Receiver and radio communication program

Abstract

This disclosure relates to a receiver and a radio communication program. The receiver is for receiving a data signal from a transmitter, and includes a processor and a memory storing a program to be executed by the processor. The processor is configured to execute: processing for performing learning by a denoising autoencoder (DAE) on the basis of labeled training data corresponding to transmission data and learning data corresponding to reception data; processing for storing a learning result; and processing for performing compensation on a received data signal by using a learning model generated on the basis of the learning result.

Description

Receiver and wireless communication program

[0001] The present disclosure relates to a receiver and a wireless communication program.

[0002] In order to improve communication quality, there is a technology that outputs an original signal based on a signal that has changed during the communication process. For example, Non-Patent Document 1 discloses a method of outputting an original signal based on a pilot signal affected by amplifier distortion and a multiple regression model obtained by pre-learning. This method improves communication quality by deriving the input / output characteristics of the amplifier and generating a reference signal to be used for demodulation based on the derived characteristics.

[0003] T. Tanaka, K. Kuriyama, H. Hasegawa, and T. Miyagi, "An Estimation Method of Input / Output Characteristics of Transmitting Amplifiers Using Multiple Regression Analysis," IEICE General Conference B-5-81, 2023.

[0004] However, with the above method, if there are factors other than amplifier distortion that cause changes in the signal during the communication process, it becomes difficult to output the original signal.Furthermore, the use of a pilot signal increases the amount of shared information, which reduces communication speed.

[0005] In order to solve the above-mentioned problems, the first objective of the present disclosure is to provide a receiver that can perform appropriate compensation and improve communication speed even when signal changes during communication are due to factors other than amplifier distortion.

[0006] A second object of the present disclosure is to provide a wireless communication program that can perform appropriate compensation and improve communication speed even when signal changes during communication are due to factors other than amplifier distortion.

[0007] A first aspect of the present disclosure is a receiver that receives a data signal from a transmitter, and is preferably configured to include a processor and a memory that stores a program to be executed by the processor, and to perform a process of learning using a Denoising Autoencoder (DAE) based on teacher data corresponding to the transmitted data and learning data corresponding to the received data, a process of storing the learning results, and a process of compensating the received data signal using a learning model generated based on the learning results.

[0008] A second aspect of the present disclosure is a wireless communication program to be executed by a receiver having a processor and a memory, the wireless communication program being stored in the memory and computer-readable, and preferably including a program for causing the processor to perform a process of learning using a Denoising Autoencoder (DAE) based on teacher data corresponding to transmitted data and learning data corresponding to received data, a process of storing the learning results, and a process of compensating a received data signal using a learning model generated based on the learning results.

[0009] According to the first and second aspects of the present disclosure, even if a change in a signal during communication is due to a factor other than amplifier distortion, appropriate compensation can be performed and communication speed can be improved.

[0010] 1 is a diagram illustrating a configuration example 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 receiver according to a first embodiment of the present disclosure; FIG. 3 is a diagram illustrating pre-processing according to a first embodiment of the present disclosure; and FIG. 4 is a diagram illustrating processing during communication according to a first embodiment of the present disclosure.

[0011] 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 transmitter 20. The transmitter 20 transmits a signal to a receiver 40.

[0012] The transmitter 20 has an information generating unit 21. The information generating unit 21 generates information bits for information to be transmitted to the receiver 40. The information generating unit 21 may also have a function of adding an error correction code or an interleaving function.

[0013] The generated information bits are transmitted to a data signal modulation unit 22. The data signal modulation unit 22 modulates the information bits into a data signal. The modulation method used here is, for example, quadrature amplitude modulation (QAM).

[0014] The data signal obtained by the modulation is transmitted to the D / A converter 23. The D / A converter 23 converts the digitally modulated data signal into an analog signal, generating an I signal and a Q signal.

[0015] The analog data signal is transmitted to the IQ signal modulation unit 24. The IQ signal modulation unit 24 performs quadrature modulation on the I signal and the Q signal.

[0016] The quadrature-modulated data signal is transmitted to the amplifier 25. The amplifier 25 amplifies the data signal and transmits it to the receiver 40.

[0017] The receiver 40 includes an amplifier 41. The amplifier 41 amplifies the data signal received from the transmitter 20.

[0018] The amplified data signal is transmitted to the IQ signal demodulation unit 42. The IQ signal demodulation unit 42 demodulates the received data signal into an I signal and a Q signal.

[0019] The demodulated data signal is transmitted to the A / D converter 43. The A / D converter 43 digitizes the analog data signal for digital demodulation.

[0020] The digitized data signal is transmitted to a channel equalization unit 44. The channel equalization unit 44 obtains an estimate of the originally transmitted signal by inversely calculating the amplitude and phase information of the channel response based on the data signal.

[0021] The data signal from which the estimated value has been obtained is transmitted to the compensation unit 45. The compensation unit 45 generates a learning model based on the learning results of the DAE (Denoising Autoencoder) obtained in the pre-processing. The compensation unit 45 then compensates the received data signal using this learning model. Details of the pre-processing and compensation methods will be described later.

[0022] The imperfection of the RF circuit may be, for example, nonlinear distortion, IQ imbalance, or phase noise of an amplifier. The object of compensation may be imperfections of a plurality of RF circuits.

