Digital model of user equipment receiver for communication channel adaptation at base station

Abstract

Certain aspects of the present disclosure provide techniques for simulating a receiver for link adaptation. A method for wireless communication by an apparatus includes obtaining a parameter of a UE receiver from a UE; determining a channel characteristic of a communication channel between the apparatus and the UE based on the measurement of the signal received from the UE; estimating, based on the digital representation of the UE receiver, a response of the UE receiver to communicate over the communication channel having the channel characteristics, wherein the digital representation of the UE receiver is based on the parameters of the UE receiver; determining at least one parameter for communicating with the UE over the communication channel based on the estimated response; transmitting an indication of the at least one parameter to the UE; and communicating with the UE according to the at least one parameter.

Description

Cross-references to related applications

[0001] This application claims priority to U.S. Patent Application Serial No. 18 / 481,788, filed October 5, 2023, entitled “DIGITAL REPRESENTATION OF USEREQUIPMENT RECEIVER FOR COMMUNICATION CHANNEL ADAPTATION”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] Various aspects of this disclosure relate to wireless communication, and more specifically to techniques for communication channel adaptation. Background Technology

[0003] Wireless communication systems are widely deployed to provide a variety of telecommunications services, such as telephone, video, data, messaging, broadcasting, or other similar services. These wireless communication systems may employ multiple access technologies that enable communication with multiple users by sharing available wireless communication system resources.

[0004] Despite significant technological advancements in wireless communication systems over the years, challenges remain. For example, complex and dynamic environments can still attenuate or block signals between wireless transmitters and receivers. Therefore, there is a continuous expectation for improving the technical performance of wireless communication systems, including, for example: improving communication speed and data carrying capacity; improving the efficiency of shared communication media; reducing the power used by transmitters and receivers during communication; improving the reliability of wireless communication; avoiding redundant transmission and / or reception and related processing; improving the coverage area of ​​wireless communication; increasing the number and types of devices that can access the wireless communication system; increasing the ability of different types of devices to communicate with each other; and increasing the number and types of available wireless communication media. Therefore, there is a need for further improvements to wireless communication systems to overcome the aforementioned technical challenges and other obstacles. Summary of the Invention

[0005] One aspect provides a method for wireless communication by a device. The method may include: obtaining one or more parameters of a UE receiver from a user equipment (UE); determining one or more channel characteristics of a communication channel between the device and the UE based on measurements of signals received from the UE; estimating a response of the UE receiver to communicate on the communication channel having the one or more channel characteristics based on a digital representation of the UE receiver, wherein the digital representation of the UE receiver is based on the one or more parameters of the UE receiver; determining at least one parameter for communicating with the UE on the communication channel based on the estimated response; transmitting an indication of the at least one parameter to the UE; and communicating with the UE according to the at least one parameter.

[0006] Another aspect provides a method for wireless communication by a device. The method includes: transmitting one or more parameters of a UE receiver, the one or more parameters indicating a digital representation of the UE receiver, the digital representation representing a response for estimating the UE receiver's communication on a communication channel having one or more channel characteristics; receiving at least one parameter for communicating on the communication channel, the at least one parameter being at least partially based on the one or more parameters and the one or more channel characteristics of the communication channel; and communicating on the communication channel according to the at least one parameter.

[0007] Other aspects provide: one or more means operable to, configured to, or otherwise adapted to perform any portion of any method described herein (e.g., such that performance can be implemented by only one means or in a distributed manner across multiple means); one or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors of the one or more means, cause the one or more means to perform any portion of any method described herein (e.g., such that instructions can be included in only one computer-readable medium or in a distributed manner across multiple computer-readable media, such that instructions can be executed by only one processor or by multiple processors in a distributed manner, such that one or more processors can perform any portion of any method described herein). Each of the following apparatuses may include one or more processors, and / or enable execution to be performed by only one apparatus or in a distributed manner across multiple apparatuses; one or more computer program products embodied on one or more computer-readable storage media, the one or more computer program products including code for performing any part of any method described herein (e.g., enabling the code to be stored in only one computer-readable medium or in a distributed manner across computer-readable media); and / or one or more apparatuses including one or more components for performing any part of any method described herein (e.g., enabling execution to be performed by only one apparatus or by multiple apparatuses in a distributed manner). By way of example, an apparatus may include a processing system, a device having a processing system, or a processing system cooperating via one or more networks.

[0008] For illustrative purposes, the following description and figures illustrate certain features. Attached Figure Description

[0009] The accompanying drawings depict certain features of the various aspects described herein and should not be considered as limiting the scope of this disclosure.

[0010] Figure 1 An example wireless communication network is depicted.

[0011] Figure 2 An example decomposed base station architecture is described.

[0012] Figure 3 Various aspects of the example base station and example user equipment (UE) are described.

[0013] Figure 4A , Figure 4B , Figure 4C and Figure 4D Various example aspects of data structures used in wireless communication networks are described.

[0014] Figure 5 This is a diagram illustrating an example receiver that communicates with a transmitter via a communication channel.

[0015] Figure 6 The process flow for closed-loop feedback associated with the communication channel between network entities and UEs in the network is described.

[0016] Figure 7 This is a diagram illustrating an example artificial intelligence (AI) architecture that can be used for AI-enhanced wireless communication.

[0017] Figure 8 This is a diagram illustrating an example of UE receiver response prediction performed by a network entity.

[0018] Figure 9 This is a schematic diagram of an example artificial neural network (ANN).

[0019] Figure 10 This is a diagram illustrating an example mapping scheme that maps the receiver architecture to various types of signal decoding operations used at the UE receiver.

[0020] Figure 11 The process flow for communication between network entities and UEs in the network is described.

[0021] Figure 12 A method for wireless communication is described.

[0022] Figure 13 Another method for wireless communication is described.

[0023] Figure 14 Various aspects of the example communication device are described.

[0024] Figure 15 Various aspects of the example communication device are described. Detailed Implementation

[0025] This disclosure provides apparatus, methods, processing systems, and computer-readable media for simulating the response of a user equipment receiver to perform link adaptation.

