810 and the second device 820 may be configured to communicate with each other using a polarization multiplexing scheme. Polarization multiplexing is a well-known technique, and is a method of transmitting horizontally polarized waves vibrating in the horizontal direction and vertically polarized waves in the vertical direction over one optical fiber.

The first device 810 and the second device 820 may be configured to communicate with each other using a method of time multiplexing. Time-multiplexed communication is a well-known technology, and is a method of sequentially transmitting a plurality of signals over one optical fiber so that the signals do not overlap on the time axis.

The optical fiber may be a multi-core fiber having multiple cores. In this case, the first device 810 and the second device 820 may be configured to communicate with each other using a scheme of spatial multiplexing. Spatial multiplex communication is a well-known technology, and is a method of transmitting different signals for each core.

(6) Sixth Modification FIG. Wireless communication device 2300 comprises a first device 810 and a second device 820 . Radio communication apparatus 2300 has a configuration for outputting N types of signals. Here, N is an integer of 2 or more.

Specifically, the first device 810 includes multiple antennas 141-1 to 141-N, multiple BPFs 142-1 to 142-N, and multiple amplifiers 143-1 to 143-N.

The second device 820 comprises a plurality of delta-sigma modulating sections 111-1 to 111-N. Furthermore, the first device 810 and the second device 820 are connected via a plurality of first communication paths 131-1 to 131-N. A plurality of delta-sigma modulation sections 111-1 to 111-N are connected to a plurality of antennas 141-1 to 141-N via a plurality of first communication paths 131-1 to 131-N, respectively. For example, delta-sigma modulator 111-N is connected to antenna 141-N via first communication path 131-N, BPF 142-N and amplifier 143-N.

The first device 810 has a switch 146 . The switch 146 can switch the signal to be output to the modulating section 144 . According to this configuration, the first device 810 can feed back transmission-related information (the third signal in this example) to the second device 820 for each of the N types of second signals. Thereby, it is possible to suppress the transmission distortion that occurs in the transmission process of each of the N kinds of second signals.

(7) Seventh Modification FIG. Wireless communication device 2400 comprises a first device 810 and a second device 820 . Wireless communication device 2400 has a transmission function and a reception function.

Hereinafter, the link in which signals are transmitted from the second device 820 to the terminal device 190 via the first device 810 may be referred to as a "downlink". Signals transmitted on the downlink are sometimes referred to as "downlink signals."

On the other hand, the link in which signals are transmitted from the terminal device 190 through the first device 810 to the second device 820 is sometimes called "uplink". Signals transmitted on the uplink are sometimes referred to as "uplink signals."

The second device 820 transmits downlink signals to the first device 810 via the first communication path 131 . First device 810 transmits uplink signals to second device 820 over second communication path 132 .

The first device 810 has an antenna switch 147 . The antenna switch 147 has a first terminal 147a connected to the amplifier 143, a second terminal 147b connected to the antenna 141, and a third terminal 147c connected to a low noise amplifier (LNA) 148. Prepare.

The antenna switch 147 can operate in three modes: transmission mode, reception mode and feedback mode.

In the transmission mode, the first terminal 147a and the second terminal 147b are connected. Therefore, a downlink signal is output from the antenna 141 .

In the case of the reception mode, the second terminal 147b and the third terminal 147c are connected. Accordingly, an uplink signal is transmitted to the second device 820 via the LNA 148 , the modulator 144 , the information transmitter 145 and the second communication path 132 . The second device 820 uses a reception function (not shown) to perform predetermined processing on the uplink signal.

In the feedback mode, the first terminal 147a and the third terminal 147c are connected. Therefore, the downlink signal is sent to the information transmission section 145 via the LNA 148 and modulation section 144 . The information transmitting unit 145 transmits transmission-related information to the second device 820 via the second communication path 132 at a predetermined timing. The transmission-related information in this example is information about downlink signals to be transmitted from the first device 810 to the terminal device 190 . Specifically, the transmission-related information is a signal (that is, a third signal) obtained by frequency-converting (down-converting) the downlink signal through the modulation section 144 .

In such a configuration, the radio communication apparatus 2400 may transmit downlink signals and receive uplink signals using a Time Division Duplex (TDD) scheme. TDD is a scheme in which uplink signals and downlink signals are alternately transmitted in different slots. Note that the above slots may also be referred to as "time slots".

When wireless communication device 2400 operates in the TDD scheme, instruction transmission section 114 operates as follows. For uplink slots, the second communication path 132 is used for transmission of uplink signals, while the first communication path 131 is not used. Therefore, the instruction transmitter 114 transmits the first instruction signal to the first device 810 via the first communication path 131 in the uplink slot. The instruction transmission unit 114 transmits a second instruction signal to the first device 810 via the first communication path 131 in an uplink slot.

Furthermore, the information transmission unit 145 operates as follows. For downlink slots, the first communication path 131 is used for transmission of downlink signals, while the second communication path 132 is not used. Therefore, the information transmitter 145 transmits the transmission-related information to the second device 820 via the second communication path 132 in the downlink slot.

<<4. Third Embodiment>>
Next, with reference to FIG. 25, a third embodiment will be described. In addition, about 3rd Embodiment, the same code|symbol is attached|subjected to the same component as 1st and 2nd Embodiment, and detailed description of those components is abbreviate|omitted.

<4-1. Schematic Configuration of Wireless Communication Device>
FIG. 25 is a diagram showing the configuration of wireless communication apparatus 2500. As shown in FIG. Wireless communication device 2500 comprises a first device 810 and a second device 820 . The first device 810 and the second device 820 are connected via the first communication path 131 .

