Reception device

Abstract

The present disclosure pertains to a reception device. This reception device receives a data signal from a transmission device, and is provided with a processor and a memory storing a program to be executed by the processor. The processor is configured to perform: a process of setting, as a first dataset, a group of signal points in a received data signal which are determined to have a large degree of distortion influence according to a predetermined criterion; a process of performing machine learning based on the first dataset to acquire a first learning model; a process of setting, as a second dataset, a group of signal points determined to have a small degree of distortion influence according to the predetermined criterion; a process of performing machine learning based on the second dataset to acquire a second learning model; a process of determining the magnitude of the degree of distortion influence superimposed on signal points included in the received data signal according to the predetermined criterion; a process of compensating the signal points on the basis of the first learning model if the degree of distortion influence is determined to be large; a process of compensating the signal points on the basis of the second learning model if the degree of distortion influence is determined to be small; and a process of demodulating the data signal by using the compensated signal points.

Description

Receiving device

[0001] The present disclosure relates to a receiving device.

[0002] In order to improve communication quality, there is a technology that outputs the original signal by performing compensation based on the signal that has changed during the communication process. For example, Non-Patent Document 1 discloses a method for improving demodulation performance by performing likelihood calculation based on the signal affected by amplifier distortion and information on the distortion constellation. The distortion constellation used in this method is identified based on the device specifications of the amplifier installed in the transmitting station.

[0003] Fukuzono, Kuriyama, Uchida, Yoshioka, and Miyagi, “Log-Likelihood Ratio for Nonlinear Distortion Constellations in High-Frequency Band Single-Carrier Transmission,” IEICE Society Conference B-5-57, August 31, 2021.

[0004] However, in the above-described method, when the magnitude of signal change differs depending on the position of the signal point, if all signal points are demodulated using the same compensation method, there is a problem that the compensation accuracy varies depending on the position of the signal point.

[0005] In order to solve the above-mentioned problems, an object of the present disclosure is to provide a receiving device that can perform appropriate compensation at all signal points even when the magnitude of signal changes differs depending on the position of the signal points.

[0006] An aspect of the present disclosure is a receiving device that receives a data signal from a transmitting device, the receiving device including a processor and a memory that stores a program to be executed by the processor, wherein the processor is configured to perform the following processes: designating a signal point group, among the received data signal, that is determined to have a large degree of distortion influence according to a predetermined criterion as a first data set; performing machine learning based on the first data set to obtain a first learning model; designating a signal point group, among the received data signal, that is determined to have a small degree of distortion influence according to the predetermined criterion as a second data set; performing machine learning based on the second data set to obtain a second learning model; determining, according to the predetermined criterion, the magnitude of the degree of distortion influence to be superimposed on signal points included in the received data signal; if the degree of distortion influence is determined to be large, compensating the signal points based on the first learning model; and if the degree of distortion influence is determined to be small, compensating the signal points based on the second learning model and demodulating the data signal using the compensated signal points.

[0007] According to an aspect of the present disclosure, even if the magnitude of signal change differs depending on the position of the signal point, appropriate compensation can be performed at all signal points.

[0008] FIG. 1 is a diagram illustrating an example configuration of a wireless communication system according to a first embodiment of the present disclosure. FIG. 2 is a diagram illustrating a hardware configuration of a receiving device according to a first embodiment of the present disclosure. FIG. 3 is a diagram illustrating data signals before and after a signal change according to a first embodiment of the present disclosure. FIG. 4 is a diagram illustrating data signals before and after compensation according to a first embodiment of the present disclosure. FIG. 5 is a diagram illustrating a method for determining a predetermined criterion in judgment according to a second embodiment of the present disclosure. FIG. 6 is a diagram illustrating data signals before and after a signal change according to a second embodiment of the present disclosure. FIG. 7 is a diagram illustrating data signals before and after compensation according to a second embodiment of the present disclosure.

[0009] 1 is a diagram illustrating a configuration example of a wireless communication system according to a first embodiment of the present disclosure. The wireless communication system 100 includes a transmitting device 20. The transmitting device 20 is a device that transmits a data signal to a receiving device 40.

[0010] The transmitting device 20 includes a data generating unit 22. The data generating unit 22 generates a data signal for information to be transmitted to the receiving device 40, and transmits the data signal to a modulating unit .

[0011] The modulator 24 modulates the data signal and transmits it to the RF circuit unit 26. The RF circuit unit 26 performs transmission processing on the modulated data signal. The transmission processing includes, for example, converting a digitally modulated data signal into an analog signal, quadrature modulation of an I signal and a Q signal, or amplifying the data signal using an amplifier. The RF circuit unit 26 transmits the data signal that has undergone transmission processing to the receiving device 40.