[0023] The compensated data signal is transmitted to the information detector 46. The information detector 46 detects information bits from the compensated data signal. Depending on the function of the information generator 21, the information detector 46 may also have a function of decoding error correction codes or a deinterleaving function.

[0024] Next, the pre-processing will be described. The wireless communication system 100 includes a pre-processing unit 60. The pre-processing unit 60 may be included in each receiver 40. Alternatively, one pre-processing unit 60 may be connected to multiple receivers 40, and perform pre-processing collectively.

[0025] The pre-processing unit 60 includes a learning data generating unit 61. The learning data generating unit 61 generates learning data to be used in the DAE.

[0026] The generated learning data is transmitted to the DAE learning unit 62. The DAE learning unit 62 performs learning by the DAE based on the learning data.

[0027] The learning results of the DAE are transmitted to a learning result storage unit 47 included in the receiver 40. The learning result storage unit 47 stores the learning results of the DAE obtained by the pre-processing unit 60. The compensation unit 45 described above generates a learning model based on the learning results.

[0028] 2 is a diagram illustrating a hardware configuration of a receiver according to the first embodiment of the present disclosure. Each function of the receiver 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.

[0029] For example, the receiver 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.

[0030] 2, the receiver 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 receiver 40 is also capable of inputting and outputting data to and from a computer-readable storage medium 407.

[0031] 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.

[0032] The communication unit 402 is, for example, a communication interface that communicates with a wireless device to be controlled.

[0033] The CPU 403 controls each component of the receiver 40 and performs predetermined processing, etc. The memory 404 and HDD 405 store data, etc.

[0034] The storage medium 407 is capable of storing programs and the like that cause the receiver 40 to execute the functions of the receiver 40. Note that the architecture that configures the receiver 40 is not limited to the example shown in FIG.

[0035] 3 is a diagram illustrating pre-processing according to the first embodiment of the present disclosure. First, a learning data generation unit 61 generates learning data. The learning data is, for example, a pair of learning data 2 and teacher data 4. The learning data 2 corresponds to received data, and is, for example, a complex signal that has been changed due to the influence of imperfections in the RF circuit. The teacher data 4 corresponds to transmitted data, and is, for example, a complex signal that the learning data 2 had before being changed due to the influence of imperfections in the RF circuit.

[0036] Next, the DAE learning unit 62 performs learning using the DAE based on the learning data. The learning results of the DAE are transmitted to the learning result storage unit 47. The learning result storage unit 47 stores the learning results of the DAE. The compensation unit 45 generates a learning model based on the DAE learning results acquired from the learning result storage unit 47. This learning model is a learning model that generates the original signal from a signal that has been changed due to the influence of imperfections in the RF circuit.

[0037] The DAE used in this embodiment is a type of autoencoder. When imperfections in multiple RF circuits affect a signal, the effects of each are superimposed, resulting in complex signal changes. Therefore, even when machine learning is used for compensation, it becomes necessary to extract fine features. Therefore, this embodiment employs an autoencoder, which is less susceptible to overfitting and is suitable for extracting fine features.

[0038] 4 is a diagram illustrating a process during communication according to the first embodiment of the present disclosure. During communication, information bits generated by the information generating unit 21 of the transmitter 20 are first transmitted as a data signal 6. The data signal 6 is changed due to the influence of imperfections in the RF circuit before it reaches the compensating unit 45. Therefore, the compensated unit 45 receives the changed data signal 8.

[0039] Therefore, the compensation unit 45 uses a learning model generated in advance to generate the original data signal 10 from the data signal 8. Specifically, the compensation unit 45 inputs the received data signal 8 to the DAE, and outputs the original data signal 10.

[0040] As described above, in the present disclosure, by using a DAE learning model, appropriate compensation can be performed all at once. That is, appropriate compensation can be performed even when signal changes during the communication process are due to factors other than amplifier distortion. At the same time, since the original data signal can be generated from the received data signal, there is no need to use a pilot signal, and communication speed can be improved.

[0041] In this embodiment, the influence of imperfections in the RF circuit has been described as an example, but the present invention is effective for all causes of signal changes, such as fading.

[0042] The learning model shown in this embodiment 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.

[0043] 2 Learning data 4 Teacher data 6 Data signal 8 Data signal 10 Data signal 20 Transmitter 40 Receiver

Claims

1. A receiver that receives a data signal from a transmitter, comprising a processor and a memory storing a program to be executed by the processor, wherein the processor performs a process of learning by a Denoising Autoencoder (DAE) based on teacher data corresponding to transmission data and learning data corresponding to received data, a process of storing a learning result, and a process of compensating the received data signal using a learning model generated based on the learning result.

2. The receiver according to claim 1, wherein the learning data is a complex signal changed due to the influence of the incompleteness of the RF circuit, and the teacher data is a complex signal before being changed due to the influence of the incompleteness of the RF circuit.

3. The receiver according to claim 2, wherein the incompleteness of the RF circuit is at least one of non-linear distortion of an amplifier, IQ imbalance, and phase noise.

4. A wireless communication program to be executed by a receiver including a processor and a memory, the program being stored in the memory, being computer-readable, and including a program for causing the processor to perform a process of learning by a Denoising Autoencoder (DAE) based on teacher data corresponding to transmission data and learning data corresponding to received data, a process of storing a learning result, and a process of compensating the received data signal using a learning model generated based on the learning result.

Images