Signal emitting apparatus and method for generating emission signal

Abstract

The present disclosure relates to a 5G communication system or a 6G communication system for supporting higher data rates than 4G communication systems such as Long Term Evolution (LTE). The present disclosure relates to a signal emitting apparatus and a method for generating an emission signal. The method comprises: performing, in a first mode, following operations: performing predistortion processing on a first digital signal through a first neural network to obtain a second digital signal; performing a digital-to-analog conversion on the second digital signal to obtain a first analog signal; performing up-conversion processing on the first analog signal; and performing a power amplification on the up-converted first analog signal through a power amplifying device to generate an emission signal, wherein a parameter of the first neural network is determined based on a non-linear characteristic of the power amplifying device.

Description

SIGNAL EMITTING APPARATUS AND METHOD FOR GENERATING EMISSION SIGNAL

[0001] The following description relates to a signal emitting apparatus and a method for generating an emission signal in a wireless communication system.

[0002] Considering the development of wireless communication from generation to generation, the technologies have been developed mainly for services targeting humans, such as voice calls, multimedia services, and data services. Following the commercialization of 5th-generation (5G) communication systems, it is expected that the number of connected devices will exponentially grow. Increasingly, these will be connected to communication networks. Examples of connected things may include vehicles, robots, drones, home appliances, displays, smart sensors connected to various infrastructures, construction machines, and factory equipment. Mobile devices are expected to evolve in various form-factors, such as augmented reality glasses, virtual reality headsets, and hologram devices. In order to provide various services by connecting hundreds of billions of devices and things in the 6th-generation (6G) era, there have been ongoing efforts to develop improved 6G communication systems.

[0003] 6G communication systems, which are expected to be commercialized around 2030, have various significantly improved metrics compared to the current 5G communication systems. The peak data rate will reach at least 50 Gbit / s, and the user experienced data rate will reach at least 300 Mbit / s, the air-interface latency will be less than 1 ms, and the air-interface reliability will reach 10^(-5). In addition to the above basic communication metrics, the 6G communication systems will also have sensing capabilities, AI-related capabilities, better security, better interoperability and better sustainability.

[0004] In order for the 6G communication systems to fulfill the above metrics, more advanced air-interface technologies and network technologies need to be developed. The evolution of extreme Multiple Input Multiple Output (extreme MIMO) has been already under consideration, including the use of ultra-large scale antenna arrays, the development and evolution of distributed antenna systems, and the design of MIMO air-interface algorithms assisted by Artificial Intelligence (AI). This technology enables higher spectral efficiency, greater coverage, and precise localization and sensing capabilities. Additionally, for technologies that contribute to improve high-frequency band coverage, including metamaterial-based lenses and antennas, new antenna architectures, and reconfigurable intelligent surface (RIS), etc., they also need to be better evolved and developed.

[0005] In order to meet some of newly added functions of the 6G communication systems, new technologies need to be developed in the terms of network energy saving, air-interface security, and network security, meanwhile the feasibility of fusion technologies such as Integrated Sensing and Communication, needs to be studied.

[0006] Moreover, in order to improve the spectral efficiency and the overall network performances, the following technologies have been developed for 6G communication systems: a full-duplex technology for enabling an uplink transmission and a downlink transmission to simultaneously use the same frequency resource at the same time; a network technology for utilizing satellites, high-altitude platform stations (HAPS), and the like in an integrated manner; an improved network structure for supporting mobile base stations and the like and enabling network operation optimization and automation and the like; a dynamic spectrum sharing technology via collision avoidance based on a prediction of spectrum usage; an use of artificial intelligence (AI) in wireless communication for improvement of overall network operation by utilizing AI from a designing phase for developing 6G and internalizing end-to-end AI support functions; and a next-generation distributed computing technology for overcoming the limit of user equipment (UE) computing ability through reachable super-high-performance communication and computing resources (such as mobile edge computing (MEC), clouds, and the like) over the network. In addition, through designing new protocols to be used in 6G communication systems, developing mechanisms for implementing a hardware-based security environment and safe use of data, and developing technologies for maintaining privacy, attempts to strengthen the connectivity between devices, optimize the network, promote softwarization of network entities, and increase the openness of wireless communications are continuing.

[0007] It is expected that research and development of 6G communication systems in hyper-connectivity, including person to machine (P2M) as well as machine to machine (M2M), will allow the next hyper-connected experience. Particularly, it is expected that services such as truly immersive extended reality (XR), high-fidelity mobile hologram, and digital replica could be provided through 6G communication systems. In addition, services such as remote surgery for security and reliability enhancement, industrial automation, and emergency response will be provided through the 6G communication system such that the technologies could be applied in various fields such as industry, medical care, automobiles, and home appliances.

[0008] According to an aspect of the present disclosure, a method performed by an electronic device for generating an emission signal is provided. The method comprises: performing, in a first mode, following operations: performing predistortion processing on a first digital signal through a first neural network to obtain a second digital signal; performing a digital-to-analog conversion on the second digital signal to obtain a first analog signal; performing up-conversion processing on the first analog signal; and performing a power amplification on the up-converted first analog signal through a power amplifying device to generate an emission signal, wherein a parameter of the first neural network is determined based on a non-linear characteristic of the power amplifying device.

[0009] According to an aspect of the present disclosure, an electronic device for generating emission signal is provided. The electronic device comprises at least one transceiver, at least one processor communicatively coupled to the at least one transceiver, and at least one memory communicatively coupled to the at least one processor, storing instructions executable by at least one processor individually or in any combination to cause the electronic device to operate in a first mode; perform predistortion processing on a first digital signal through a first neural network to obtain a second digital signal; perform a digital-to-analog conversion on the second digital signal to obtain a first analog signal; perform up-conversion processing on the first analog signal; and perform a power amplification on the up-converted first analog signal to generate an emission signal; and wherein a parameter of the first neural network is determined based on a non-linear characteristic of the power amplifying device.

[0010] The above and other aspects and features of the present disclosure will be more clearly understood from the following detailed description of exemplary and non-limiting embodiments given with reference to the accompanying drawings.

[0011] FIG. 1 illustrates an example wireless network according to an embodiment of the present disclosure;

[0012] FIG. 2A and FIG. 2B illustrate an example base station according to an embodiment of the present disclosure;

[0013] FIG. 3A and FIG. 3B illustrate an example user equipment according to an embodiment of the present disclosure;

[0014] FIG. 4 is a block diagram of an example signal emitting apparatus according to an embodiment of the present disclosure;

[0015] FIG. 5 is a flowchart of a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure;

[0016] FIG. 6 is a block diagram of an example signal emitting apparatus according to an embodiment of the present disclosure;

[0017] FIG. 7 is a flowchart of an update to a first neural network according to a non-linear characteristic of a power amplifying device in a second mode or after the switching from a first mode to the second mode in a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure;

[0018] FIG. 8 is a block diagram of an example signal emitting apparatus according to an embodiment of the present disclosure;

[0019] FIG. 9 is a flowchart of an update to a first neural network according to a non-linear characteristic of a power amplifying device in a second mode or after the switching from a first mode to the second mode in a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure;

[0020] FIG. 10 is a block diagram of an example signal emitting apparatus according to an embodiment of the present disclosure;

[0021] FIG. 11 is a flowchart of a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure;

[0022] FIG. 12 is a block diagram of an example signal emitting apparatus according to an embodiment of the present disclosure;

[0023] FIG. 13 is a flowchart of a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure; and

[0024] FIG. 14 is a schematic structural diagram of an electronic device applicable to an embodiment of the present disclosure.

[0025] Before undertaking the DETAILED DESCRIPTION below, it may be advantageous to set forth definitions of certain words and phrases used throughout this patent document. The term "couple" and its derivatives refer to any direct or indirect communication between two or more elements, whether those elements are in physical contact with one another. The terms "transmit," "receive," and "communicate," as well as derivatives thereof, encompass both direct and indirect communication. The terms "include" and "comprise," as well as derivatives thereof, mean inclusion without limitation. The term "or" is inclusive, meaning and / or. The phrase "associated with," as well as derivatives thereof, means to include, be included within, interconnect with, contain, be contained within, connect to or with, couple to or with, be communicable with, cooperate with, interleave, juxtapose, be proximate to, be bound to or with, have, have a property of, have a relationship to or with, or the like. The term "controller" means any device, system or part thereof that controls at least one operation. Such a controller may be implemented in hardware or a combination of hardware and software and / or firmware. The functionality associated with any particular controller may be centralized or distributed, whether locally or remotely. The phrase "at least one of," when used with a list of items, means that different combinations of one or more of the listed items may be used, and only one item in the list may be needed. For example, "at least one of: A, B, and C" includes any of the following combinations: A, B, C, A and B, A and C, B and C, and A and B and C. Likewise, the term "set" means one or more. Accordingly, a set of items can be a single item or a collection of two or more items.

[0026] Moreover, various functions described below can be implemented or supported by one or more computer programs, each of which is formed from computer readable program code and embodied in a computer readable medium. The terms "application" and "program" refer to one or more computer programs, software components, sets of instructions, procedures, functions, objects, classes, instances, related data, or a portion thereof adapted for implementation in a suitable computer readable program code. The phrase "computer readable program code" includes any type of computer code, including source code, object code, and executable code. The phrase "computer readable medium" includes any type of medium capable of being accessed by a computer, such as read only memory (ROM), random access memory (RAM), a hard disk drive, a compact disc (CD), a digital video disc (DVD), or any other type of memory. A "non-transitory" computer readable medium excludes wired, wireless, optical, or other communication links that transport transitory electrical or other signals. A non-transitory computer readable medium includes media where data can be permanently stored and media where data can be stored and later overwritten, such as a rewritable optical disc or an erasable memory device.

[0027] Definitions for other certain words and phrases are provided throughout this patent document. Those of ordinary skill in the art should understand that in many if not most instances, such definitions apply to prior as well as future uses of such defined words and phrases.

[0028] The figures included herein, and the various embodiments used to describe the principles of the present disclosure are by way of illustration only and should not be construed in any way to limit the scope of the disclosure. Further, those skilled in the art will understand that the principles of the present disclosure may be implemented in any suitably arranged wireless communication system.

[0029] FIGS. 1-3 below describe various embodiments of the present disclosure implemented in wireless communications systems. The descriptions of FIGS. 1-3 are not meant to imply physical or architectural limitations to the manner in which different embodiments may be implemented. Different embodiments of the present disclosure may be implemented in any suitably-arranged communications system.

[0030] FIG. 1 illustrates an example wireless network according to embodiments of the present disclosure. The embodiment of the wireless network shown in FIG. 1 is for illustration only. Other embodiments of the wireless network 100 could be used without departing from the scope of the present disclosure.

[0031] As shown in FIG. 1, the wireless network includes a base station (next generation nodeB, gNB or gNodeB) 101, a gNB 102, and a gNB 103. The gNB 101 communicates with the gNB 102 and the gNB 103. The gNB 101 also communicates with at least one network 130, such as the Internet, a proprietary Internet Protocol (IP) network, or other data network.

[0032] The gNB 102 provides wireless broadband access to the network 130 for a first plurality of user equipments (UEs) within a coverage area 120 of the gNB 102. The first plurality of UEs includes a UE 111, which may be located in a small business; a UE 112, which may be located in an enterprise (E); a UE 113, which may be located in a WiFi hotspot (HS); a UE 114, which may be located in a first residence (R1); a UE 115, which may be located in a second residence (R2); and a UE 116, which may be a mobile device (M), such as a cell phone, a wireless laptop, a wireless personal digital assistant (PDA), or the like. The gNB 103 provides wireless broadband access to the network 130 for a second plurality of UEs within a coverage area 125 of the gNB 103. The second plurality of UEs includes the UE 115 and the UE 116, as well as subscriber stations (SS, for example, UEs) 117, 118 and 119. In some embodiments, one or more of the gNBs 101-103 may communicate with each other and with the UEs 111-116 using existing wireless communication techniques, and one or more of the UE 111-119 may communicate directly with each other (e.g., UEs 117-119) using other existing or proposed wireless communication techniques.

[0033] Depending on the network type, the term "base station" or "BS" can refer to any component (or collection of components) configured to provide wireless access to a network, such as transmit point (TP), transmit-receive point (TRP), an enhanced (or "evolved") base station (eNodeB or eNB), a 5G base station (gNB), a macrocell, a femtocell, a wireless fidelity (WiFi) access point (AP), or other wirelessly enabled devices. Base stations may provide wireless access in accordance with one or more wireless communication protocols, e.g., 3GPP 5G New Radio (NR), Long Term Evolution (LTE), LTE Advanced (LTE-A), high speed packet access (HSPA), Wi-Fi 802.11a / b / g / n / ac, etc. For the sake of convenience, the various names for a base station-type apparatus and functionality are used interchangeably in this patent document to refer to network infrastructure components that provide wireless access to remote terminals. Also, depending on the network type, the term "user equipment" (UE) can refer to any component such as a mobile station (MS), subscriber station (SS), remote terminal, wireless terminal, receive point, or user device. For the sake of convenience, the various names for a user equipment-type device and functionality are used interchangeably in this patent document to refer to remote wireless equipment that wirelessly accesses a BS, whether the UE is a mobile device (such as a mobile telephone or smartphone) or is normally considered a stationary device (such as a desktop computer or vending machine).

[0034] Dotted lines show the approximate extents of the coverage areas 120 and 125, which are shown as approximately circular for the purposes of illustration and explanation only. It should be clearly understood that the coverage areas associated with gNBs, such as the coverage areas 120 and 125, may have other shapes, including irregular shapes, depending upon the configuration of the gNBs and variations in the radio environment associated with natural and man-made obstructions.

[0035] As described in more detail below, one or more of the UEs 111-119 include circuitry, programing, or a combination thereof. In certain embodiments, and one or more of the gNBs 101-103 includes circuitry, programing, or a combination thereof.

[0036] Although FIG. 1 illustrates one example of a wireless network, various changes may be made to FIG. 1. For example, the wireless network could include any number of gNBs and any number of UEs in any suitable arrangement. Also, the gNB 101 could communicate directly with any number of UEs and provide those UEs with wireless broadband access to the network 130. Similarly, each gNB 102-103 could communicate directly with the network 130 and provide UEs with direct wireless broadband access to the network 130. Further, the gNBs 101, 102, and / or 103 could provide access to other or additional external networks, such as external telephone networks or other types of data networks.

[0037] FIG. 2A and FIG. 2B illustrate an example base station according to embodiments of the present disclosure. The embodiment of the gNB 102 illustrated in FIG. 2A is for illustration only, and the gNBs 101 and 103 of FIG. 1 could have the same or similar configuration. However, gNBs come in a wide variety of configurations, and FIG. 2A does not limit the scope of the present disclosure to any particular implementation of a gNB.

[0038] As shown in FIG 2A, the gNB 102 includes multiple antennas 200a-200n, multiple radio frequency (RF) transceivers 201a-201n, transmit (TX) processing circuitry 203, and receive (RX) processing circuitry 204. The gNB 102 also includes a controller / processor 205, a memory 206, and a backhaul or network interface 207.

[0039] The RF transceivers 201a-201n receive, from the antennas 200a-200n, incoming RF signals, such as signals transmitted by UEs in the network 100. The RF transceivers 201a-201n down-convert the incoming RF signals to generate intermediate frequency (IF) or baseband signals. The IF or baseband signals are sent to the RX processing circuitry 204, which generates processed baseband signals by filtering, decoding, and / or digitizing the baseband or IF signals. The RX processing circuitry 204 transmits the processed baseband signals to the controller / processor 205 for further processing.

[0040] The TX processing circuitry 203 receives analog or digital data (such as voice data, web data, electronic mail, or interactive video game data) from the controller / processor 205. The TX processing circuitry 203 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate processed baseband or IF signals. The RF transceivers 201a-201n receive the outgoing processed baseband or IF signals from the TX processing circuitry 203 and up-converts the baseband or IF signals to RF signals that are transmitted via the antennas 201a-201n.

[0041] The controller / processor 205 can include one or more processors or other processing devices that control the overall operation of the gNB 102. For example, the controller / processor 205 could control the reception of forward channel signals and the transmission of reverse channel signals by the RF transceivers 201a-201n, the RX processing circuitry 204, and the TX processing circuitry 203 in accordance with well-known principles. The controller / processor 205 could support additional functions as well, such as more advanced wireless communication functions.

[0042] For instance, the controller / processor 205 could support beam forming or directional routing operations in which outgoing signals from multiple antennas 200a-200n are weighted differently to effectively steer the outgoing signals in a desired direction. Any of a wide variety of other functions could be supported in the gNB 102 by the controller / processor 205.

[0043] The controller / processor 205 is also capable of executing programs and other processes resident in the memory 206, such as an operating system (OS). The controller / processor 205 can move data into or out of the memory 206 as required by an executing process.

[0044] The controller / processor 205 is also coupled to the backhaul or network interface 207. The backhaul or network interface 207 allows the gNB 102 to communicate with other devices or systems over a backhaul connection or over a network. The interface 207 could support communications over any suitable wired or wireless connection(s). For example, when the gNB 102 is implemented as part of a cellular communication system (such as one supporting 5G, LTE, or LTE-A), the interface 207 could allow the gNB 102 to communicate with other gNBs over a wired or wireless backhaul connection. When the gNB 102 is implemented as an access point, the interface 207 could allow the gNB 102 to communicate over a wired or wireless local area network or over a wired or wireless connection to a larger network (such as the Internet). The interface 207 includes any suitable structure supporting communications over a wired or wireless connection, such as an Ethernet or RF transceiver.

[0045] The memory 206 is coupled to the controller / processor 205. Part of the memory 206 could include a random access memory (RAM), and another part of the memory 206 could include a Flash memory or other read only memory (ROM).

[0046] Although FIG. 2A illustrates one example of gNB 102, various changes may be made to FIG. 2A. For example, the gNB 102 could include any number of each component shown in FIG. 2A. As a particular example, an access point could include a number of interfaces 207, and the controller / processor 205 could support routing functions to route data between different network addresses. As another particular example, while shown as including a single instance of TX processing circuitry 203 and a single instance of RX processing circuitry 204, the gNB 102 could include multiple instances of each (such as one per RF transceiver). Also, various components in FIG. 2A could be combined, further subdivided, or omitted and additional components could be added according to particular needs.

[0047] FIG. 2B is a block diagram of a base station (BS) 102 according to an embodiment of the disclosure.

[0048] The BS 102 may perform wireless communication with at least one user equipment (UE) located within the area of the BS 102 through a wireless channel. The BS 102 may perform communication with a node or an entity of a network through wired or wireless communication.

[0049] Referring to FIG. 2B, the BS 102 may include at least one transceiver (hereinafter, referred to as simply "transceiver") 201 at least one processor (hereinafter, referred to as simply "processor") 205and at least one memory (hereinafter, referred to as simply "memory") 206. According to at least one or a combination of methods corresponding to the embodiments described in the present disclosure, the transceiver 201, the processor 205, and the memory 206 of the BS 102 may operate. However, components of the BS 102 are not limited to the example components illustrated in FIG. 2B. In another embodiment, the BS 102 may further include additional components in addition to the above-mentioned components, or some components may be omitted. Further, in some embodiments, any combination of the transceiver 201, the processor 205, or the memory 206 may be integrated in the form of one component.

[0050] The transceiver 201 may be a communication circuit or communication circuitry that enables the BS 102 to perform wireless communication with a node or an entity of a network. For example, the transceiver 201 may enable the BS 102 to transmit or receive a signal to or from the UE 116 through cellular communication, or to transmit or receive a signal to or from another network entity through wireless communication. For example, the transceiver 201 may support various cellular communication technologies including 3rd generation (3G), 4th generation (4G), long term evolution (LTE), 5th generation (5G) NR, 6th generation (6G), and various cellular wireless communication technologies supported by the transceiver (201) may include all subsequent generations of evolved wireless communications. According to an embodiment, the transceiver 201 may include various circuit structures used to transmit or receive signals to or from a UE through a wireless channel. The signals may include control information and data. For example, the transceiver 201 may include a radio frequency (RF) transmitter for up-converting and amplifying the frequency of a transmitted signal and an RF receiver for low-noise-amplifying a received signal and down-converting the frequency thereof. The transceiver 201 may output a signal received through a wireless channel to the processor 205 and may transmit, through a wireless channel, a signal output from the processor 205.

[0051] Meanwhile, according to an embodiment of the present disclosure, the BS 102 may perform communication with a node or an entity of a network through wired or wireless communication. For example, the BS 102 may perform wired or wireless communication with an adjacent BS, or a node or an entity of a core network through a backhaul network. Although not illustrated in FIG. 2B, when the BS 102 performs wired communication, the BS 102 may further include a separate network interface for wired communication in addition to the transceiver 201. The network interface may be referred to as network interface circuitry or communication interface circuitry.

[0052] The processor 205 may control general operations of the BS 102 according to embodiments of the disclosure. The processor 205 may be implemented by one or more integrated circuit (or circuitry) (IC) chips and may execute various data processing operations. The processor 205 may include at least one electric circuit, and may execute instructions (or a program, codes, data, etc.) stored in the memory 206, individually, collectively or in any combination thereof. Further, the processor 205 may include a single-core processor or multi-core processor, and may include a processor assembly including a plurality of processing circuits (circuitry) according to a specific implementation scheme.

[0053] The processor 205 may be electrically, operatively, and / or communicatively coupled to the transceiver 201 to control the transceiver 201.

[0054] The processor 205 may include at least one processor (or processing circuitry), and the at least one processor may perform the following operations individually, collectively or in any combination thereof. In a specific embodiment, at least a part of the processor 205 may be included in one chip (or IC) and the other part of the processor 205 may be included in another chip (or IC). Otherwise, at least one processor may be included in another component, for example, the transceiver 201 or the memory 206.

[0055] The processor 205 may perform or control or cause an operation of the BS 102 for executing at least one or a combination of methods according to embodiments of the disclosure. For example, the processor 205 may control operations of the BS 102 for generating and transmitting a downlink signal to a UE or processing an uplink signal received from a UE. Otherwise, the BS 102 may transmit or receive a signal to or from a neighbouring BS, transfer a signal received from a UE to an upper node of the network, or transmit a signal transferred from an upper node of the network to a UE. To this end, the processor 205 may execute a computer program, codes, or instructions stored in the memory 206, so as to control other components of the BS 102 to enable execution of various operations.

[0056] The memory 206 corresponds to a hardware storage device capable of temporarily or permanently storing information and may include one or more storage media. For example, the memory 206 may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory, such as a hard drive, flash memory, or read-only memory (ROM), semipermanent memory, such as random-access memory (RAM), cache memory, or a combination thereof.

[0057] The memory 206 may be electrically, operatively, and / or communicatively coupled to the processor 205 and may be accessed by the processor 205.

[0058] The memory 206 may store a computer program, codes, or instructions executable by the processor 205. According to an embodiment, a computer program, codes, or instructions executable by the processor 205 may be either stored in a single memory device or separated and distributedly stored in two or more memory devices. By executing the instructions stored in the memory 206, the processor 205 may perform various functions according to an embodiment of the disclosure.

[0059] According to an embodiment of the disclosure, operations of the BS 102 may be caused to be performed based on execution of instructions (or a computer program or codes) stored in the memory 206 by at least one processor (or processing circuitry) configured to execute the same individually, collectively, or in any combination thereof, based on processing circuitry that is not configured to execute instructions, and / or based on components of processing circuitry that is not configured to execute instructions.

[0060] FIG. 3A and FIG. 3B illustrate an example user equipment according to embodiments of the present disclosure. The embodiment of the UE 116 illustrated in FIG. 3A is for illustration only, and the UEs 111-115 and 117-119 of FIG. 1 could have the same or similar configuration. However, UEs come in a wide variety of configurations, and FIG. 3A does not limit the scope of the present disclosure to any particular implementation of a UE.

[0061] As shown in FIG. 3A, the UE 116 includes an antenna 301, a radio frequency (RF) transceiver 302, TX processing circuitry 303, a microphone 304, and receive (RX) processing circuitry 305. The UE 116 also includes a speaker 306, a controller or processor 307, an input / output (I / O) interface (IF) 308, an input device 309, a touchscreen display 310, and a memory 311. The memory 311 includes an OS 312 and one or more applications 313.

[0062] The RF transceiver 302 receives, from the antenna 301, an incoming RF signal transmitted by a gNB of the network 100. The RF transceiver 302 down-converts the incoming RF signal to generate an IF or baseband signal. The IF or baseband signal is sent to the RX processing circuitry 305, which generates a processed baseband signal by filtering, decoding, and / or digitizing the baseband or IF signal. The RX processing circuitry 305 transmits the processed baseband signal to the speaker 306 (such as for voice data) or to the processor 307 for further processing (such as for web browsing data).

[0063] The TX processing circuitry 303 receives analog or digital voice data from the microphone 304 or other outgoing baseband data (such as web data, e-mail, or interactive video game data) from the processor 307. The TX processing circuitry 303 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate a processed baseband or IF signal. The RF transceiver 302 receives the outgoing processed baseband or IF signal from the TX processing circuitry 303 and up-converts the baseband or IF signal to an RF signal that is transmitted via the antenna 301.

[0064] The processor 307 can include one or more processors or other processing devices and execute the OS 312 stored in the memory 311 in order to control the overall operation of the UE 116. For example, the processor 307 could control the reception of forward channel signals and the transmission of reverse channel signals by the RF transceiver 302, the RX processing circuitry 305, and the TX processing circuitry 303 in accordance with well-known principles. In some embodiments, the processor 307 includes at least one microprocessor or microcontroller.

[0065] The processor 307 is also capable of executing other processes and programs resident in the memory 311, such as processes for CSI reporting on uplink channel. The processor 307 can move data into or out of the memory 311 as required by an executing process. In some embodiments, the processor 307 is configured to execute the applications 313 based on the OS 312 or in response to signals received from gNBs or an operator. The processor 307 is also coupled to the I / O interface 308, which provides the UE 116 with the ability to connect to other devices, such as laptop computers and handheld computers. The I / O interface 308 is the communication path between these accessories and the processor 307.

[0066] The processor 307 is also coupled to the touchscreen display 310. The user of the UE 116 can use the touchscreen display 310 to enter data into the UE 116. The touchscreen display 310 may be a liquid crystal display, light emitting diode display, or other display capable of rendering text and / or at least limited graphics, such as from web sites.

[0067] The memory 311 is coupled to the processor 307. Part of the memory 311 could include RAM, and another part of the memory 311 could include a Flash memory or other ROM.

[0068] Although FIG. 3A illustrates one example of UE 116, various changes may be made to FIG. 3A. For example, various components in FIG. 3A could be combined, further subdivided, or omitted and additional components could be added according to particular needs. As a particular example, the processor 307 could be divided into multiple processors, such as one or more central processing units (CPUs) and one or more graphics processing units (GPUs). Also, while FIG. 3A illustrates the UE 116 configured as a mobile telephone or smartphone, UEs could be configured to operate as other types of mobile or stationary devices.

[0069] At least some of the functions of the device or electronic device provided in the embodiments of this disclosure can be implemented through an AI model. For example, at least one of the multiple modules of the device or electronic device can be implemented through an AI model. The functions associated with AI can be executed via a non-volatile memory, a volatile memory, and a processor.

[0070] The processor may include one or more processors. In this case, the one or more processors can be general-purpose processors, such as a central processing unit (CPU), an application processor (AP), etc., or pure graphics processing units, such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-specific processor, such as a neural processing unit (NPU).

[0071] The one or more processors control the processing of input data according to predefined operation rules or an artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operation rules or the artificial intelligence model are provided through training or learning.

[0072] Here, providing through learning means obtaining predefined operation rules or an AI model with desired characteristics by applying a learning algorithm to multiple learning data. The learning can be performed in the device or electronic device itself in which the AI according to the embodiment is executed, and / or can be implemented through a separate server / system.

[0073] The AI model can contain multiple neural network layers. Each layer has multiple weight values, and each layer performs neural network calculations through calculations between the input data of the layer (such as the calculation results of the previous layer and / or the input data of the AI model) and the multiple weight values of the current layer. Examples of neural networks include but are not limited to convolutional neural networks (CNN), deep neural networks (DNN), recurrent neural networks (RNN), restricted Boltzmann machines (RBM), deep belief networks (DBN), bidirectional recurrent deep neural networks (BRDNN), generative adversarial networks (GAN), and deep Q networks.

[0074] A learning algorithm is a method of training a predetermined target device (e.g., a robot) using multiple learning data to enable, allow, or control the target device to make determinations or predictions. Examples of the learning algorithm include but are not limited to supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0075] As the demands for higher-speed wireless communication systems increase, wireless communication systems are required to have better reliability. The present disclosure provides a signal emitting apparatus and a method for generating an emission signal in a wireless communication system, which makes the wireless communication system have better reliability.

[0076] A signal emitting apparatus according to an embodiment of the present disclosure may be used in a wireless communication system, for example, in a base station-side receiver and a terminal-side receiver.

[0077] FIG. 3B is a block diagram of a terminal or user equipment (UE) 116 according to an embodiment of the disclosure.

[0078] The terminal is an electronic device capable of wireless communication and having various form factors, examples of the terminal may include a UE, a mobile station (MS), a cellular phone, a smartphone, a computer, a tablet, a wearable device, an Internet of Things (IoT) device, or any other device / system capable of performing wireless communication with a base station (BS) and / or another terminal through a wireless channel.

[0079] Referring to FIG. 3B, the UE 116 may include at least one transceiver (hereinafter, referred to as simply "transceiver") 302, at least one processor (hereinafter, referred to as simply "processor") 307, and at least one memory (hereinafter, referred to as simply "memory") 311. According to at least one or a combination of methods corresponding to the embodiments described in the present disclosure, the transceiver 302, the processor 307, and the memory 311 of the UE 116 may operate. However, components of the UE 116 are not limited to the example components illustrated in FIG. 3B. In another embodiment, the UE 116 may further include additional components in addition to the above-mentioned components, or some components may be omitted. Further, in some embodiments, any combination of the transceiver 302, the processor 307, or the memory 311 may be integrated in the form of one component.

[0080] The transceiver 302 may be a communication circuit or communication circuitry that enables the UE 116 to perform wireless communication with a node or an entity of a network. For example, the transceiver 302 may enable the UE 116 to transmit or receive a signal to or from a BS through cellular communication, or to transmit or receive a signal to or from another UE through cellular communication. For example, the transceiver 302 may support at least one of various cellular communication technologies including 3rd generation (3G), 4th generation (4G), long term evolution (LTE), 5th generation (5G) NR, 6th generation (6G), and various cellular wireless communication technologies supported by the transceiver (302) may include all subsequent generations of evolved wireless communications.

[0081] According to an embodiment, the UE 116 may include a plurality of transceivers. For example, in the case of supporting evolved-universal terrestrial radio access-new radio (E-UTRA-NR) dual connectivity (EN-DC), the UE 116 may include a first transceiver supporting the 4G LTE wireless communication and a second transceiver supporting the 5G NR wireless communication. According to another embodiment, in the case of supporting NR-dual connectivity (NR-DC), the UE 116 may include a plurality of transceivers supporting the 5G NR wireless communication. According to still another embodiment, in the case of supporting near field wireless communication, the UE 116 may separately include a transceiver supporting at least one standard in the group of wireless communication protocol standards as defined in the protocol standards for Bluetooth®, wireless local area network (WLAN) network (including institute of electrical and electronics engineers (IEEE) 802.11-2016 standard or its amendments, e.g., 802.11ah, 802.11ad, 802.11ay, 802.11ax, 802.11az, 802.11ba, and 802.11be, without being limited thereto).

[0082] According to an embodiment, the transceiver 302 may include various circuit structures used to transmit or receive signals to or from a BS through a wireless channel. The signals may include control information and data. For example, the transceiver 302 may include a radio frequency (RF) transmitter for up-converting and amplifying the frequency of a transmitted signal and an RF receiver for low-noise-amplifying a received signal and down-converting the frequency thereof. The transceiver 302 may output a signal received through a wireless channel to the processor 307 and may transmit, through a wireless channel, a signal output from the processor 307.

[0083] The processor 307 may control general operations of the UE 116 according to embodiments of the disclosure. The processor 307 may be implemented by one or more integrated circuit (or circuitry) (IC) chips and may execute various data processing operations. The processor 307 may include at least one electric circuit, and may execute instructions (or a program, codes, data, etc.) stored in the memory 311, individually, collectively or in any combination thereof. Further, the processor 307 may include a single-core processor or multi-core processor, and may include a processor assembly including a plurality of processing circuits (circuitry) according to a specific implementation scheme.

[0084] The processor 307 may be electrically, operatively, and / or communicatively coupled to the transceiver 302 to control the transceiver 302.

[0085] The processor 307 may include at least one processor (or processing circuitry), and the at least one processor may perform the following operations individually, collectively or in any combination thereof. For example, the processor 307 may include a communication processor (CP) configured to control communication operations and an application processor (AP) configured to control execution of an upper layer (for example, an application layer). In a specific embodiment, at least a part of the processor 307 may be included in one chip (or IC) and the other part of the processor 307 may be included in another chip (or IC). Otherwise, at least one processor may be included in another component, for example, the transceiver 302 or the memory 311.

[0086] The processor 307 may perform or control or cause an operation of the UE 116 for executing at least one or a combination of methods according to embodiments of the disclosure. For example, the processor 307 may control operations of the UE 116 for processing a downlink signal received from a BS or generating and transmitting an uplink signal to a BS. To this end, the processor 307 may execute a computer program, codes, or instructions stored in the memory 311, so as to control other components of the UE 116 to enable execution of various operations.

[0087] The memory 311 corresponds to a hardware storage device capable of temporarily or permanently storing information and may include one or more storage media. For example, the memory 311 may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory, such as a hard drive, flash memory, or read-only memory (ROM), semipermanent memory, such as random-access memory (RAM), cache memory, or a combination thereof.