[0012] The RF circuit unit 42 of the receiving device 40 performs reception processing of the transmitted data signal. The reception processing includes, for example, amplifying the data signal using an amplifier, demodulating the data signal into I and Q signals, or digitizing a digitized data signal. The RF circuit unit 42 transmits the data signal that has undergone reception processing to the determination unit 44.

[0013] The determination unit 44 determines the magnitude of the distortion influence superimposed on the signal points included in the received and processed data signal based on a predetermined criterion, which will be described later. If the distortion influence is determined to be large, the determination unit 44 transmits the corresponding data to the compensation unit 46a. If the distortion influence is determined to be small, the determination unit 44 transmits the corresponding data to the compensation unit 46b.

[0014] Here, the distortion influence refers to the magnitude of change in data due to transmission and reception processes. The distortion influence is caused, for example, by imperfections in the RF circuit or random noise. Imperfections in the RF circuit include, for example, nonlinear distortion, IQ imbalance, or phase noise of the amplifier. The data may also be a collection of multiple known data signals for one frame.

[0015] The compensator 46a performs first compensation, which is compensation suitable for cases where the degree of influence of distortion is large, and transmits the compensated data to the demodulator 48. This first compensation is performed based on a first learning model acquired by machine learning performed in a preprocessor 60, which will be described later in detail.

[0016] The compensator 46b performs second compensation, which is compensation suitable for cases where the degree of influence of distortion is small, and transmits the compensated data to the demodulator 48. This second compensation is performed based on a second learning model acquired by machine learning performed in a preprocessor 60, which will be described later in detail.

[0017] The demodulator 48 demodulates the data signal using the signal points compensated by the compensators 46a and 46b.

[0018] The acquisition of a model required for compensation will now be described. The wireless communication system 100 includes a preprocessing device 60. The preprocessing device 60 has a dataset generation unit 62a. The dataset generation unit 62a generates a first dataset required to acquire a learning model used for compensation, and transmits the first dataset to the machine learning unit 64a.

[0019] The first data set may be generated by, for example, selecting a signal point group from among the data signals received by the receiving device 40 that is determined to have a large degree of distortion influence according to a predetermined criterion as the first data set.

[0020] The machine learning unit 64a performs machine learning based on the first data set to obtain a first learning model. The machine learning unit 64a also transmits the first learning model to the compensation unit 46a. As described above, the compensation unit 46a performs compensation based on the first learning model.

[0021] The preprocessing device 60 also includes a data set generation unit 62b. The data set generation unit 62b generates a second data set required to obtain a learning model used for compensation, and transmits the data set to the machine learning unit 64b.

[0022] The second data set may be generated by, for example, selecting a signal point group from the data signals received by the receiving device 40 that is determined to have a small degree of distortion influence according to a predetermined standard as the second data set.

[0023] The machine learning unit 64b performs machine learning based on the second data set to obtain a second learning model. The machine learning unit 64b also transmits the second learning model to the compensation unit 46b. As described above, the compensation unit 46b performs compensation based on the second learning model.

[0024] As described above, in the present disclosure, different compensation is performed based on the magnitude of the distortion influence at the corresponding signal point. When the magnitude of signal variation differs depending on the position of the signal point, demodulating all signal points using the same compensation method can result in a problem of varying compensation accuracy depending on the position of the signal point. According to the aspects of the present disclosure, appropriate compensation can be performed at all signal points even when the magnitude of signal variation differs depending on the position of the signal point.

[0025] 2 is a diagram illustrating a hardware configuration of a receiving device according to the first embodiment of the present disclosure. Each function of the receiving device 40 may be partially or entirely configured by hardware such as a programmable logic device (PLD) or a field programmable gate array (FPGA), or may be configured as a program executed by a processor such as a CPU.

[0026] For example, the receiving device 40 can be realized using a computer and a program, and the program can be recorded on a storage medium or provided via a network.

[0027] 2, the receiving device 40 has an input unit 400, an output unit 401, a communication unit 402, a CPU 403, a memory 404, and an HDD 405 connected via a bus 406, and functions as a computer. The receiving device 40 is also capable of inputting and outputting data to and from a computer-readable storage medium 407.

[0028] The input unit 400 is, for example, a keyboard and a mouse, etc. The output unit 401 is, for example, a display device such as a display.

[0029] The communication unit 402 is, for example, a communication interface that communicates with a wireless device to be controlled.