[0026] In some wireless communication systems, closed-loop feedback associated with a communication channel can be used to dynamically adapt to time-varying channel conditions, such as changes in user equipment (UE) mobility, weather conditions, scattering, fading, interference, noise, etc. For example, the UE can report Channel State Feedback (CSF) to a network entity, which can adjust certain communication parameters in response to the feedback from the UE. For example, link adaptation (such as adaptive modulation and decoding) with various modulation schemes and channel decoding rates can be applied to certain communication channels. For channel state estimation purposes, the UE can be configured to measure a reference signal and estimate the channel state based on the measurement of that reference signal. The UE can report the estimated channel state to the network entity in the form of a CSF, which can be used in link adaptation. The CSF can indicate the channel properties of the communication link between the network entity and the UE. The CSF can indicate, for example, the effects of scattering, fading, and path loss of signals propagating across the communication link. As an example, a CSF report may include one or more of the following: Channel Quality Indicator (CQI), Pre-decoding Matrix Indicator (PMI), Layer Indicator (LI), Rank Indicator (RI), Reference Signal Received Power (RSRP), Signal-to-Interference-plus-Noise Ratio (SINR). Additional information or other information may be included in the CSF report.

[0027] Technical challenges related to link adaptation include, for example, the overhead of communicating CSF (Content Request for Information) from the UE to network entities and the CSF reporting rate. Since the CSF carries information about the channel state, its overhead consumes valuable communication channel resources that could be used to carry, for example, user plane services or other services. For example, PMI (Pre-decoder Information) can instruct the UE to use a preferred pre-decoder (e.g., beamforming) for downlink transmission by network entities. PMI can include pre-decoder information at various resolution levels across the spatial and frequency domains. For example, PMI can include excessive pre-decoder information associated with multiple beams, multiple bandwidths (wideband and / or subband reporting stages), multiple MIMO (Multiple-Input Multiple-Output) layers, etc. (e.g., a weighted combination of beams with relative amplitude and co-phase phase shifts). PMI and the corresponding RI (Report Request for Information) can consume a significant portion of the CSF reported from the UE.

[0028] The tracking rate (e.g., the rate at which the communication link adapts to changing channel conditions) can depend on the CSF reporting rate. For example, a network entity may be unaware of rapidly changing channel conditions encountered at the UE due to the relatively long periodicity between consecutive CSF reports, and the network entity may not be able to respond to such changing channel conditions without affecting the performance of the communication link between the network entity and the UE. Furthermore, adjusting the CSF reporting rate affects the tracking rate, for example, to adapt to rapidly changing channel conditions, and adjustments to the CSF reporting rate affect CSF overhead. For example, reduced periodicity for CSF reporting to meet rapidly changing channel conditions can be equivalent to increased signaling overhead for CSF reporting.

[0029] The aspects described herein overcome the aforementioned technical problems by providing techniques for estimating the receiver's response using a digital representation of the UE receiver for link adaptation. Network entities can predict the UE receiver's performance in decoding received signals based on the digital representation of the UE receiver and an estimation of the communication channel. This estimation can be determined using measurements of a reference signal received from the UE, for example, as described herein. Figure 6 Further described. A network entity may, for example, obtain from the UE an indication of the UE receiver used for wireless communication at the UE via UE capability information. As an example, the network entity may obtain an indication of an artificial intelligence (AI) model (e.g., neural network coefficients) that simulates one or more signal decoding operations of the UE receiver, such as baseband recovery, channel estimation, channel equalization, and / or demodulation, as described herein. Figure 5 and Figures 8 to 10 Further described, the network entity may determine link adaptation parameters (e.g., PMI, RI, and / or modulation and decoding scheme (MCS)) for the communication link between the network entity and the UE based on the estimated performance of the UE receiver. The network entity may transmit the link adaptation parameters to the UE for use in communication between the network entity and the UE.

[0030] The communication link adaptation techniques using the digital representation of the UE receiver as described herein can provide any of a variety of beneficial effects and / or advantages. The communication link adaptation techniques described herein can achieve improved wireless communication performance, such as reduced signaling overhead associated with CSF reporting, increased tracking rate for link adaptation, increased throughput, reduced latency, spectral efficiency, etc. The improved wireless communication performance can be attributed to the communication link adaptation described herein, which allows network entities to estimate the performance of the UE receiver with or without CSF reporting. Reduced CSF reporting facilitates the use of such signaling overhead for other communications. The communication link adaptation described herein can track channels with high-rate variations, for example, because network entities are able to estimate the performance of the UE receiver at a rate matching or exceeding the rate associated with the changing channel conditions. In some cases, the communication link adaptation described herein can facilitate high-rate tracking link adaptation without overhead. Introduction to wireless communication networks

[0031] The techniques and methods described herein can be used in a variety of wireless communication networks. Although aspects herein may be described using terms commonly associated with 3G, 4G, 5G, 6G and / or other generations of wireless technologies, aspects of this disclosure are equally applicable to other communication systems and standards not explicitly mentioned herein.

[0032] Figure 1 An example of a wireless communication network 100 in which the aspects described herein can be implemented is depicted.

[0033] Generally, wireless communication network 100 includes various network entities (alternatively, network elements or network nodes). Network entities are typically communication devices and / or communication functions performed by communication devices (e.g., user equipment (UE), base station (BS), components of a BS, servers, etc.). Since such communication devices are part of wireless communication network 100 and facilitate wireless communication, they may be referred to as wireless communication devices. For example, various functions of the network and various devices associated with and interacting with the network may be considered network entities. Furthermore, wireless communication network 100 includes terrestrial and non-terrestrial aspects (also referred to herein as non-terrestrial network entities). Terrestrial aspects include ground-based network entities (e.g., BS 102), and non-terrestrial aspects include satellite 140 and transport aircraft, which may include onboard network entities (e.g., one or more BSs) capable of communicating with other network elements (e.g., terrestrial BSs) and UEs.

[0034] In the depicted example, wireless communication network 100 includes BS 102, UE 104 and one or more core networks (such as Evolved Packet Core (EPC) 160 and 5G Core (5GC) network 190) that interoperate to provide communication services over various communication links, including wired and wireless links.

[0035] Figure 1 Various example UEs 104 are described, which may more generally include: cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, GPS devices, multimedia devices, video devices, digital audio players, cameras, game consoles, tablet computers, smart devices, wearable devices, vehicles, electricity meters, air pumps, large or small kitchen appliances, healthcare devices, implants, sensors / actuators, displays, Internet of Things (IoT) devices, always-on (AON) devices, edge processing devices, data centers, or other similar devices. UE 104 may also be more generally referred to as mobile devices, wireless devices, stations, mobile stations, subscriber stations, mobile subscriber stations, mobile units, subscriber units, wireless units, remote units, remote devices, access terminals, mobile terminals, wireless terminals, remote terminals, mobile phones, and others.

[0036] BS 102 communicates wirelessly with UE 104 via communication link 120 (e.g., transmitting or receiving signals to or from UE 104). Communication link 120 between BS 102 and UE 104 may include uplink (UL) (also known as reverse link) transmission from UE 104 to BS 102 and / or downlink (DL) (also known as forward link) transmission from BS 102 to UE 104. In various aspects, communication link 120 may utilize multiple-input multiple-output (MIMO) antenna techniques, including spatial multiplexing, beamforming, and / or transmit diversity.

[0037] BS 102 may typically include: NodeB, enhanced NodeB (eNB), next-generation enhanced NodeB (ng-eNB), next-generation NodeB (gNB or gNodeB), access point, transceiver base station, radio base station, radio transceiver, transceiver functionality, transmit / receive point, and / or others. Each of BS 102 provides communication coverage for a corresponding coverage area 110, which may sometimes be referred to as a cell, and in some cases may overlap (e.g., a small cell 102' may have a coverage area 110' that overlaps with the coverage area 110 of a macro cell). For example, BS may provide communication coverage for macro cells (covering a relatively large geographic area), pico cells (covering a relatively small geographic area, such as a stadium), femtocells (covering a relatively small geographic area (e.g., a home)), and / or other types of cells.

[0038] Generally, a cell can refer to a portion, partition, or segment of wireless communication coverage served by a network entity within a wireless communication network. A cell may have geographical characteristics (such as a geographical coverage area) and radio frequency characteristics (such as time and / or frequency resources dedicated to the cell). For example, multiple cells employing different frequency resources (e.g., bandwidth portions) and / or different time resources can cover a specific geographical coverage area. As another example, a single cell can cover a specific geographical coverage area. In some contexts (e.g., carrier aggregation scenarios and / or multi-connectivity scenarios), the terms "cell" or "serving cell" may refer to or correspond to a specific carrier frequency (e.g., component carrier) used for wireless communication, and "cell group" may refer to or correspond to multiple carriers used for wireless communication. As an example, in a carrier aggregation scenario, a UE can communicate on multiple component carriers corresponding to multiple (serving) cells in the same cell group, and in a multi-connectivity (e.g., dual-connectivity) scenario, a UE can communicate on multiple component carriers corresponding to multiple cell groups.

[0039] Although BS 102 is described as a single communication device in various aspects, it can be implemented in a variety of configurations. For example, to give a few examples, one or more components of the base station can be decomposed, including a central unit (CU), one or more distributed units (DU), one or more radio units (RU), a near real-time (near RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC. In another example, various aspects of the base station can be virtualized. More generally, a base station (e.g., BS 102) can include components located at a single physical location or components located at various physical locations. In examples where the base station includes components located at various physical locations, the various components can each perform functions, such that the various components collectively achieve functionality similar to a base station located at a single physical location. In some aspects, a base station including components located at various physical locations can be referred to as a decomposed radio access network architecture (such as an open RAN (O-RAN) or virtualized RAN (VRAN) architecture). Figure 2 An example decomposed base station architecture is depicted and described.

[0040] Different BSs 102 within the wireless communication network 100 can also be configured to support different radio access technologies (such as 3G, 4G, and / or 5G). For example, a BS 102 configured for 4G LTE (collectively referred to as Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN)) can interface with EPC 160 via a first backhaul link 132 (e.g., S1 interface). A BS 102 configured for 5G (e.g., 5G NR or Next Generation RAN (NG-RAN)) can interface with 5GC 190 via a second backhaul link 184. BSs 102 can communicate directly or indirectly with each other (e.g., via EPC 160 or 5GC 190) on a third backhaul link 134 (e.g., X2 interface), which can be wired or wireless.

[0041] Wireless communication network 100 can subdivide the electromagnetic spectrum into various categories, bands, channels, or other characteristics. In some aspects, subdivision is provided based on wavelength and frequency, where frequency may also be referred to as carrier, subcarrier, channel, tone, or subband. For example, 3GPP currently defines frequency range 1 (FR1) as including 410MHz to 7125MHz, which is often (interchangeably) referred to as “sub-6GHz”. Similarly, 3GPP currently defines frequency range 2 (FR2) as including 24,250MHz to 71,000MHz, which is sometimes (interchangeably) referred to as “millimeter wave” (“mmW” or “mmWave”). In some cases, FR2 can be further defined according to subranges (such as a first subrange FR2-1 including 24,250MHz to 52,600MHz and a second subrange FR2-2 including 52,600MHz to 71,000MHz). Base stations configured to communicate using mmWave / near-mmWave radio bands (e.g., mmWave base stations such as BS 180) can utilize beamforming (e.g., 182) with UEs (e.g., 104) to improve path loss and range.

[0042] The communication link 120 between BS 102 and, for example, UE 104 can be via one or more carriers, which may have different bandwidths (e.g., 5MHz, 10MHz, 15MHz, 20MHz, 100MHz, 400MHz and / or other MHz) and may be aggregated in various ways. The carriers may be adjacent to each other or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated to DL compared to UL).

[0043] Compared to lower-frequency communication, communication using higher frequency bands may have higher path loss and shorter range. Therefore, some base stations (e.g., Figure 1The beamforming 182 of the BS 180 (180) with the UE 104 can be used to improve path loss and range. For example, the BS 180 and UE 104 may each include multiple antennas, such as antenna elements, antenna panels, and / or antenna arrays, to facilitate beamforming. In some cases, the BS 180 may transmit beamformed signals to the UE 104 in one or more transmit directions 182''. The UE 104 may receive beamformed signals from the BS 180 in one or more receive directions 182''. The UE 104 may also transmit beamformed signals to the BS 180 in one or more transmit directions 182''. The BS 180 may also receive beamformed signals from the UE 104 in one or more receive directions 182''. The BS 180 and UE 104 may then perform beamforming training to determine the optimal receive and transmit directions for each of the BS 180 and UE 104. It is worth noting that the transmit and receive directions of the BS 180 may or may not be the same. Similarly, the transmission and reception directions of UE 104 may or may not be the same.

[0044] The wireless communication network 100 also includes a Wi-Fi AP 150 that communicates with a Wi-Fi station (STA) 152 via a communication link 154 in, for example, unlicensed spectrum in 2.4 GHz and / or 5 GHz.

[0045] Some UEs 104 may use device-to-device (D2D) communication links 158 to communicate with each other. The D2D communication link 158 may use one or more sidelink channels, such as physical sidelink broadcast channel (PSBCH), physical sidelink discovery channel (PSDCH), physical sidelink shared channel (PSSCH), physical sidelink control channel (PSCCH), and / or physical sidelink feedback channel (PSFCH).

[0046] EPC 160 may include various functional components, including: Mobility Management Entity (MME) 162, other MMEs 164, Serving Gateway 166, Multimedia Broadcast Multicast Service (MBMS) Gateway 168, Broadcast Multicast Service Center (BM-SC) 170, and / or Packet Data Network (PDN) Gateway 172, as in the illustrated example. MME 162 may communicate with Home Subscriber Server (HSS) 174. MME 162 is the control node that handles signaling between UE 104 and EPC 160. Generally, MME 162 provides bearer and connectivity management.

[0047] Generally, user Internet Protocol (IP) packets are transmitted through Serving Gateway 166, which is itself connected to PDN Gateway 172. PDN Gateway 172 provides UE IP address allocation and other functions. PDN Gateway 172 and BM-SC 170 are connected to IP service 176, which may include, for example, the Internet, intranet, IP Multimedia Subsystem (IMS), packet-switched (PS) streaming service, and / or other IP services.

[0048] The BM-SC 170 provides functions for MBMS user service dispatch and delivery. The BM-SC 170 can serve as an entry point for content provider MBMS transmissions, can be used to authorize and initiate MBMS bearer services within a Public Land Mobile Network (PLMN), and / or can be used to schedule MBMS transmissions. The MBMS gateway 168 can be used to distribute MBMS services to BS 102 belonging to a Broadcast-Specific Service Single Frequency Network (MBSFN) area, and / or can be responsible for session management (start / stop) and collecting eMBMS-related billing information.

[0049] 5GC 190 may include various functional components, including: Access and Mobility Management Function (AMF) 192, other AMFs 193, Session Management Function (SMF) 194, and User Plane Function (UPF) 195. AMF 192 can communicate with Unified Data Management (UDM) 196.

[0050] AMF 192 is the control node that handles signaling between UE 104 and 5GC 190. AMF 192 provides services such as Quality of Service (QoS) flow and session management.

[0051] Internet Protocol (IP) packets are transmitted via UPF 195, which connects to IP service 197 and provides the UE with IP address allocation and other functions for 5GC 190. IP service 197 may include, for example, the Internet, intranet, IMS, PS streaming service, and / or other IP services.

[0052] In various aspects, to give a few examples, network entities or network nodes can be implemented as aggregated base stations, decomposed base stations, components of base stations, integrated access and backhaul (IAB) nodes, relay nodes, and sidelink nodes.

[0053] Figure 2An example decomposed base station 200 architecture is depicted. The decomposed base station 200 architecture may include one or more central units (CUs) 210, which may communicate directly with the core network 220 via a backhaul link, or indirectly with the core network 220 through one or more decomposed base station units, such as a near real-time (near-RT) RAN Intelligent Controller (RIC) 225 via an E2 link, or a non-real-time (non-RT) RIC 215 associated with a Service Management and Orchestration (SMO) framework 205, or both. CUs 210 may communicate with one or more distributed units (DUs) 230 via corresponding midhaul links (such as F1 interfaces). DUs 230 may communicate with one or more radio units (RUs) 240 via corresponding fronthaul links. RUs 240 may communicate with a corresponding UE 104 via one or more radio frequency (RF) access links. In some specific implementations, UE 104 may be served simultaneously by multiple RUs 240.

[0054] Each unit in a cell (e.g., CU 210, DU 230, RU 240, and near-RT RIC 225, non-RT RIC 215, and SMO frame 205) may include or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) via wired or wireless transmission media. Each unit in the cell, or an associated processor or controller providing instructions to the unit's communication interface, may be configured to communicate with one or more other units via transmission media. For example, these units may include wired interfaces configured to receive signals or transmit signals to one or more other units via wired transmission media. Additionally or alternatively, a unit may include a wireless interface that may include a receiver, transmitter, or transceiver (such as a radio frequency (RF) transceiver) configured to receive signals on a wireless transmission medium or transmit signals to one or more other units, or both.

[0055] In some aspects, CU 210 can host one or more higher-level control functions. Such control functions may include Radio Resource Control (RRC), Packet Data Convergence Protocol (PDCP), Serving Data Adaptation Protocol (SDAP), etc. Each control function can be implemented using an interface configured to signal to other control functions hosted by CU 210. CU 210 can be configured to handle user plane functions (e.g., Central Unit-User Plane (CU-UP)), control plane functions (e.g., Central Unit-Control Plane (CU-CP)), or combinations thereof. In some implementations, CU 210 can be logically divided into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, CU-UP units can communicate bidirectionally with CU-CP units via an interface such as an E1 interface. CU 210 can be implemented to communicate with DU 230 for network control and signaling, as needed.

[0056] DU 230 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RU 240s. In some aspects, DU 230 may host one or more of the Radio Link Control (RLC) layer, Medium Access Control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) at least in part according to functional splits (such as those defined by the 3rd Generation Partnership Project (3GPP). In some aspects, DU 230 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface configured to communicate signals with other layers (and modules) hosted by DU 230 or with control functions hosted by CU 210.

[0057] Lower-layer functionality can be implemented by one or more RU 240s. In some deployments, the RU240 controlled by the DU 230 may correspond to a logical node that is at least partially based on functional decomposition, such as lower-layer functional decomposition, to host RF processing functions or low-PHY layer functions (such as performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, Physical Random Access Channel (PRACH) extraction and filtering, etc.) or both. In such architectures, the RU 240 may be implemented to handle over-the-air (OTA) communications with one or more UE 104s. In some specific implementations, the real-time and non-real-time aspects of control plane and user plane communications with the RU 240 may be controlled by the corresponding DU 230. In some scenarios, this configuration allows the DU 230 and CU210 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0058] SMO framework 205 can be configured to support RAN deployment and provisioning of both non-virtualized and virtualized network elements. For non-virtualized network elements, SMO framework 205 can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via operation and maintenance interfaces such as the O1 interface. For virtualized network elements, SMO framework 205 can be configured to interact with cloud computing platforms such as Open Cloud (O-Cloud) 290 to perform network element lifecycle management (such as instantiating virtualized network elements) via cloud computing platform interfaces such as the O2 interface. Such virtualized network elements may include, but are not limited to, CU 210, DU 230, RU 240, and near-RT RIC 225. In some specific implementations, SMO framework 205 may communicate with the hardware aspects of the 4G RAN (such as Open eNB (O-eNB) 211) via the O1 interface. Additionally, in some implementations, the SMO framework 205 may communicate directly with one or more DU 230s and / or one or more RU 240s via the O1 interface. The SMO framework 205 may also include a non-RT RIC 215 configured to support the functionality of the SMO framework 205.

[0059] The non-RT RIC 215 can be configured to include logical functions enabling non-real-time control and optimization of RAN elements and resources, including artificial intelligence / machine learning (AI / ML) workflows for model training and updates, or policy-based guidance for applications / features in the near-RT RIC 225. The non-RT RIC 215 can be coupled to or communicate with the near-RT RIC 225, such as via an A1 interface. The near-RT RIC 225 can be configured to include logical functions enabling near real-time control and optimization of RAN elements and resources via data collection and actions through an interface such as an E2 interface, connecting one or more CU 210s, one or more DU 230s, or both, and O-eNBs to the near-RT RIC 225.

[0060] In some implementations, to generate AI / ML models to be deployed in the near-RT RIC 225, the non-RT RIC 215 may receive parameters or external enrichment information from an external server. This information can be utilized by the near-RT RIC 225 and may be received from non-network data sources or network functions at the SMO framework 205 or the non-RT RIC 215. In some examples, the non-RT RIC 215 or the near-RT RIC 225 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 215 may monitor long-term trends and patterns in performance and employ AI / ML models to perform corrective actions via the SMO framework 205 (such as reconfiguration via O1) or by creating RAN management policies (such as A1 policies).

[0061] Figure 3 Various aspects of examples BS 102 and UE 104 are described.

[0062] Generally, BS 102 includes various processors (e.g., 318, 320, 330, 338, and 340), antennas 334a-334t (collectively referred to as 334), transceivers 332a-332t (collectively referred to as 332) including modulators and demodulators, and other aspects that enable the wireless transmission of data (e.g., data source 312) and the wireless reception of data (e.g., data sink 314). For example, BS 102 can transmit and receive data between BS 102 and UE 104. BS 102 includes a controller / processor 340 that can be configured to implement the various functions described herein related to wireless communication.

[0063] Generally, UE 104 includes various processors (e.g., 358, 364, 366, 370, and 380), antennas 352a-352r (collectively referred to as 352), transceivers 354a-354r (collectively referred to as 354) including modulators and demodulators, and other aspects for implementing wireless transmission of data (e.g., retrieved from data source 362) and wireless reception of data (e.g., provided to data sink 360). UE 104 includes a controller / processor 380 that can be configured to implement the various functions described herein related to wireless communication.

[0064] Regarding example downlink transmission, BS 102 includes a transmission processor 320 that can receive data from data source 312 and control information from controller / processor 340. This control information may be for a Physical Broadcast Channel (PBCH), Physical Control Format Indicator Channel (PCFICH), Physical Hybrid Automatic Repeat Request (HARQ) Indicator Channel (PHICH), Physical Downlink Control Channel (PDCCH), Group Common PDCCH (GC PDCCH), and / or others. In some examples, this data may be for a Physical Downlink Shared Channel (PDSCH).

[0065] The transmitter processor 320 can process (e.g., encode and symbol map) data and control information to obtain data symbols and control symbols, respectively. The transmitter processor 320 can also generate reference symbols (such as those for the primary synchronization signal (PSS), secondary synchronization signal (SSS), PBCH demodulation reference signal (DMRS), and channel state information reference signal (CSI-RS)).

[0066] The transmit (TX) multiple-input multiple-output (MIMO) processor 330 can perform spatial processing (e.g., pre-decoding) on ​​data symbols, control symbols, and / or reference symbols where applicable, and can provide the output symbol stream to the modulators (MODs) in transceivers 332a-332t. Each modulator in transceivers 332a-332t can process the corresponding output symbol stream to obtain an output sample stream. Each modulator can further process (e.g., convert to analog, amplify, filter, and up-convert) the output sample stream to obtain a downlink signal. The downlink signal from the modulators in transceivers 332a-332t can be transmitted via antennas 334a-334t respectively.

[0067] To receive downlink transmissions, UE 104 includes antennas 352a-352r that receive downlink signals from BS 102 and provide the received signals to demodulators (DEMODs) in transceivers 354a-354r respectively. Each demodulator in transceivers 354a-354r can adjust (e.g., filter, amplify, down-convert, and digitize) the corresponding received signal to obtain an input sample. Each demodulator can further process the input sample to obtain the received symbols.

[0068] The RX MIMO detector 356 acquires received symbols from all demodulators in transceivers 354a-354r, performs MIMO detection on the received symbols where applicable, and provides the detected symbols. The receive processor 358 can process (e.g., demodulate, deinterleave, and decode) the detected symbols, provide the decoded data for UE 104 to data sink 360, and provide the decoded control information to controller / processor 380.

[0069] Regarding example uplink transmission, UE 104 also includes a transmit processor 364 that receives and processes data from data source 362 (e.g., for PUSCH) and control information from controller / processor 380 (e.g., for Physical Uplink Control Channel (PUCCH)). Transmit processor 364 can also generate reference symbols for reference signals (e.g., for Sounding Reference Signal (SRS)). Symbols from transmit processor 364 can be pre-decoded by TX MIMO processor 366, where applicable, further processed by modulators in transceivers 354a-354r (e.g., for SC-FDM), and transmitted to BS 102.

[0070] At BS 102, uplink signals from UE 104 can be received by antennas 334a-334t, processed by demodulators in transceivers 332a-332t, detected where applicable by RX MIMO detector 336, and further processed by receiver processor 338 to obtain decoded data and control information transmitted by UE 104. Receiver processor 338 can provide the decoded data to data sink 314 and the decoded control information to controller / processor 340.

[0071] Memory 342 and memory 382 can store data and program code for BS 102 and UE 104, respectively.

[0072] Scheduler 344 can schedule UEs to transmit data on the downlink and / or uplink.

[0073] In various respects, BS 102 can be described as transmitting and receiving various types of data associated with the methods described herein. In these contexts, “transmitting” can refer to various mechanisms that output data, such as from data source 312, scheduler 344, memory 342, transmit processor 320, controller / processor 340, TX MIMO processor 330, transceiver 332a-332t, antenna 334a-334t, and / or other aspects described herein. Similarly, “receiving” can refer to various mechanisms that acquire data, such as from antenna 334a-334t, transceiver 332a-332t, RX MIMO detector 336, controller / processor 340, receive processor 338, scheduler 344, memory 342, and / or other aspects described herein.

[0074] In various respects, UE 104 can also be described as transmitting and receiving various types of data associated with the methods described herein. In these contexts, “transmitting” can refer to various mechanisms that output data, such as from data source 362, memory 382, ​​transmit processor 364, controller / processor 380, TX MIMO processor 366, transceiver 354a-354t, antenna 352a-352t, and / or other aspects described herein. Similarly, “receiving” can refer to various mechanisms that acquire data, such as from antenna 352a-352t, transceiver 354a-354t, RX MIMO detector 356, controller / processor 380, receive processor 358, memory 382, ​​and / or other aspects described herein.

[0075] In some respects, the processor can be configured to perform various operations (such as those associated with the methods described herein) and to send (output) data to or receive data from another interface configured to send or receive data, respectively.

[0076] In various aspects, artificial intelligence (AI) processors 318 and 370 may perform AI processing for BS 102 and / or UE 104, respectively. AI processor 318 may include AI accelerator hardware or circuitry, such as one or more neural processing units (NPUs), one or more neural network processors, one or more tensor processors, one or more deep learning processors, etc. AI processor 370 may also include AI accelerator hardware or circuitry. As an example, AI processor 370 may perform AI-based beam management, AI-based channel state feedback (CSF), AI-based antenna tuning, and / or AI-based positioning (e.g., Global Navigation Satellite System (GNSS) positioning). In some cases, AI processor 318 may use hardware-accelerated AI inference and / or AI training to process feedback (e.g., CSF) from UE 104. AI processor 318 may, for example, use hardware-accelerated AI inference associated with the CSF to decode compressed CSF from UE 104. In some cases, AI processor 318 may perform certain RAN-based functions, including, for example, network planning, network performance management, energy-efficient network operation, etc.

[0077] Figure 4A , Figure 4B , Figure 4C and Figure 4D Describes the use of wireless communication networks (such as Figure 1 All aspects of the data structure of the wireless communication network 100.

[0078] Specifically, Figure 4A Figure 400 is an example of the first subframe within a 5G (e.g., 5G NR) frame structure. Figure 4B Figure 430 illustrates an example of a DL channel within a 5G subframe. Figure 4C Figure 450 illustrates an example of the second subframe within a 5G frame structure, and Figure 4D Figure 480 illustrates an example of a UL channel within a 5G subframe.

[0079] Wireless communication systems can utilize Orthogonal Frequency Division Multiplexing (OFDM) with a cyclic prefix (CP) on both the uplink and downlink. Such systems can also support half-duplex operation using Time Division Duplex (TDD). OFDM and Single-Carrier Frequency Division Multiplexing (SC-FDM) will (e.g., as...) Figure 4B and Figure 4D The system bandwidth (as depicted in the text) is divided into multiple orthogonal subcarriers. Each subcarrier can be modulated with data. Modulation symbols can be transmitted in the frequency domain using OFDM and / or in the time domain using SC-FDM.

[0080] Wireless communication frame structures can be Frequency Division Duplex (FDD), where for a specific set of subcarriers, subframes within that set are dedicated to either DL (Deep Length) or UL (Ultra-Length). Wireless communication frame structures can also be Time Division Duplex (TDD), where for a specific set of subcarriers, subframes within that set are dedicated to both DL and UL.

[0081] exist Figure 4A and Figure 4C In this example, the wireless communication frame structure is TDD, where D stands for DL, U for UL, and X is flexibly used between DL and UL. The UE can configure the time slot format via the received Slot Format Indicator (SFI) (dynamically configured via DL Control Information (DCI) or semi-statically / statically configured via Radio Resource Control (RRC) signaling). In the depicted example, a 10ms frame is divided into 10 equal-sized 1ms subframes. Each subframe may include one or more time slots. In some examples, each time slot may include 12 or 14 symbols, depending on the Cyclic Prefix (CP) type (e.g., 12 symbols per time slot for extended CP, or 14 symbols per time slot for normal CP). Subframes may also include micro-slots, which typically have fewer symbols than the entire time slot. Other wireless communication technologies may have different frame structures and / or different channels.

[0082] In some respects, the number of time slots within a subframe (e.g., the time slot duration within a subframe) is based on a parameter set that defines the frequency-domain subcarrier spacing and symbol duration, as further described herein. In some respects, given a parameter set μ, there are 2... μ The number of time slots is 1. Therefore, parameter sets (µ) 0 through 6 allow for 1, 2, 4, 8, 16, 32, and 64 time slots per subframe, respectively. In some cases, extended CP (e.g., 12 symbols per time slot) can be used with specific parameter sets (e.g., parameter set 2, allowing 4 time slots per subframe). Subcarrier spacing and symbol length / duration are functions of the parameter sets. The subcarrier spacing can be equal to... kHz, where μ is the parameter set from 0 to 6. As an example, the parameter set... Corresponding to a subcarrier spacing of 15 kHz, and the parameter set This corresponds to a subcarrier spacing of 960 kHz. Symbol length / duration is negatively correlated with subcarrier spacing. Figure 4A , Figure 4B , Figure 4C and Figure 4D It provides a slot format with 14 symbols per slot (e.g., normal CP) and a parameter set with 4 slots per subframe. Example. In this case, the slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μs.

[0083] like Figure 4A , Figure 4B , Figure 4C and Figure 4D As depicted, the resource grid can be used to represent the frame structure. Each time slot includes a resource block (RB) (also known as a physical RB (PRB)) extending for, for example, 12 consecutive subcarriers. The resource grid is divided into multiple resource elements (REs). The number of bits carried by each RE depends on the modulation scheme, which includes, for example, quadrature phase shift keying (QPSK) or quadrature amplitude modulation (QAM).

[0084] like Figure 4A As illustrated in the example, some REs in the RE carry information for the UE (e.g., Figure 1 and Figure 3 The reference (pilot) signal (RS) for the UE (104) may include a demodulation RS (DMRS) and / or a channel state information reference signal (CSI-RS) for channel estimation at the UE. The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and / or a phase tracking RS (PT-RS).

[0085] Figure 4B Examples of various DL channels within a subframe of a frame are illustrated. The Physical Downlink Control Channel (PDCCH) carries the DCI within one or more Control Channel Elements (CCEs), each CCE comprising, for example, nine RE groups (REGs), each REG comprising, for example, four consecutive REs in an OFDM symbol.

[0086] The Primary Synchronization Signal (PSS) can be located within symbol 2 of a specific subframe of the frame. The PSS is generated by the UE (e.g., Figure 1 and Figure 3 104) is used to determine subframe / symbol timing and physical layer identifier.

[0087] The secondary synchronization signal (SSS) can be located in symbol 4 of a specific subframe of the frame. The SSS is used by the UE to determine the physical layer cell identifier group number and radio frame timing.

[0088] Based on the Physical Layer Identifier and Physical Layer Cell Identifier Group Number, the UE can determine the Physical Cell Identifier (PCI). Based on the PCI, the UE can determine the location of the aforementioned DMRS. The Physical Broadcast Channel (PBCH), carrying the Master Information Block (MIB), can be logically grouped with the PSS and SSS to form a Synchronization Signal (SS) / PBCH block. The MIB provides the System Frame Number (SFN) and the number of Restricted Frames (RBs) in the system bandwidth. The Physical Downlink Shared Channel (PDSCH) carries user data, broadcast system information (such as System Information Blocks (SIBs)) not transmitted via the PBCH, and / or paging messages.

[0089] like Figure 4C As illustrated, some REs in the REs carry DMRS for channel estimation at the base station (indicated as R for a particular configuration, but other DMRS configurations are possible). The UE can transmit DMRS for PUCCH and DMRS for PUSCH. PUSCH DMRS can be transmitted, for example, in the first or second symbol before the PUSCH. PUCCH DMRS can be transmitted in different configurations depending on whether a short or long PUCCH is being transmitted and depending on the specific PUCCH format used. UE104 can transmit a Sounding Reference Signal (SRS). SRS can be transmitted, for example, in the last symbol of a subframe. SRS can have a comb structure, and the UE can transmit SRS on one of the comb teeth. SRS can be used by the base station for channel quality estimation to enable frequency-dependent scheduling of the UL.

[0090] Figure 4D Examples of various UL channels within a subframe of a frame are illustrated. The PUCCH can be located as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), pre-decoding matrix indicators (PMI), rank indicators (RI), and HARQ ACK / NACK feedback. The PUSCH carries data and may additionally be used to carry buffer status reports (BSR), power clearance reports (PHR), and / or UCI. Example receiver architecture

[0091] Some wireless communication systems can be implemented using Orthogonal Frequency Division Multiplexing (OFDM). The basic concept of a multi-carrier system (such as OFDM) is to divide a data stream into several narrow subcarriers. An OFDM signal is essentially a bundle of narrow-band carriers (e.g., subcarriers) transmitted across the carrier bandwidth. Each of these subcarriers transmits information by modulating the phase and / or amplitude of the subcarrier over a specific symbol duration. For example, each subcarrier can use Phase Shift Keying (PSK) or Quadrature Amplitude Modulation (QAM) to transmit information.

[0092] Figure 5 This is a diagram illustrating an example receiver 502 communicating with a transmitter 504 via a communication channel 506. In this example, the transmitter 504 transmits a signal (e.g., an OFDM signal) on the communication channel 506 (e.g., a wireless communication channel between the transmitter 504 and the receiver 502). The signal is encoded to transmit information using a modulation scheme such as PSK or QAM, for example. The receiver 502 receives the signal affected by the channel 506, for example, due to various signal propagation effects, including path loss, multipath effects, fading, Doppler effects, etc.

[0093] Receiver 502 can use the receiver architecture 508 of the output decoded information 526 to decode the received signal. In this example, receiver architecture 508 processes the received signal through various RF circuitry and digital signal processing operations. In some aspects, receiver 502 may include Figure 3 The UE 104 illustrated includes a transceiver 354, antenna 352, RX MIMO processor 356, receiver processor 358, AI processor 370, and / or controller / processor 380. At block 510, the receiver can amplify the received RF signal and, for example, use one or more mixers and baseband filters to downconvert the amplified signal to recover the baseband signal. RF carrier signal to baseband signal recovery can be achieved using RF front-end or RF receiver circuitry.

[0094] At box 512, for example, an analog-to-digital converter (ADC) is used to digitally sample the baseband signal. The baseband signal is converted from an analog signal to a digital signal for demodulation.

[0095] At box 514, the cyclic prefix (CP) is removed from the symbols of the signal. The CP provides a guard period to help prevent inter-symbol interference, which may be caused by, for example, propagation channel delay spread.

[0096] At box 516, the serial symbol stream can be converted into... N A parallel symbol stream.

[0097] At box 518, a Fast Fourier Transform (FFT) can be used, for example, to... N A parallel symbol stream is transformed into the frequency domain. The FFT can include any of the various types of FFT, such as radix-2 FFT, radix-4 FFT, and mixed radix FFT.

[0098] At block 520, channel estimation is performed to determine various signal propagation effects of channel 506 associated with the subcarriers of the OFDM signal. Channel estimation can include any of various types of channel estimation, such as frequency-domain minimum mean square error (MMSE) or time-domain MMSE. As an example, the received signal may include pilot values ​​at some pilot subcarriers (e.g., DMRS) and information modulated in some data subcarriers. The pilot values ​​and their corresponding positions in the frequency domain (e.g., pilot carrier indices) are known to receiver 502, and using this information, receiver 502 can estimate the signal propagation effects of channel 506 on the pilot subcarriers. Therefore, the receiver can estimate (e.g., interpolate) the channel values ​​between the pilot subcarriers and the data subcarriers to determine an estimate of the signal propagation effects on the data subcarriers.

[0099] At box 522, channel equalization is performed using the channel estimate determined at box 520 to compensate for signal propagation effects in channel 506. Channel equalization can include any of the various types of channel equalization, such as MMSE, blind equalization, adaptive median filtering, etc. As an example, noise and / or interference determined from the channel estimate can be filtered out from the data subcarriers. In some cases, channel equalization can compensate for other effects, such as propagation delay, fading, multipath effects, Doppler effects, etc.

[0100] At box 524, for each equalized symbol stream in the equalized symbol stream, the phase and amplitude can be represented as constellation points. The constellation points of the symbol stream can form a constellation of complex values ​​representing codewords (e.g., combinations of one or more bits). The constellation points are demapped (demodulated or decoded) to transform the constellation points into codewords or decoded information 526. Because the subcarriers undergo various signal propagation effects through channel 506, the constellation points may have errors in their position (e.g., phase and / or magnitude errors). The receiver can perform any of a variety of decoding operations (such as hard-decision decoding (demodulation) or soft-decision decoding (demodulation)) to estimate the data transmitted in the constellation points.

[0101] As an example, each received constellation point can be compared with a reference constellation point (e.g., using an MMSE-based demodulator or a maximum likelihood-based demodulator). The receiver can determine the reference constellation point closest to the receiving point and can assign codewords belonging to the closest reference constellation point to the receiving point. Decoded information may include one or more codewords decoded between constellation points in the symbol stream. Information encoded at the transmitter and successfully decoded at the receiver may be referred to as mutual information, which may indicate the capacity of channel 506, such as data rate or throughput. Various types of decoding operations (e.g., specific types of FFT, channel estimation, channel equalization, and / or demodulation) can be selected based on the performance of the corresponding operation (e.g., latency, computation time, memory usage, number of computations performed, etc.). Aspects related to channel state feedback

[0102] In some wireless communication systems, closed-loop feedback associated with the communication channel can be dynamically adapted to channel conditions that change over time, such as changes in UE mobility, weather conditions, interference, or noise. In some cases, the UE may receive reference signals (e.g., synchronization signal blocks (SSB), CSI-RS, DMRS, etc.) from a network entity (or another UE) and report channel state feedback to the network entity (or another UE), where the channel state feedback is determined based on measurements of the reference signals received at the UE. In other cases, the UE may transmit reference signals (e.g., SSB, CSI-RS, DMRS, PT-RS, SRS, etc.), and the network entity (or another UE) may determine channel-related characteristics based on measurements of the received reference signals.

[0103] Figure 6 A process flow 600 is described for closed-loop feedback associated with the communication channel between network entity 602 and UE 604 in the network.

[0104] At 606, UE 604 receives reference signals (e.g., SSB, CSI-RS, etc.) from network entity 602.

[0105] At 608, UE 604 performs channel calculations based on a reference signal, such as determining a channel estimate H based on the received reference signal. For example, UE 604 may include a demodulator, which may be a transceiver of UE 604 (e.g., Figure 3 (Transceiver 354), RX MIMO detector (e.g., Figure 3 (RX MIMO detector 356) and / or receive processor (e.g., Figure 3 It is part of the receiver processor 358. The demodulator (such as components of a demodulator) can take reference signals received on multiple antennas of the UE 604 as input and output vector... This vector is a representation of the received reference signal received on each of the multiple antennas of the UE 604.

[0106] Based on the received signal model, vector This can be expressed in equation (1) as follows: (1)

[0107] In equation (1), H corresponds to the matrix representation of the communication channel, as in the channel estimation of a communication channel in which a signal is transmitted (e.g., a downlink communication channel in which a reference signal is transmitted). It is a vector representing symbols sent by network entity 602 across multiple spatial layers, and It is thermal noise across communication channels. In some respects,H It has a number of antennas equal to the number used for receiving signaling. N ant Multiply by the number of spatial layers N l The size (e.g., the number of beamformed transmitters, the number of antenna ports, etc.). For example, H has an equal to N ant The sum of the number of rows equals N l The number of columns. In some respects, the symbols forming the reference signal are known to UE 604 (e.g., configured or pre-configured at the UE). UE 604 can determine the channel estimate H based on the received reference signal.

[0108] In some respects, as part of channel calculation, UE 604 can also calculate the pre-decoder (e.g., the pre-decoder matrix) V based on the channel estimate H. For example, UE 604 can be configured to perform pre-decoding based on singular value decomposition (SVD) to determine the pre-decoder V. For example, SVD(H) = [USV], such that SVD provides the pre-decoder V. U may be related to the row ordering of H, just as H represents the antenna ordering. It should be understood that other suitable techniques can be used to determine the pre-decoder V based on the channel estimate H.

[0109] At 610, UE 604 transmits a CSI report to network entity 602 indicating the determined channel estimate H and / or pre-decoder V. For example, the UE may determine one or more CSI parameters based on H and / or V, such as a channel quality indicator (CQI), a pre-decoding matrix indicator (PMI), and / or a rank indicator (RI). RI may represent the number of MIMO layers requested by the UE for downlink transmission. PMI may define a set of indices corresponding to one or more pre-decoding matrices (e.g., pre-decoding matrix V) to be applied to downlink transmission. In some respects, PMI may indicate the preferred pre-decoding for downlink transmission on the PDSCH. CQI may be an indicator of channel quality, such as corresponding to H. UE 604 may transmit indications of one or more determined CSI parameters to network entity 602 in the CSI report. