Nonlinear compensating apparatus, nonlinear compensating method, and program

Abstract

To provide a nonlinear compensation device, a nonlinear compensation method, and a program for appropriately updating a parameter even when a reference signal cannot be used every time.SOLUTION: A nonlinear compensation device 200 includes a plurality of nonlinear circuits 201 - 1 to 201 - N that output signals obtained by adding nonlinear characteristics to reception signals transmitted by a transmitter and received by a receiver, a linear circuit 202 that outputs a sum of values obtained by multiplying outputs of the plurality of nonlinear circuits by weighting coefficients as a compensation signal, and a first learning unit 204 that sets at least one of parameters of the nonlinear characteristics of the plurality of nonlinear circuits and the weighting coefficients of the linear circuit on the basis of an error between the compensation signal and a reference signal. And a second learning unit 203 that changes each weight coefficient of the linear circuit 202.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a nonlinear compensation device, a nonlinear compensation method, and a program. [Background technology]

[0002] Patent Document 1 discloses that a signal transmitted from a transmitter is coherently received, and filter coefficients are adaptively controlled using the backpropagation method based on the difference between the output signal output from a filter group and a predetermined value of the output signal. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2022-174467 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology described in Patent Document 1 does not consider, for example, the problem of when the reference signal cannot be used every time.

[0005] In view of the above-mentioned problems, an object of the present disclosure is to provide a technology that can appropriately update parameters even when a reference signal cannot be used every time. [Means for solving the problem]

[0006] In a first aspect of the present disclosure, a nonlinear compensation device is provided, comprising: a plurality of nonlinear circuits that output a signal to which nonlinear characteristics have been added to a received signal transmitted from a transmitter and received by a receiver; a linear circuit that outputs a compensation signal by summing values ​​obtained by multiplying the outputs of the plurality of nonlinear circuits by respective weighting coefficients; a first learning unit that sets parameters of the nonlinear characteristics of each of the plurality of nonlinear circuits and at least one of the weighting coefficients of the linear circuits based on an error between the compensation signal and a reference signal; and a second learning unit that changes the weighting coefficients of the linear circuits so that frequency components outside a specific band of the compensation signal are reduced.

[0007] In addition, a second aspect of the present disclosure provides a nonlinear compensation method in which each of a plurality of nonlinear circuits outputs a signal to which a nonlinear characteristic has been added to a received signal transmitted from a transmitter and received by a receiver, a linear circuit outputs a compensation signal which is the sum of values ​​obtained by multiplying each output of the plurality of nonlinear circuits by each weighting coefficient, and based on an error between the compensation signal and a reference signal, sets at least one parameter of the nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit, and changes each weighting coefficient of the linear circuit so that frequency components outside a specific band of the compensation signal are reduced.

[0008] In addition, a third aspect of the present disclosure provides a program for causing a computer to execute a process of obtaining a compensation signal which is the sum of values ​​obtained by multiplying each signal, to which a nonlinear characteristic has been added by each of a plurality of nonlinear circuits, by each weighting coefficient using a linear circuit, and setting at least one parameter of the nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuits based on an error between the compensation signal and a reference signal, and changing each weighting coefficient of the linear circuits so that frequency components outside a specific band of the compensation signal are reduced. [Effects of the Invention]

[0009] According to one aspect, parameters can be appropriately updated even when a reference signal cannot be used every time. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an example of a configuration of a wireless communication system 1 according to an embodiment. [Figure 2] 1 is a diagram illustrating an example of a configuration of a wireless communication system 1 including RoF according to an embodiment. [Figure 3] 1 is a diagram illustrating an example of the configuration of a nonlinear compensation device 200 according to an embodiment. [Figure 4] 4 is a flowchart showing an example of a setting process of the nonlinear compensation device 200 according to the embodiment. [Figure 5] 4 is a graph showing the relationship between input power (received power) of a received signal and SNR (signal to noise ratio) according to the embodiment. [Figure 6] FIG. 6 is a diagram showing an example of a parameter table 601 according to the embodiment. [Figure 7] 1 is a diagram illustrating an example of a hardware configuration of a nonlinear compensation device 200 according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] The principles of the present disclosure will be described with reference to some exemplary embodiments. It should be understood that these embodiments are set forth for illustrative purposes only, to aid those skilled in the art in understanding and practicing the present disclosure, without implying any limitation on the scope of the disclosure. The disclosure described herein may be implemented in various ways other than those described below.

[0012] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessarily required to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0014] <System configuration> An example of the configuration of a wireless communication system 1 according to the embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a diagram illustrating an example of the configuration of the wireless communication system 1 according to the embodiment. In the example of FIG. 1, the wireless communication system 1 includes a transmitter 10 and a receiver 20. In the example of FIG. 1, the transmitter 10 includes a signal modulation unit 11, a DAC (digital to analog converter) 12, a mixer 13, a LO (local oscillator) 14, a PA (power amplifier) ​​15, and an antenna 16. The transmitter 10 converts transmission data into a radio signal and outputs the signal from the antenna 16 into space. Specifically, the transmission data is converted into a transmission signal by the signal modulation unit 11, converted into an analog signal by the DAC 12, upconverted to a high frequency by the mixer 13 and the LO 14, and amplified by the PA 15. The transmission data is then output into space from the antenna 16 as a radio signal.

[0015] 1, the receiver 20 includes an antenna 21, an LNA (low noise amplifier) ​​22, a mixer 23, an LO 24, an ADC (Analog to Digital Converter) 25, a nonlinear compensation device 200, and a signal demodulation unit 27. The receiver 20 converts a radio signal received from the antenna 21 into an electrical signal to obtain received data, which is the same data sequence as the transmitted data. Specifically, the radio signal obtained via the antenna 21 is amplified by the LNA 22, down-converted to a low frequency by the mixer 23 and the LO 24, and converted into a digital received signal by the ADC 25. Thereafter, the received signal is converted into a compensation signal that compensates for nonlinear distortion occurring in the transmission path by the nonlinear compensation device 200, and then converted into a received data sequence that is the same data sequence as the transmitted data by the signal demodulation unit 27.

[0016] The nonlinear compensation device 200 improves the signal quality of the received signal by canceling the nonlinear distortion occurring in each of the PA 15, mixer 13, LNA 22, and mixer 23, which are the transmission path.

[0017] FIG. 2 is a diagram illustrating an example of the configuration of a wireless communication system 1 including a radio over fiber (RoF) according to an embodiment. The example of FIG. 2 differs from the example of FIG. 1 in that a receiver 20 includes an E / O converter 2-a-1, an optical fiber 28, and an O / E converter 2-b-1 that constitute the RoF in a transmission path between an LNA 22 and a mixer 23. As a result, an electrical signal output from the LNA 22 is converted into an optical signal by the E / O converter 2-a-1, and then restored to an electrical signal by the O / E converter 2-b-1 via the optical fiber 28. The inclusion of this RoF allows the receiver 2 to be functionally divided into an access point 2-a and a baseband unit 2-b. This allows the access point 2-a, which is a functional block including an antenna 21, to be miniaturized.

[0018] In this case, it is considered that nonlinear distortion occurs in the transmission path including the RoF not only in the PA 15, mixer 13, LNA 22, and mixer 23, but also in the E / O converter 2-a-1, optical fiber 28, and O / E converter 2-b-1. The nonlinear compensation device 200 improves the signal quality of the received signal by canceling these nonlinear distortions.

[0019] <Configuration of nonlinear compensation device 200> An example of the configuration of the nonlinear compensation device 200 according to the embodiment will be described with reference to FIG. 3. FIG. 3 is a diagram illustrating an example of the configuration of the nonlinear compensation device 200 according to the embodiment. In the example of FIG. 3, the nonlinear compensation device 200 includes N (N is an integer equal to or greater than 2) nonlinear circuits 201-1 to 201-N. Hereinafter, when it is not necessary to distinguish between the nonlinear circuits 201-1 to 201-N, they will also be simply referred to as "nonlinear circuits 201" as appropriate. The nonlinear compensation device 200 also includes a linear circuit 202, a learning unit 203 (an example of a "second learning unit"; a learning unit without a reference signal), and a learning unit 204 (an example of a "first learning unit"; a learning unit with a reference signal). The learning unit 203 and the learning unit 204 may be realized by cooperation of one or more programs installed in the nonlinear compensation device 200 and hardware such as a processor and memory of the nonlinear compensation device 200.

[0020] Each nonlinear circuit 201 receives as input a received signal transmitted from the transmitter 10 and received by the receiver 20, and outputs a signal obtained by adding nonlinear characteristics to the received signal. Note that a known nonlinear compensation circuit may be used as the nonlinear circuit 201. In this case, the nonlinear circuit 201 may be, for example, a nonlinear compensation circuit using a memory polynomial shown in "Lei Ding et al., "A robust digital baseband predistorter constructed using memory polynomials," in IEEE Transactions on Communications, vol. 52, no. 1, pp. 159-165, Jan. 2004."

[0021] Furthermore, the nonlinear circuit 201 may be a nonlinear compensation circuit using a neural network, as described in, for example, "M. Rawat and F. M. Ghannouchi, "A Mutual Distortion and Impairment Compensator for Wideband Direct-Conversion Transmitters Using Neural Networks," in IEEE Transactions on Broadcasting, vol. 58, no. 2, pp. 168-177, June 2012," or "M. Tanio, N. Ishii and N. Kamiya, "Efficient Digital Predistortion Using Sparse Neural Network," in IEEE Access, vol. 8, pp. 117841-117852, 2020." In this case, the input received signal uses not only the current signal but also a past signal sequence. Note that the nonlinear circuit 201 is not limited to the above circuit, and other nonlinear compensation circuits can also be used. Also, different nonlinear circuits can be used in combination.

[0022] The linear circuit 202 outputs the sum of values ​​obtained by multiplying the output of each nonlinear circuit 201 by each predetermined parameter (weighting coefficient) as a compensation signal.

[0023] The learning unit 203 uses the received signal and the updated compensation signal to update the parameters of the linear circuit 202. The learning unit 204 updates the parameters of each nonlinear circuit 201, etc., based on, for example, a learning result using the compensation signal and the reference signal.

[0024] <Processing> Next, an example of the setting process of the nonlinear compensation device 200 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of the setting process of the nonlinear compensation device 200 according to the embodiment. The process of Fig. 4 may be executed, for example, periodically. The nonlinear compensation device 200 may execute the various processes of Fig. 4 in a different order as appropriate, as long as there is no contradiction.

[0025] In step S101, the learning unit 204 acquires a received signal and a reference signal. Here, the learning unit 204 may acquire a received signal that is received by the receiver 20 after specific transmission data is converted into a radio signal and output into space by the transmitter 10, and the reference signal based on the specific transmission data.

[0026] In this case, the learning unit 204 may generate a reference signal by processing similar to that performed by the signal modulation unit 11 of the transmitter 10, for example, based on data shared in advance between the transmitter 10 and the receiver 20. In this case, the reference signal may be generated based on the same transmission data shared in advance between the transmitter 10 and the receiver 20. Alternatively, the reference signal may be generated based on the same data generated by a common algorithm shared in the transmitter 10 and the receiver 20.

[0027] Next, the learning unit 204 inputs the received signal to each nonlinear circuit 201, thereby causing the linear circuit 202 to output a compensation signal (step S102). Next, the learning unit 204 updates the parameters of each nonlinear circuit 201, etc., based on the learning result using the compensation signal and the reference signal (step S103). Here, the learning unit 204 may calculate an error between the compensation signal and the reference signal, and then set at least one of the parameters (nonlinear characteristics) of each nonlinear circuit 201 and the parameters of the linear circuit 202 so as to reduce the error. In this case, the learning unit 204 may change, for example, at least one of the parameters of each nonlinear circuit 201 and the weighting coefficients of the linear circuit 202 from a first parameter to a second parameter that is calculated to reduce the error compared to the first parameter. In this case, the learning unit 204 may update each parameter using, for example, an error propagation algorithm or a stochastic gradient descent algorithm used in neural network training.

[0028] Next, the learning unit 204 inputs the received signal again to each updated nonlinear circuit 201, causing the linear circuit 202 to output an updated compensation signal (step S104). Next, the learning unit 203 updates the parameters of the linear circuit 202 using the received signal and the updated compensation signal (step S105). Here, the learning unit 203 may, for example, use the received signal and the updated compensation signal to change each weighting coefficient of the linear circuit 202 so that frequency components outside a specific band of the compensation signal are reduced. This may cancel, for example, the spread of frequency components caused by nonlinear distortion of the compensation signal. More specifically, the learning unit 203 may, for example, calculate out-of-band frequency components of the output signal of each nonlinear circuit 201 using the received signal and the updated compensation signal, and determine (optimize) parameters of the linear combination so as to suppress the out-of-band components of the compensation signal after linear combination in the linear circuit 202. The learning unit 203 may also set each parameter of the linear circuit 202 using a known process. In this case, the learning unit 203 may set each parameter of the linear circuit 202 using, for example, the method disclosed in "T. Abe and Y. Yamao, "Blind Post-Compensation of Tandem Nonlinearity Caused by Transmitter and Receiver," 2020 IEEE Radio and Wireless Symposium (RWS), San Antonio, TX, USA, 2020, pp. 12-15."

[0029] Next, the learning unit 204 inputs the received signal again to each updated nonlinear circuit 201, causing the updated linear circuit 202 to output a re-updated compensation signal (step S106). Next, the learning unit 204 calculates the difference (error) between the re-updated compensation signal and the reference signal, and determines whether the error is equal to or less than a threshold (step S107). If the error is not equal to or less than the threshold (NO in step S107), the process proceeds to step S103. This provides a nonlinear compensation device 200 that calculates a compensation signal with an error lower than the threshold. That is, the nonlinear compensation device 200 is capable of sufficiently suppressing nonlinear distortion occurring in the transmission path. On the other hand, if the error is equal to or less than the threshold (YES in step S107), the process ends.

[0030] According to the nonlinear compensation device 200 of the present disclosure, the dynamic range of the received signal can be expanded by improving the signal quality. Fig. 5 is a graph showing the relationship between the input power (received power) of the received signal and the SNR (signal to noise ratio) according to the embodiment.

[0031] Without a reception distortion compensation circuit, when the input power of the received signal 511 is relatively large, the SNR degradation due to nonlinear distortion is significant, and the dynamic range 521 of the input power that is equal to or greater than the allowable SNR value is limited. On the other hand, when the nonlinear compensation device 200 of the present disclosure is used, even when the input power of the received signal 511 is relatively large, the SNR degradation can be improved by the compensation signal 512. Therefore, the dynamic range 522 that is equal to or greater than the allowable SNR can be expanded.

[0032] (Example of optimizing parameters for each state, such as input power) As shown in Fig. 5, when the state (input power, etc.) of the received signal differs, the nonlinear distortion characteristics differ, and therefore the SNR differs. Therefore, nonlinear compensation device 200 may optimize nonlinear compensation parameters corresponding to received signals in multiple different states (for example, different reception power). This makes it possible to perform appropriate nonlinear compensation even when the received signal has multiple states, for example.

[0033] In this case, in step S101 of Fig. 4, learning unit 204 may acquire a reference signal and received signals having different states such as input power. Then, nonlinear compensation device 200 may perform the processes of steps S102 to S107 of Fig. 4 on the received signals in each state. More specifically, when there are K types of states (K is an integer equal to or greater than 2), the processes of steps S102 to S107 of Fig. 4 may be performed on each received signal k (k is an integer from 1 to K).

[0034] Then, the learning unit 204 may record the parameters of each nonlinear circuit 201 and the parameters of the linear circuit 202 in the parameter table 701 in association with each state of the received signal, for example.

[0035] Fig. 6 is a diagram showing an example of a parameter table 601 according to the embodiment. In the example of Fig. 6, the parameter table 601 records combinations of parameters of each nonlinear circuit 201 and parameters of the linear circuit 202 in association with a state ID. The state ID is identification information of the state of the received signal.

[0036] Then, for example, when the receiver 20 is in operation, the learning unit 204 may obtain nonlinear compensation parameters corresponding to the received signal at each time point from the parameter table 601 and set them in each nonlinear circuit 201 and linear circuit 202.

[0037] (Example of optimizing parameters during operation of the receiver 20) Although a reference signal can be obtained through offline communication, it is difficult to obtain a reference signal in real time for a received signal during operation. Therefore, the nonlinear compensation device 200 may optimize nonlinear compensation parameters without using a reference signal while the receiver 20 is in operation. This allows, for example, appropriate nonlinear compensation to be performed even while the receiver 20 is in operation.

[0038] In this case, the learning unit 203 may use a received signal in a specific period and a compensation signal for the received signal to update the parameters of the linear circuit 202. The learning unit 203 may set, for example, the symbol length or frame length of an OFDM (Orthogonal Frequency Division Multiplexing) signal as the specific period.

[0039] Furthermore, the learning unit 203 may update the parameters of the linear circuit 202 every specific time length using the received signal to be processed this time and a compensation signal for the received signal, thereby making it possible to follow changes in the distortion characteristics of the transmission path.

[0040] When the receiver 20 is in operation, the learning unit 204 may demodulate the compensation signal and then modulate it to generate a signal from which distortion has been removed, and use the generated signal as a reference signal to optimize the parameters of the nonlinear compensation. This allows, for example, appropriate nonlinear compensation to be performed even while the receiver 20 is in operation.

[0041] In this case, the learning unit 204 may update at least some of the parameters of each nonlinear circuit 201 and the parameters of the linear circuit 202 based on an error between a compensation signal in a specific period and a reference signal based on the compensation signal. The learning unit 204 may set, for example, the symbol length or frame length of an OFDM (Orthogonal Frequency Division Multiplexing) signal as the specific period.

[0042] Furthermore, the learning unit 204 may update each parameter based on the error between the compensation signal to be processed this time and the reference signal based on the compensation signal, for each specific time length. This allows the learning unit 204 to follow, for example, the tracking of changes in the distortion characteristics of the transmission path by the learning unit 203.

[0043] <Hardware configuration> Fig. 7 is a diagram showing an example of the hardware configuration of a nonlinear compensation device 200 according to an embodiment. In the example of Fig. 7, the nonlinear compensation device 200 (computer 100) includes a processor 101, a memory 102, and a communication interface 103. These components may be connected via a bus or the like. The memory 102 stores at least a part of a program 104. The communication interface 103 includes an interface required for communication with other network elements.

[0044] When the program 104 is executed by the processor 101, memory 102, and the like in cooperation with each other, the computer 100 performs at least some of the processing of the embodiments of the present disclosure. The memory 102 may be of any type. As a non-limiting example, the memory 102 may be a non-transitory computer-readable storage medium. The memory 102 may also be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory, and removable memory. Although only one memory 102 is shown in the computer 100, several physically different memory modules may exist in the computer 100. The processor 101 may be of any type. The processor 101 may include one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture, as a non-limiting example. The computer 100 may have multiple processors, such as application-specific integrated circuit chips that are time-slaved to a clock that synchronizes the main processor.

[0045] Embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device.

[0046] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, that execute on a target real or virtual processor or device to perform the processes or methods of the present disclosure. Program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or divided among program modules as desired in various embodiments. The machine-executable instructions of the program modules may be executed in local or distributed devices. In a distributed device, the program modules may be located in both local and remote storage media.

[0047] The program code for executing the methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus. When the program code is executed by the processor or controller, the functions / acts in the flowcharts and / or implementing block diagrams are performed. The program code may be executed entirely on the machine, partly on the machine, as a standalone software package, partly on the machine and partly on a remote machine, or entirely on a remote machine or server.

[0048] The program can be stored and provided to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible recording media. Examples of non-transitory computer-readable media include magnetic recording media, magneto-optical recording media, optical disk media, and semiconductor memory. Magnetic recording media include, for example, flexible disks, magnetic tapes, and hard disk drives. Magneto-optical recording media include, for example, magneto-optical disks. Optical disk media include, for example, Blu-ray discs, CD (Compact Disc)-ROMs (Read Only Memory), CD-Rs (Recordable), and CD-RWs (Rewritable). Semiconductor memory includes, for example, solid-state drives, mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory). The program may also be provided to a computer by various types of temporary computer-readable media. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0049] <Other> A known wireless access system used in a mobile network includes multiple slave stations (e.g., access points) each having an antenna, and a master station (e.g., a central control station) that controls the multiple slave stations.

[0050] In recent years, it has been proposed to reduce the size of substations in such wireless access systems by using analog RoF (Radio over fiber), a technology that intensity-modulates optical signals with radio signals and transmits the optical signals in the form of radio signals over optical fiber.

[0051] In analog RoF, when the input signal power is relatively high, signal quality deteriorates due to nonlinear distortion that occurs in the transmission path.Specific components of the RoF transmission path that cause nonlinear distortion include the PA (power amplifier) ​​at the access point, the LNA (low noise amplifier) ​​at the central control station, photoelectric conversion (E / O (Electrical signal / Optical signal) and O / E (Optical signal / Electrical signal)), and optical fiber.

[0052] According to the present disclosure, the parameters of nonlinear compensation are updated based on the error between the compensation signal and the reference signal, which makes it possible to perform nonlinear compensation more appropriately, even in a system that uses RoF, for example. <Modification>

[0053] The nonlinear compensation device 200 may be a device contained in a single housing, but the nonlinear compensation device 200 of the present disclosure is not limited to this. Each unit of the nonlinear compensation device 200 may be realized, for example, by cloud computing configured with one or more computers. Furthermore, the nonlinear compensation device 200 may be provided inside the housing of the receiver 20, or may be provided as a device separate from the receiver 20. Such nonlinear compensation devices 200 are also included as examples of the "nonlinear compensation device" of the present disclosure.

[0054] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0055] Some or all of the above embodiments may also be described as, but are not limited to, the following appendices. Note that some or all of the elements (e.g., configurations and functions) described in each appendix dependent on appendix 1 may also be dependent on independent appendices in other categories in a similar dependency relationship. Some or all of the elements described in any appendix may be applied to various hardware, software, recording means for recording software, systems, and methods. (Appendix 1) a plurality of nonlinear circuits that output signals to which nonlinear characteristics have been added in response to signals transmitted from a transmitter and received by a receiver; a linear circuit that outputs a compensation signal by multiplying the outputs of the plurality of nonlinear circuits by respective weighting coefficients; and a first learning unit that sets at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and a reference signal; a second learning unit that changes each weighting coefficient of the linear circuit so that frequency components outside a specific band of the compensation signal are reduced. Nonlinear compensation device. (Appendix 2) the first learning unit changes at least one of the parameters of the nonlinear characteristics of each of the plurality of nonlinear circuits and the weighting coefficients of the linear circuit from a first parameter to a second parameter that is calculated to have a smaller error than the first parameter; 2. The nonlinear compensation device of claim 1. (Appendix 3) the first learning unit sets at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and the reference signal for each state of the received signal. 3. The nonlinear compensation device according to claim 1 or 2. (Appendix 4) The reference signal is generated based on data shared between the transmitter and the receiver. 3. The nonlinear compensation device according to claim 1 or 2. (Appendix 5) The reference signal is generated by demodulating the compensation signal and then modulating it. 3. The nonlinear compensation device according to claim 1 or 2. (Appendix 6) the second learning unit calculates an out-of-band frequency component of the output signal of the nonlinear circuit using the received signal and the updated compensation signal, and determines parameters of the linear combination so as to suppress the out-of-band of the compensation signal after linear combination in the linear circuit. 3. The nonlinear compensation device according to claim 1 or 2. (Appendix 7) the second learning unit changes each weighting coefficient of the linear circuit for each specific time length so that frequency components outside a specific band of the compensation signal are reduced. 7. The nonlinear compensation device according to claim 6. (Appendix 8) the first learning unit sets at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and the reference signal based on the compensation signal for each of the specific time lengths. 8. The nonlinear compensation device according to claim 7. (Appendix 9) each of the plurality of nonlinear circuits outputs a signal obtained by adding a nonlinear characteristic to a received signal transmitted from the transmitter and received by the receiver; a linear circuit that outputs a compensation signal that is a sum of values ​​obtained by multiplying the outputs of the plurality of nonlinear circuits by respective weighting coefficients; setting at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and a reference signal; changing the weighting coefficients of the linear circuit so that frequency components outside a specific band of the compensation signal are reduced; Nonlinear compensation methods. (Appendix 10) a compensation signal is obtained which is the sum of values ​​obtained by multiplying each of the signals, which are transmitted from the transmitter and received by the receiver, by weighting coefficients in a linear circuit, to which nonlinear characteristics are added in each of the plurality of nonlinear circuits; setting at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and a reference signal; changing the weighting coefficients of the linear circuit so that frequency components outside a specific band of the compensation signal are reduced; A program that causes a computer to perform a process. [Explanation of symbols]

[0056] 1. Wireless communication systems 10 Transmitter 20 Receiver 200 Nonlinear Compensator 201 Nonlinear Circuits 202 Linear Circuits 203 Learning Department 204 Learning Department

Claims

1. a plurality of nonlinear circuits that output signals to which nonlinear characteristics have been added in response to signals transmitted from a transmitter and received by a receiver; a linear circuit that outputs a compensation signal by multiplying the outputs of the plurality of nonlinear circuits by respective weighting coefficients; and a first learning unit that sets at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and a reference signal; a second learning unit that changes each weighting coefficient of the linear circuit so that frequency components outside a specific band of the compensation signal are reduced. Nonlinear compensation device.

2. the first learning unit changes at least one of the parameters of the nonlinear characteristics of each of the plurality of nonlinear circuits and the weighting coefficients of the linear circuit from a first parameter to a second parameter that is calculated to have a smaller error than the first parameter; The nonlinear compensation device according to claim 1 .

3. the first learning unit sets at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and the reference signal for each state of the received signal.

3. The nonlinear compensation device according to claim 1.

4. The reference signal is generated based on data shared between the transmitter and the receiver.

3. The nonlinear compensation device according to claim 1.

5. The reference signal is generated by demodulating the compensation signal and then modulating it.

3. The nonlinear compensation device according to claim 1.

6. the second learning unit calculates an out-of-band frequency component of the output signal of the nonlinear circuit using the received signal and the updated compensation signal, and determines parameters of the linear combination so as to suppress the out-of-band of the compensation signal after linear combination in the linear circuit.

3. The nonlinear compensation device according to claim 1.

7. the second learning unit changes each weighting coefficient of the linear circuit for each specific time length so that frequency components outside a specific band of the compensation signal are reduced. The nonlinear compensation device according to claim 6.

8. the first learning unit sets at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and the reference signal based on the compensation signal for each of the specific time lengths. The nonlinear compensation device according to claim 7.

9. each of the plurality of nonlinear circuits outputs a signal obtained by adding a nonlinear characteristic to a received signal transmitted from the transmitter and received by the receiver; a linear circuit that outputs a compensation signal that is a sum of values ​​obtained by multiplying the outputs of the plurality of nonlinear circuits by respective weighting coefficients; setting at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and a reference signal; changing the weighting coefficients of the linear circuit so that frequency components outside a specific band of the compensation signal are reduced; Nonlinear compensation methods.

10. a compensation signal is obtained which is the sum of values ​​obtained by multiplying each of the signals, which are transmitted from the transmitter and received by the receiver, by weighting coefficients in a linear circuit, to which nonlinear characteristics are added in each of the plurality of nonlinear circuits; setting at least one of a parameter of a nonlinear characteristic of each of the plurality of nonlinear circuits and each weighting coefficient of the linear circuit based on an error between the compensation signal and a reference signal; changing the weighting coefficients of the linear circuit so that frequency components outside a specific band of the compensation signal are reduced; A program that causes a computer to perform a process.

Images