[0030] The CPU 403 controls each component of the receiving device 40 and performs predetermined processing, etc. The memory 404 and HDD 405 store data, etc.

[0031] The storage medium 407 is capable of storing programs and the like that cause the receiving device 40 to execute the functions of the receiving device 40. Note that the architecture that configures the receiving device 40 is not limited to the example shown in FIG.

[0032] 3 is a diagram illustrating a data signal before and after a signal change according to the first embodiment of the present disclosure. Here, a predetermined criterion when two patterns of learning are performed based on the magnitude of the distortion influence degree will be described.

[0033] Data signal 2 is a diagram showing signal points based on original data generated by transmitting device 20. Data signal 2 is changed by transmission processing and reception processing to become data signal 4. Here, data signal 4 is assumed to be a diagram showing signal points based on data after it has changed due to the influence of imperfections in the RF circuit.

[0034] The data signal 4 is classified into two regions 5a and 5b based on the magnitude of the distortion influence. Region 5a is a region that includes signal points that are highly influenced by distortion, and region 5b is a region that includes signal points that are less influenced by distortion.

[0035] That is, in this embodiment, data corresponding to signal points included in region 5a must be compensated appropriately when the degree of distortion influence is large, and data corresponding to signal points included in region 5b must be compensated appropriately when the degree of distortion influence is small.

[0036] 4 is a diagram illustrating a data signal before and after compensation according to the first embodiment of the present disclosure. First, receiving device 40 receives data signal 4. Next, receiving device 40 determines the magnitude of the distortion influence degree for data corresponding to each signal point of data signal 4.

[0037] Next, receiving device 40 performs first compensation 6a on data corresponding to signal points included in region 5a, i.e., data corresponding to signal points with a large degree of distortion influence, and performs second compensation 6b on data corresponding to signal points included in region 5b, i.e., data corresponding to signal points with a small degree of distortion influence.

[0038] Furthermore, the receiving device 40 performs demodulation based on the compensated data, so that the receiving device 40 can obtain a data signal 2a that matches the data signal 2.

[0039] 5 is a diagram illustrating a method for determining a predetermined criterion for determination according to Embodiment 1 of the present disclosure. In this embodiment, an example of determining a predetermined determination value that serves as the predetermined criterion when determination is made based on the amplitude value at each signal point is shown.

[0040] Here, the amplitude value is a value indicating the amplitude of the previous and next signal points that has changed due to the influence of imperfections in the RF circuit. Furthermore, if the amplitude value at the corresponding signal point is equal to or greater than a predetermined judgment value, the judgment unit 44 judges that the degree of influence of distortion is large. Furthermore, if the amplitude value at the corresponding signal point is smaller than the predetermined judgment value, the judgment unit 44 judges that the degree of influence of distortion is small.

[0041] In data signal 2, the signal point where the amplitude value is maximum is signal point 8a, and the signal point where the amplitude value is minimum is signal point 8b. In this case, the maximum amplitude value Amax occurring in data signal 2 is the amplitude value at signal point 8a, and the minimum amplitude value Amin occurring in data signal 2 is the amplitude value at signal point 8b.

[0042] In this case, the predetermined reference may be a predetermined judgment value. The predetermined judgment value may be determined based on the maximum amplitude value Amax and the minimum amplitude value Amin. For example, the predetermined judgment value may be the average value of the maximum amplitude value Amax and the minimum amplitude value Amin.

[0043] As described above, in the present disclosure, different compensation is performed based on the magnitude of the distortion influence at the corresponding signal point. As a result, appropriate compensation can be performed at all signal points even if the magnitude of signal change differs depending on the position of the signal point.

[0044] In addition, in the present disclosure, the distortion influence degree, which is the magnitude of change in the data signal due to the transmission process and the reception process, is set as a predetermined standard. Therefore, the preprocessing device 60 according to the present disclosure performs machine learning using, as training data, signals before and after the influence of RF circuit imperfections due to multiple RF circuits. As a result, the receiving device 40 performs compensation based on the learning model acquired by the machine learning. In other words, the receiving device 40 can collectively compensate for the influence of RF circuit imperfections due to multiple RF circuits.

[0045] Furthermore, the present disclosure can be applied to signal changes due to the influence of imperfections in various RF circuits, and therefore can accommodate individual differences in the target of wireless communication.

[0046] 6 is a diagram illustrating a data signal before and after a signal change according to a second embodiment of the present disclosure. Here, a predetermined criterion for performing two patterns of learning by further performing machine learning for determining the magnitude of the influence of distortion will be described.

[0047] Data signal 2 is a diagram showing signal points based on original data generated by transmitting device 20. Data signal 2 is changed by transmission processing and reception processing to become data signal 4a. Here, data signal 4a is assumed to be a diagram showing signal points based on data after it has been changed due to the influence of imperfections in the RF circuit.

[0048] The data signal 4a is classified into two regions 5c and 5d based on the degree of distortion influence. Region 5c is a region that includes signal points with a large degree of distortion influence. Region 5d is a region that includes signal points with a small degree of distortion influence.

[0049] That is, in this embodiment, data corresponding to signal points included in region 5c must be compensated for when the degree of distortion influence is large, and data corresponding to signal points included in region 5d must be compensated for when the degree of distortion influence is small.

[0050] 7 is a diagram illustrating a data signal before and after compensation according to the second embodiment of the present disclosure. First, the receiving device 40 receives the data signal 4 a. Next, the receiving device 40 determines the magnitude of the distortion influence degree for the data corresponding to each signal point of the data signal 4 a.

[0051] In this embodiment, machine learning is used for the judgment. For example, the preprocessing device 60 acquires a learning model by learning the magnitude of the distortion influence degree before and after a signal change for each signal point. The preprocessing device 60 then determines a judgment value based on the acquired learning model. For example, the preprocessing device 60 may determine the judgment value based on the maximum and minimum values ​​of the distortion influence degree obtained based on the acquired learning model.

[0052] Next, receiving device 40 performs first compensation 6c on data corresponding to signal points included in region 5c, i.e., data corresponding to signal points with high distortion sensitivity, and performs second compensation 6d on data corresponding to signal points included in region 5d, i.e., data corresponding to signal points with low distortion sensitivity.

[0053] Furthermore, the receiving device 40 performs demodulation based on the compensated data, so that the receiving device 40 can obtain a data signal 2a that matches the data signal 2.

[0054] As described above, in the present disclosure, different compensation is performed based on the magnitude of the distortion influence at the corresponding signal point. As a result, appropriate compensation can be performed at all signal points even if the magnitude of signal change differs depending on the position of the signal point.

[0055] Although the present disclosure has been described with reference to the example of the influence of RF circuit imperfections, the present disclosure is not limited to this example and is applicable to any distortion that causes contraction or rotation in a constellation that does not have random fluctuations within a radio frame.

[0056] Furthermore, the machine learning described in the present disclosure is merely an example, and there are no limitations on the network configuration, learning data, etc. Furthermore, there are no limitations on the configuration of the wireless communication system, etc.

[0057] Furthermore, although the present disclosure has shown an aspect in which two patterns of compensation are prepared, the present disclosure is not limited to this and may be any other aspect as long as multiple patterns are prepared. Furthermore, the present disclosure has shown an aspect in which the determination process is performed based on amplitude values ​​or machine learning, but the present disclosure is not limited to this.

[0058] 2 Data signal 2a Data signal 4 Data signal 4a Data signal 8a Signal point 8b Signal point 20 Transmitting device 40 Receiving device

Claims

1. A receiving device that receives a data signal from a transmitting device, comprising a processor and a memory that stores a program to be executed by the processor, wherein the processor is configured to perform the following processes: a process of designating a group of signal points in the received data signal that are determined to have a large degree of distortion influence according to a predetermined criterion as a first data set; a process of performing machine learning based on the first data set to obtain a first learning model; a process of designating a group of signal points in the received data signal that are determined to have a small degree of distortion influence according to the predetermined criterion as a second data set; a process of performing machine learning based on the second data set to obtain a second learning model; a process of determining, according to the predetermined criterion, the magnitude of the degree of distortion influence to be superimposed on a signal point included in the received data signal; a process of compensating the signal point based on the first learning model if the degree of distortion influence is determined to be large; and a process of compensating the signal point based on the second learning model if the degree of distortion influence is determined to be small; and a process of demodulating the data signal using the compensated signal points.

2. The receiving device according to claim 1, wherein the judgment is a process of judging that the degree of distortion influence is large if the amplitude value at the signal point is equal to or greater than a predetermined judgment value, and judging that the degree of distortion influence is small if the amplitude value is smaller than the judgment value.

3. The receiving device according to claim 2, wherein the judgment value is the average value of the maximum and minimum amplitude values ​​occurring in the data signal.

4. The receiving device of claim 1, wherein the judgment is realized by a process of acquiring a learning model by learning the magnitude of the distortion influence degree for each signal point, and a process of determining a judgment value based on the acquired learning model.

Images