[0088] The memory 311 may be electrically, operatively, and / or communicatively coupled to the processor 307 and may be accessed by the processor 307.

[0089] The memory 311 may store a computer program, codes, or instructions executable by the processor 307. According to an embodiment, a computer program, codes, or instructions executable by the processor 307 may be either stored in a single memory device or separated and distributedly stored in two or more memory devices. By executing the instructions stored in the memory 311, the processor 307 may perform various functions according to an embodiment of the disclosure.

[0090] According to an embodiment of the disclosure, operations of the UE 116 may be caused to be performed based on execution of instructions (or a computer program or codes) stored in the memory 311 by at least one processor (or processing circuitry) configured to execute the same individually, collectively, or in any combination thereof, based on processing circuitry that is not configured to execute instructions, and / or based on components of processing circuitry that is not configured to execute instructions.

[0091] FIG. 4 is a block diagram of an example signal emitting apparatus according to an embodiment of the present disclosure.

[0092] As shown in FIG. 4, the signal emitting apparatus 400 may include a first module 401, a digital-to-analog conversion module (DAC) 402, an up-conversion module 403 and a power amplifying device 404.

[0093] In an embodiment, the signal emitting apparatus 400 may refer as the signal emitting electronic device.

[0094] In order to increase a link speed, a larger output signal power is usually provided or a spectral efficiency is improved, and accordingly, the power amplifier (PA; or the power amplifying device) in the signal emitting apparatus generally operates in an operating range close to a saturation point. However, in this situation, the non-linear characteristic of the power amplifier will result in the non-linear distortion of an emission signal, which will produce new frequency components in the emission signal. For example, a second order distortion will produce second harmonics and a double-tone beat frequency, and a third order distortion will produce third harmonics and a multi-tone beat frequency. These new frequency components, whether in or out of the passband, will adversely affect the useful signal. This non-linear distortion not only eliminates the advantages of high spectral efficiency obtained by the application of a linear modulation method, but also causes a series of performance indexes of an emitting-end antenna such as a beam width, a sidelobe suppression and a null depth to deteriorate.

[0095] In addition, in order to improve the spectral efficiency, orthogonal frequency division multiplexing (OFDM) is used in long term evolution (LTE) applications, and high-order quadrature amplitude modulation (QAM) is used in 5G applications, which can also improve the connection speed but will increase a peak-to-average power ratio (PAPR). The high peak-to-average ratio characteristic of modern efficient spectral modulation (such as OFDM and CDMA) signals will make the non-linear distortion of the power amplifier operating near the saturation point more severe.

[0096] The first module 401 according to an embodiment of the present disclosure may include a first neural network, and may be configured to perform predistortion processing on a first digital signal through the first neural network to obtain a second digital signal. The first digital signal may be a to-be-emitted digital signal. The first neural network in the first module 401 may be a trained first neural network. For example, the first neural network may be pre-trained using a sample set of emission signals having a non-linear distortion, such that the first neural network may perform the predistortion processing on the inputted digital signal, to make the outputted digital signal include, for example, the distortion opposite to the non-linear distortion caused by the power amplifying device 404 in advance. In this way, the non-linear distortion of the emission signal caused by the non-linear characteristic of the power amplifying device 404 may be compensated for in a subsequent power amplifying device 404. The non-linear distortion of the emission signals in the sample set may correspond to the power amplifying device 404. For example, the sample set may be obtained by collecting signals power-amplified by the power amplifying device 404. Through the above training, a parameter of the first neural network may be adjusted based on the non-linear characteristic of the power amplifying device 404, that is, the parameter of the first neural network may be determined based on the non-linear characteristic of the power amplifying device 404. The meaning of the parameter of the first neural network at least contains one or more of: a neural network type (e.g., CNN, RNN, and ESN), a number of neural networks, a number of intermediate layers of a neural network, a number of neurons in an intermediate layer of the neural network, an input layer length, an output layer length, and a weight of a neuron.

[0097] The digital-to-analog conversion module 402 may perform a digital-to-analog conversion on the second digital signal outputted by the first module 401, to obtain a first analog signal.

[0098] The up-conversion module 403 may be provided behind the digital-to-analog conversion module 402. The up-conversion module 403 may be configured to perform up-conversion processing on the first analog signal and output the up-converted first analog signal to the power amplifying device 404.

[0099] The power amplifying device 404 may be configured to perform a power amplification on the first analog signal outputted by the digital-to-analog conversion module 402, to generate an emission signal. The generated emission signal may be emitted via an antenna.

[0100] FIG. 5 is a flowchart of a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure.

[0101] The method shown in FIG. 5 may be performed by the signal emitting apparatus 400 shown in FIG. 4.

[0102] As shown in FIG. 5, the method 500 may include steps S501-S504. In step S501, predistortion processing is performed on a first digital signal through a first neural network to obtain a second digital signal. Step S501 may be performed by the first module 401 shown in FIG. 4. For example, in step S501, the predistortion processing may be performed on a to-be-emitted first digital signal through the first neural network in the first module 401 to obtain the second digital signal.

[0103] In step S502, a digital-to-analog conversion may be performed on the second digital signal to obtain a first analog signal. Step S502 may be performed by the digital-to-analog conversion module 402 shown in FIG. 4. For example, the second digital signal is inputted to the digital-to-analog conversion module 402, and the digital-to-analog conversion module 402 is used to perform the digital-to-analog conversion on the second digital signal to obtain the first analog signal.

[0104] In step S503, up-conversion processing may be performed on the first analog signal obtained in step S502. Step S503 may be performed by the up-conversion module 403 shown in FIG. 4.

[0105] In step S504, a power amplification may be performed on the first analog signal through a power amplifying device to generate an emission signal. Step S504 may be performed by the power amplifying device 404 shown in FIG. 4. For example, the power amplification may be performed on the first analog signal through the power amplifying device 404.

[0106] According to the above signal emitting apparatus 400 and the method 500, the neural network-based pre-distortion processing is performed to eliminate the non-linear distortion. From the point of view of deep learning, the pre-distortion processing can be interpreted as a sequence-to-sequence conversion task, in which an input signal in a digital domain is given, the signal is pre-distorted through the pre-distortion processing and a sequence is outputted, thereby improving the linearity of the power amplifying device, making the wireless communication system have better reliability.

[0107] In addition, volterra series-based memory polynomial models are mostly used in traditional predistortion methods. These models use volterra kernels with different non-linearity and memory orders. However, the polynomial fitting of these models can not fully simulate the non-linearity of the power amplifying device, and thus, there will be an error in modeling. In order to improve the precision of the modeling, it is required to increase the order of the fitting polynomial, which will lead to an increase in computational complexity, accompanied by higher requirements on an oversampling frequency. The oversampling frequency often needs to be several times a channel bandwidth, resulting in an increase in device costs. The traditional polynomial methods can only handle the non-linear feature of the device, and accordingly, it is difficult to fit the non-ideal factors of other emitters such as IQ path imbalance.

[0108] Compared with the traditional methods, the neural network-based predistortion processing avoids the disadvantages such as the increase of device costs and the high complexity.

[0109] The non-linear characteristic of the power amplifying device may change with time, temperature, etc., and accordingly, it may be required to update the neural network in the signal emitting apparatus to match the non-linear characteristic of the changed power amplifying device after the changing. The following embodiment provides a structure capable of conveniently updating the neural network in the signal emitting apparatus.

[0110] FIG. 6 is a block diagram of an example signal emitting apparatus according to an other embodiment of the present disclosure.

[0111] As shown in FIG. 6, the signal emitting apparatus 600 may include a first module 601, a digital-to-analog conversion module 602, an up-conversion module 603, a power amplifying device 604, a first switch 605, a down-conversion module 606, an analog-to-digital conversion module (ADC) 607, a second switch 608, and a second module 609. Here, the first module 601, the digital-to-analog conversion module 602, the up-conversion module 603 and the power amplifying device 604 are the same as the first module 401, the digital-to-analog conversion module 402, the up-conversion module 403 and the power amplifying device 404 in FIG. 4, and thus, the detailed description thereof will be omitted.

[0112] The signal emitting apparatus 600 in this embodiment may be configured to operate in a first mode or a second mode. The first mode may be a compensation mode and the second mode may be a training mode. In the first mode, the signal emitting apparatus 600 generates an emission signal based on a first digital signal, that is, operates in the same way as the signal emitting apparatus 400 shown in FIG. 4. In the second mode, the signal emitting apparatus 600 updates a first neural network according to a non-linear characteristic of the power amplifying device. The above signal emitting apparatus 400 and the above method 500 may work in the first mode. For example, the above signal emitting apparatus 400 and the above method 500 only work in the first mode.

[0113] The first switch 605 in the signal emitting apparatus 600 turns on a lower link in the first mode, that is, the first module 601 is connected to the digital-to-analog conversion module 602. The first switch 605 in the signal emitting apparatus 600 turns on an upper link in the second mode, that is, a digital signal is directly inputted to the digital-to-analog conversion module 602 without performing predistortion processing on the digital signal by the first module 601. The digital signal inputted to the digital-to-analog conversion module 602 via the first switch 605 in the second mode may be a third digital signal, and the third digital signal may be a training digital signal from a training sample set, or a to-be-emitted digital signal.

[0114] The second switch 608 in the signal emitting apparatus 600 is in an open state in the first mode. That is, in the first mode, the second switch 608 disconnects the connection between the analog-to-digital conversion module 607 and the second module 609. The second switch 608 in the signal emitting apparatus 600 is in a closed state in the second mode. That is, the second switch 608 connects the analog-to-digital conversion module 607 and the second module 609.

[0115] In the first mode, the first switch 605 turns on the lower link and the second switch 608 is in the open state. The signal emitting apparatus 600 may operate in the same way as the signal emitting apparatus 400 shown in FIG. 4. For example, the first digital signal is pre-distorted by the first module 601, and the pre-distorted digital signal is converted into an analog signal by the digital-to-analog conversion module 602. The analog signal is up-converted by the up-conversion module 603, and then power-amplified by the power amplifying device 604, and the power-amplified analog signal is used as the emission signal to be esmitted through the antenna. The emission signal at this time is a signal after a non-linear compensation, reflecting the error feature after the non-linear compensation.

[0116] In the second mode, the third digital signal may be directly inputted to the digital-to-analog conversion module 602 via the first switch 605 that turns on the upper link, the digital-to-analog conversion module 602 performs a digital-to-analog conversion, the up-conversion module 603 performs up-conversion processing on the analog signal obtained after the digital-to-analog conversion, and the power amplifying device 604 performs a power amplification on the analog signal. The analog signal obtained after the power amplification carries information reflecting the non-linear characteristic of the power amplifying device. The analog signal obtained after the power amplification can be down-converted by the down-conversion module 606, and the down-converted analog signal can be converted into a fourth digital signal by the analog-to-digital conversion module 607. The second module 609 may include a second neural network, and the structure of second neural network is identical to that of the first neural network. The meaning of the structure of the neural network at least contains one or more of: a neural network type (e.g., CNN, RNN, and ESN), a number of included sub-neural networks, a number of intermediate layers of the neural network, a number of neurons in an intermediate layer of the neural network, an input layer length, and an output layer length. The second module 609 may be configured to train, in the second mode, the second neural network with the fourth digital signal as sample data and the third digital signal as tag data (when a training digital signal is inputted to the first switch 605, the training digital signal is used as the tag data, and when a to-be-emitted digital signal is inputted to the first switch 605, the to-be-emitted digital signal is used as the tag data), and update a parameter of the first neural network with a parameter of the trained second neural network. For example, a weight parameter of the trained second neural network is updated to the first neural network. For example, the second module 609 outputs a pre-distorted prediction signal based on the fourth digital signal through the second neural network, compares the prediction signal with the third digital signal used as the tag data, adjusts a neuron weight in the neural network according to the difference between the two signals, and then performs a new round of prediction and comparison until the difference between the prediction signal and the third digital signal is less than a predetermined threshold. At this time, the second module 609 may copy the neuron weight of the second neural network to the first neural network to update the parameter of the first neural network. However, the method of training the neural network according to the embodiment of the present disclosure is not limited thereto, and the second neural network may alternatively be trained using other methods.

[0117] The first switch 605 and the second switch 608 are optional, that is, the first switch 605 and the second switch 608 may not be included in the signal emitting apparatus 600 shown in FIG. 6. In this situation, the switching between the first mode and the second mode may be implemented by, for example, setting an operating state (e.g., an enabled state or a disabled state) of the first module or the second module or an operating state (e.g., an enabled state or a disabled state) of the line connected to the first module or the second module.

[0118] Alternatively, the signal emitting apparatus 600 may further include a power attenuation module 610. The power attenuation module 610 may be configured to perform a power attenuation on an analog signal obtained after the power amplification and outputted by the power amplifying device 604, and output the power-attenuated analog signal to the down-conversion module 606. For example, the power amplifying device 604 may amplify the signal inputted thereto by n times, and the power attenuation module 610 may attenuate the signal inputted thereto to 1 / n of the original power. It should be noted that, due to the non-linear characteristic of the power amplifying device, during the power amplification, the power amplifying device 604 not only amplifies the signal inputted thereto by n times, but also may introduce the non-linear distortion caused by the non-linear characteristic.

[0119] In a method for generating an emission signal in a wireless communication system according to this embodiment, the parameter of the first neural network is determined based on the digital signal before the power amplification and the digital signal after the power amplification. Since the non-linear distortion is due to the non-linear characteristic of the power amplifying device, the digital signal before the power amplification has no non-linear features, but the digital signal after power amplification has non-linear features. By training the first neural network based on the difference between the two signals, the pre-distortion processing performed by the first neural network can be made to contain the feature corresponding to the non-linear characteristic of the power amplifying device.

[0120] The method for generating an emission signal in the wireless communication system according to this embodiment may include the first mode and the second mode. Here, in the first mode, the pre-distortion processing and the digital-to-analog conversion for the first digital signal, the up-conversion for the first analog signal and the generation of the emission signal are performed. In the second mode, the parameter of the first neural network is updated according to the non-linear characteristic of the power amplifying device. The method for generating an emission signal that includes the first mode and the second mode may be performed by the signal emitting apparatus 600 shown in FIG. 6.

[0121] In the first mode, the method for generating an emission signal may be the same as that shown in FIG. 5. For example, when the first switch 605 in the signal emitting apparatus 600 turns on the lower link and the second switch 608 in the signal emitting apparatus 600 is in the open state, the signal emitting apparatus 600 may perform the first mode using the method shown in FIG. 5.

[0122] In the second mode or after the switching from the first mode to the second mode, the method for generating an emission signal in the wireless communication system according to an embodiment of the present disclosure includes updating the first neural network. For example, when the first switch 605 in the signal emitting apparatus 600 turns on the upper link and the second switch 608 in the signal emitting apparatus 600 is in the closed state, the signal emitting apparatus 600 may perform the second mode.

[0123] In some embodiments, the method for generating an emission signal in the wireless communication system according to an embodiment of the present disclosure may further include: switching from the first mode to the second mode, and performing, in the second mode, following operations: performing sequentially the digital-to-analog conversion, the up-conversion processing and the power amplification on the third digital signal; performing the down-conversion processing on the analog signal obtained after the power amplification; converting the down-converted analog signal into the fourth digital signal; and determining the parameter of the first neural network based on the fourth digital signal and the third digital signal.

[0124] FIG. 7 is a flowchart of an update to a first neural network according to a non-linear characteristic of a power amplifying device in a second mode or after the switching from a first mode to the second mode in a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure.

[0125] As shown in FIG. 7, in the second mode or after the switching from the first mode to the second mode, the update to the first neural network according to the non-linear characteristic of the power amplifying device may include steps S701-S704.

[0126] In step S701, a digital-to-analog conversion, an up-conversion and a power amplification may be sequentially performed on a third digital signal without performing predistortion processing by a first module. For example, the third digital signal is inputted to the digital-to-analog conversion module 602 via the first switch 605 that turns on the upper link shown in FIG. 6, an analog signal obtained by performing a digital-to-analog conversion by the digital-to-analog conversion module 602 is inputted to the up-conversion module 603 for up-conversion processing, and the up-converted analog signal is power-amplified by the power amplifying device 604. In this step, the third digital signal is not pre-distorted by the first module.

[0127] In step S702, a down-conversion may be performed on an analog signal obtained after the power amplification and outputted by the power amplifying device 604. For example, the down-conversion module 606 shown in FIG. 6 may perform down-conversion processing on the analog signal obtained after the power amplification and outputted by the power amplifying device 604.

[0128] In step S703, the down-converted analog signal may be converted into a fourth digital signal. For example, the down-converted analog signal outputted by the down-conversion module 606 shown in FIG. 6 may be converted into the fourth digital signal by the analog-to-digital conversion module 607.

[0129] In step S704, a second neural network may be trained with the fourth digital signal as sample data and the third digital signal as tag data, and a parameter of the first neural network may be updated based on a parameter of the trained second neural network. Here, the structure of the second neural network is identical to that of the first neural network. For example, the second neural network may be trained by the second module 609 shown in FIG. 6 with the fourth digital signal as the sample data and the third digital signal as the tag data, and the neuron weight of the trained second neural network is updated to the first neural network.

[0130] Alternatively, in the second mode, the update to the first neural network according to the non-linear characteristic of the power amplifying device may further include: performing a power attenuation on the analog signal obtained after the power amplification, before performing the down-conversion processing. For example, when the signal emitting apparatus 600 shown in FIG. 6 includes the power attenuation module 610, the power attenuation module 610 may perform the power attenuation on the analog signal obtained after the power amplification and outputted by the power amplifying device 604, and input the power-attenuated signal to the down-conversion module 606.

[0131] For the signal emitting apparatus 600 described with reference to FIG. 6 and the method depicted with reference to FIG. 7, it is possible to flexibly switch between the operating modes (the first mode and the second mode), and select a time to perform non-linear feature learning and compensation so as to better accommodate changes in the non-linear characteristic of the power amplifying device.

[0132] FIG. 8 is a block diagram of an example signal emitting apparatus according to an other embodiment of the present disclosure.

[0133] As shown in FIG. 8, the signal emitting apparatus 800 may include a first module 801, a digital-to-analog conversion module 802, an up-conversion module 803, a power amplifying device 804, a first switch 805, a down-conversion module 806, an analog-to-digital conversion module 807, and a second switch 808. Here, the digital-to-analog conversion module 802, the up-conversion module 803, the power amplifying device 804, the first switch 805, the down-conversion module 806 and the analog-to-digital conversion module 807 are the same as the digital-to-analog conversion module 602, the up-conversion module 603, the power amplifying device 604, the first switch 605, the down-conversion module 606 and the analog-to-digital conversion module 607 in FIG. 6, and thus, the detailed description thereof will be omitted.

[0134] The signal emitting apparatus 800 differs from the signal emitting apparatus 600 in that the signal emitting apparatus 800 does not include the second module 609, and trains the first neural network through the first module 801 so as to update the first neural network.

[0135] The signal emitting apparatus 800 in this embodiment may be configured to operate in a first mode or a second mode. In the first mode, the signal emitting apparatus 800 outputs an emission signal based on a first digital signal, that is, operates in the same way as the signal emitting apparatus 400 shown in FIG. 4.

[0136] In this embodiment, the second switch 808 in the signal emitting apparatus 800 is in an open state in the first mode. That is, in the first mode, the second switch 808 disconnects the connection between the analog-to-digital conversion module 807 and the first module 801. The second switch 808 in the signal emitting apparatus 800 is in a closed state in the second mode. That is, the second switch 808 connects the analog-to-digital conversion module 807 and the first module 801.

[0137] In the second mode or after the switching from the first mode to the second mode, the first switch 805 turns on an upper link, and a third digital signal is transmitted to the digital-to-analog conversion module 802 via the first switch 805 without passing through the first module 801. The third digital signal is converted into a first analog signal by the digital-to-analog conversion module 802, and inputted to the up-conversion module 803 for up-conversion processing, and then the up-converted analog signal is power-amplified by the power amplifying device 804. The power-amplified analog signal outputted from the power amplifying device 804 is down-converted by the down-conversion module 806, and then converted into a fourth digital signal by performing an analog-to-digital conversion by the analog-to-digital conversion module 807. The fourth digital signal is transmitted to the first module 801 via the second switch 808. The first module 801 trains the first neural network with the fourth digital signal as sample data and the third digital signal as tag data (e.g., when a training digital signal is inputted to the first switch 805, the training digital signal is used as the tag data, and when a to-be-emitted digital signal is inputted to the first switch 805, the to-be-emitted digital signal is used as the tag data). For example, the first module 801 outputs a pre-distorted prediction signal based on the fourth digital signal through the first neural network, compares the prediction signal with the third digital signal used as the tag data, adjusts a neuron weight in the neural network based on a difference between the two signals, and then performs a new round of prediction and comparison until the difference between the prediction signal and the third digital signal is less than a predetermined threshold. At this time, the adjusted first neural network is the updated first neural network. However, the method of training the neural network according to the embodiment of the present disclosure is not limited thereto, and the first neural network may alternatively be trained using other methods.

[0138] The first switch 805 and the second switch 808 are optional, that is, the first switch 805 and the second switch 808 may not be included in the signal emitting apparatus 800 shown in FIG. 8. In this situation, the switching between the first mode and the second mode may be implemented by, for example, setting an operating state (e.g., an enabled state or a disabled state) of the first module or an operating state (e.g., an enabled state or a disabled state) of the line connected to the first module.

[0139] A method for generating an emission signal in a wireless communication system according to this embodiment may include the first mode and the second mode. Here, in the first mode, the pre-distortion processing and the digital-to-analog conversion for the first digital signal, the up-conversion processing for the first analog signal and the generation of the emission signal are performed. In the second mode, the first neural network is updated according to the non-linear characteristic of the power amplifying device. The method for generating an emission signal that includes the first mode and the second mode may be performed by the signal emitting apparatus 800 shown in FIG. 8.

[0140] In the first mode, the method for generating an emission signal may be the same as that shown in FIG. 5. For example, when the first switch 805 in the signal emitting apparatus 800 turns on a lower link and the second switch 808 in the signal emitting apparatus 800 is in the open state, the signal emitting apparatus 600 may perform the first mode using the method shown in FIG. 5.

[0141] In the second mode or after the switching from the first mode to the second mode, the method for generating an emission signal in the wireless communication system according to an embodiment of the present disclosure includes updating the first neural network. For example, when the first switch 805 in the signal emitting apparatus 800 turns on the upper link and the second switch 808 in the signal emitting apparatus 800 is in the closed state, the signal emitting apparatus 800 may perform the second mode.

[0142] In some embodiments, the method for generating an emission signal in the wireless communication system according to an embodiment of the present disclosure may further include: switching from the first mode to the second mode, and performing, in the second mode, following operations: performing sequentially the digital-to-analog conversion, the up-conversion processing and the power amplification on the third digital signal; performing the down-conversion processing on the analog signal obtained after the power amplification; converting the down-converted analog signal into the fourth digital signal; and determining the parameter of the first neural network based on the fourth digital signal and the third digital signal. FIG. 9 is a flowchart of an update to a first neural network according to a non-linear characteristic of a power amplifying device in a second mode or after the switching from a first mode to the second mode in a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure.

[0143] The update to the first neural network according to the non-linear characteristic of the power amplifying device may include steps S901-S904. Here, steps S901-S903 are the same as steps S701-S703 described with reference to FIG. 7, and thus, the detailed description thereof will be omitted.

[0144] In step S904, a first neural network may be trained with the fourth digital signal as sample data and the third digital signal as tag data, to update a parameter of the first neural network. For example, by inputting the fourth digital signal and the third digital signal to the first module 801 in FIG. 8, the first module 801 trains the first neural network with the third digital signal as the tag data and the fourth digital signal as the sample data.

[0145] The signal emitting apparatus 800 in FIG. 8 may further include a power attenuation module 810. The power attenuation module 810 is the same as the power attenuation module 610 in FIG. 6, and thus, the detailed description thereof will be omitted. The method for generating an emission signal in the wireless communication system according to this embodiment may further include a step corresponding to the power attenuation module 810, and the step is the same as the corresponding step described with reference to FIGS. 6 and 7, and thus, the detailed description thereof will be omitted.

[0146] For the signal emitting apparatus 800 described with reference to FIG. 8 and the method depicted with reference to FIG. 9, it is possible to flexibly switch between the operating modes (the first mode and the second mode), and select a time to perform non-linear feature learning and compensation so as to better accommodate changes in the non-linear characteristic of the power amplifying device. Moreover, one neural network is used, thereby saving hardware resource overheads.

[0147] For the signal emitting apparatuses and the methods described with reference to FIGS. 6-9, it is possible to switch between the first mode and the second mode with a first period. The first period may be predefined or configured.

[0148] According to an other embodiment of the present disclosure, for the signal emitting apparatuses and the methods described with reference to FIGS. 6-9, the first mode is switched to the second mode when a first condition is satisfied. Alternatively, the first mode is switched to the second mode when the first condition is satisfied, and the switching between the first mode and the second mode is performed with the first period. The first condition includes at least one of:

[0149] a ratio of an average power of an adjacent frequency channel of an emission signal to an average power of a currently used channel being greater than or equal to a first threshold;

[0150] a difference between a reference signal of the emission signal and the emission signal within a predetermined time being greater than or equal to a second threshold; and

[0151] a change amount of a ratio between a peak power and an average power of the first digital signal within the predetermined time being greater than or equal to a third threshold.

[0152] The ratio (ACPR) of the average power of the adjacent frequency channel of the emission signal to the average power of the currently used channel may be used to evaluate the non-linearity of the signal emitting apparatus, and should generally be less than a predetermined threshold, e.g., the first threshold. In addition, ACLR, the reciprocal of the ACPR, may alternatively be used as a determination condition for the switching of the operation mode. Therefore, when the ACPR is greater than or equal to the first threshold, it indicates that the neural network currently used for pre-distortion does not match the non-linear characteristic of the power amplifying device and thus needs to be updated. At this time, the signal emitting apparatus may start to operate in the second mode or switch between the first mode and the second mode with a predetermined period. When the ACPR is less than the first threshold, it can be determined that the non-linear characteristic of the power amplifying device is effectively eliminated, that is, the neural network matches the non-linear characteristic of the power amplifying device. At this time, the periodic switching between the operating modes can be stopped or the second mode can be stopped. The first threshold for the ACPR may vary depending on an apparatus type. For example, the first threshold when the signal emission apparatus is positioned at a base station is different from the first threshold when the signal emission apparatus is positioned at a terminal. Alternatively, the first threshold varies depending on a wireless communication system. For example, in an LTE system, an NR system and a WiFi system, the first thresholds are different.

[0153] The difference between the reference signal of the emission signal and the emission signal within the predetermined time is an index that quantifies a modulation quality, which reflects the distortion of received and sent signals caused by non-ideal factors. The difference generally needs to be less than a predetermined threshold, for example, the second threshold. The difference between the reference signal of the emission signal and the emission signal within the predetermined time may be measured, for example, using an error vector magnitude (EVM). The EVM is a magnitude of a vector difference between the reference signal and the emission signal that are normalized to a peak signal amplitude, and the EVM index increases with the increase of the modulation order, and accordingly, a higher order modulation needs to satisfy a more severe EVM index. Therefore, when EVM is greater than or equal to the second threshold, it can be determined that the non-linear characteristic of the signal emitting apparatus is not effectively eliminated, that is, the compensation of the neural network for the non-linear characteristic of the power amplifying device does not match, and the network parameter of the neural network needs to be updated to match the non-linear feature of the current power amplifying device. At this time, the signal emitting apparatus may start to operate in the second mode or switch between the first mode and the second mode with the predetermined period. When the EVM is less than the second threshold, it can be determined that the non-linear characteristic of the power amplifying device is effectively eliminated, that is, the neural network matches the non-linear characteristic of the power amplifying device. At this time, the periodic switching between the operating modes may be stopped or the second mode may be stopped. Alternatively, the second threshold varies depending on an adopted modulation order. For example, the second thresholds are different when a QAM modulation and a QPSK modulation are adopted. Alternatively, when the modulation order increases, the second threshold decreases correspondingly. For example, when the wireless communication system is converted from the QPSK modulation to the 16 QAM modulation, the second threshold increases.

[0154] The ratio (PAPR) between the peak power and the average power of the first digital signal is an index used to describe the difference between the peak power and the average power of the emission signal. The greater the PAPR value is, the larger the dynamic range that the signal needs during transmission is. Since the dynamic range of a general power amplifying device is limited, a signal with a large PAPR easily enters a non-linear region of the power amplifying device, which causes the non-linear distortion of the signal, resulting in a significant spectrum spreading interference and in-band signal distortion. Accordingly, the overall system performance is seriously degraded. Therefore, for the power amplifying device given in the signal emitting apparatus, the greater the PAPR of the inputted first digital signal is, the greater the influence caused by the non-linearity of the power amplifying device is, and the higher the requirement on the degree of matching between the neural network performing the non-linear compensation and the non-linearity of the power amplifying device is. Thus, when the change amount (e.g., a relatively rising value) of the PAPR within the predetermined time is greater than or equal to a predetermined threshold (e.g., the third threshold), it can be determined that there is a high probability the non-linear characteristic of the power amplifying device cannot be effectively eliminated, that is, the compensation of the neural network for the non-linear characteristic of the power amplifying device does not match, the network parameter of the neural network needs to be updated to better match the non-linear feature of the current power amplifying device, thereby ensuring the performance of the signal emitting apparatus under the condition that the first digital signal has a high PAPR. At this time, the signal emitting apparatus may start to operate in the second mode or switch between the first mode and the second mode with the predetermined period. Similarly, when the relatively rising value of the PAPR within the predetermined time is less than the third threshold, it can be determined that there is high probability that the non-linear characteristic of the power amplifying device can be effectively eliminated, that is, the neural network matches the non-linear characteristic of the power amplifying device. At this time, the periodic switching between the operating modes may be stopped or the second mode may be stopped.

[0155] For the signal emitting apparatuses and the methods described with reference to FIGS. 6-9, it is further possible to switch from the second mode to the first mode after the predetermined time or a predetermined number of times of training of a neural network (e.g., the first neural network or the second neural network), or when a model training loss is less than or equal to a fourth threshold; or when the first condition is not satisfied, stop the switching between the first mode and the second mode with the first period, and switch from the second mode to the first mode. The fourth threshold may be a threshold corresponding to the model training loss. In some implementations, for the signal emitting apparatuses and the methods described with reference to FIGS. 6-9, it is further possible to switch from the second mode to the first mode according to one or more of the predetermined time, the number of times of training of the neural network (the first neural network or the second neural network) and the model training loss. Specifically, it is possible to switch from the second mode to the first mode when one or more of the predetermined time, the predetermined number of times of training of the neural network (e.g., the first neural network or the second neural network) and the model training loss being less than or equal to the fourth threshold are satisfied.

[0156] FIG. 10 is a block diagram of an example signal emitting apparatus according to an other embodiment of the present disclosure.

[0157] As shown in FIG. 10, the signal emitting apparatus 1000 may include a first module 1001, a digital-to-analog conversion module 1002, an up-conversion module 1003, a power amplifying device 1004, a down-conversion module 1006, an analog-to-digital conversion module 1007, and a second module 1009. Here, the first module 1001, the digital-to-analog conversion module 1002, the up-conversion module 1003 and the power amplifying device 1004 are the same as the first module 401, the digital-to-analog conversion module 402, the up-conversion module 403 and the power amplifying device 404 in FIG. 4, and thus, the detailed description thereof will be omitted.

[0158] According to this embodiment, a first digital signal is pre-distorted by the first module 1001, the pre-distorted digital signal is converted into a first analog signal by the digital-to-analog conversion module 1002, the first analog signal is up-converted by the up-conversion module 1003, the up-converted analog signal is power-amplified by the power amplifying device 1004 to obtain an emission signal, and the emission signal may be emitted via an antenna. The emission signal may further be inputted to the down-conversion module 1006. For example, the emission signal may be inputted to the down-conversion module 1006 before being emitted by the antenna, and used in the training and updating process of the second module 1009 described later. In this situation, the updated first neural network may be used to pre-distort a to-be-emitted first digital signal. Then, the digital-to-analog conversion, the up-conversion processing and the power amplification are sequentially performed on the pre-distorted signal to obtain a new emission signal, and the new emission signal is finally emitted by the antenna. The emission signal may alternatively be inputted to the down-conversion module 1006 after being emitted by the antenna, to be used as sample data for use in the training and updating process of the second module 1009 described later, and the updated first neural network may perform updated pre-distortion processing on a new to-be-emitted digital signal.

[0159] The emission signal inputted to the down-conversion module 1006 may be down-converted by the down-conversion module 1006, and then converted into a fifth digital signal by performing an analog-to-digital conversion by the analog-to-digital conversion module 1007.

[0160] The fifth digital signal is inputted to the second module 1009. The second module 1009 includes a third neural network. The structure of the third neural network may be different from that of the first neural network in the first module 1001. The second module 1009 is configured to train the third neural network with the fifth digital signal as sample data and the first digital signal as tag data, and update the parameter of the first neural network based on an output result of the third neural network. For example, the second module 1009 may output a pre-distorted prediction signal based on the fifth digital signal through the third neural network, compare the prediction signal with the first digital signal used as the tag data, adjust a neuron weight in the neural network based on a difference between the two signals, and then perform a new round of prediction and comparison until the difference between the prediction signal and the first digital signal is less than a predetermined threshold. At this time, the second module 1009 may input, to the first module, the output result (e.g., an intermediate quantity) of the third neural network that is used to update the first neural network, and the first neural network is updated according to the output result. However, the method of training the neural network according to the embodiment of the present disclosure is not limited thereto, and the second neural network may alternatively be trained using other methods.

[0161] In some embodiments, a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure may further include: performing the down-conversion processing on the emission signal; converting the down-converted emission signal into the fifth digital signal; and updating the first neural network based on the fifth digital signal and the first digital signal.

[0162] FIG. 11 is a flowchart of a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure.

[0163] As shown in FIG. 11, the method 1100 includes steps S1101-S1107. Here, the steps S1101-S1104 are the same as the steps S501-S504 in the method 500 shown in FIG. 5, and thus, the detailed description thereof will be omitted.

[0164] In step S1105, down-conversion processing may be performed on the emission signal. For example, step S1105 may be performed by the down-conversion module 1006 in FIG. 10.

[0165] In step S1106, the down-converted emission signal may be converted into a fifth digital signal. For example, step S1106 may be performed by the analog-to-digital conversion module 1007 in FIG. 10.

[0166] In step S1107, a third neural network may be trained with the fifth digital signal as sample data and the first digital signal as tag data, and a parameter of the first neural network may be updated according to an output result of the third neural network. The structure of the third neural network is different from that of the first neural network. For example, step S1107 may be performed by the second module 1009 in FIG. 10.

[0167] The signal emitting apparatus 1000 in FIG. 10 may further include a power attenuation module 1010. The power attenuation module 1010 is the same as the power attenuation module 610 in FIG. 6, and thus, the detailed description thereof will be omitted. The method for generating an emission signal in the wireless communication system according to this embodiment may further include a step corresponding to the power attenuation module 1010, and the step is the same as the corresponding step described with reference to FIGS. 6 and 7, and thus, the detailed description thereof will be omitted.

[0168] In the signal emitting apparatus 1000 described with reference to FIG. 10 and the method depicted with reference to FIG. 11, the first neural network and the third neural network that have different structures are used, such that their designs can be more flexible.

[0169] FIG. 12 is a block diagram of an example signal emitting apparatus according to an other embodiment of the present disclosure.

[0170] As shown in FIG. 12, the signal emitting apparatus 1200 may include a first module 1201, a digital-to-analog conversion module 1202, an up-conversion module 1203, a power amplifying device 1204, a down-conversion module 1206, an analog-to-digital conversion module 1207, and a second module 1209. Alternatively, the signal emitting apparatus 1200 may further include a power attenuation module 1210. The first module 1201, the digital-to-analog conversion module 1202, the up-conversion module 1203, the power amplifying device 1204, the down-conversion module 1206, the analog-to-digital conversion module 1207 and the power attenuation module 1210 shown in FIG. 12 are the same as the first module 1001, the digital-to-analog conversion module 1002, the up-conversion module 1003, the power amplifying device 1004, the down-conversion module 1006, the analog-to-digital conversion module 1007, and the power attenuation module 1010 shown in FIG. 10, and thus, the detailed description thereof will be omitted.

[0171] The signal emitting apparatus 1200 differs from the signal emitting apparatus 1000 shown in FIG. 10 in that the second module 1209 includes a second neural network having the same structure as the first neural network in the first module 1201; and the second module 1209 is configured to train the second neural network with a fifth digital signal as sample data and a second digital signal as tag data, and update a parameter of the first neural network based on a parameter of the trained second neural network. For example, the structure and the neuron weight of the first neural network are updated based on the structure and the neuron weight of the trained second neural network. The second digital signal may be obtained by performing predistortion processing on a first digital signal by the first module 1201.

[0172] The first module and the second module can be provided in the same hardware in the present disclosure. For example, the second module and the first module may be implemented by a processor or computing apparatus.

[0173] In some embodiments, a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure may further include: performing a down-conversion on an emission signal; converting the down-converted emission signal into the fifth digital signal; and updating the parameter of the first neural network based on the fifth digital signal and the first digital signal.

[0174] FIG. 13 is a flowchart of a method for generating an emission signal in a wireless communication system according to an embodiment of the present disclosure.

[0175] As shown in FIG. 13, the method 1300 includes steps S1301-S1307. Here, steps S1301-S1306 are the same as steps S1101-S1106 in the method 1100 shown in FIG. 11, and thus, the detailed description thereof will be omitted.

[0176] In step S1307, a second neural network may be trained with the fifth digital signal as sample data and the second digital signal as tag data, and a parameter of the first neural network may be updated based on a parameter of the trained second neural network. For example, step S1307 may be performed by the second module 1209 in FIG. 12.

[0177] The method for generating an emission signal in the wireless communication system according to this embodiment may further include a step corresponding to the power attenuation module 1210, and the step is the same as the corresponding step described with reference to FIGS. 6 and 7, and thus, the detailed description thereof will be omitted.

[0178] According to an other embodiment of the present disclosure, for the signal emitting apparatus 1200 described with reference to FIG. 12 and the method depicted with reference to FIG. 13, it is possible to start updating when at least one of the following conditions is satisfied:

[0179] a ratio of an average power of an adjacent frequency channel of the emission signal to an average power of a currently used channel being greater than or equal to a first threshold;

[0180] a difference between a reference signal of the emission signal and the emission signal within a predetermined time being greater than or equal to a second threshold; and

[0181] a change amount of a ratio between a peak power and an average power of the first digital signal within the predetermined time being greater than or equal to a third threshold.

[0182] According to an other embodiment of the present disclosure, for the signal emitting apparatus 1200 described with reference to FIG. 12 and the method depicted with reference to FIG. 13, it is possible to update the parameter of the first neural network with a predetermined period.

[0183] In the signal emitting apparatus 1200 described with reference to FIG. 12 and the method depicted with reference to FIG. 13 use the first neural network and the second neural network that have the same structure, such that their designs can be simpler.

[0184] The pre-distortion may alternatively not be performed in a situation where the non-linear distortion influence is small or the requirement of the system on the signal precision is not high, so as to save computational resource consumption and power consumption. Thus, in some embodiments, for the signal emitting apparatuses and the methods described with reference to FIGS. 1-12, when an amplitude of the first digital signal is less than or equal to a predetermined threshold (e.g., a fifth threshold) and / or a modulation order of the first digital signal is less than or equal to a predetermined threshold (e.g., a sixth threshold), it is possible to not perform the pre-distortion processing on the first digital signal using the first module, that is, it is possible to operate in a third mode. For example, the signal emitting apparatus 600 in FIG. 6 and the signal emitting apparatus 800 in FIG. 8 may not enable the predistortion processing by connecting the first switch to the upper link. The signal emitting apparatus 400 in FIG. 4, the signal emitting apparatus 1000 in FIG. 10 and the signal emitting apparatus 1200 in FIG. 12 may not enable the pre-distortion processing by setting the first module to be inoperative.

[0185] For example, in a short-distance and low-power communication link, since the amplitude of the signal is not high, it is not easy to enter the non-linear interval of the power amplifying device. When the amplitude of the first digital signal is less than or equal to the fifth threshold, it can be determined that the influence of the non-linearity of the power amplifying device on the small signal is limited, and thus the pre-distortion processing can be disabled, that is, the third mode can be entered.

[0186] For example, in 5G NR, 3GPP TS38.141 has different requirements for the PDSCH EVMs of different modulation schemes, for example, QPSK-18.50%, 16QAM-13.50%, 64QAM-9% and 256QAM-4.50%. With the decrease of the modulation order, the requirements for the EVM are continuously decreased. For a signal having a lower modulation order and adopting QPSK, and the like, the requirements for the EVM are relatively loose, and the requirements can be satisfied even without the pre-distortion processing. When the modulation order of the to-be-emitted first digital signal is less than or equal to the sixth threshold, it can be determined that the influence of the non-linear characteristic of the power amplifying device on the small signal is limited, and thus the pre-distortion processing can be disabled, that is, the third mode can be entered.

[0187] In the third mode, the signal emitting apparatus may be configured to: perform the digital-to-analog conversion on the first digital signal through the digital-to-analog conversion module to obtain a second analog signal; perform the up-conversion processing on the second analog signal through the up-conversion module; and perform the power amplification on the up-converted second analog signal through the power amplifying device, to generate an emission signal.

[0188] In addition, by increasing the number of cascaded neural networks and the number of intermediate layers of a neural network, and increasing the number of neurons in an intermediate layer, the neural networks can be made more complex, and the capability of the neural networks to process complex data can be improved, and the structural complexity of the neural networks should match the complexity of the non-linear problem of the power amplifying device to be processed. Therefore, it would be advantageous to be able to adjust the structure of a neural network according to a to-be-processed signal.

[0189] In some embodiments, for the signal emitting apparatuses and the methods described with reference to FIGS. 1-12, it is possible to adjust the structure of the first neural network according to configuration information of the to-be-emitted first digital signal. The configuration information of the first digital signal may include information related to the first digital signal, for example, a system bandwidth, a modulation and coding scheme and the like. Therefore, the structure of the first neural network may be adjusted according to the configuration information, such that the first neural network can match the to-be-processed signal.

[0190] In some embodiments, adjusting the structure of the first neural network according to the configuration information of the first digital signal includes: reducing a number of neurons in an intermediate layer of the first neural network and / or reducing a number of intermediate layers when the system bandwidth in the configuration information of the first digital signal; or increasing the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers, when a modulation order in the configuration information of the first digital signalincreases.

[0191] The reduction of the system bandwidth means the simplification of the non-linear feature of the power amplifying device, and at this time, it is possible to correspondingly reduce the number of the neurons in the intermediate layer of the neural network or reduce the number of the intermediate layers. That is, the smaller the system bandwidth is, the smaller the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers are, which can reduce the computational complexity of the neural network and, at the same time, can avoid the performance loss due to the overfitting during training.

[0192] The increase of the modulation order means that the influence of the non-linear characteristic of the power amplifying device will be more severe, and at this time, the neural network can be adjusted to increase the number of the neurons in the intermediate layer or increase the number of the intermediate layers. That is, the larger the modulation order is, the greater the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers are.

[0193] By adjusting the structure of the first neural network according to the configuration information of the first digital signal, it can be realized that the performance of the neural network matches the complexity of the non-linear problem of the power amplifying device, so as to avoid the performance loss caused by the overfitting during the training.

[0194] An electronic device is further provided in an embodiment of the present disclosure. The electronic device includes a processor, and alternatively, may further include a transceiver and / or memory coupled to the processor. The processor is configured to perform the steps in the method provided in any of the alternative embodiments of the present disclosure.

[0195] FIG. 14 is a schematic structural diagram of an electronic device applicable to an embodiment of the present disclosure. As shown in FIG. 14, the electronic device 1400 shown in FIG. 14 includes a processor 1401 and a memory 1403. Here, the processor 1401 is connected with the memory 1403 through, for example, a bus 1402. Alternatively, the electronic device 1400 may further include a transceiver 1404, and the transceiver 1404 may be used for data interaction (e.g., the sending of data and / or the reception of data) between the electronic device and an other electronic device. It should be noted that, in practice, the transceiver 1404 is not limited to one, and the structure of the electronic device 1400 does not constitute a limitation to the embodiments of the present disclosure. Alternatively, the electronic device may be a first network node, a second network node, or a third network node.

[0196] The processor 1401 may be a CPU (central processing unit), a general purpose processor, a DSP (digital signal processor), an ASIC (application specific integrated circuit), an FPGA (field programmable gate array) or　other programmable logic devices, a transistor logic device, a hardware component, or any combination thereof. The processor 1401 may implement or perform various exemplary logical blocks, modules and circuits described in combination with the present disclosure. The processor 1401 may alternatively be implemented as a combination of computing functions, containing, for example, a combination of one or more microprocessors and a combination of a DSP and a microprocessor.

[0197] The bus 1402 may include a path to communicate information between the above components. The bus 1402 may be a PCI (peripheral component interconnect) bus, an EISA (extended industry standard architecture) bus or the like. The bus 1402 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the bus is only represented by one thick line in FIG. 14, but it does not indicate that there is only one bus or one type of bus.

[0198] The memory 1403 may be a ROM (read only memory) or other types of static storage devices that can store static information and instructions, or a RAM (random access memory) or other types of dynamic storage devices that can store information and instructions, or may be an EEPROM (electrically erasable programmable read only memory), a CD-ROM (compact disc read only memory) or other optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disc storage medium, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and that can be read by a computer, and is not limited herein.

[0199] The memory 1403 is configured to store a computer program for performing embodiments of the present disclosure, and the computer program is controlled and executed by the processor 1401. The processor 1401 is configured to execute the computer program stored in the memory 1403 to implement the steps shown in the foregoing method embodiments.

[0200] According to an embodiment of the present disclosure, a computer readable storage medium is provided, the computer readable storage medium storing a computer program. The computer program, when executed by a processor, may implement the steps in the foregoing method embodiments and the corresponding contents.

[0201] According to an embodiment of the present disclosure, a computer program product is further provided, the a computer program product including a computer program. The computer program, when executed by a processor, may implement the steps in the foregoing method embodiments and the corresponding contents.

[0202] In an embodiment, the parameter of the first neural network is determined based on a digital signal before the power amplification and a digital signal after the power amplification.

[0203] In an embodiment, the method further comprises: switching from the first mode to a second mode, and performing, in the second mode, following operations: performing sequentially the digital-to-analog conversion, the up-conversion processing and the power amplification on a third digital signal; performing down-conversion processing on an analog signal obtained after the power amplification; converting the down-converted analog signal into a fourth digital signal; and determining the parameter of the first neural network based on the fourth digital signal and the third digital signal.

[0204] In an embodiment, the determining the parameter of the first neural network based on the fourth digital signal and the third digital signal comprises: training a second neural network with the fourth digital signal as sample data and the third digital signal as tag data, and updating the parameter of the first neural network based on a parameter of the trained second neural network, wherein a structure of the second neural network is identical to a structure of the first neural network.

[0205] In an embodiment, the determining the parameter of the first neural network based on the fourth digital signal and the third digital signal comprises: training the first neural network with the fourth digital signal as sample data and the third digital signal as tag data, to update the parameter of the first neural network.

[0206] In an embodiment, switching between the first mode and the second mode is performed with a first period.

[0207] In an embodiment, when a first condition is satisfied, the first mode is switched to the second mode; or when the first condition is satisfied, the first mode is switched to the second mode, and the switching between the first mode and the second mode is performed with a first period; wherein the first condition comprises at least one of: a ratio of an average power of an adjacent frequency channel of the emission signal to an average power of a currently used channel being greater than or equal to a first threshold; a difference between a reference signal of the emission signal and the emission signal within a predetermined time being greater than or equal to a second threshold; and a change amount of a ratio between a peak power and an average power of the first digital signal within the predetermined time being greater than or equal to a third threshold.

[0208] In an embodiment, the method further comprises: switching from the second mode to the first mode when one or more of the predetermined time passing, a predetermined number of times of training being finished and a model training loss being less than or equal to a fourth threshold are satisfied; or when the first condition is not satisfied, stopping the switching between the first mode and the second mode with the first period, and switching from the second mode to the first mode.

[0209] In an embodiment, the method further comprises: entering a third mode when an amplitude of the first digital signal is less than or equal to a fifth threshold and / or a modulation order of the first digital signal is less than or equal to a sixth threshold, and performing, in the third mode, following operations: performing the digital-to-analog conversion on the first digital signal to obtain a second analog signal; performing the up-conversion processing on the second analog signal; and performing the power amplification on the up-converted second analog signal through the power amplifying device, to generate an emission signal.

[0210] In an embodiment, the method further comprises: performing down-conversion processing on the emission signal; converting the down-converted emission signal into a fifth digital signal; and determining the parameter of the first neural network based on the fifth digital signal and the first digital signal.

[0211] In an embodiment, the method further comprises: training a third neural network with the fifth digital signal as sample data and the first digital signal as tag data, and updating the parameter of the first neural network according to an output result of the third neural network.

[0212] In an embodiment, the method further comprises: training a second neural network with the fifth digital signal as sample data and the second digital signal as tag data, and updating the parameter of the first neural network based on a parameter of the trained second neural network, wherein a structure of the second neural network is identical to a structure of the first neural network.

[0213] In an embodiment, the method further comprises: adjusting a structure of the first neural network according to configuration information of the first digital signal.

[0214] In an embodiment, the structure of the first neural network comprises at least one of: a type of the first neural network; a number of sub-neural networks comprised in the first neural network; a number of intermediate layers of the first neural network; a number of neurons in an intermediate layer of the first neural network; and lengths of an input layer and an output layer of the first neural network.

[0215] In an embodiment, the adjusting a structure of the first neural network according to configuration information of the first digital signal comprises: determining the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers based on information related to a system bandwidth in the configuration information of the first digital signal; or determining the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers based on a modulation order in the configuration information of the first digital signal.

[0216] In an embodiment, the smaller the system bandwidth is, the fewer the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers are; and the larger the modulation order is, the greater the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers are.

[0217] In an embodiment, the method further comprises: performing a power attenuation on the analog signal after the power amplification, before performing the down-conversion processing.

[0218] The terms "first," "second," "third," "fourth," "1," "2," and the like, if present, in the specification and claims of the present disclosure and the drawings are used to distinguish between similar objects, and not necessarily used to describe a specific order or sequence. It should be understood that, if appropriate, the data so used is interchangeable, such that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described literally.

[0219] It should be understood that the operation steps are indicated by arrows in the flowcharts of the embodiments of the present disclosure, but the orders in which these steps are performed are not limited to the orders indicated by the arrows. Unless explicitly described herein, in some implementation scenarios of embodiments of the present disclosure, the implementation steps in the flowcharts may be performed in a different order as desired. In addition, some or all of the steps in each flowchart may include a plurality of sub-steps or a plurality of stages based on an actual implementation scenario. Some or all of these sub-steps or stages may be performed at the same moment, and alternatively, each of these sub-steps or stages may be respectively performed at a different moment. In a scenario in which the execution moments are different, the execution order of these sub-steps or stages may be flexibly configured as desired, and is not limited in the embodiments of the present disclosure.

[0220] The text and drawings are provided as examples only to help readers understand the present disclosure. The text and drawings are not intended to limit and should not be interpreted as limiting the scope of the present disclosure in any way. Although certain embodiments and examples have been provided, based on the content disclosed herein, it is obvious to those skilled in the art that modifications can be made to the illustrated embodiments and examples without departing from the scope of the present disclosure. The use of other similar implementations based on the technical concept of the present disclosure also falls within the scope of embodiments of the present disclosure.

Claims

A method performed by an electronic device for generating an emission signal, the method comprising:performing, in a first mode, following operations:performing predistortion processing on a first digital signal through a first neural network to obtain a second digital signal;performing a digital-to-analog conversion on the second digital signal to obtain a first analog signal;performing up-conversion processing on the first analog signal; andperforming a power amplification on the up-converted first analog signal through a power amplifying device to generate an emission signal,wherein a parameter of the first neural network is determined based on a non-linear characteristic of the power amplifying device.The method according to claim 1, wherein the parameter of the first neural network is determined based on a digital signal before the power amplification and a digital signal after the power amplification.The method according to claim 2, further comprising:switching from the first mode to a second mode, and performing, in the second mode, following operations:performing sequentially the digital-to-analog conversion, the up-conversion processing and the power amplification on a third digital signal;performing down-conversion processing on an analog signal obtained after the power amplification;converting the down-converted analog signal into a fourth digital signal; anddetermining the parameter of the first neural network based on the fourth digital signal and the third digital signal.The method according to claim 3, wherein the determining the parameter of the first neural network based on the fourth digital signal and the third digital signal comprises:training a second neural network with the fourth digital signal as sample data and the third digital signal as tag data, and updating the parameter of the first neural network based on a parameter of the trained second neural network, wherein a structure of the second neural network is identical to a structure of the first neural network.The method according to claim 3, wherein the determining the parameter of the first neural network based on the fourth digital signal and the third digital signal comprises:training the first neural network with the fourth digital signal as sample data and the third digital signal as tag data, to update the parameter of the first neural network.The method according to claim 3, whereinin case that a first condition is satisfied, the first mode is switched to the second mode,wherein the first condition comprises at least one of:a ratio of an average power of an adjacent frequency channel of the emission signal to an average power of a currently used channel being greater than or equal to a first threshold;a difference between a reference signal of the emission signal and the emission signal within a predetermined time being greater than or equal to a second threshold; anda change amount of a ratio between a peak power and an average power of the first digital signal within the predetermined time being greater than or equal to a third threshold.The method according to claim 6, further comprising:switching from the second mode to the first mode when one or more of the predetermined time passing, a predetermined number of times of training being finished and a model training loss being less than or equal to a fourth threshold are satisfied; orin case that the first condition is not satisfied, stopping the switching between the first mode and the second mode with the first period, and switching from the second mode to the first mode.The method according to claim 1, further comprising:entering a third mode when an amplitude of the first digital signal is less than or equal to a fifth threshold and / or a modulation order of the first digital signal is less than or equal to a sixth threshold, andperforming, in the third mode, following operations:performing the digital-to-analog conversion on the first digital signal to obtain a second analog signal;performing the up-conversion processing on the second analog signal; andperforming the power amplification on the up-converted second analog signal through the power amplifying device, to generate an emission signal.The method according to claim 2, further comprising:performing down-conversion processing on the emission signal;converting the down-converted emission signal into a fifth digital signal; anddetermining the parameter of the first neural network based on the fifth digital signal and the first digital signal.The method according to claim 9, further comprising:training a third neural network with the fifth digital signal as sample data and the first digital signal as tag data, and updating the parameter of the first neural network according to an output result of the third neural network.The method according to claim 9, further comprising:training a second neural network with the fifth digital signal as sample data and the second digital signal as tag data, and updating the parameter of the first neural network based on a parameter of the trained second neural network, wherein a structure of the second neural network is identical to a structure of the first neural network.The method according to claim 1, further comprising:adjusting a structure of the first neural network according to configuration information of the first digital signal.The method according to claim 12, wherein the adjusting a structure of the first neural network according to configuration information of the first digital signal comprises:determining the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers based on information related to a system bandwidth in the configuration information of the first digital signal; ordetermining the number of the neurons in the intermediate layer of the first neural network and / or the number of the intermediate layers based on a modulation order in the configuration information of the first digital signal.The method according to claim 3, further comprising:performing a power attenuation on the analog signal after the power amplification, before performing the down-conversion processing.An electronic device in a wireless communication for generating an emission signal comprising:at least one transceiver;at least one processor communicatively coupled to the at least one transceiver; andat least one memory, communicatively coupled to the at least one processor, storing instructions executable by at least one processor (307) individually or in any combination to cause the electronic device to:operate in a first mode,perform predistortion processing on a first digital signal through a first neural network to obtain a second digital signal;perform a digital-to-analog conversion on the second digital signal to obtain a first analog signal;perform up-conversion processing on the first analog signal; andperform a power amplification on the up-converted first analog signal to generate an emission signal, andwherein a parameter of the first neural network is determined based on a non-linear characteristic of the power amplifying device.

Images