Method and device for performing wireless computation using reconfigurable intelligent surface in wireless communication system
The integration of a reconfigurable intelligent surface in wireless communication systems addresses channel capacity and efficiency issues by optimizing the wireless channel environment, enhancing data transmission reliability and efficiency in challenging settings.
Patent Information
- Application Number
- PCT/KR2023/005936
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-02
- Publication Date
- 2024-11-07
AI Technical Summary
Current wireless communication systems face limitations in channel capacity and efficiency, particularly in non-line of sight (NLOS) environments and 6G THz settings, where signal loss and multipath issues hinder data transmission and reception, and existing methods like repeaters increase interference and energy consumption.
The implementation of a reconfigurable intelligent surface (RIS) in wireless communication systems to control and optimize the wireless channel environment, enabling simultaneous data transmission and reception through AirComp technology, which improves channel gain and resource utilization by grouping terminals based on channel conditions.
This approach enhances channel capacity, reduces interference, and improves communication efficiency by optimizing the wireless channel environment, overcoming Shannon's channel capacity limitations and increasing data transmission reliability in challenging environments.
Smart Images

Figure KR2023005936_07112024_PF_FP_ABST
Abstract
Description
Method and device for performing wireless computation using a reconfigurable intelligent surface in a wireless communication system
[0001] The following description relates to a wireless communication system, and to a device and method for performing wireless operations using a reconfigurable intelligent surface at a terminal and a base station in the wireless communication system.
[0002] In particular, the terminal and the support station can provide a method and device for transmitting and receiving signals by controlling a wireless channel environment through a reconfigurable intelligent surface (RIS).
[0003] Wireless access systems are widely deployed to provide various types of communication services, such as voice and data. Typically, wireless access systems are multiple access systems that support communications with multiple users by sharing available system resources (e.g., bandwidth, transmission power). Examples of multiple access systems include code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), and single-carrier frequency division multiple access (SC-FDMA).
[0004] In particular, as numerous communication devices demand greater communication capacity, enhanced mobile broadband (eMBB) communication technologies are being proposed, improving upon existing radio access technology (RAT). Furthermore, massive machine type communications (mMTC), which connects numerous devices and objects to provide diverse services anytime and anywhere, as well as communication systems that consider reliability and latency-sensitive services / user equipment (UE), are being proposed. Various technological configurations are being proposed for these purposes.
[0005] The present disclosure can provide a signal transmission and reception device and method in a wireless communication system.
[0006] The present disclosure may provide a method and device for transmitting and receiving a signal using a reconfigurable intelligent surface (RIS) in a wireless communication system.
[0007] The present disclosure can provide a method for a terminal and a base station to perform over-the-air computation (AirComp) technology using RIS in a wireless communication system.
[0008] The present disclosure may provide a method for performing grouping for AirComp using RIS in a wireless communication system.
[0009] The present disclosure can provide a method for grouping based on a channel gain measured by each terminal in a wireless communication system.
[0010] The present disclosure can provide a method for grouping based on the location of each terminal in a wireless communication system.
[0011] The present disclosure can provide a method for optimizing parameters required for AirComp using grouping in a wireless communication system.
[0012] The present disclosure can provide a method for a terminal and a base station to perform joint learning using AirComp with RIS in a wireless communication system.
[0013] The present disclosure can provide a method for a terminal and a base station to perform joint learning using grouping in a wireless communication system.
[0014] The present disclosure relates to a device and method for transmitting a plurality of transport blocks (TBs) as a single unit in a wireless communication system.
[0015] The technical objectives to be achieved in the present disclosure are not limited to those mentioned above, and other technical tasks not mentioned can be considered by a person having ordinary skill in the technical field to which the technical configuration of the present disclosure is applied from the embodiments of the present disclosure described below.
[0016] As an example of the present disclosure, a method for operating a base station in a wireless communication system includes the steps of: transmitting a first reference signal to a plurality of terminals; transmitting a second reference signal to the plurality of terminals based on a channel between the base station and a reconfigurable intelligent surface (RIS); receiving channel information based on the first reference signal and the second reference signal from the plurality of terminals; performing grouping into a plurality of groups based on the channel information; transmitting a power control factor determined based on the channel information to the plurality of terminals; and receiving a signal expressing an operation result of signals wirelessly transmitted in an overlapping manner by the plurality of terminals for each group, wherein the plurality of groups may include a first group using a first channel for direct communication with the base station for the plurality of terminals, and a second group using a second channel through the RIS.
[0017] Also, as an example of the present disclosure, a method of operating a terminal in a wireless communication system may include a step of receiving a first reference signal from a base station, a step of receiving a second reference signal based on a channel between the base station and a reconfigurable intelligent surface (RIS), a step of transmitting channel information based on the first reference signal and the second reference signal to the base station, a step of receiving a power control factor determined based on the channel information, a step of determining a transmission coefficient based on the power control factor, and a step of transmitting a signal to the base station based on the transmission coefficient.
[0018] Also, as an example of the present disclosure, a communication device includes at least one processor, and at least one computer memory connected to the at least one processor and storing instructions that direct operations when executed by the at least one processor, wherein the operations include controlling transmission of a first reference signal to a plurality of terminals, transmission of a second reference signal to the plurality of terminals based on a channel between the device and a reconfigurable intelligent surface (RIS), receiving channel information based on the first reference signal and the second reference signal from the plurality of terminals, transmitting a power control factor determined based on the channel information to the plurality of terminals, and receiving a signal expressing an operation result of signals wirelessly transmitted in an overlapping manner by the plurality of terminals for each group, wherein the plurality of groups may include a first group using a channel for direct communication with the communication device for the plurality of terminals, and a second group using a communication channel through the RIS.
[0019] Also, as an example of the present disclosure, a communication device includes at least one processor, at least one computer memory connected to the at least one processor and storing instructions that direct operations when executed by the at least one processor, wherein the operations may include receiving a first reference signal from a base station, receiving a second reference signal from the base station based on a channel between the base station and a reconfigurable intelligent surface (RIS), transmitting channel information based on the first reference signal and the second reference signal to the base station, receiving a power control factor determined based on the channel information, determining a transmission coefficient based on the power control factor, and transmitting a signal based on the transmission coefficient to the base station.
[0020] Also, as an example of the present disclosure, a non-transitory computer-readable medium storing at least one instruction, the at least one instruction being executable by a processor, the at least one instruction controlling a device to transmit a first reference signal to a plurality of terminals, to transmit a second reference signal to the plurality of terminals based on a channel between the device and a reconfigurable intelligent surface (RIS), to receive channel information based on the first reference signal and the second reference signal from the plurality of terminals, to transmit a power control factor determined based on the channel information to the plurality of terminals, and to receive a signal representing an operation result of signals wirelessly superimposedly transmitted by the plurality of terminals for each group, wherein the plurality of groups may include a first group using a channel for direct communication with the device and a second group using a communication channel through the RIS.
[0021] Additionally, the following may be commonly applied:
[0022] As an example of the present disclosure, the step of transmitting the first reference signal to the plurality of terminals may include the step of transmitting a stop signal to the RIS.
[0023] In addition, as an example of the present disclosure, the step of transmitting the second reference signal to the plurality of terminals based on the channel between the base station and the RIS includes:
[0024] The method may include a step of determining a beamforming coefficient and a reflection pattern of the RIS based on a channel between the measured base station and the RIS, a step of transmitting the reflection pattern to the RIS, and a step of transmitting the second reference signal based on the beamforming coefficient to the plurality of terminals.
[0025] Additionally, as an example of the present disclosure, the channel information includes channel identification information and a channel gain value having the largest channel gain, and the grouping can be performed with terminals having the same channel identification information having the largest channel gain.
[0026] Additionally, as an example of the present disclosure, the plurality of groups may further include a group in which terminals whose channel gain value does not exceed a threshold value do not transmit signals to the base station.
[0027] In addition, as an example of the present disclosure, the method may further include a step of adding a compensation margin to the channel gain based on at least one of the number of antennas of the base station, the number of elements of the RIS, the power of the first reference signal, the power of the second reference signal, and the beam gain of beam sweeping of the RIS.
[0028] In addition, as an example of the present disclosure, the step of transmitting the power control element determined based on the channel information to the plurality of terminals may include the step of determining a beamforming vector of the second group based on a channel environment of the base station and the RIS measured in the second group, the step of determining a decoding vector of the second group based on the beamforming vector of the second group, the step of optimizing a RIS reflection pattern for communication of the second group based on a decoding vector value of the second group, and the step of determining a power control element for the second group based on the decoding vector and the optimized RIS reflection pattern.
[0029] In addition, as an example of the present disclosure, the step of receiving a signal expressing an operation result of signals wirelessly transmitted in an overlapping manner by the plurality of terminals for each group may include the step of transmitting a start signal of the first group to the plurality of terminals, the step of receiving a signal based on a control element of the first group from the terminals of the first group, the step of transmitting a start signal of the second group to the plurality of terminals, and the step of receiving a signal based on a power control element of the second group from the terminals of the second group.
[0030] In addition, as an example of the present disclosure, the method may further include a step of transmitting attribute values of a global model for federated learning to the plurality of terminals, and a step of learning the global model based on the signal in which the computational results of signals wirelessly transmitted in an overlapping manner by each group of the plurality of terminals are expressed.
[0031] In addition, as an example of the present disclosure, the step of learning the global model based on the signal in which the computational results of the signals wirelessly transmitted in an overlapping manner by the plurality of terminals for each group are expressed may include the step of determining a local model of each group based on the overlapping signals for each group, and the step of learning the global model based on the local model of each group.
[0032] The above-described aspects of the present disclosure are only some of the preferred embodiments of the present disclosure, and various embodiments reflecting the technical features of the present disclosure can be derived and understood by a person having ordinary skill in the art based on the detailed description of the present disclosure to be described below.
[0033] The following effects may be achieved by embodiments based on the present disclosure.
[0034] Embodiments based on the present disclosure enable a terminal and a base station to transmit and receive signals using a reconfigurable intelligent surface (RIS).
[0035] Embodiments based on the present disclosure enable a terminal and a base station to perform over-the-air computation (AirComp) technology using RIS.
[0036] By using RIS, a base station and a terminal can perform grouping for AirComp according to embodiments based on the present disclosure.
[0037] According to embodiments based on the present disclosure, a base station can perform grouping based on the channel gain measured by each terminal.
[0038] Embodiments based on the present disclosure enable a base station to group terminals based on the location of each terminal.
[0039] Embodiments based on the present disclosure enable a terminal to optimize parameters required for AirComp.
[0040] Embodiments based on the present disclosure can provide a method for a terminal and a base station to perform joint learning using AirComp with RIS.
[0041] The present disclosure can provide a method for a terminal and a base station to perform joint learning using grouping in a wireless communication system.
[0042] The effects that can be obtained from the embodiments of the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly derived and understood by those skilled in the art to which the technical configuration of the present disclosure is applied, from the description of the embodiments of the present disclosure below. In other words, unintended effects that result from implementing the configuration described in the present disclosure can also be derived by those skilled in the art from the embodiments of the present disclosure.
[0043] The accompanying drawings are intended to aid in understanding the present disclosure and, together with detailed descriptions, may provide embodiments of the present disclosure. However, the technical features of the present disclosure are not limited to specific drawings, and the features disclosed in each drawing may be combined with each other to form new embodiments. Reference numerals in each drawing may indicate structural elements.
[0044] FIG. 1 is a diagram illustrating an example of a communication system applicable to the present disclosure.
[0045] FIG. 2 is a drawing showing an example of a wireless device applicable to the present disclosure.
[0046] FIG. 3 is a diagram showing another example of a wireless device applicable to the present disclosure.
[0047] FIG. 4 is a drawing showing an example of a mobile device applicable to the present disclosure.
[0048] FIG. 5 is a drawing showing an example of a vehicle or autonomous vehicle applicable to the present disclosure.
[0049] Figure 6 is a diagram showing an example of AI (Artificial Intelligence) applicable to the present disclosure.
[0050] FIG. 7 is a diagram illustrating a method for processing a transmission signal applicable to the present disclosure.
[0051] FIG. 8 is a diagram showing an example of a communication structure that can be provided in a 6G system applicable to the present disclosure.
[0052] Figure 9 is a diagram showing an electromagnetic spectrum applicable to the present disclosure.
[0053] Fig. 10 is a diagram showing a THz communication method applicable to the present disclosure.
[0054] FIG. 11 is a diagram illustrating a wireless channel environment according to an embodiment of the present disclosure.
[0055] FIG. 12 is a diagram illustrating an intelligent wireless environment according to one embodiment of the present disclosure.
[0056] FIGS. 13a and 13b are diagrams illustrating a conventional wireless channel environment and an intelligent wireless channel environment according to one embodiment of the present disclosure.
[0057] FIG. 14 is a diagram illustrating a method for performing optimization in an intelligent wireless channel environment according to one embodiment of the present disclosure.
[0058] FIG. 15 is a diagram showing a confidence interval according to one embodiment of the present disclosure.
[0059] FIG. 16 is a diagram illustrating the structure of a federated learning system using AirComp (over-the-air computation) technology according to one embodiment of the present disclosure.
[0060] FIG. 17 is a diagram illustrating an AirComp system and channel information using a reconfigurable intelligent surface (RIS) according to one embodiment of the present disclosure.
[0061] FIG. 18 is a diagram illustrating a transceiver structure of a terminal and a base station for an AirComp system according to one embodiment of the present disclosure.
[0062] FIG. 19 is a diagram illustrating an operation method of a base station in an AirComp system using RIS according to one embodiment of the present disclosure.
[0063] FIG. 20 is a diagram illustrating an operation method of a terminal participating in an AirComp system using RIS according to one embodiment of the present disclosure.
[0064] FIG. 21 is a diagram illustrating signal flow between a base station, RIS, and terminals in an AirComp system using RIS according to one embodiment of the present disclosure.
[0065] FIG. 22 is a diagram illustrating an AirComp system environment using RIS according to one embodiment of the present disclosure.
[0066] FIG. 23 is a diagram illustrating a method for performing grouping for terminals to be used in AirComp technology using RIS according to one embodiment of the present disclosure.
[0067] FIG. 24 is a diagram illustrating an operation method of a base station that performs grouping based on channel gain using RIS according to one embodiment of the present disclosure.
[0068] FIG. 25 is a diagram illustrating signal flow between a base station, a terminal, and an RIS when grouping is performed using RIS according to one embodiment of the present disclosure.
[0069] FIG. 26 is a diagram illustrating a method for a base station to perform AirComp communication through grouping for device selection according to one embodiment of the present disclosure.
[0070] FIG. 27 is a diagram illustrating signal flow between a base station, RIS, and each terminal group in an environment performing AirComp communication using RIS according to one embodiment of the present disclosure.
[0071] FIG. 28 is a diagram illustrating signal flow between a base station, RIS, and k groups in a federated learning system environment using AirComp communication using RIS according to one embodiment of the present disclosure.
[0072] The following embodiments combine components and features of the present disclosure in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented without being combined with other components or features. Furthermore, some components and / or features may be combined to form embodiments of the present disclosure. The order of operations described in the embodiments of the present disclosure may be changed. Some components or features of one embodiment may be included in another embodiment or may be replaced with corresponding components or features of another embodiment.
[0073] In the description of the drawings, procedures or steps that may obscure the gist of the present disclosure are not described, and procedures or steps that can be understood by a person skilled in the art are also not described.
[0074] Throughout the specification, when a part is said to "comprising" or "including" a component, this does not mean that other components may be included, but rather that other components may be excluded, unless otherwise specifically stated. In addition, terms such as "...part," "...unit," and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented by hardware, software, or a combination of hardware and software. In addition, the words "a" or "an," "one," "the," and similar related words may be used in the context of describing the present disclosure (especially in the context of the claims below) to include both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context.
[0075] Embodiments of the present disclosure described herein focus on the data transmission and reception relationship between a base station and a mobile station. Here, the base station is understood as a terminal node of a network that directly communicates with the mobile station. Certain operations described herein as being performed by the base station may, in some cases, be performed by an upper node of the base station.
[0076] That is, in a network consisting of multiple network nodes including a base station, various operations performed for communication with a mobile station may be performed by the base station or other network nodes other than the base station. In this case, the term 'base station' may be replaced by terms such as fixed station, Node B, eNB (eNode B), gNB (gNode B), ng-eNB, advanced base station (ABS), or access point.
[0077] Additionally, in embodiments of the present disclosure, the term terminal may be replaced with terms such as user equipment (UE), mobile station (MS), subscriber station (SS), mobile subscriber station (MSS), mobile terminal, or advanced mobile station (AMS).
[0078] Additionally, a transmitter refers to a fixed and / or mobile node that provides data or voice services, and a receiver refers to a fixed and / or mobile node that receives data or voice services. Therefore, for uplink, a mobile station can be the transmitter, and a base station can be the receiver. Similarly, for downlink, a mobile station can be the receiver, and a base station can be the transmitter.
[0079] Embodiments of the present disclosure may be supported by standard documents disclosed in at least one of wireless access systems, such as IEEE 802.xx system, 3rd Generation Partnership Project (3GPP) system, 3GPP Long Term Evolution (LTE) system, 3GPP 5G (5th generation) NR (New Radio) system and 3GPP2 system, and in particular, embodiments of the present disclosure may be supported by 3GPP TS (technical specification) 38.211, 3GPP TS 38.212, 3GPP TS 38.213, 3GPP TS 38.321 and 3GPP TS 38.331 documents.
[0080] Furthermore, the embodiments of the present disclosure can be applied to other wireless access systems and are not limited to the aforementioned systems. For example, they can be applied to systems implemented after the 3GPP 5G NR system and are not limited to a specific system.
[0081] That is, obvious steps or parts not described in the embodiments of the present disclosure can be explained by referring to the above documents. In addition, all terms disclosed in this document can be explained by the above standard documents.
[0082] Hereinafter, preferred embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. The detailed description set forth below, together with the accompanying drawings, is intended to explain exemplary embodiments of the present disclosure and is not intended to represent the only embodiments in which the technical configurations of the present disclosure can be implemented.
[0083] Additionally, specific terms used in the embodiments of the present disclosure are provided to aid in understanding the present disclosure, and the use of such specific terms may be changed to other forms without departing from the technical spirit of the present disclosure.
[0084] The following technology can be applied to various wireless access systems such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), and SC-FDMA (single carrier frequency division multiple access).
[0085] In order to make the following description clear, the following description is based on a 3GPP communication system (e.g., LTE, NR, etc.), but the technical idea of the present invention is not limited thereto. LTE may refer to technology after 3GPP TS 36.xxx Release 8. Specifically, LTE technology after 3GPP TS 36.xxx Release 10 may be referred to as LTE-A, and LTE technology after 3GPP TS 36.xxx Release 13 may be referred to as LTE-A pro. 3GPP NR may refer to technology after TS 38.xxx Release 15. 3GPP 6G may refer to technology after TS Release 17 and / or Release 18. "xxx" refers to a standard document detail number. LTE / NR / 6G may be collectively referred to as a 3GPP system.
[0086] For background information, terms, abbreviations, etc. used in this disclosure, reference may be made to standard documents published prior to the present invention. For example, reference may be made to the 36.xxx and 38.xxx standard documents.
[0087] Communication system applicable to the present disclosure
[0088] Although not limited thereto, the various descriptions, functions, procedures, proposals, methods and / or operational flowcharts of the present disclosure disclosed in this document may be applied to various fields requiring wireless communication / connectivity (e.g., 5G) between devices.
[0089] Hereinafter, more specific examples will be provided with reference to the drawings. In the drawings / descriptions below, the same drawing reference numerals may represent identical or corresponding hardware blocks, software blocks, or functional blocks, unless otherwise described.
[0090] FIG. 1 is a diagram illustrating an example of a communication system applied to the present disclosure.
[0091] Referring to FIG. 1, a communication system (100) applied to the present disclosure includes a wireless device, a base station, and a network. Here, the wireless device refers to a device that performs communication using a wireless access technology (e.g., 5G NR, LTE) and may be referred to as a communication / wireless / 5G device. Although not limited thereto, the wireless device may include a robot (100a), a vehicle (100b-1, 100b-2), an XR (extended reality) device (100c), a hand-held device (100d), a home appliance (100e), an IoT (Internet of Things) device (100f), and an AI (artificial intelligence) device / server (100g). For example, the vehicle may include a vehicle equipped with a wireless communication function, an autonomous vehicle, a vehicle capable of performing vehicle-to-vehicle communication, etc. Here, the vehicles (100b-1, 100b-2) may include unmanned aerial vehicles (UAVs) (e.g., drones). The XR devices (100c) include augmented reality (AR) / virtual reality (VR) / mixed reality (MR) devices, and may be implemented in the form of head-mounted devices (HMDs), head-up displays (HUDs) installed in vehicles, televisions, smartphones, computers, wearable devices, home appliances, digital signage, vehicles, robots, etc. The portable devices (100d) may include smartphones, smart pads, wearable devices (e.g., smartwatches, smart glasses), computers (e.g., laptops, etc.), etc. The home appliances (100e) may include TVs, refrigerators, washing machines, etc. The IoT devices (100f) may include sensors, smart meters, etc. For example, the base station (120) and the network (130) may also be implemented as wireless devices, and a specific wireless device (120a) may act as a base station / network node to other wireless devices.
[0092] Wireless devices (100a to 100f) can be connected to a network (130) via a base station (120). AI technology can be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (100g) via a network (130). The network (130) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR) network, etc. The wireless devices (100a to 100f) can communicate with each other via the base station (120) / network (130), but can also communicate directly (e.g., sidelink communication) without going through the base station (120) / network (130). For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (vehicle to vehicle) / V2X (vehicle to everything) communication). In addition, IoT devices (100f) (e.g., sensors) can communicate directly with other IoT devices (e.g., sensors) or other wireless devices (100a to 100f).
[0093] Wireless communication / connection (150a, 150b, 150c) can be established between wireless devices (100a to 100f) / base stations (120), and base stations (120) / base stations (120). Here, the wireless communication / connection can be established through various wireless access technologies (e.g., 5G NR) such as uplink / downlink communication (150a), sidelink communication (150b) (or D2D communication), and base station-to-base station communication (150c) (e.g., relay, IAB (integrated access backhaul)). Through the wireless communication / connection (150a, 150b, 150c), the wireless device and base station / wireless device, and base stations and base stations can transmit / receive wireless signals to / from each other. For example, the wireless communication / connection (150a, 150b, 150c) can transmit / receive signals through various physical channels. To this end, based on various proposals of the present disclosure, at least some of various configuration information setting processes for transmitting / receiving wireless signals, various signal processing processes (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), resource allocation processes, etc. may be performed.
[0094] Communication system applicable to the present disclosure
[0095] FIG. 2 is a diagram illustrating an example of a wireless device applicable to the present disclosure.
[0096] Referring to FIG. 2, the first wireless device (200a) and the second wireless device (200b) can transmit and receive wireless signals via various wireless access technologies (e.g., LTE, NR). Here, {the first wireless device (200a), the second wireless device (200b)} can correspond to {the wireless device (100x), the base station (120)} and / or {the wireless device (100x), the wireless device (100x)} of FIG. 1.
[0097] A first wireless device (200a) includes one or more processors (202a) and one or more memories (204a), and may further include one or more transceivers (206a) and / or one or more antennas (208a). The processor (202a) controls the memories (204a) and / or the transceivers (206a), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. For example, the processor (202a) may process information in the memory (204a) to generate first information / signals, and then transmit a wireless signal including the first information / signals via the transceivers (206a). In addition, the processor (202a) may receive a wireless signal including second information / signals via the transceivers (206a), and then store information obtained from signal processing of the second information / signals in the memory (204a). The memory (204a) may be connected to the processor (202a) and may store various information related to the operation of the processor (202a). For example, the memory (204a) may perform some or all of the processes controlled by the processor (202a), or may store software code including instructions for performing the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. Here, the processor (202a) and the memory (204a) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). The transceiver (206a) may be connected to the processor (202a) and may transmit and / or receive wireless signals via one or more antennas (208a). The transceiver (206a) may include a transmitter and / or a receiver. The transceiver (206a) may be used interchangeably with an RF (radio frequency) unit. In the present disclosure, a wireless device may also mean a communication modem / circuit / chip.
[0098] The second wireless device (200b) includes one or more processors (202b), one or more memories (204b), and may further include one or more transceivers (206b) and / or one or more antennas (208b). The processor (202b) controls the memories (204b) and / or the transceivers (206b), and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. For example, the processor (202b) may process information in the memory (204b) to generate third information / signals, and then transmit a wireless signal including the third information / signals via the transceivers (206b). In addition, the processor (202b) may receive a wireless signal including fourth information / signals via the transceivers (206b), and then store information obtained from the signal processing of the fourth information / signals in the memory (204b). The memory (204b) may be connected to the processor (202b) and may store various information related to the operation of the processor (202b). For example, the memory (204b) may perform some or all of the processes controlled by the processor (202b), or may store software code including commands for performing the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. Here, the processor (202b) and the memory (204b) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). The transceiver (206b) may be connected to the processor (202b) and may transmit and / or receive wireless signals via one or more antennas (208b). The transceiver (206b) may include a transmitter and / or a receiver. The transceiver (206b) may be used interchangeably with an RF unit. In the present disclosure, a wireless device may also mean a communication modem / circuit / chip.
[0099] Hereinafter, hardware elements of the wireless device (200a, 200b) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (202a, 202b). For example, one or more processors (202a, 202b) may implement one or more layers (e.g., functional layers such as physical (PHY), media access control (MAC), radio link control (RLC), packet data convergence protocol (PDCP), radio resource control (RRC), and service data adaptation protocol (SDAP)). One or more processors (202a, 202b) may generate one or more Protocol Data Units (PDUs) and / or one or more Service Data Units (SDUs) according to the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document. One or more processors (202a, 202b) may generate messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed herein. One or more processors (202a, 202b) may generate signals (e.g., baseband signals) including PDUs, SDUs, messages, control information, data or information according to the functions, procedures, proposals and / or methods disclosed herein, and provide the signals to one or more transceivers (206a, 206b). One or more processors (202a, 202b) may receive signals (e.g., baseband signals) from one or more transceivers (206a, 206b) and obtain PDUs, SDUs, messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and / or operational flowcharts disclosed herein.
[0100] One or more processors (202a, 202b) may be referred to as a controller, a microcontroller, a microprocessor, or a microcomputer. One or more processors (202a, 202b) may be implemented by hardware, firmware, software, or a combination thereof. For example, one or more application specific integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more digital signal processing devices (DSPDs), one or more programmable logic devices (PLDs), or one or more field programmable gate arrays (FPGAs) may be included in one or more processors (202a, 202b). The descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, etc. The descriptions, functions, procedures, suggestions, methods and / or operation flowcharts disclosed in this document may be implemented using firmware or software configured to perform one or more processors (202a, 202b) or stored in one or more memories (204a, 204b) and executed by one or more processors (202a, 202b). The descriptions, functions, procedures, suggestions, methods and / or operation flowcharts disclosed in this document may be implemented using firmware or software in the form of codes, instructions and / or sets of instructions.
[0101] One or more memories (204a, 204b) may be coupled to one or more processors (202a, 202b) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. The one or more memories (204a, 204b) may be configured as read only memory (ROM), random access memory (RAM), erasable programmable read only memory (EPROM), flash memory, hard drives, registers, cache memory, computer readable storage media, and / or combinations thereof. The one or more memories (204a, 204b) may be located internally and / or externally to the one or more processors (202a, 202b). Additionally, the one or more memories (204a, 204b) may be coupled to the one or more processors (202a, 202b) via various technologies, such as wired or wireless connections.
[0102] One or more transceivers (206a, 206b) can transmit user data, control information, wireless signals / channels, etc., as mentioned in the methods and / or flowcharts of this document, to one or more other devices. One or more transceivers (206a, 206b) can receive user data, control information, wireless signals / channels, etc., as mentioned in the descriptions, functions, procedures, proposals, methods and / or flowcharts of this document, from one or more other devices. For example, one or more transceivers (206a, 206b) can be coupled to one or more processors (202a, 202b) and can transmit and receive wireless signals. For example, one or more processors (202a, 202b) can control one or more transceivers (206a, 206b) to transmit user data, control information, or wireless signals to one or more other devices. Additionally, one or more processors (202a, 202b) may control one or more transceivers (206a, 206b) to receive user data, control information, or wireless signals from one or more other devices. Additionally, one or more transceivers (206a, 206b) may be coupled to one or more antennas (208a, 208b), and one or more transceivers (206a, 206b) may be configured to transmit and receive user data, control information, wireless signals / channels, or the like, as referred to in the descriptions, functions, procedures, proposals, methods, and / or operational flowcharts disclosed in this document, via one or more antennas (208a, 208b). In this document, one or more antennas may be multiple physical antennas or multiple logical antennas (e.g., antenna ports). One or more transceivers (206a, 206b) can convert received user data, control information, wireless signals / channels, etc. from RF band signals to baseband signals in order to process the received user data, control information, wireless signals / channels, etc. using one or more processors (202a, 202b).One or more transceivers (206a, 206b) may convert user data, control information, wireless signals / channels, etc. processed by one or more processors (202a, 202b) from baseband signals to RF band signals. For this purpose, one or more transceivers (206a, 206b) may include an (analog) oscillator and / or filter.
[0103] Wireless device structure applicable to the present disclosure
[0104] FIG. 3 is a diagram illustrating another example of a wireless device applicable to the present disclosure.
[0105] Referring to FIG. 3, the wireless device (300) corresponds to the wireless devices (200a, 200b) of FIG. 2 and may be composed of various elements, components, units, and / or modules. For example, the wireless device (300) may include a communication unit (310), a control unit (320), a memory unit (330), and additional elements (340). The communication unit may include a communication circuit (312) and a transceiver(s) (314). For example, the communication circuit (312) may include one or more processors (202a, 202b) and / or one or more memories (204a, 204b) of FIG. 2. For example, the transceiver(s) (314) may include one or more transceivers (206a, 206b) and / or one or more antennas (208a, 208b) of FIG. 2. The control unit (320) is electrically connected to the communication unit (310), the memory unit (330), and the additional elements (340) and controls the overall operation of the wireless device. For example, the control unit (320) may control the electrical / mechanical operation of the wireless device based on the program / code / command / information stored in the memory unit (330). In addition, the control unit (320) may transmit information stored in the memory unit (330) to an external device (e.g., another communication device) via a wireless / wired interface through the communication unit (310), or store information received from an external device (e.g., another communication device) via a wireless / wired interface in the memory unit (330).
[0106] The additional element (340) may be configured in various ways depending on the type of the wireless device. For example, the additional element (340) may include at least one of a power unit / battery, an input / output unit, a driving unit, and a computing unit. Although not limited thereto, the wireless device (300) may be implemented in the form of a robot (Fig. 1, 100a), a vehicle (Fig. 1, 100b-1, 100b-2), an XR device (Fig. 1, 100c), a portable device (Fig. 1, 100d), a home appliance (Fig. 1, 100e), an IoT device (Fig. 1, 100f), a digital broadcasting terminal, a hologram device, a public safety device, an MTC device, a medical device, a fintech device (or a financial device), a security device, a climate / environmental device, an AI server / device (Fig. 1, 140), a base station (Fig. 1, 120), a network node, etc. Wireless devices may be mobile or stationary depending on the use / service.
[0107] In FIG. 3, various elements, components, units / parts, and / or modules within the wireless device (300) may be entirely interconnected via a wired interface, or at least some may be wirelessly connected via a communication unit (310). For example, within the wireless device (300), the control unit (320) and the communication unit (310) may be wired, and the control unit (320) and the first unit (e.g., 130, 140) may be wirelessly connected via the communication unit (310). In addition, each element, component, unit / part, and / or module within the wireless device (300) may further include one or more elements. For example, the control unit (320) may be composed of a set of one or more processors. For example, the control unit (320) may be composed of a set of a communication control processor, an application processor, an electronic control unit (ECU), a graphics processing processor, a memory control processor, etc. As another example, the memory unit (330) may be composed of RAM, DRAM (dynamic RAM), ROM, flash memory, volatile memory, non-volatile memory, and / or a combination thereof.
[0108] Mobile devices to which the present disclosure applies
[0109] FIG. 4 is a drawing illustrating an example of a mobile device applied to the present disclosure.
[0110] Figure 4 illustrates an example of a mobile device applicable to the present disclosure. The mobile device may include a smartphone, a smart pad, a wearable device (e.g., a smart watch, smart glasses), or a portable computer (e.g., a laptop, etc.). The mobile device may be referred to as a mobile station (MS), a user terminal (UT), a mobile subscriber station (MSS), a subscriber station (SS), an advanced mobile station (AMS), or a wireless terminal (WT).
[0111] Referring to FIG. 4, the portable device (400) may include an antenna unit (408), a communication unit (410), a control unit (420), a memory unit (430), a power supply unit (440a), an interface unit (440b), and an input / output unit (440c). The antenna unit (408) may be configured as a part of the communication unit (410). Blocks 410 to 430 / 440a to 440c correspond to blocks 310 to 330 / 340 of FIG. 3, respectively.
[0112] The communication unit (410) can transmit and receive signals (e.g., data, control signals, etc.) with other wireless devices and base stations. The control unit (420) can control components of the portable device (400) to perform various operations. The control unit (420) can include an AP (application processor). The memory unit (430) can store data / parameters / programs / codes / commands required for operating the portable device (400). In addition, the memory unit (430) can store input / output data / information, etc. The power supply unit (440a) supplies power to the portable device (400) and can include a wired / wireless charging circuit, a battery, etc. The interface unit (440b) can support connection between the portable device (400) and other external devices. The interface unit (440b) can include various ports (e.g., audio input / output ports, video input / output ports) for connection with external devices. The input / output unit (440c) can input or output video information / signals, audio information / signals, data, and / or information input from a user. The input / output unit (440c) may include a camera, a microphone, a user input unit, a display unit (440d), a speaker, and / or a haptic module.
[0113] For example, in the case of data communication, the input / output unit (440c) obtains information / signals (e.g., touch, text, voice, image, video) input by the user, and the obtained information / signals can be stored in the memory unit (430). The communication unit (410) can convert the information / signals stored in the memory into wireless signals, and transmit the converted wireless signals directly to other wireless devices or to a base station. In addition, the communication unit (410) can receive wireless signals from other wireless devices or base stations, and then restore the received wireless signals to the original information / signals. The restored information / signals can be stored in the memory unit (430) and then output in various forms (e.g., text, voice, image, video, haptic) through the input / output unit (440c).
[0114] Types of wireless devices to which the present disclosure applies
[0115] FIG. 5 is a drawing illustrating an example of a vehicle or autonomous vehicle to which the present disclosure applies.
[0116] Figure 5 illustrates a vehicle or autonomous vehicle applicable to the present disclosure. The vehicle or autonomous vehicle may be implemented as a mobile robot, car, train, manned / unmanned aerial vehicle (AV), ship, etc., and is not limited to the form of a vehicle.
[0117] Referring to FIG. 5, a vehicle or autonomous vehicle (500) may include an antenna unit (508), a communication unit (510), a control unit (520), a driving unit (540a), a power supply unit (540b), a sensor unit (540c), and an autonomous driving unit (540d). The antenna unit (550) may be configured as a part of the communication unit (510). Blocks 510 / 530 / 540a to 540d correspond to blocks 410 / 430 / 440 of FIG. 4, respectively.
[0118] The communication unit (510) can transmit and receive signals (e.g., data, control signals, etc.) with external devices such as other vehicles, base stations (e.g., base stations, roadside base stations, etc.), servers, etc. The control unit (520) can control elements of a vehicle or autonomous vehicle (500) to perform various operations. The control unit (520) can include an electronic control unit (ECU).
[0119] Figure 6 is a diagram illustrating an example of an AI device applicable to the present disclosure. For example, the AI device may be implemented as a fixed or mobile device, such as a TV, projector, smartphone, PC, laptop, digital broadcasting terminal, tablet PC, wearable device, set-top box (STB), radio, washing machine, refrigerator, digital signage, robot, or vehicle.
[0120] Referring to FIG. 6, the AI device (600) may include a communication unit (610), a control unit (620), a memory unit (630), an input / output unit (640a / 640b), a learning processor unit (640c), and a sensor unit (640d). Blocks 610 to 630 / 640a to 640d may correspond to blocks 310 to 330 / 340 of FIG. 3, respectively.
[0121] The communication unit (610) can transmit and receive wired and wireless signals (e.g., sensor information, user input, learning models, control signals, etc.) with external devices such as other AI devices (e.g., FIG. 1, 100x, 120, 140) or AI servers (FIG. 1, 140) using wired and wireless communication technology. To this end, the communication unit (610) can transmit information within the memory unit (630) to the external device or transfer a signal received from the external device to the memory unit (630).
[0122] The control unit (620) may determine at least one executable operation of the AI device (600) based on information determined or generated using a data analysis algorithm or a machine learning algorithm. In addition, the control unit (620) may control components of the AI device (600) to perform the determined operation. For example, the control unit (620) may request, search, receive, or utilize data from the learning processor unit (640c) or the memory unit (630), and may control components of the AI device (600) to perform a predicted operation or an operation determined to be desirable among at least one executable operation. In addition, the control unit (620) may collect history information including the operation contents of the AI device (600) or user feedback on the operation, and store the collected history information in the memory unit (630) or the learning processor unit (640c), or transmit the collected history information to an external device such as an AI server (FIG. 1, 140). The collected history information may be used to update a learning model.
[0123] The memory unit (630) can store data that supports various functions of the AI device (600). For example, the memory unit (630) can store data obtained from the input unit (640a), data obtained from the communication unit (610), output data of the learning processor unit (640c), and data obtained from the sensing unit (640). In addition, the memory unit (630) can store control information and / or software codes necessary for the operation / execution of the control unit (620).
[0124] The input unit (640a) can obtain various types of data from the outside of the AI device (600). For example, the input unit (620) can obtain learning data for model learning, input data to which the learning model will be applied, etc. The input unit (640a) may include a camera, a microphone, and / or a user input unit. The output unit (640b) may generate output related to vision, hearing, or touch. The output unit (640b) may include a display unit, a speaker, and / or a haptic module, etc. The sensing unit (640) can obtain at least one of internal information of the AI device (600), information about the surrounding environment of the AI device (600), and user information using various sensors. The sensing unit (640) may include a proximity sensor, an illuminance sensor, an acceleration sensor, a magnetic sensor, a gyro sensor, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, a light sensor, a microphone, and / or a radar, etc.
[0125] The learning processor unit (640c) can train a model composed of an artificial neural network using learning data. The learning processor unit (640c) can perform AI processing together with the learning processor unit of the AI server (Fig. 1, 140). The learning processor unit (640c) can process information received from an external device via the communication unit (610) and / or information stored in the memory unit (630). In addition, the output value of the learning processor unit (640c) can be transmitted to an external device via the communication unit (610) and / or stored in the memory unit (630).
[0126] FIG. 7 is a diagram illustrating a method for processing a transmission signal applied to the present disclosure. For example, the transmission signal may be processed by a signal processing circuit. At this time, the signal processing circuit (700) may include a scrambler (710), a modulator (720), a layer mapper (730), a precoder (740), a resource mapper (750), and a signal generator (760). At this time, as an example, the operations / functions of FIG. 7 may be performed in the processors (202a, 202b) and / or the transceivers (206a, 206b) of FIG. 2. Furthermore, as an example, the hardware elements of FIG. 7 may be implemented in the processors (202a, 202b) and / or the transceivers (206a, 206b) of FIG. 2. As an example, blocks 710 to 760 may be implemented in the processors (202a, 202b) of FIG. 2. Additionally, blocks 710 to 750 may be implemented in the processor (202a, 202b) of FIG. 2, and block 760 may be implemented in the transceiver (206a, 206b) of FIG. 2, and are not limited to the above-described embodiments.
[0127] The codeword can be converted into a wireless signal through the signal processing circuit (700) of FIG. 7. Here, the codeword is an encoded bit sequence of an information block. The information block may include a transport block (e.g., a UL-SCH transport block, a DL-SCH transport block). The wireless signal may be transmitted through various physical channels (e.g., a PUSCH, a PDSCH). Specifically, the codeword can be converted into a bit sequence scrambled by a scrambler (710). The scramble sequence used for scrambling is generated based on an initialization value, and the initialization value may include ID information of the wireless device, etc. The scrambled bit sequence can be modulated into a modulation symbol sequence by a modulator (720). The modulation scheme may include pi / 2-binary phase shift keying (pi / 2-BPSK), m-phase shift keying (m-PSK), m-quadrature amplitude modulation (m-QAM), etc.
[0128] A complex modulation symbol sequence can be mapped to one or more transmission layers by a layer mapper (730). The modulation symbols of each transmission layer can be mapped to the corresponding antenna port(s) by a precoder (740) (precoding). The output z of the precoder (740) can be obtained by multiplying the output y of the layer mapper (730) by an N*M precoding matrix W. Here, N is the number of antenna ports, and M is the number of transmission layers. Here, the precoder (740) can perform precoding after performing transform precoding (e.g., discrete Fourier transform (DFT) transform) on the complex modulation symbols. In addition, the precoder (740) can perform precoding without performing transform precoding.
[0129] The resource mapper (750) can map modulation symbols of each antenna port to time-frequency resources. The time-frequency resources can include multiple symbols (e.g., CP-OFDMA symbols, DFT-s-OFDMA symbols) in the time domain and multiple subcarriers in the frequency domain. The signal generator (760) generates a wireless signal from the mapped modulation symbols, and the generated wireless signal can be transmitted to another device through each antenna. To this end, the signal generator (760) can include an inverse fast Fourier transform (IFFT) module, a cyclic prefix (CP) inserter, a digital-to-analog converter (DAC), a frequency uplink converter, and the like.
[0130] The signal processing process for receiving signals in a wireless device can be configured in reverse order of the signal processing process (710 to 760) of FIG. 7. For example, a wireless device (e.g., 200a and 200b of FIG. 2) can receive wireless signals from the outside through an antenna port / transceiver. The received wireless signals can be converted into baseband signals through a signal restorer. For this purpose, the signal restorer can include a frequency downlink converter, an analog-to-digital converter (ADC), a CP remover, and a fast Fourier transform (FFT) module. Thereafter, the baseband signal can be restored to a codeword through a resource demapper process, a postcoding process, a demodulation process, and a descrambling process. The codewords can be restored to the original information blocks through decoding. Accordingly, a signal processing circuit (not shown) for a received signal may include a signal restorer, a resource de-mapper, a postcoder, a demodulator, a de-scrambler, and a decoder.
[0131] 6G communication system
[0132] The 6G (wireless communication) system aims to achieve (i) very high data rates per device, (ii) a very large number of connected devices, (iii) global connectivity, (iv) very low latency, (v) low energy consumption for battery-free IoT devices, (vi) ultra-reliable connectivity, and (vii) connected intelligence with machine learning capabilities. The vision of the 6G system can be divided into four aspects: "intelligent connectivity," "deep connectivity," "holographic connectivity," and "ubiquitous connectivity," and the 6G system can satisfy the requirements as shown in Table 1 below. In other words, Table 1 is a table showing the requirements of the 6G system.
[0133] Per device peak data rate1 TbpsE2E latency1 msMaximum spectral efficiency100 bps / HzMobility supportup to 1000 km / hrSatellite integrationFullyAIFullyAutonomous vehicleFullyXRFullyHaptic CommunicationFully
[0134] At this time, the 6G system may have key factors such as enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLLC), massive machine type communications (mMTC), AI integrated communication, tactile internet, high throughput, high network capacity, high energy efficiency, low backhaul and access network congestion, and enhanced data security.
[0135] FIG. 8 is a diagram illustrating an example of a communication structure that can be provided in a 6G system applicable to the present disclosure.
[0136] Referring to Figure 8, 6G systems are expected to have 50 times higher simultaneous wireless connectivity than 5G wireless systems. URLLC, a key feature of 5G, is expected to become a more prominent technology in 6G communications by providing end-to-end latency of less than 1 ms. Furthermore, 6G systems will have significantly better volumetric spectral efficiency, unlike the commonly used area spectral efficiency. 6G systems can offer extremely long battery life and advanced battery technologies for energy harvesting, eliminating the need for separate charging for mobile devices in 6G systems.
[0137] Core implementation technology of 6G systems
[0138] - Artificial Intelligence (AI)
[0139] The most crucial and newly introduced technology for 6G systems is AI. 4G systems did not involve AI. 5G systems will support partial or very limited AI. However, 6G systems will fully support AI for automation. Advances in machine learning will create more intelligent networks for real-time communications in 6G. Incorporating AI into communications can streamline and improve real-time data transmission. AI can use numerous analyses to determine how complex target tasks should be performed. In other words, AI can increase efficiency and reduce processing delays.
[0140] Time-consuming tasks such as handover, network selection, and resource scheduling can be performed instantly using AI. AI can also play a crucial role in machine-to-machine (M2M), machine-to-human, and human-to-machine communications. Furthermore, AI can facilitate rapid communication in brain-computer interfaces (BCIs). AI-based communication systems can be supported by metamaterials, intelligent structures, intelligent networks, intelligent devices, intelligent cognitive radios, self-sustaining wireless networks, and machine learning.
[0141] Recent attempts to integrate AI into wireless communication systems have focused on the application layer and network layer, particularly deep learning in wireless resource management and allocation. However, this research is increasingly evolving to the MAC layer and physical layer, with attempts to combine deep learning with wireless transmission, particularly in the physical layer. AI-based physical layer transmission refers to applying AI-based signal processing and communication mechanisms, rather than traditional communication frameworks, in the fundamental signal processing and communication mechanisms. For example, this may include deep learning-based channel coding and decoding, deep learning-based signal estimation and detection, deep learning-based multiple input multiple output (MIMO) mechanisms, and AI-based resource scheduling and allocation.
[0142] Machine learning can be used for channel estimation and channel tracking, as well as for power allocation and interference cancellation at the physical layer of the downlink (DL). Machine learning can also be used for antenna selection, power control, and symbol detection in MIMO systems.
[0143] However, the application of DNN for transmission at the physical layer may have the following problems.
[0144] Deep learning-based AI algorithms require a large amount of training data to optimize training parameters. However, due to limitations in obtaining training data from specific channel environments, a large amount of training data is used offline. This means that static training on training data in specific channel environments can lead to conflicts with the dynamic characteristics and diversity of the wireless channel.
[0145] Furthermore, current deep learning primarily targets real-world signals. However, signals at the physical layer of wireless communications are complex signals. Further research is needed on neural networks capable of detecting complex domain signals to match the characteristics of wireless communication signals.
[0146] Below, we will look at machine learning in more detail.
[0147] Machine learning refers to a series of operations that train machines to perform tasks that humans can or cannot perform. Machine learning requires data and a learning model. In machine learning, data learning methods can be broadly categorized into three types: supervised learning, unsupervised learning, and reinforcement learning.
[0148] Neural network training aims to minimize output errors. It involves repeatedly inputting training data into a neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error.
[0149] Supervised learning uses labeled training data, while unsupervised learning may not have labeled training data. For example, in the case of supervised learning for data classification, the training data may be data in which each training data category is labeled. Labeled training data is input to a neural network, and the error can be calculated by comparing the output (categories) of the neural network with the training data labels. The calculated error is backpropagated through the neural network in the backward direction (i.e., from the output layer to the input layer), and the connection weights of each node in each layer of the neural network can be updated according to the backpropagation. The amount of change in the connection weights of each updated node can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, in the early stages of training a neural network, a high learning rate can be used to quickly allow the network to reach a certain level of performance, thereby improving efficiency, while in the later stages of training, a low learning rate can be used to improve accuracy.
[0150] Learning methods may vary depending on the characteristics of the data. For example, if the goal is to accurately predict data transmitted by a transmitter in a communication system, supervised learning is preferable to unsupervised learning or reinforcement learning.
[0151] The learning model corresponds to the human brain, and the most basic linear model can be thought of, but the machine learning paradigm that uses highly complex neural network structures, such as artificial neural networks, as learning models is called deep learning.
[0152] The neural network cores used in learning methods are mainly deep neural networks (DNN), convolutional deep neural networks (CNN), and recurrent Boltzmann machines (RNN), and these learning models can be applied.
[0153] THz (Terahertz) communication
[0154] THz communications can be applied in 6G systems. For example, data transmission rates can be increased by increasing bandwidth. This can be achieved by using sub-THz communications with wide bandwidths and applying advanced massive MIMO technology.
[0155] FIG. 9 is a diagram illustrating an electromagnetic spectrum applicable to the present disclosure. For example, referring to FIG. 9, THz waves, also known as sub-millimeter radiation, typically represent a frequency band between 0.1 THz and 10 THz with corresponding wavelengths ranging from 0.03 mm to 3 mm. The 100 GHz to 300 GHz band (Sub-THz band) is considered a major portion of the THz band for cellular communications. Adding the Sub-THz band to the mmWave band will increase the capacity of 6G cellular communications. Among the defined THz bands, 300 GHz to 3 THz is in the far infrared (IR) frequency band. Although the 300 GHz to 3 THz band is part of the optical band, it is at the boundary of the optical band and lies just behind the RF band. Therefore, this 300 GHz to 3 THz band exhibits similarities to RF.
[0156] Key characteristics of THz communications include (i) the widely available bandwidth to support very high data rates and (ii) the high path loss that occurs at high frequencies (requiring highly directional antennas). The narrow beamwidths generated by highly directional antennas reduce interference. The small wavelength of THz signals allows for a significantly larger number of antenna elements to be integrated into devices and base stations operating in this band. This enables the use of advanced adaptive array technologies to overcome range limitations.
[0157] Terahertz (THz) wireless communications
[0158] FIG. 10 is a diagram illustrating a THz communication method applicable to the present disclosure.
[0159] Referring to Fig. 10, THz wireless communication is a wireless communication using THz waves with a frequency of approximately 0.1 to 10 THz (1 THz = 1012 Hz), and may refer to terahertz (THz) band wireless communication using a very high carrier frequency of 100 GHz or higher. THz waves are located between the RF (Radio Frequency) / millimeter (mm) and infrared bands, and (i) compared to visible light / infrared rays, they penetrate non-metallic / non-polarizable materials well, and compared to RF / millimeter waves, they have a shorter wavelength, so they have high straightness and can focus beams.
[0160] Specific embodiments of the present invention
[0161] Below, we propose a method and federated learning system for efficiently operating wireless computation using a reconfigurable intelligent surface (RIS). The RIS may be an intelligent reflective surface (IRS). That is, RISs may take various forms and are not necessarily limited to a specific name. For convenience, the following description focuses on RISs, but is not limited thereto. Here, an artificial intelligence system can be used to adjust the wireless channel environment utilizing the RIS, which will be further described below.
[0162] For example, current wireless communication technologies can be controlled through endpoint optimization that adapts to the channel environment (H). For example, when optimization is performed at the transmitter and receiver, the transmitter and receiver can adjust at least one of beamforming, power control, and adaptive modulation to the channel environment (H) between the transmitter and receiver, thereby increasing transmission efficiency.
[0163] At this time, the channel environment can be random, uncontrolled, and naturally fixed. That is, in existing communication systems, the channel environment was fixed, and each endpoint could be controlled to optimize the channel environment. Therefore, the transmitter and receiver must optimize to adapt to the channel and transmit and receive data through this. However, in environments with high signal loss and low multipath, such as NLOS (non-line of sight) in shaded areas or 6G THz, it may be difficult to overcome Shannon's capacity limit with endpoint optimization alone, making it difficult to expect the desired throughput.
[0164] Considering the above, new communication systems can perform communication based on a smart radio environment. In this smart radio environment, a factor that can control the wireless channel, such as a transmitter and receiver, using RIS can be used.
[0165] That is, factors related to the wireless channel can be added as factors used to optimize wireless communication transmission. This can enable channel reconfiguration or overcome Shannon's channel capacity limit, which are insurmountable problems in existing communication systems. However, in an intelligent wireless environment, the measurement of the additional channel due to RIS and the simultaneous consideration of RIS with the transmitter and receiver are necessary to optimize wireless communication transmission, which can complicate the optimization process.
[0166] Furthermore, with the increase in AI applications such as federated learning, wireless distributed computation may become necessary. Wireless distributed computation involves multiple devices performing distributed computations via wireless communication for a specific goal. For example, multiple devices may train an AI model in a distributed manner for AI learning. Another example is autonomous driving technology, where multiple sensors may be installed to measure road condition information, requiring a base station to simultaneously receive sensor data from multiple sensors. For personalized broadcasting, communication may be required to simultaneously transmit data to devices capable of storing large amounts of data. In other words, wireless federated computation can take many forms and is not necessarily limited to a specific name. For convenience, the following description focuses on wireless computation performed using AirComp technology, but is not limited thereto.
[0167] AirComp technology is being studied in various ways. For example, it can be implemented by having terminals performing AirComp transmit local parameters using the same resources. In this approach, the base station can naturally obtain the sum of local parameters due to the superposition characteristics of analog signal formats. Another example is when terminals preprocess signals before transmitting them, and the base station interprets the superposed signals over the air through post-processing. Depending on the pre-processing and post-processing functions, various functions such as weighted average and geometric average can be implemented.
[0168] AirComp (over-the-air computation) technology allows for wireless signal overlap. If a particular terminal's transmission power is too strong, signals from other terminals may be ignored. Therefore, to achieve the desired wireless computation, the base station may need to allocate power to each terminal individually. Because this requires allocating significant power to devices in shadow areas, AirComp technology may be difficult to utilize solely through transceiver optimization. To overcome this issue, RIS-based AirComp technology emerged, enabling simultaneous wireless data transmission and reception. However, utilizing RIS-based AirComp technology can present the following challenges.
[0169] For example, there may be limitations in controlling RIS using the alternating optimization (AO) algorithm applied in an intelligent wireless environment along with the limitations of current wireless communication technology.
[0170] More specifically, existing communication systems have been able to operate in a manner that approaches Shannon's channel capacity limit through transmitter and receiver control in a fixed wireless channel environment. However, in poor NLOS environments, such as shaded areas, transmission and reception may be nearly impossible due to channel capacity limitations. For example, in an NLOS channel environment, a transmitter can improve the channel capacity limit by increasing power, but this can also increase the amount of noise and interference. In this case, in environments with high signal loss and difficult multipath, such as 6G THz environments, there may be limitations in overcoming Shannon's channel capacity limit through transmitter and receiver optimization alone.
[0171] Here, as an example, in a new communication system (e.g., 6G), there is a need to satisfy requirements for providing new services such as MBRLLC (Mobile Broadband Reliable Low Latency Communication), mURLLC (Massive Ultra-Reliable, Low Latency communications), HCS (Human-Centric Services), and 3CLS (Convergence of Communications, Computing, Control, Localization, and Sensing), and for this purpose, communication based on an intelligent wireless environment may be required.
[0172] For example, many relays are currently used to increase base station cell coverage and support shadow areas. However, while using relays can increase transmission efficiency, they can also generate additional interference signals for other users. Consequently, this can limit overall communication resource efficiency. Furthermore, the use of relays requires significant additional costs and energy, and can hinder the management of complex and mixed interference signals. Furthermore, the use of half-duplex mode, for example, can reduce spectral efficiency, and relays can also impact space utilization and aesthetics.
[0173] In contrast, in a smart radio environment, RIS can be used to control the radio channel environment. Simultaneously, the transmitter and receiver perform joint optimization, providing a solution to overcome Shannon's channel capacity limit in a smart radio environment, as described below.
[0174] However, in addition to the existing channel between the base station and the terminal, the channels between the base station and the RIS and between the RIS and the terminal also need to be considered. Furthermore, while previously optimizing only the transceiver for the specific environment was sufficient, in a smart radio environment, the RIS also needs to be controlled.
[0175] Furthermore, since these values may be dependent on the transmitter / receiver optimization, the complexity of optimization may increase. The Alternating Optimization (AO) algorithm used for optimization may be repeated until convergence, which can impose the burden of having to measure all channels.
[0176] When using AirComp technology, the channel environment of devices in shaded areas can be improved by utilizing RIS, but the difficulty of optimization considering RIS remains the same.
[0177] Below, considering the above-described points, a method for performing optimization in an intelligent wireless environment using RIS and an artificial intelligence system are described.
[0178] Also, as an example, Table 2 may be a term that takes into account the above and below, and below, a method for performing optimization in an intelligent wireless environment with RIS and an artificial intelligence system are described based on this.
[0179] - Federated Learning: federated learning - RIS (Reconfigurable Intelligent Surface): Reconfigurable intelligent surface - SRE (Smart Radio Environment): Intelligent radio environment - MBRLLC (Mobile Broadband Reliable Low Latency Communication): 6G services requiring high speed, high reliability, and low latency (e.g., BCI) - mMTC (Massive Machine Type Communications): Massive machine type communications - mURLLC (Massive Ultra-Reliable, Low Latency communications): mMTC + URLLC - QoPE (quality-of-physical-experience): QOS + QOE + physiological response - HCS (Human-Centric Services): Communication based on QoPE - 3CLS (Convergence of Communications, Computing, Control, Localization, and Sensing)
[0180] FIG. 11 is a diagram illustrating a wireless channel environment according to an embodiment of the present disclosure. Referring to FIG. 11, in an existing communication system, the wireless channel environment (H) may be naturally fixed and may be in a random state that cannot be controlled. Therefore, the transmitter (1110) and the receiver (1120) may find an optimized transmission and reception method by adapting to the channel. The transmitter (1110) and the receiver (1120) may be controlled to measure the channel state through a signal (e.g., a reference signal) and perform optimization based on the measured channel state. However, as described above, in a terahertz environment where signal loss is high and multipath application is difficult, and in an NLOS environment such as a shadow area, there may be limitations in data transmission. For example, the following [Mathematical Formula 1] may represent Shannon's capacity limit. In this case, even if the transmission signal P in [Mathematical Formula 1] is increased by applying precoding and processing, the channel If the size is small, there may be a limit to increasing the channel capacity.
[0181] In a fixed wireless channel environment, there may be a limit to increasing the channel capacity based on [Mathematical Formula 1]. In this case, communication using RIS can secure multiple paths between the transmitter (1110) and the receiver (1120), and can increase the channel as described above. That is, in an intelligent wireless environment, the wireless channel environment based on RIS can be an adjustable factor, and through this, the channel capacity can be increased.
[0182]
[0183] As an example, FIG. 12 is a diagram illustrating an intelligent wireless environment according to an embodiment of the present disclosure. Referring to FIG. 12, in an intelligent wireless channel environment, a wireless channel can be a factor for optimization. More specifically, in the above-described Fig. 11, optimization can be performed in the transmitter (1110) and the receiver (1120) based on "max{f(Tx, Rx)}" as an endpoint optimization, as described above. However, in the Fig. 12, optimization can be performed in the transmitter (1210) and the receiver (1220) based on "max{f(Tx, Rx, H)}" as an endpoint optimization. That is, in an intelligent wireless environment, the channel can be optimized based on an intelligent reflector. can be used as a factor for optimization.
[0184] FIGS. 13A and 13B are diagrams illustrating an existing wireless channel environment and an intelligent wireless channel environment according to an embodiment of the present disclosure. For example, referring to FIG. 13A, the existing wireless channel environment may be P1. Also, referring to FIG. 13B, the intelligent wireless channel environment may be P2. At this time, in FIGS. 13A and 13B, when signal x is transmitted from a transmitter through a wireless channel, the receiver may receive signal y. At this time, the probability of P1 in the existing wireless channel environment is fixed, and the receiver (decoder) may transmit feedback to the transmitter through measurement of the transmitted signal. The transmitter may perform optimization to adapt to the wireless channel environment through the feedback from the receiver. As a more specific example, the receiver may measure a channel quality indicator (CQI) for the transmitted signal based on a reference signal transmitted by the transmitter and feed it back. The transmitter can adjust the MCS (modulation coding scheme) based on the fed-back information and provide the information to the receiver to perform communication.
[0185] On the other hand, referring to Fig. 13b, in an intelligent wireless channel environment, the wireless channel environment P2 is recognized, and the wireless channel environment can be changed through RIS control. At the same time, the receiver can perform measurements on the received transmission signal and transmit feedback thereon to the transmitter. In other words, the transmitter can perform optimization by receiving feedback information based on RIS control and feedback information from the receiver. At this time, the transmitter can change the wireless channel environment by adjusting RIS, and optimization can be performed considering the wireless channel environment and the transmitter.
[0186] More specifically, FIG. 14 is a diagram illustrating a method for performing optimization in an intelligent wireless channel environment according to an embodiment of the present disclosure. Referring to FIG. 14, an RIS (1420) may exist between a base station (1410) and a terminal (1430) in an intelligent wireless channel environment. For example, a signal transmitted by a base station (1410) may have a path through which it is directly transmitted to the terminal (1430) and a path through which it is reflected and transmitted to the RIS (1420). That is, in an intelligent wireless channel environment, a wireless channel (G) between a base station (1410) and a RIS (1420), a wireless channel (h) between a RIS (1420) and a terminal (1430) r,k ) and a direct wireless channel (h) between the base station (1410) and the terminal (1430) d,k ) may exist. Here, based on the control of RIS (1420), a wireless channel (G) between the base station (1410) and RIS (1420) and a wireless channel (h) between RIS (1420) and terminal (1430) r,k ) may be changed. Therefore, in an intelligent wireless channel environment, optimization can be performed by taking into account the wireless channel environment described above.
[0187] More specifically, when the base station (1410) transmits a signal to terminal k (1430), the base station transmission beamforming vector for terminal k (1430) is w k, the signal transmitted to terminal k (1430) is s k and reception noise is n k It can be. At this time, the signal that terminal k (1430) receives from the base station (1410) based on the environment in which RIS (1420) is used can be as shown in [Mathematical Formula 2] below, and for each channel, it can be as shown in [Table 3] below.
[0188]
[0189] - : Channel from BS to user k, : Channel from RIS to user k- : Channel from BS to RIS, : transmit beamforming vector for signal - : Phase and amplitude coefficient for element n, [0,1], - : AWGN at user k
[0190] Here, the signal-to-noise ratio (SNR) received by terminal k (1430) may be as shown in [Mathematical Formula 3] below.
[0191]
[0192] Therefore, when configuring an intelligent radio environment (SRE) to optimize the reception SNR, it may be a case where the control of RIS and transmit beamforming are set as in [Mathematical Formula 4] below.
[0193]
[0194] At this time, considering the maximum-rate transmission in MIMO, the transmission beamforming of terminal k (1230) w k can be as shown in [Mathematical Formula 5] below.
[0195]
[0196] Here, P max can be the maximum transmission power in RIS, and w k and the formula for optimizing φ is w k * If we substitute , the optimization can be as follows [Mathematical Formula 6].
[0197]
[0198] At this time, if the RIS control value φ is determined, w k can be determined by operation. Here, the Alternating Optimization (AO) algorithm can be used to solve the above-described optimization problem. For example, the AO algorithm uses channel information (h d,k , h r,k , G) can be a method for determining the trust region for each RIS element, and can be as shown in Fig. 15. In addition, a binary decision is repeatedly performed until the objective value converges, and through this can be obtained. Here, the upper bound of the convergence value is the ideal RIS, =1 may be. At this time, as an example, in Fig. 14, RIS may repeat the above-described operation to find an optimized value for each RIS element described above.
[0199] Here, the Alternating Optimization (AO) algorithm needs to be repeated until convergence. Furthermore, because each optimized value must be derived for each RIS element, complexity and computational complexity may increase. Furthermore, the complexity and computational complexity may increase depending on the number of base station antennas M and the number of RIS elements N, and there may be limitations in calculating these. Furthermore, when optimizing the Alternating Optimization (AO) algorithm, measurement values for all channels including RIS may be required, and considering the above, there may be limitations in optimization.
[0200] The differences between RIS and repeaters can be shown in [Table 4] below.
[0201] TechnologyDuplexPower budgeNoiseCompatibilityInterferenceHardware complexityEnergy consumptionRISFullPassive, LowNo noiseVery highVery lowVery lowLowAF relayHalf / FullActive, highAdditive noiseLowHighHighHighDF relayHalf / FullActive, highAdditive noiseLowHighHighhigh
[0202] The most significant difference between RIS and a repeater is the use of an amplifier. A repeater either amplifies the received signal and transmits it directly, or decodes the signal, performs arithmetic operations, and then amplifies and transmits the encoded signal. Unlike RIS, which transmits the received signal through reflection or refraction, RIS communication eliminates the need for an amplifier, enabling power-efficient communication.
[0203] Therefore, the present invention proposes a transmission and reception method using AirComp technology by IoT devices such as artificial intelligence and various sensors using RIS in a communication system. By improving the channel gain of devices in shadow areas through RIS, a waste of communication resources may occur due to the influence of some terminals or devices existing in shadow areas where communication is impossible. In other words, the overall communication performance may deteriorate due to some devices in shadow areas, or some devices may monopolize the resources of the base station, resulting in a situation where communication between the base station and terminals is impossible. By using RIS, the channel gain of terminals or devices existing in shadow areas is improved, and additionally, if grouping is performed based on RIS when selecting devices, the performance of AirComp technology can be increased.
[0204] FIG. 16 is a diagram illustrating the structure of a federated learning system using AirComp technology according to an embodiment of the present disclosure. Referring to FIG. 16, a base station (1610) can learn a federated model through each terminal (1620 to 1640). The base station (1610) transmits a global model g to devices (1620 to 1640) participating in federated learning. Each terminal (1620 to 1640) learns a local model (z1 to z) through artificial intelligence learning based on the global model g. m ) are generated respectively. Since continuous transmission and reception of a large amount of data may be required for federated learning, AirComp technology, which transmits data simultaneously, can be utilized. Each terminal (1620 to 1640) participating in federated learning has its own transmission coefficient (b1 to b m ) and transmits it to the base station (1610). The base station (1610) uses the received signal to generate a local model (z1 to z m) is averaged to determine a new global model, and the new global model is transmitted to each terminal (1620 to 1640). In the above embodiment, the new global models are determined by arithmetic averaging the new models of each device (1620 to 1640), but may also be implemented using a geometric mean, weighted mean, etc.
[0205] FIG. 17 is a diagram illustrating an AirComp system and channel information using RIS (1720) according to one embodiment of the present disclosure. Referring to FIG. 17, a base station (1710) can perform data aggregation from terminals (1730-1 to 1730-m) using AirComp technology using RIS (1720). Since the AirComp system is a communication method in which the base station (1710) wirelessly aggregates information transmitted by connected terminals (1730-1 to 1730-m), channel information is displayed from the terminal toward the base station (1710). In a TDD (time division duplexing) system, transmission and reception can be performed within the same frequency. Therefore, it can be assumed that channel reciprocity exists in the AirComp system. In FIG. 17, h r,k is a channel from the kth terminal (1730-k) to the RIS (1720), G is a channel from the RIS (1720) to the base station (1710), and h d,k refers to the channel from the kth terminal (1730-k) to the base station (1710). Data s from the terminal (1730-k) k When transmitting, the base station (1710) receives data y as shown in [Mathematical Formula 7] below.
[0206]
[0207] In [Equation 7], b kis the transmission coefficient of the terminal (1730-k), φ is the symmetric phase shift matrix of the RIS (1720), m is the number of terminals participating in the AirComp system, and n is the noise generated when the base station (1710) receives the signal. It means AWGN which can be expressed as .
[0208] Transmission coefficient b of the terminal k is determined based on the channel information of each terminal (1730-1 to 1730-m), and is a factor used to enable the base station (1710) to equally aggregate the signals transmitted by each terminal (1730-1 to 1730-m).
[0209] FIG. 18 is a diagram illustrating a transceiver structure of a terminal and a base station for an AirComp system according to an embodiment of the present disclosure. Referring to FIG. 18, a base station can estimate signals transmitted by terminals using a decoding vector. The terminal receives data s k The value obtained by multiplying the transmission coefficient is transmitted to the base station. h shown in Fig. 18 e,k is an effective channel, meaning a wireless channel that includes RIS.
[0210] The definition of a valid channel is as follows [Mathematical Formula 8].
[0211]
[0212] The base station receives a signal y that includes AWGN in the sum of the signals transmitted by each device. Estimated signal can be as shown in [Mathematical Formula 9] below.
[0213]
[0214] In [Mathematical Formula 9], η represents the power normalization factor of the terminal and w represents the decoding vector of the base station.
[0215] η and w can be determined in the optimization stage to minimize the mean squared error (MSE). The performance of the AirComp system using RIS can be expressed using the MSE, which represents the difference between the estimated signal and the reference signal. The MSE can be determined as shown in [Mathematical Equation 10] below.
[0216]
[0217] In [Equation 10], P m refers to the maximum power of the terminal.
[0218] Therefore, in order to maximize the performance of the AirComp system using RIS, the values of the decoding vector w and the reflection pattern φ of RIS that minimize MSE can be determined through [Mathematical Formula 10] below.
[0219]
[0220] Various methods can be used to obtain the values of the decoding vector w and the reflection pattern φ of RIS using [Mathematical Formula 11]. For example, the semi-defined relaxation (SDR) method based on alternative optimization (AO) or an approximation method such as the difference of convex (DC) algorithm can be used.
[0221] Based on the values of the decoding vector w and the reflection pattern φ of RIS that minimizes MSE, the transmission coefficient b of the terminal is calculated using [Mathematical Formula 12] and [Mathematical Formula 13]. k And the power control factor η can be determined.
[0222]
[0223]
[0224] FIG. 19 is a diagram illustrating the operation method of a base station in an AirComp system using RIS according to one embodiment of the present disclosure. Referring to FIG. 19, the base station can group terminals and perform data aggregation using AirComp technology.
[0225] In step S1901, the base station transmits a first reference signal to the terminals. The first reference signal may be a reference signal for measuring the channel status of direct transmission and reception between the base station and the terminals without using RIS. The base station can also measure the channel status with the influence of RIS removed by transmitting a control signal to RIS to stop it.
[0226] In step S1903, the base station transmits a second reference signal to the terminals. The second reference signal may be a reference signal for measuring the channel status between the base station and the terminals using RIS. In the case of the base station and the RIS, the channel between the base station and the RIS may be previously measured due to reasons such as fixed locations or continuous transmission and reception. The base station may determine a beamforming vector, etc. based on the previously measured channel information between the base station and the RIS, and transmit the second reference signal.
[0227] In step S1905, the base station receives channel information from the terminals. The channel information may include the channel gain of the channel to be measured in steps S1901 and S1903. The channel state information may also include terminal location information in addition to the channel gain.
[0228] In step S1907, terminals participating in AirComp communication are classified and grouped. Various grouping methods may exist. For example, the base station may classify terminals into those that will participate in AirComp and those that will not based on a predetermined threshold. As another example, the base station may group terminals with the same channel with the highest channel gain. As another example, grouping may be performed based on location information into terminals located in shaded areas and those not located therein. In another example, when multiple RISs exist, grouping may be performed based on location information to classify terminals into a direct communication group, a terminal using the first RIS, and a terminal using the second RIS. The grouping criteria may be changed according to the circumstances of the person implementing the communication system, and a specific method is not excluded.
[0229] In step S1909, the base station transmits a power control element to the terminal. To determine the power control element, the base station determines a parameter value for each group to utilize AirComp technology. The parameter value may be a parameter value that reduces the MSE value of the received signal based on the channel information received by the base station. The parameter value determined at this time may not be a parameter value with the theoretically minimum MSE value. The parameter value determined by the base station may include at least one of a decoding vector and an RIS reflection pattern.
[0230] The method for transmitting the power control element is not limited to a specific method. For example, the power control element may be transmitted to terminals belonging to the first group, step S1909 of the first group may be performed, and then the power control element may be transmitted to terminals belonging to the second group. Alternatively, the power control element may be transmitted to terminals in both the first and second groups via broadcasting, and then step S1909 of the first group may be performed.
[0231] In step S1909, the base station aggregates data for each group using AirComp technology. Terminals in each group can transmit signals wirelessly using the same communication resources. Signals transmitted via the same communication resources are wirelessly superimposed and appear as a single signal. The base station can utilize this wireless superimposition process to compute specific computations. For example, in uncoded AirComp, terminals can simultaneously transmit signals wirelessly at the same frequency. The base station receives these signals as a single superimposed signal, and the value indicated by the received signal can be the sum of the values indicated by the signals transmitted by the terminals. Therefore, the base station cannot distinguish the individual signals sent by the terminals, but can calculate the sum of the values indicated by the signals transmitted by the terminals without additional computation. In addition to uncoded AirComp, there is also a coded AirComp method that uses the signSGD algorithm.
[0232] The base station can wirelessly receive data that the terminals have segmented using a decoding vector determined for each group, and can also perform federated learning based on the received data.
[0233] FIG. 20 is a diagram illustrating an operation method of a terminal participating in an AirComp system using RIS according to an embodiment of the present disclosure. Referring to FIG. 20, the terminal may transmit channel information to a base station and transmit data to the base station to perform AirComp. In steps S2001 and S2003, the terminal receives a first reference signal and a second reference signal from the base station. The first reference signal may be a reference signal for measuring a channel through which direct communication occurs between the base station and the terminal. The second reference signal may be a reference signal for measuring a channel through which the base station communicates with the terminal using RIS. If there are multiple RISs and communication is impossible without using RISs, the first reference signal and the second reference signal may be reference signals for measuring channels using each RIS.
[0234] In step S2005, the terminal that has received at least one reference signal transmits information about the channel with the highest channel gain to the base station. Step S2003 can be replaced by a method in which the terminal transmits information about all channels to the base station. The channel information may also include the terminal's location. Based on the received channel information, the terminal determines the group to which it belongs.
[0235] In step S2005, the terminal receives a power control element from the base station to perform AirComp. AirComp technology can be applied to each group. Therefore, if the terminal is not in its own group's order, steps S2009 and S2011 may not be performed.
[0236] In step S2009, the terminal determines a transmission coefficient based on the power control element. The transmission coefficient can be determined using [Mathematical Formula 12].
[0237] In step S2007, the terminal transmits distributed data based on transmission coefficients. The base station can aggregate data for each group.
[0238] FIG. 21 is a diagram illustrating a signal flow between a base station (2110), a RIS (2120), and terminals (2130-1 to 2130-k) in an AirComp system using RIS according to one embodiment of the present disclosure. Referring to FIG. 21, the base station (2110) can determine a reflection pattern of the RIS to improve the channel gain of terminals existing in a shadow area and aggregate data using AirComp technology. In step S2101, the base station (2110) transmits the reflection pattern to the RIS (2120) to measure the channel status for terminals (2130-1 to 2130-k) that will participate in AirComp communication. The reflection pattern (2120) of the RIS (2120) can be provided in the form of a square wave to alleviate the shadow area or in the form of a beam pattern learned based on information of each terminal (2130-1 to 2130-k). Information of each terminal (2130-1 to 2130-k) may include the connected terminal corresponding to the direction angle, channel size, etc.
[0239] At step S2103, the RIS (2120) controls the elements of the RIS (2120) based on the received reflection pattern. Through step S2103, the reflection angles of the elements of the RIS (2120) may be changed, and the base station (2110) may provide at least one channel to each terminal (2130-1 to 2130-k) through the adjustment of the reflection pattern.
[0240] In step S2105, the base station (2110) transmits a reference signal to each of the terminals (2130-1 to 2130-k) to measure channel information. The reference signal may include at least one of a cell-specific reference signal (CRS), a UE-specific reference signal (UE-RS), a demodulation reference signal (DM-RS), a channel state information reference signal (CSI-RS), an MBSFN reference signal, a positioning reference signal (PRS), and a phase tracking reference signal (PTRS). The method by which the base station (2110) transmits the reference signal is not particularly limited. For example, the base station (2110) may transmit the reference signal to all terminals (2130-1 to 2130-k) using a broadcasting method.
[0241] In step S2107, each terminal (2130-1 to 2130-k) that has received a reference signal transmits channel state information to the base station (2110).
[0242] At step S2109, the base station (2110) determines the decoding vector w and the reflection pattern φ of the RIS that minimize the objective function MSE based on the received channel state information. The objective function for optimization may be as shown in [Mathematical Formula 10] above. To minimize the objective function, the alternating optimization (AO) algorithm may be used, and artificial intelligence may be utilized.
[0243] In steps S2111 and S2113, the base station (2110) transmits the reflection pattern φ determined in step S2109 to the RIS (2120), and the RIS (2120) controls each element of the RIS (2120) based on the received reflection pattern φ.
[0244] In steps S2115 and S2117, the base station (2110) sets the decoding vector determined in step S2109 as the decoding vector of the base station (2110) and transmits the power control element η to each of the terminals (2130-1 to 2130-k). The power control element η can be determined through [Mathematical Formula 13] based on the decoding vector w and the reflection pattern φ of the RIS.
[0245] At step S2119, each terminal (2130-1 to 2130-k) transmits a transmission coefficient b1 to b k is determined. The transmission coefficient can be determined through [Mathematical Formula 12] based on the decoding vector w and the channel information of each terminal.
[0246] In step S2121, each terminal (2130-1 to 2130-k) transmits data by applying the determined transmission coefficient. After receiving the data with the transmission coefficient applied, the base station (2110) can estimate the signal sent by each terminal by [Mathematical Formula 9].
[0247] Although the resources of a base station, such as antenna beamforming and available base station power, are finite, there may be many terminals to aggregate. For an efficient communication system, the base station may require a device selection process. Since the channel gains of terminals also vary, a small number of terminals in shadow areas can increase the overall MSE, a performance indicator of the AirComp system, thereby degrading the performance of the AirComp system. Therefore, to improve the performance of the AirComp system, the base station may need to group terminals with similar channel gains. Furthermore, by utilizing RIS, the base station can communicate with terminals in groups with low channel gains to improve the channel gain.
[0248] When performing AirComp communications using RIS, one approach may be to simultaneously use both the direct channel and the RIS-based reflected channel. Simultaneously considering both the direct and reflected channels during optimization can result in significant computational overhead for the base station due to the complex algorithms used. Particularly in cases with numerous terminals, the base station may need to limit the number of devices. If a device selection process is required, randomly selecting the devices to participate in the calculation can lead to accumulated computational waste. Therefore, when device selection is required, the base station can group terminals based on RIS and control the RIS to ensure consistent channel gain. Through grouping, the base station can reduce the computational overhead of the optimization process while simultaneously improving the performance of the AirComp system.
[0249] FIG. 22 is a diagram illustrating an AirComp system environment using RIS according to one embodiment of the present disclosure. Referring to FIG. 22, for device selection, terminals can be classified into a direct channel group (2230-1) that communicates with a base station (2210) via a direct channel and a reflection channel group (2230-2) that communicates via an intelligent reflector (2220). When data is aggregated using AirComp technology, terminals belonging to each group (2230-1 and 2230-2) transmit and receive with the base station (2210) via the channels corresponding to each group (2230-1 and 2230-2). In cases where there are multiple RISs, there may be multiple reflection channel groups. In addition, if the base station (2210) has difficulty processing terminals of the direct channel group (2230-1) at once, the base station (2210) can further classify the direct channel group (2230-1) into multiple groups. As another example, a base station can group terminals with similar channel gains to reduce the MSE of the AirComp system.
[0250] The following Figures 23 to 25 illustrate specific examples of a base station performing grouping.
[0251] FIG. 23 is a diagram illustrating a method for grouping terminals to be used in AirComp technology using RIS according to one embodiment of the present disclosure. Referring to FIG. 23, a base station can determine terminals to be used in AirComp technology and perform grouping. In step S2301, the base station estimates a direct channel that does not utilize RIS. The base station can estimate a channel unaffected by RIS by sending a stop control signal to RIS. At this time, the base station can transmit a reference signal to the terminal and have it transmit a report on the reference signal.
[0252] In step S2303, the base station estimates a reflection channel using the RIS. Since multiple RISs may be used, there may be at least one reflection channel. When there are multiple reflection channels, the base station may transmit a control signal for the first RIS with a predetermined reflection pattern, and transmit a signal to stop the control signal for the second RIS. The reflection pattern for the first RIS may be determined by referring to channel information for the base station and the first RIS that has been measured. In order to measure the environment of each reflection channel, the base station may transmit multiple reference signals to the terminal and transmit reports for all reflection channels. As another example, the base station may cause each terminal to transmit a channel and channel gain having the largest channel gain among each reflection channel.
[0253] In step S2305, the base station sets the terminals to participate in AirComp communication into user groups based on the channel information received from the terminals, and may further group the user groups by channel. For example, the base station may determine all terminals as user groups and then group them by channel. The method by which the base station performs grouping is not limited to a specific method. For example, the base station may allow only terminals with a channel gain exceeding a certain threshold to participate in AirComp communication. As another example, the base station may allow a predetermined number of terminals to participate in AirComp communication in descending order of channel gain. The base station may further group the terminals in the determined user groups by channel to be used. For example, the base station may group the terminals into a direct channel group that does not utilize RIS and a first reflected channel group that utilizes the first RIS. As another example, if there are multiple RISs, the base station may also classify the reflected channel groups into multiple groups. The method for determining which group each terminal belongs to may be determined based on at least one piece of information such as the channel gain measured by each terminal and the terminal's location.
[0254] FIG. 24 is a diagram illustrating an operation method of a base station that groups based on channel gain using RIS according to an embodiment of the present disclosure. Referring to FIG. 24, the base station aggregates channel information of all terminals and then classifies each terminal into a direct channel group and an RIS channel group. In step S2401, the base station classifies the RIS into RIS. off Transmits control signals. RIS off The control signal is a signal that stops RIS operation and is used when receiving information about a direct channel without using RIS.
[0255] In step S2403, the base station transmits a reference signal to each terminal. The terminals that receive the reference signal from the base station transmit the channel gain to the base station.
[0256] In step S2405, the base station receives direct channel information. The base station that receives the direct channel information stores the direct channel information for comparison with the reflected channel information.
[0257] At step S2407, the base station determines the beamforming vector W based on the channel information between the base station and the RIS. RIS If the base station and RIS have fixed locations, the channel information between the base station and RIS can be measured in advance. In this case, the base station can utilize the previously measured channel information to determine the beamforming vector W. RIS can be decided.
[0258] In step S2409, the base station transmits the reflection pattern to the RIS. The base station may transmit the reflection pattern directly or transmit a control signal requesting the initiation of passive beam sweeping. Upon receiving the reflection pattern, the RIS controls each of its components, thereby improving the channel gain of terminals in the shadow area.
[0259] At step S2411, the base station provides the terminals with a beamforming vector W RIS The reference signal to which the reference signal is applied is transmitted. The terminals receiving the reference signal measure the channel gain.
[0260] In step S2413, the base station receives reflected channel information transmitted by terminals. The reflected channel information may include reflected channel gain.
[0261] In step S2415, the base station synthesizes the received direct channel information and reflected channel information and selects terminals to perform AirComp, prioritizing those with high channel gains. The base station may group the terminals belonging to the direct channel group and the reflected channel group, with a limited number of terminals. Furthermore, since AirComp communication is performed for each group, a single terminal may be included in multiple groups. In other words, a terminal with relatively high direct channel gain and reflected channel gain may be included in both the direct channel group and the reflected channel group. By selecting a channel with a high channel gain, the base station can determine the order of terminals participating in data aggregation during AirComp communication.
[0262] FIG. 25 is a diagram illustrating signal flow between a base station (2510), terminals (2530-1 to 2530-k), and RIS (2520) when grouping using RIS according to one embodiment of the present disclosure. Referring to FIG. 25, the base station (2510) can perform grouping in a manner in which each terminal (2530-1 to 2530-k) transmits a channel with the highest channel gain based on channel information.
[0263] In steps S2501 and S2503, the base station (2510) transmits RIS- off Transmit signal and RIS off RIS (2520) that receives the signal stops operating.
[0264] In step S2505, the base station (2510) transmits a reference signal to each terminal (2530-1 to 2530-k) to measure direct channel gain.
[0265] In steps S2507 and S2509, each terminal (2530-1 to 2530-k) receives a reference signal and estimates the state of the direct channel by measuring the direct channel gain.
[0266] In steps S2511 and S2513, the base station (2510) transmits a predetermined reflection pattern to the RIS (2520), and the RIS (2520) changes each element based on the received reflection pattern.
[0267] At step S2515, the base station (2510) transmits a reference signal to which a predetermined reflection pattern is applied.
[0268] In steps S2517 and S2519, each terminal (2530-1 to 2530-k) receives a reference signal and estimates the state of the reflection channel by measuring the channel gain of the reflection channel.
[0269] In steps S2521 and S2523, each terminal (2530-1 to 2530-k) compares the direct channel gain and the reflected channel gain, and determines the channel with the larger channel gain to be used for AirComp communication. Since the reflection pattern of the RIS is not yet fully optimized, the measured direct channel and reflected channel gains may differ from the direct channel and reflected channel gains after optimization. The same phenomenon may also occur when the base station (2510) measures the direct channel. Therefore, the sizes of the direct channel gain and the reflected channel gain may be compared while considering a compensation margin. The factors determining the compensation margin may include at least one of the number of antennas of the base station (2510), the number of elements of the RIS (2520), the power of a reference signal for direct channel measurement or a reference signal for reflected channel measurement, and a beam gain of beam sweeping during the control operation of the RIS (2520).
[0270] In step S2525, the base station (2510) receives channel information transmitted by terminals (2520-1 to 2530-k). The channel information may include at least one of information regarding channel conditions, such as the channel with the highest gain and channel gain.
[0271] In step S2527, the base station (2510) can classify the terminals (2520-1 to 2530-k) into a group that will use the direct channel and a group that will use the reflected channel by grouping the terminals that have the same channel with the highest channel gain.
[0272] FIG. 26 is a diagram illustrating a method for a base station to perform AirComp communication through grouping for device selection according to one embodiment of the present disclosure. Referring to FIG. 26, the base station classifies terminals into a first group and a second group and then performs AirComp communication.
[0273] In steps S2601 and S2603, the base station collects grouping information and groups the terminals. The method by which the base station performs grouping is not limited to a specific method, and the base station can perform the grouping using the procedures illustrated in FIGS. 23 to 25 . It is assumed that the base station has classified the terminals into Group 1 and Group 2 through grouping.
[0274] In step S2605, the base station optimizes the parameter values of the first group and the second group. The parameter values to be optimized may include the decoding vector w and the reflection pattern φ. AirComp communication that simultaneously considers both the direct channel and the reflected channel requires that the decoding vector and the reflection pattern be determined through [Mathematical Formula 11], and thus, a large amount of computation may be required if an alternative method is used. However, through grouping for device selection, the base station can distinguish between the direct channel and the reflected channel and perform optimization for each group. The method for optimization by the base station may be determined differently depending on which channel each group uses.
[0275] When optimizing a group using a direct channel, the base station can determine the decoding vector without considering the reflection pattern of the RIS. The decoding vector w can be determined by [Mathematical Formula 14] below.
[0276]
[0277] When optimizing a group using a reflection channel, the base station uses the decoding vector w as a beamforming vector W according to channel reciprocity. RIS , and the reflection pattern φ can be determined by the following [Mathematical Formula 15].
[0278]
[0279] By performing the optimization method in a partitioned manner using [Equation 14] and [Equation 15], the base station can reduce the computations related to optimization and simultaneously improve the performance of the AirComp system. Based on the decoding vector w and the reflection pattern φ determined through [Equation 14] and [Equation 15], the base station can perform matrix lifting and perform additional optimization using the SDR method, DC algorithm, etc. Finally, based on the determined decoding vector w and the reflection pattern φ, the base station can determine the power control factor η through [Equation 13].
[0280] In step S2607, the base station controls the elements of the RIS by transmitting the reflection pattern for the first group determined in step S2605 to the RIS. If the first group is a direct channel group, the base station may not transmit the reflection pattern to the RIS.
[0281] In step S2609, the base station transmits a power control element to terminals belonging to the first group. The base station may also transmit the power control element to the terminals via broadcast. Each terminal belonging to the first group calculates a transmission coefficient appropriate for its channel environment using [Mathematical Equation 12]. If the power control element is transmitted via broadcast, each terminal belonging to the second group may not calculate a transmission coefficient.
[0282] In step S2611, the base station receives a signal with a transmission coefficient applied from a terminal belonging to the first group and aggregates the data.
[0283] In steps S2613 to S2619, the base station performs AirComp communication for the second group in the same manner as in steps S2607 to S2611.
[0284] Although the method disclosed in FIG. 26 discloses one embodiment of dividing into a first group and a second group, the number of groups for which the base station performs grouping is not limited. For example, the base station may set terminals to participate in AirComp into user groups based on channel information received from the terminals, and may further group the user groups by channel. As another example, if there are multiple RISs, the list of terminals grouped by the base station may be classified into a direct channel group, a first reflected channel group, and a second reflected channel group.
[0285] FIG. 27 is a diagram illustrating signal flow between a base station (2710), an RIS (2720), and each terminal group (2730 and 2740) in an environment performing AirComp communication using RIS according to one embodiment of the present disclosure. Referring to FIG. 27, the base station (2710) can perform AirComp communication for a direct channel group (2730) and a reflected channel group (2740).
[0286] In step S2701, the base station (2710) performs grouping for device selection. The method by which the base station (2710) performs grouping is not limited to a specific method, and the procedures of FIGS. 23 to 25 disclosed above may be performed. The base station (2710) performs grouping to classify terminals into a direct channel group (2730) and a reflected channel group (2740). The base station (2710) may transmit the grouping results to each terminal.
[0287] In step S2703, the base station (2710) transmits a direct channel group (2730) start signal to terminals belonging to the direct channel group (2730). The base station (2710) may transmit the start signal to terminals belonging to all groups (2730 and 2740) through broadcasting. If the base station uses broadcasting, terminals not belonging to the direct channel may ignore the signal regarding AirComp communication.
[0288] In steps S2705 and S2707, the base station (2710) sends the RIS to the RIS (2720). off By transmitting a signal, the operation of RIS (2720) can be stopped. Since terminals belonging to the direct channel group (2730) have a low signal gain using RIS (2720), steps S2705 and S2707 can be omitted. Therefore, step S2705 is indicated by a dotted line in Fig. 27.
[0289] In steps S2709 and S2711, the base station (2710) optimizes the decoding vector w based on [Mathematical Formula 14] and determines the power control factor η based on the decoding vector w through [Mathematical Formula 13]. The base station (2710) transmits the power control factor to terminals belonging to the direct channel group (2730).
[0290] In step S2713, each terminal belonging to the direct channel group (2730) determines a transmission coefficient. The transmission coefficient can be determined based on [Mathematical Formula 12].
[0291] In step S2715, each terminal belonging to the direct channel group (2730) transmits data to be used for Air Comp based on the determined transmission coefficient, and the base station (2710) aggregates the data transmitted by each terminal.
[0292] In step S2717, the base station (2710) transmits a direct channel group (2730) end signal and a reflected channel group (2740) start signal to terminals belonging to all groups (2730 and 2740). The base station (2710) may transmit the end signal and the start signal to terminals belonging to all groups (2730 and 2740) through broadcasting. If a method is used in which a terminal recognizes that AirComp performance of the direct channel group has ended when it receives the reflected channel group start signal, the base station may omit transmitting the direct channel group (2730) end signal.
[0293] In step S2719, the base station (2710) determines the reflection pattern φ for the reflection channel group (2740). The base station can determine the beamforming vector based on the previously measured channel environment of the base station (2710) and the RIS (2720). The base station performs optimization by setting the determined beamforming vector as a decoding vector and determining the reflection pattern φ through [Mathematical Formula 15].
[0294] In steps S2721 and S2723, the base station (2710) transmits a reflection pattern φ to the RIS (2720), and each element of the RIS (2720) is controlled based on the reflection pattern φ.
[0295] In step S2725, the base station (2710) determines the power control element η through [Mathematical Formula 13] based on the decoding vector w and the reflection pattern φ, and transmits the reflection pattern φ to the terminal belonging to the reflection channel group (2740).
[0296] In step S2727, each terminal belonging to the reflection channel group (2740) determines a transmission coefficient. The transmission coefficient can be determined based on [Mathematical Formula 12].
[0297] In step S2729, each terminal belonging to the reflection channel group (2740) transmits data to be used for AirComp communication based on the determined transmission coefficient, and the base station (2710) aggregates the data transmitted by each terminal.
[0298] In step S2731, the base station (2710) transmits a signal to terminate the reflected channel group (2740) to all terminals. The base station (2710) may transmit the signal to terminals belonging to all groups (2730 and 2740) through broadcasting. If AirComp communication is continuously required, an operation to transmit a signal to start a new group or direct channel group (2730) may be included.
[0299] FIG. 28 is a diagram illustrating a signal flow between a base station (2810), an RIS (2820), and k groups (2830-1 to 2830-k) in a federated learning system environment using AirComp communication using RIS according to one embodiment of the present disclosure. Referring to FIG. 28, the base station (2810) can perform federated learning for each group (2830-1 to 2830-k) and determine a global model based on the model learned for each group (2830-1 to 2830-k). There may be at least one group, and there may be multiple direct channel groups or multiple indirect channel groups.
[0300] At step S2801, the base station (2810) is the previous global model g pre transmits to all terminals. The base station is a global model g pre It can be transmitted to all terminals through broadcasting. Terminals belonging to each group (2830-1 to 2830-k) are g pre After receiving g for each terminal pre Local learning is performed based on .
[0301] In step S2803, the base station performs grouping to select devices to perform federated learning. The base station can perform grouping using the method disclosed in FIG. 25.
[0302] In steps S2805-1 to S2805-k, the base station performs AirComp for each group. The base station can perform AirComp for the direct channel group (2805-1) through steps S2703 to S2717 as disclosed in FIG. 27. The base station can perform AirComp for the reflected channel group (2805-k) through steps S2717 to S2731 as disclosed in FIG.
[0303] At step S2807, the base station will be equipped with a new global model g new decides on a new global model g new can be determined based on the local model learned by all terminals belonging to each group.
[0304] Through [Mathematical Formula 16] below, the base station can obtain the global model g of the uth group. u can be decided.
[0305]
[0306] In [Equation 16], M u means the number of terminals included in the u-th group, and z i refers to the local model learned by the ith terminal of the uth group.
[0307] The base station is a global model g for each group u Based on [Equation 17], a new global model g new can be decided.
[0308]
[0309] In [Equation 17], N g means the total number of groups.
[0310] In steps S2809 to S2813, the base station determines a predetermined transmission beamforming vector W for broadcasting. BC and determines the reflection pattern φ. The base station transmits the reflection pattern φ to the RIS, and the RIS controls each element based on the received reflection pattern φ.
[0311] At step S2815, the base station is in global model g new Complete the first stage of federated learning by sending to all groups (2830-1 to 2830-k).
[0312] After completing step 1, the base station may continue to perform step 2 of federated learning by performing step S2805-1 again.
[0313] In Fig. 28, it is assumed that there are sufficient downlink resources compared to uplink resources, and the base station transmits the global model to all groups through broadcasting to all devices. However, a method in which the base station transmits the global model to each group through grouping may also be included in one embodiment of the present disclosure.
[0314] It is clear that the examples of the proposed methods described above can also be considered as a type of proposed methods, as they can be included as one of the implementation methods of the present disclosure. Furthermore, the proposed methods described above can be implemented independently, but they can also be implemented in the form of a combination (or merge) of some of the proposed methods. Information regarding the applicability of the proposed methods (or information regarding the rules of the proposed methods) can be defined by a rule such that the base station notifies the terminal of the application of the proposed methods through a predefined signal (e.g., a physical layer signal or a higher layer signal).
[0315] The present disclosure may be embodied in other specific forms without departing from the technical ideas and essential features described herein. Therefore, the above detailed description should not be construed as limiting in all respects but rather as illustrative. The scope of the present disclosure should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present disclosure are intended to be included within the scope of the present disclosure. Furthermore, claims that do not explicitly cite each other in the claims may be combined to form embodiments or incorporated into new claims through post-filing amendments.
[0316] Embodiments of the present disclosure can be applied to various wireless access systems. Examples of various wireless access systems include the 3rd Generation Partnership Project (3GPP) or 3GPP2 systems.
[0317] The embodiments of the present disclosure can be applied not only to the various wireless access systems described above, but also to all technical fields that utilize these various wireless access systems. Furthermore, the proposed method can also be applied to mmWave and THz communication systems utilizing ultra-high frequency bands.
[0318] Additionally, embodiments of the present disclosure can be applied to various applications such as autonomous vehicles and drones.
Claims
1. In a method of operating a base station in a wireless communication system, A step of transmitting a first reference signal to multiple terminals; A step of transmitting a second reference signal to the plurality of terminals based on a channel between the base station and a reconfigurable intelligent surface (RIS); A step of receiving channel information based on the first reference signal and the second reference signal from the plurality of terminals; A step of grouping into multiple groups based on the above channel information; A step of transmitting a power control factor determined based on the above channel information to the plurality of terminals; and; Including a step of receiving a signal in which the calculation result of signals transmitted wirelessly in an overlapping manner by each group of the plurality of terminals is expressed, A base station operating method, wherein the plurality of groups include a first group using a first channel for direct communication with the base station for the plurality of terminals and a second group using a second channel through the RIS.
2. In paragraph 1, The step of transmitting the first reference signal to the plurality of terminals is: A method of operating a base station, comprising the step of transmitting a stop signal to the RIS.
3. In paragraph 2, The step of transmitting the second reference signal to the plurality of terminals based on the channel between the base station and the RIS is: A step of determining a beamforming coefficient and a reflection pattern of the RIS based on a channel between the measured base station and the RIS; a step of transmitting the reflection pattern to the RIS; and A base station operating method, comprising a step of transmitting the second reference signal based on the beamforming coefficient to the plurality of terminals.
4. In paragraph 3, The above channel information includes channel identification information and channel gain value having the largest channel gain, A base station operation method in which the above grouping is performed on terminals having the same channel identification information having the greatest channel gain.
5. In paragraph 4, A base station operating method, wherein the plurality of groups further include a group in which terminals whose channel gain value does not exceed a threshold value do not transmit signals to the base station.
6. In paragraph 4, A base station operating method further comprising a step of adding a compensation margin to the channel gain based on at least one of the number of antennas of the base station, the number of elements of the RIS, the power of the first reference signal, the power of the second reference signal, and the beam gain of beam sweeping of the RIS.
7. In paragraph 1, The step of transmitting the power control element determined based on the channel information to the plurality of terminals is as follows: A step of determining a beamforming vector of the second group based on the channel environment of the base station and the RIS measured in the second group; A step of determining a decoding vector of the second group based on the beamforming vector of the second group; A step of optimizing the RIS reflection pattern for communication of the second group based on the decoding vector value of the second group; and A base station operating method, comprising the step of determining a power control element for the second group based on the decoding vector and the optimized RIS reflection pattern.
8. In paragraph 7, The step of receiving a signal expressing the result of calculation of signals wirelessly transmitted in an overlapping manner by each group of the above multiple terminals is as follows: A step of transmitting a start signal of the first group to the plurality of terminals; A step of receiving a signal based on a control element of the first group from a terminal of the first group; a step of transmitting a start signal of the second group to the plurality of terminals; and A base station operating method, comprising the step of receiving a signal based on a power control element of the second group from a terminal of the second group.
9. In paragraph 1, A step of transmitting attribute values of a global model for federated learning to the plurality of terminals; and A base station operating method further comprising a step of learning the global model based on the signal in which the calculation results of signals transmitted wirelessly in an overlapping manner by each group of the plurality of terminals are expressed.
10. In paragraph 9, The step of learning the global model based on the signal in which the computational results of the signals transmitted wirelessly in an overlapping manner by each group of the plurality of terminals are expressed is as follows: A step of determining a local model of each group based on the overlapping signals of each group; and A base station operating method, comprising a step of learning the global model based on the local model of each group.
11. In a method of operating a terminal in a wireless communication system, A step of receiving a first reference signal from a base station; A step of receiving a second reference signal based on a channel between the base station and a reconfigurable intelligent surface (RIS) from the base station; A step of transmitting channel information based on the first reference signal and the second reference signal to the base station; A step of receiving a power control factor determined based on the above channel information; A step of determining a transmission coefficient based on the above power control element; and A method of operating a terminal, comprising the step of transmitting a signal based on the transmission coefficient to the base station.
12. In paragraph 11, A method of operating a terminal, wherein the channel information includes channel identification information and a channel gain value having the greatest channel gain.
13. In paragraph 12, A method of operating a terminal, further comprising a step of adding a compensation margin to the channel gain based on at least one of the number of antennas of the base station, the number of elements of the RIS, the power of the first reference signal, the power of the second reference signal, and the beam gain of beam sweeping of the RIS.
14. In paragraph 11, The step of transmitting a signal based on the transmission coefficient to the above base station is: A step of receiving a start signal of the first group; A step of transmitting a signal based on the determined transmission coefficient when belonging to the first group; A step of receiving a start signal of a second group; and A method of operating a terminal, comprising the step of transmitting a signal based on the determined transmission coefficient when the terminal belongs to the second group.
15. In paragraph 11, A step of receiving a global model for federated learning from the base station; and A step in which the terminal learns the global model; A method of operating a terminal further comprising a step of transmitting attribute values of a learned global model to the terminal.
16. In communication devices, At least one processor; At least one computer memory connected to said at least one processor and storing instructions that direct operations when executed by said at least one processor, The above actions are, Transmitting a first reference signal to multiple terminals, Transmitting a second reference signal to the plurality of terminals based on a channel between the device and a reconfigurable intelligent surface (RIS), Receive channel information based on a first reference signal and a second reference signal from the plurality of terminals, Grouping into multiple groups is performed based on the above channel information, Transmitting a power control factor determined based on the above channel information to the plurality of terminals, The above multiple terminals receive a signal representing the computational result of signals transmitted wirelessly in an overlapping manner by each group, A communication device, wherein the plurality of groups include a first group that uses a channel for direct communication with the communication device for the plurality of terminals, and a second group that uses a communication channel through the RIS.
17. In communication devices, At least one processor; At least one computer memory connected to said at least one processor and storing instructions that direct operations when executed by said at least one processor, The above actions are, Receive a first reference signal from a base station, Receive a second reference signal based on a channel between the base station and a reconfigurable intelligent surface (RIS) from the base station, Transmit channel information based on the first reference signal and the second reference signal to the base station, Receive a power control factor determined based on the above channel information, Determine the transmission coefficient based on the above power control elements, A communication device that transmits a signal based on the transmission coefficient to the base station.
18. In a non-transitory computer-readable medium storing at least one instruction, comprising at least one instruction executable by the processor, At least one of the above commands causes the device to: Control to transmit a first reference signal to multiple terminals, Transmitting a second reference signal to the plurality of terminals based on a channel between the device and a reconfigurable intelligent surface (RIS), Receive channel information based on a first reference signal and a second reference signal from the plurality of terminals, Grouping into multiple groups is performed based on the above channel information, Transmitting a power control factor determined based on the above channel information to the plurality of terminals, The above multiple terminals receive a signal representing the computational result of signals transmitted wirelessly in an overlapping manner by each group, A computer-readable medium wherein the plurality of groups include a first group using a channel for direct communication with the device for the plurality of terminals and a second group using a communication channel through the RIS.
Citation Information
Patent Citations
STAR-RIS-assisted NOMA system uplink low-power-consumption transmission method
CN115915362A
Wireless federal learning method based on next generation multiple access technology
CN116017577A
Reconfigurable intelligent surface, RSI, aided and non-RIS-aided signal timing
WO2022186903A1
Method and apparatus for channel separation for intelligent reflecting surface (IRS)-based transmission
WO2023055704A1
Cited By
Near-field active monitoring method and system based on intelligent metasurface
CN120165730A