<4-2. Configuration of the first device>
A first device 810 includes an antenna 141 , a BPF 142 , an amplifier 143 , an antenna 150 , a frequency conversion section 151 , a second modulation section 152 and a third modulation section 153 . Third modulating section 153 has the same configuration as modulating section 144 . The third modulation section 153 processes the analog signal (corresponding to the downlink signal) amplified by the amplifier 143 as described above, and outputs the third signal (including the I signal and the Q signal).

The second modulating section 152 receives the output of the third modulating section 153 . The second modulating section 152 performs signal modulation processing on the output of the third modulating section 153 . A general modulation scheme may be used as the signal modulation process. For example, signal modulation processing may be single carrier modulation or OFDM (Orthogonal Frequency Division Multiplexing). The frequency conversion section 151 receives the output of the second modulation section 152 . The frequency conversion section 151 up-converts the output of the second modulation section 152 . In this case, frequency conversion section 151 up-converts the output of second modulation section 152 to frequency f1 different from frequency f0. The output of frequency converter 151 is transmitted via antenna 150 .

<4-3. Configuration of the second device>
Second device 820 includes delta-sigma modulation section 111 , NN processing section 112 , NN learning section 113 , antenna 115 , demodulation section 117 and modulation section 144 . The second device 820 receives the signal output from the antenna 150 of the first device 810 via the antenna 115 . Modulator 144 processes the received signal as described above. Demodulator 117 demodulates the output of modulator 144 . The demodulation method of demodulator 117 is a method corresponding to the modulation method of second modulator 152 . Demodulator 117 outputs the demodulated third signal (including the I signal and Q signal) to NN learning section 113 .

The above configuration has the following effects. The first device 810 can feed back transmission-related information to the second device 820 via spatial transmission. The transmission-related information in this example is information about downlink signals to be transmitted from the first device 810 to the terminal device 190 . Therefore, the second device 820 can update the first parameter of the first NN 300 and the second parameter of the second NN 600 using the transmission related information. As a result, transmission distortion that occurs in the process of transmitting the second signal can be suppressed.

<<5. Fourth Embodiment>>
Next, a fourth embodiment and its modification will be described with reference to FIGS. 26 to 32. FIG. In addition, regarding the fourth embodiment, the same reference numerals are given to the same constituent elements as those of the first to third embodiments, and detailed descriptions of those constituent elements are omitted.

<5-1. Schematic Configuration of Wireless Communication Device>
FIG. 26 is a diagram showing the configuration of wireless communication apparatus 2600. As shown in FIG. Wireless communication device 2600 comprises a first device 810 and a second device 820 . The first device 810 and the second device 820 are connected via the first communication path 131 . Further, the first device 810 and the second device 820 are connected via the second communication path 132 .

<5-2. Configuration of the first device>
First device 810 includes antenna 141 , BPF 142 , amplifier 143 , modulation section 144 , information transmission section 145 , digital restoration section 149 , and NN learning section 113 .

The digital restoration unit 149 receives the output of the first communication path 131 . The digital restoration unit 149 converts the output of the first communication path 131 into a 1-bit digital signal. At this time, the transmission distortion included in the output of the first communication path 131 is shaped and a digital signal is output. Thereby, the original second signal output by the delta-sigma modulation section 111 is restored. In this way, the digital restoration unit 149 converts the restored signal of the second signal from the third signal (in this example, the signal generated through the process in which the second signal passes through the first communication path 131). to generate Hereinafter, such a restored signal of the second signal may be referred to as a "fifth signal".

The NN learning unit 113 receives the fifth signal (restored second signal) and the third signal output by the modulation unit 144 (that is, the second signal is the first communication path 131, the BPF 142, A first parameter of the first NN 300 and a second parameter of the second NN 600 are calculated using the third signal generated through the process of passing through the amplifier 143 and the modulator 144 . The NN learning unit 113 updates the second parameter of the second NN 600 to the calculated second parameter. Further, NN learning section 113 outputs the calculated first parameter to information transmitting section 145 . Information transmitter 145 transmits the first parameter to second device 820 via second communication path 132 . Therefore, the transmission-related information in this example is the first parameter. The first parameter is information used in the first NN 300 to output an approximation of the signal generated in the process of transmitting the second signal. The first parameter is therefore information about the transmission between the first device 810 and the second device 820 . Furthermore, to put it another way, the first parameter is also used to output an approximation of the transmission distortion that occurs during the transmission process of the second signal, so that the first parameter is information about the transmission distortion. It can also be said that

<5-3. Configuration of the second device>
The second device 820 comprises a delta-sigma modulation section 111 , an NN processing section 112 and an instruction transmission section 114 . Delta-sigma modulator 111 transmits the second signal to first device 810 via first communication path 131 . Instruction transmitting unit 114 transmits a first instruction signal to first device 810 via first communication path 131 . Instruction transmission unit 114 transmits a second instruction signal to first device 810 via first communication path 131 . NN processing unit 112 receives the first parameter via second communication path 132 . The NN processing unit 112 updates the first parameter of the first NN 300 to the received first parameter.

<5-4. Flow of Processing of Wireless Communication Device>
Next, referring to FIG. 27, the processing flow of wireless communication device 2600 will be described. FIG. 27 is a sequence diagram showing an example of the flow of processing by wireless communication apparatus 2600. As shown in FIG.

When the wireless communication device 2600 is activated (or the wireless communication device 2600 is reset), the instruction transmission unit 114 transmits a first instruction signal to the first device 810 (2701). In this example, the first indication signal contains information about the number of times Nk.

The delta-sigma modulation unit 111 transmits the second signal to the first device 810 (2702). The NN learning unit 113 calculates the first parameter and the second parameter (2703). The NN learning unit 113 updates the second parameter of the second NN 600 to the calculated second parameter.

The information transmitting unit 145 transmits transmission-related information (in this example, the first parameter) to the second device 820 (2704). This is the first transmission of the transmission-related information from the time when the first device 810 received the first instruction signal. A second device 820 receives the transmission related information. The NN processing unit 112 updates the first parameter of the first NN 300 to the received first parameter.

It should be noted that each time the NN learning unit 113 calculates the first parameter and the second parameter, the information transmitting unit 145 determines whether the second condition is satisfied.

After that, transmission of the second signal, calculation processing of the first and second parameters, and transmission of transmission-related information are repeatedly executed. This gradually reduces the approximation error.

The delta-sigma modulation unit 111 transmits the second signal to the first device 810 (2705). The NN learning unit 113 calculates the first parameter and the second parameter (2706).

The information transmission unit 145 transmits transmission-related information to the second device 820 (2707). This is the Nj-th transmission of the transmission-related information from when the first device 810 received the first instruction signal. Note that Nj<Nk.

At this point, the information transmission unit 145 determines that the second condition is satisfied (2708). The information transmission unit 145 transmits the notification to the second device 820 (2709). This notification is for notifying the second device 820 that the second condition has been met. In response to this notification, instruction transmitting section 114 transmits a second instruction signal to first device 810 (2710). As a result, the information transmitting unit 145 stops transmitting transmission-related information.

After that, when the waiting time Tw elapses, the instruction transmission unit 114 transmits a first instruction signal including information about the number of times Nk to the first device 810 (2711).

The above configuration has the following effects. The first device 810 repeatedly feeds back the transmission-related information (first parameter) to the second device 820 until the second condition is met. The second device 820 can update the first parameter of the first NN 300 with the transmission related information. As a result, transmission distortion that occurs in the process of transmitting the second signal can be suppressed. Furthermore, a distributed MIMO system can be implemented that increases the number of simultaneous connections and transmission capacity.

<5-5. Variation>
The technology according to the present disclosure is not limited to the above-described embodiments.

(1) First Modification FIG. 28 is a sequence diagram showing an example of the flow of processing by wireless communication apparatus 2600. In FIG.

When the wireless communication device 2600 is activated (or the wireless communication device 2600 is reset), the instruction transmission unit 114 transmits a first instruction signal to the first device 810 (2801). The first signal contains information about the period Tp. The period Tp may be defined by the learning period, as described above. Furthermore, the period Tp may be defined by frames, subframes or slots as described above.

The delta-sigma modulation unit 111 transmits the second signal to the first device 810 (2802). The NN learning unit 113 calculates the first parameter and the second parameter (2803). The NN learning unit 113 updates the second parameter of the second NN 600 to the calculated second parameter.

The information transmitting unit 145 transmits transmission-related information (in this example, the first parameter) to the second device 820 (2804). A second device 820 receives the transmission related information. The NN processing unit 112 updates the first parameter of the first NN 300 to the received first parameter.

After that, the delta-sigma modulation unit 111 repeatedly transmits the second signal to the first device 810 (2805).

A cycle Tp has passed since the NN learning unit 113 executed the process of step 2803 . The NN learning unit 113 calculates the first parameter and the second parameter (2806). The information transmitting unit 145 transmits transmission-related information to the second device 820 (2807).

The above configuration has the following effects. The first device 810 periodically feeds back transmission related information (first parameter) to the second device 820 . The second device 820 can periodically update the first parameter of the first NN 300 with the transmission related information.

Note that the NN learning unit 113 may calculate the first parameter and the second parameter each time the first device 810 receives the second signal. The information transmitting section 145 may transmit the transmission-related information to the second device 820 every time the cycle Tp elapses.

(2) Second Modification FIG. 29 is a sequence diagram showing an example of the flow of processing by wireless communication device 2600 .

When the wireless communication device 2600 is activated (or the wireless communication device 2600 is reset), the delta-sigma modulation section 111 transmits the second signal to the first device 810 (2901). The NN learning unit 113 calculates the first parameter and the second parameter (2902). NN learning section 113 outputs the approximation error to information transmitting section 145 . The information transmitter 145 uses the approximation error to determine whether the first condition is satisfied. In this example, the information transmitting section 145 determines that the first condition is satisfied (2903). In this case, the information transmitting section 145 transmits the transmission-related information (the first parameter in this example) to the second device 820 (2904).

After that, the delta-sigma modulation unit 111 repeatedly transmits the second signal to the first device 810 (2905). The NN learning unit 113 calculates the first parameter and the second parameter (2906). Each time the NN learning unit 113 calculates the first parameter and the second parameter, the information transmitting unit 145 determines whether or not the first condition is satisfied. If the first condition is satisfied, the information transmitting section 145 transmits transmission related information to the second device 820 . On the other hand, if the first condition is not satisfied, the information transmitting section 145 does not transmit the transmission-related information to the second device 820 .

The above configuration has the following effects. The first device 810 can send the transmission-related information (the first parameter) to the second device 820 when the first condition is satisfied (ie, the approximation error is large).

(3) Third Modification The processing shown in FIG. 27 and the processing shown in FIG. 28 may be combined. FIG. 30 is a sequence diagram showing an example of the flow of processing by wireless communication apparatus 2600. As shown in FIG.

Steps 3001 to 3009 in FIG. 30 and steps 2701 to 2709 in FIG. 27 are the same processing. Therefore, a detailed description of these steps is omitted. In steps 3001 to 3009, the time interval at which the first device 810 transmits the transmission-related information to the second device 820 is shorter than the period Tp.

When the instruction transmission unit 114 receives the notification in step 3009, the instruction transmission unit 114 transmits a first instruction signal including the period Tp to the first device 810 (3010). Steps 3011 to 3016 in FIG. 30 and steps 2802 to 2807 in FIG. 28 are the same processing. Therefore, a detailed description of these steps is omitted.

The above configuration has the following effects. First device 810 first transmits transmission-related information (first parameter) to second device 820 in a relatively short cycle. The second device 820 can quickly reflect the state of the transmission path 120 to the first NN 300 . On the other hand, if the second condition is met (that is, if the approximation error is small), the necessity of updating the first parameter of the first NN 300 is low. Under such circumstances, the first device 810 feeds back transmission-related information to the second device 820 with a relatively long period Tp.

Note that the processing shown in FIG. 29 may be combined with the sequence of FIG. For example, in the middle of cycle Tp (that is, between steps 3012 and 3015), information transmitting section 145 may determine whether or not the first condition is satisfied. If the first condition is satisfied, the information transmitting section 145 transmits transmission related information to the second device 820 . On the other hand, if the first condition is not satisfied, the information transmitting section 145 does not transmit the transmission-related information to the second device 820 . According to this configuration, the first device 810 can feed back transmission-related information to the second device 820 even in the middle of the cycle Tp when the approximation error becomes large.

(4) Fourth Modification The wireless communication device 2600 may have the configuration of the seventh modification of the second embodiment. That is, radio communication apparatus 2600 may operate in the TDD scheme. In this configuration, the instruction transmission unit 114 operates as follows. The instruction transmission unit 114 transmits a first instruction signal to the first device 810 via the first communication path 131 in an uplink slot. The instruction transmission unit 114 transmits a second instruction signal to the first device 810 via the first communication path 131 in an uplink slot.

Furthermore, the information transmission unit 145 operates as follows. The information transmitting unit 145 transmits the transmission-related information to the second device 820 via the second communication path 132 in downlink slots.

(5) Fifth Modified Example FIG. The components of wireless communication device 2601 are the same as those of wireless communication device 2600 in FIG.

The output of the first communication path 131 is directly input to the digital restoration section 149 . A fifth signal (restored second signal) output by the digital reconstruction unit 149 is input to the BPF 142 . The fifth signal is input to NN learning section 113 via BPF 142 , amplifier 143 and modulation section 144 . Therefore, the NN learning unit 113 uses the "fifth signal" and the "third signal generated through the process in which the fifth signal passes through the BPF 142, the amplifier 143, and the modulation unit 144", A first parameter and a second parameter are calculated.

Note that the first device 810 and the second device 820 of this example may operate according to any one of the sequences in FIGS. 27-30.

(6) Sixth Modification FIG. 32 is a diagram showing a configuration of wireless communication apparatus 3100. In FIG. Wireless communication device 3100 comprises a first device 810 and a second device 820 . The first device 810 and the second device 820 are connected via the first communication path 131 .

The first device 810 includes an antenna 141, a BPF 142, an amplifier 143, a modulation section 144, an information transmission section 145, a digital restoration section 149, an NN learning section 113, an antenna 150, and a frequency conversion section 151. , and a second modulation unit 152 .

The second device 820 includes a delta-sigma modulation section 111, an NN processing section 112, an instruction transmission section 114, an antenna 115, a modulation section 116, and a demodulation section 117.

In this example, the first device 810 transmits transmission-related information (first parameter) to the second device 820 via the antenna 150 . A second device 820 receives the transmission related information via the antenna 115 . The operation of the first device 810 and the operation of the second device 820 will be described below.

The second modulation unit 152 receives the output (first parameter) of the NN learning unit 113. Second modulation section 152 performs signal modulation processing on the output of NN learning section 113 . A general modulation scheme may be used as the signal modulation process. For example, signal modulation processing such as single carrier modulation or OFDM may be used. The frequency conversion section 151 receives the output of the second modulation section 152 . The frequency conversion section 151 up-converts the output of the second modulation section 152 . In this case, frequency conversion section 151 up-converts the output of second modulation section 152 to frequency f1 different from frequency f0. Information transmitting section 145 receives the output of frequency converting section 151 . Information transmitter 145 transmits transmission-related information via antenna 150 . The transmission-related information in this example is the output of the frequency converter 151 and is the first parameter.

A second device 820 receives the signal output from the antenna 150 via the antenna 115 . The modulation section 116 down-converts the received signal and outputs the I signal and the Q signal. The demodulator 117 demodulates the I signal and the Q signal to their original digital values (first parameters). The demodulation method of demodulator 117 is a method corresponding to the modulation method of second modulator 152 .

The demodulator 117 outputs the first parameter to the NN processor 112 . NN processing unit 112 receives the first parameter. The NN processing unit 112 updates the first parameter of the first NN 300 to the received first parameter.

It should be noted that the first device 810 and the second device 820 may operate according to any sequence shown in FIGS.

<<6. Fifth Embodiment >>
Next, a fifth embodiment will be described with reference to FIGS. 33 to 37. FIG. Although the first to fourth embodiments described above are specific embodiments, the fifth embodiment is a more generalized embodiment.

<6-1. Configuration of Wireless Communication Device>
FIG. 33 is a diagram showing the configuration of wireless communication apparatus 3200. As shown in FIG. The wireless communication device 3200 comprises a first radio access network device 3210 and a second radio access network device 3220 . Hereinafter, the first radio access network device 3210 will be referred to as "first device 3210" and the second radio access network device 3220 will be referred to as "second device 3220".

The first device 3210 is a device that performs processing related to the first physical layer. The second device 3220 is a device that performs processing related to a second physical layer higher than the first physical layer.

FIG. 34 is a diagram showing the configuration of the first device 3210. As shown in FIG. The first device 3210 comprises an acquisition section 3211 and a transmission section 3212 . Acquisition unit 3211 acquires information on transmission between first device 3210 and second device 3220 . Hereinafter, information about transmission between the first device 3210 and the second device 3220 is simply referred to as "transmission related information". The transmitter 3212 transmits the transmission related information to the second device 3220 .

The components 3211-3212 of the first device 3210 may be implemented with one or more processors and memory. The one or more processors may include, for example, one or more of a CPU, MPU and microcontroller. The memory may include volatile memory and non-volatile memory. The memory may store program code (instructions). One or more processors may implement the functionality of the first device 3210 by executing program code stored in memory.

Note that the first device 3210 may operate in the same manner as the first device 810 described above.

FIG. 35 is a diagram showing the configuration of the second device 3220. As shown in FIG. The second device 3220 comprises a receiver 3221 and a processor 3222 . The receiver 3221 receives transmission-related information from the first device 3210 . The processing unit 3222 performs processing related to communication with the first device 3210 using the transmission-related information.

The components 3221-3222 of the second device 3220 may be implemented with one or more processors and memory. The one or more processors may include, for example, one or more of a CPU, MPU and microcontroller. The memory may include volatile memory and non-volatile memory. The memory may store program code (instructions). One or more processors may implement the functionality of the second device 3220 by executing program code stored in memory.

Note that the second device 3220 may operate in the same manner as the second device 820 described above.

<6-2. Flow of Processing of Wireless Communication Device>
FIG. 36 is a flow chart showing the flow of processing of the first device 3210 . The acquisition unit 3211 acquires transmission-related information (3501). The transmitter 3212 transmits transmission-related information to the second device 3220 (3502).

FIG. 37 is a flowchart showing the processing flow of the second device 3220. FIG. The receiver 3221 receives transmission-related information from the first device 3210 (3601). The processing unit 3222 uses the transmission-related information to perform processing related to communication with the first device 3210 (3602).

The above configuration improves transmission between the first device 3210 and the second device 3220 by exchanging transmission related information between the first device 3210 and the second device 3220. be able to.

<6-3. Variation>
The technology according to the present disclosure is not limited to the above-described embodiments.

The transmission-related information may be information generated during the transmission process of the signal transmitted from the second device 3220 to the first device 3210.

The first device 3210 may be configured to transmit the signal transmitted from the second device 3220 to the first device 3210 as a downlink signal to the terminal device (not shown). In this configuration, for example, the transmission related information may be information about downlink signals to be transmitted from the first device 3210 to the terminal device. The transmission-related information may be a signal obtained by frequency-converting the downlink signal.

The transmission-related information may include information about distortion caused during the transmission process of the signal transmitted from the second device 3220 to the first device 3210.

The transmission related information may be parameters of a neural network that outputs an approximation of the signal generated through at least part of the transmission process of the signal transmitted from the second device 3220 to the first device 3210. . For example, the transmission related information may be the parameters of the first NN 300 in the above embodiments.

The transmission unit 3212 may control transmission of transmission-related information according to the instruction signal transmitted from the second device 3220. For example, the indication signal may include the first indication signal and the second indication signal in the embodiments described above.

The transmission unit 3212 may transmit transmission-related information to the second device 3220 when a predetermined condition regarding transmission between the first device 3210 and the second device 3220 is met. The predetermined condition may be a condition regarding the amount of distortion that occurs during the transmission process of the signal transmitted from the second device 3220 to the first device 3210. FIG. The predetermined condition may be the first condition in the embodiment described above. The predetermined condition may be the third condition in the embodiment described above.

The first device 3210 and the second device 3220 may be configured to operate in TDD mode. In this case, the transmitter 3212 may transmit the transmission-related information to the second device 3220 in downlink slots.

The second device 3220 may further include a transmission unit that transmits an instruction signal regarding transmission of transmission-related information to the first device 3210. For example, the indication signal may include the first indication signal and the second indication signal in the embodiments described above.

The transmission unit of the second device 3220 may transmit an instruction signal to the first device 3210 when a predetermined condition regarding transmission between the first device 3210 and the second device 3220 is satisfied. The predetermined conditions may include the first condition and the second condition in the embodiment described above.

The first device 3210 and the second device 3220 may be configured to operate in TDD mode. In this case, the transmitting section of the second device 3220 may transmit an instruction signal to the first device 3210 in an uplink slot.

The processing related to communication with the first device 3210 may include delta-sigma modulation. Processing unit 3222 may perform delta-sigma modulation using the transmission related information. The processing unit 3222 may transmit the signal output by the delta-sigma modulation to the first device 3210.

The processing for the first physical layer may include one or more of filtering processing, amplification processing, and frequency conversion processing. The processing related to the first physical layer is not limited to this example.

The processing related to the second physical layer may include modulation processing. The modulation process may include delta-sigma modulation. The processing related to the second physical layer may be other processing as long as it is higher-level processing than the processing related to the first physical layer.

The first device 3210 and the second device 3220 conform to the technical specifications of 3GPP and may conform to the technical specifications of the O-RAN (Open RAN) Alliance.

It should be noted that the embodiments and modifications described above are merely examples, and the scope of the technical idea of the present disclosure is not limited to the above configurations. Other aspects conceivable within the scope of the technical concept of the present disclosure are also included within the scope of the present disclosure.

The above-described embodiments and modifications may be applied to systems other than RoF systems using digital sigma modulation. For example, the embodiments and variations described above may be applied to analog RoF systems. An analog RoF system is a known system that converts an analog signal to an optical signal and transmits the optical signal over an optical fiber.

The processing steps shown in flowcharts or sequence diagrams do not necessarily have to be executed in the order shown. The processing steps may be performed in a different order than that shown, and two or more processing steps may be performed in parallel. Also, some processing steps may be deleted and further processing steps may be added.

The arrows in the drawings are examples showing the direction of signal (data) flow from one component to another, and do not exclude bi-directional communication between the above two components.

As used herein, "transmitting X to Y" is not limited to transmitting X directly to Y, but indirectly transmitting X to Y (i.e., X transmitting to another node and X is sent from that other node to Y). Similarly, "receiving X from Y" is not limited to receiving X directly from Y, but indirectly receiving X from Y (i.e., X transmitted from Y to another node). and X is received from the other node). Accordingly, a repeater may be placed between the first device 810 and the second device 820 . A repeater may relay the transmission of the second signal and/or the transmission of the transmission related information.

The functions of the apparatus described herein may be implemented in software, hardware, or a combination of software and hardware. Program codes (instructions) constituting software may be stored, for example, in a computer-readable recording medium inside or outside each device, and may be read into a memory and executed by a processor at the time of execution. Also, a non-transitory computer readable medium recording the program code may be provided.

Some or all of the above embodiments and modifications can also be described as the following supplementary notes, but are not limited to the following.

(Appendix 1)
A first radio access network device for processing on a first physical layer,
an acquisition unit for acquiring information on transmission between the first radio access network device and a second radio access network device that performs processing on a second physical layer higher than the first physical layer;
a transmitting unit configured to transmit the information regarding the transmission to the second radio access network device;
A first radio access network device comprising:

(Appendix 2)
The first radio of Claim 1, wherein said information relating to said transmission is information generated in the course of transmission of a signal transmitted from said second radio access network device to said first radio access network device. Access network equipment.

(Appendix 3)
3. The first radio access network device according to claim 2, wherein said information on said transmission is information on downlink signals to be transmitted from said first radio access network device to a terminal device.

(Appendix 4)
The first radio access network apparatus according to appendix 3, wherein the information about the transmission is a signal obtained by frequency-converting the downlink signal.

(Appendix 5)
3. The first radio access network apparatus according to clause 2, wherein said information relating to said transmission includes information relating to distortion caused in said transmission process.

(Appendix 6)
Said information about said transmission is a neural output approximation of a signal generated through at least part of a transmission process of a signal transmitted from said second radio access network device to said first radio access network device. A first radio access network device according to clause 1, which is a parameter of a network.

(Appendix 7)
The first radio access network device according to appendix 1, wherein the transmission unit controls the transmission of the information regarding the transmission according to an instruction signal transmitted from the second radio access network device.

(Appendix 8)
8. The claim of claim 7, wherein said indication signal comprises a first indication signal that instructs said first radio access network device to send said information regarding said transmission to said second radio access network device. A first radio access network device.

(Appendix 9)
9. The first method of claim 8, wherein the first indication signal includes information about the number of times the first radio access network device transmits the information regarding the transmission to the second radio access network device. radio access network equipment;

(Appendix 10)
9. The first method of claim 8, wherein the first indication signal includes information about a periodicity with which the first radio access network device transmits the information regarding the transmission to the second radio access network device. radio access network equipment;

(Appendix 11)
11. The first radio access network apparatus according to clause 10, wherein said periodicity is defined by frames, subframes or slots.

(Appendix 12)
The period is a training neural network that outputs an approximation of a signal generated through at least part of a transmission process of a signal transmitted from the second radio access network device to the first radio access network device. 11. The first radio access network device according to clause 10, defined by a time period.

(Appendix 13)
Clause 7, wherein said indication signal comprises a second indication signal instructing said first radio access network device to stop sending said information relating to said transmission to said second radio access network device. A first radio access network device according to .

(Appendix 14)
The first radio access network device according to appendix 1, wherein the transmitting unit transmits the information regarding the transmission to the second radio access network device when a predetermined condition regarding the transmission is satisfied.

(Appendix 15)
15. The first radio access network device according to appendix 14, wherein the predetermined condition is a condition relating to an amount of distortion occurring in a transmission process of a signal transmitted from the second radio access network device to the first radio access network device. radio access network equipment;

(Appendix 16)
The first radio access network device and the second radio access network device are configured to operate in a Time Division Duplex (TDD) scheme,
16. The first radio access network device according to any one of appendices 1 to 15, wherein said transmitting unit transmits said information regarding said transmission to said second radio access network device in a downlink slot.

(Appendix 17)
A second radio access network device that performs processing related to a second physical layer higher than the first physical layer,
a receiving unit for receiving information on transmission between a first radio access network device that performs processing related to the first physical layer and the second radio access network device;
a processing unit that performs processing related to communication with the first radio access network device using the information related to the transmission;
a second radio access network device comprising:

(Appendix 18)
18. The second radio of clause 17, wherein said information relating to said transmission is information generated in the course of transmission of signals transmitted from said second radio access network device to said first radio access network device. Access network equipment.

(Appendix 19)
19. The second radio access network device according to claim 18, wherein said information regarding said transmission is information regarding downlink signals to be transmitted from said first radio access network device to a terminal device.

(Appendix 20)
20. The second radio access network apparatus according to appendix 19, wherein said information about said transmission is a signal obtained by frequency converting said downlink signal.

(Appendix 21)
19. The second radio access network device according to clause 18, wherein said information relating to said transmission comprises information relating to distortion caused in said transmission process.

(Appendix 22)
Said information about said transmission is a neural output approximation of a signal generated through at least part of a transmission process of a signal transmitted from said second radio access network device to said first radio access network device. 18. The second radio access network device according to clause 17, which is a network parameter.

(Appendix 23)
18. The second radio access network device according to claim 17, further comprising: a transmitting unit configured to transmit an indication signal regarding transmission of said information regarding said transmission to said first radio access network device.

(Appendix 24)
wherein the transmission unit transmits the instruction signal to the first radio access network device when a predetermined condition regarding the transmission is satisfied;
24. A second radio access network device according to clause 23.

(Appendix 25)
The predetermined condition is a condition regarding the amount of distortion caused in the transmission process of the signal transmitted from the second radio access network device to the first radio access network device,
24. A second radio access network device according to clause 23.

(Appendix 26)
24. The claim of claim 23, wherein said indication signal comprises a first indication signal for instructing said first radio access network device to send said information regarding said transmission to said second radio access network device. A second radio access network device.

(Appendix 27)
27. The second of clause 26, wherein said first indication signal comprises information about the number of times said first radio access network device transmits said information regarding said transmission to said second radio access network device. radio access network equipment;

(Appendix 28)
27. The second of clause 26, wherein the first indication signal includes information about a period at which the first radio access network device transmits the information regarding the transmission to the second radio access network device. radio access network equipment;

(Appendix 29)
29. The second radio access network device according to clause 28, wherein said periodicity is defined by frames, subframes or slots.

(Appendix 30)
The period is a training neural network that outputs an approximation of a signal generated through at least part of a transmission process of a signal transmitted from the second radio access network device to the first radio access network device. 29. The second radio access network device according to clause 28, defined by a time period.

(Appendix 31)
Note 23, wherein said indication signal comprises a second indication signal instructing said first radio access network device to stop sending said information relating to said transmission to said second radio access network device. 2. A second radio access network device according to .

(Appendix 32)
The first radio access network device and the second radio access network device are configured to operate in a Time Division Duplex (TDD) scheme,
32. The second radio access network device according to any one of appendices 23 to 31, wherein said transmitting unit transmits said instruction signal to said first radio access network device in an uplink slot.

(Appendix 33)
33. The second radio access network device according to any one of the clauses 17-32, wherein said processing relating to said communication with said first radio access network device comprises delta-sigma modulation.

(Appendix 34)
34. The second radio access network device according to appendix 33, wherein the processing unit transmits the signal output by the delta-sigma modulation to the first radio access network device.

(Appendix 35)
a first radio access network device for processing on a first physical layer;
a second radio access network device that performs processing related to a second physical layer higher than the first physical layer;
with
The first radio access network device,
obtaining information regarding transmissions between the first radio access network device and the second radio access network device;
sending said information regarding said transmission to said second radio access network device;
The second radio access network device,
receiving said information relating to said transmission;
using the information relating to the transmission to perform processing relating to communication with the first radio access network device;
wireless communication device.

(Appendix 36)
A method in a first radio access network device for processing on a first physical layer, comprising:
obtaining information on transmission between the first radio access network device and a second radio access network device performing processing on a second physical layer above the first physical layer;
sending said information regarding said transmission to said second radio access network device;
method including.

(Appendix 37)
A method in a second radio access network device for processing on a second physical layer above the first physical layer, comprising:
receiving information about transmissions between a first radio access network device performing processing for the first physical layer and the second radio access network device;
performing processing related to communication with the first radio access network device using the information related to the transmission;
method including.

(Appendix 38)
relating to transmission between a first radio access network device performing processing relating to a first physical layer and a second radio access network device performing processing relating to a second physical layer higher than said first physical layer obtaining information;
sending said information regarding said transmission to said second radio access network device;
A computer-readable non-transitory recording medium that records a program that causes a processor to execute

(Appendix 39)
relating to transmission between a first radio access network device performing processing relating to a first physical layer and a second radio access network device performing processing relating to a second physical layer higher than said first physical layer receiving information;
performing processing related to communication with the first radio access network device using the information related to the transmission;
A computer-readable non-transitory recording medium that records a program that causes a processor to execute

Appropriate information can be sent or received to improve the transmission between the two communication devices.

110: delta-sigma modulation device 111: delta-sigma modulation unit 112: neural network processing unit 113: neural network learning unit 810: first device 820: second device 3210: first radio access network device 3220: second Radio access network equipment

Claims

A first radio access network device for processing on a first physical layer,
an acquisition unit for acquiring information on transmission between the first radio access network device and a second radio access network device that performs processing on a second physical layer higher than the first physical layer;
a transmitting unit configured to transmit the information regarding the transmission to the second radio access network device;
A first radio access network device comprising:
The first radio access network device according to claim 1, wherein said information relating to said transmission is information generated in the course of transmission of signals transmitted from said second radio access network device to said first radio access network device. radio access network equipment;
The first radio access network device according to claim 2, wherein said information on said transmission is information on downlink signals to be transmitted from said first radio access network device to a terminal device.
The first radio access network apparatus according to claim 3, wherein said information regarding said transmission is a signal obtained by frequency-converting said downlink signal.
The first radio access network device according to claim 2, wherein said information about said transmission includes information about distortion caused in said transmission process.
Said information about said transmission is a neural output approximation of a signal generated through at least part of a transmission process of a signal transmitted from said second radio access network device to said first radio access network device. The first radio access network device according to claim 1, being a network parameter.
The first radio access network device according to claim 1, wherein said transmission unit controls said transmission of said information regarding said transmission according to an instruction signal transmitted from said second radio access network device.
8. The indication signal according to claim 7, wherein said indication signal comprises a first indication signal for instructing said first radio access network device to send said information regarding said transmission to said second radio access network device. a first radio access network device of .
9. The first of claim 8, wherein said first indication signal comprises information about the number of times said first radio access network device transmits said information regarding said transmission to said second radio access network device. radio access network equipment.
10. The first of claim 8, wherein the first indication signal comprises information about the periodicity with which the first radio access network device sends the information regarding the transmission to the second radio access network device. radio access network equipment.
The first radio access network device according to claim 10, wherein said periodicity is defined by frames, subframes or slots.
The period is a training neural network that outputs an approximation of a signal generated through at least part of a transmission process of a signal transmitted from the second radio access network device to the first radio access network device. 11. The first radio access network device according to claim 10, defined by a time period.
3. The indication signal comprises a second indication signal instructing the first radio access network device to stop sending the information regarding the transmission to the second radio access network device. 8. A first radio access network device according to claim 7.
The first radio access network device according to claim 1, wherein said transmitting unit transmits said information regarding said transmission to said second radio access network device when a predetermined condition regarding said transmission is satisfied.
15. The first according to claim 14, wherein said predetermined condition is a condition relating to the amount of distortion occurring in a transmission process of a signal transmitted from said second radio access network device to said first radio access network device. radio access network equipment.
The first radio access network device and the second radio access network device are configured to operate in a Time Division Duplex (TDD) scheme,
The first radio access network device according to any one of claims 1 to 15, wherein said transmitter transmits said information on said transmission to said second radio access network device in a downlink slot.
A second radio access network device that performs processing related to a second physical layer higher than the first physical layer,
a receiving unit for receiving information on transmission between a first radio access network device that performs processing related to the first physical layer and the second radio access network device;
a processing unit that performs processing related to communication with the first radio access network device using the information related to the transmission;
a second radio access network device comprising:
18. The second radio access network device according to claim 17, wherein said information relating to said transmission is information generated in the course of transmission of signals transmitted from said second radio access network device to said first radio access network device. radio access network equipment;
The second radio access network device according to claim 18, wherein said information on said transmission is information on downlink signals to be transmitted from said first radio access network device to a terminal device.
The second radio access network device according to claim 19, wherein said information about said transmission is a signal obtained by frequency-converting said downlink signal.
The second radio access network device according to claim 18, wherein said information relating to said transmission comprises information relating to distortion caused during said transmission process.
Said information about said transmission is a neural output approximation of a signal generated through at least part of a transmission process of a signal transmitted from said second radio access network device to said first radio access network device. 18. The second radio access network device according to claim 17, being a network parameter.
18. The second radio access network device according to claim 17, further comprising: a transmitting unit configured to transmit an indication signal regarding transmission of said information regarding said transmission to said first radio access network device.
wherein the transmission unit transmits the instruction signal to the first radio access network device when a predetermined condition regarding the transmission is satisfied;
A second radio access network device according to claim 23.
The predetermined condition is a condition regarding the amount of distortion caused in the transmission process of the signal transmitted from the second radio access network device to the first radio access network device,
A second radio access network device according to claim 23.
24. The method of claim 23, wherein said indication signal comprises a first indication signal for instructing said first radio access network device to send said information regarding said transmission to said second radio access network device. a second radio access network device of .
27. The second of claim 26, wherein said first indication signal comprises information about the number of times said first radio access network device transmits said information regarding said transmission to said second radio access network device. radio access network equipment.
27. The second of claim 26, wherein the first indication signal comprises information about a periodicity with which the first radio access network device sends the information regarding the transmission to the second radio access network device. radio access network equipment.
The second radio access network device according to claim 28, wherein said periodicity is defined by frames, subframes or slots.
The period is a training neural network that outputs an approximation of a signal generated through at least part of a transmission process of a signal transmitted from the second radio access network device to the first radio access network device. 29. The second radio access network device according to claim 28, defined by a time period.
4. The indication signal comprises a second indication signal instructing the first radio access network device to stop sending the information regarding the transmission to the second radio access network device. 24. A second radio access network device according to 23.
The first radio access network device and the second radio access network device are configured to operate in a Time Division Duplex (TDD) scheme,
The second radio access network device according to any one of claims 23 to 31, wherein said transmitting unit transmits said instruction signal to said first radio access network device in an uplink slot.
The second radio access network device according to any one of claims 17-32, wherein said processing relating to said communication with said first radio access network device comprises delta-sigma modulation.
The second radio access network device according to claim 33, wherein said processing unit transmits the signal output by said delta-sigma modulation to said first radio access network device.
a first radio access network device for processing on a first physical layer;
a second radio access network device that performs processing related to a second physical layer higher than the first physical layer;
with
The first radio access network device,
obtaining information regarding transmissions between the first radio access network device and the second radio access network device;
sending said information about said transmission to said second radio access network device;
The second radio access network device,
receiving said information relating to said transmission;
using the information relating to the transmission to perform processing relating to communication with the first radio access network device;
wireless communication device.
A method in a first radio access network device for processing on a first physical layer, comprising:
obtaining information on transmission between the first radio access network device and a second radio access network device performing processing on a second physical layer above the first physical layer;
sending said information regarding said transmission to said second radio access network device;
method including.
A method in a second radio access network device for processing on a second physical layer above the first physical layer, comprising:
receiving information about transmissions between a first radio access network device performing processing for the first physical layer and the second radio access network device;
performing processing related to communication with the first radio access network device using the information related to the transmission;
method including.
relating to transmission between a first radio access network device performing processing relating to a first physical layer and a second radio access network device performing processing relating to a second physical layer higher than said first physical layer obtaining information;
sending said information regarding said transmission to said second radio access network device;
A computer-readable non-transitory recording medium that records a program that causes a processor to execute
relating to transmission between a first radio access network device performing processing relating to a first physical layer and a second radio access network device performing processing relating to a second physical layer higher than said first physical layer receiving information;
performing processing related to communication with the first radio access network device using the information related to the transmission;
A computer-readable non-transitory recording medium that records a program that causes a processor to execute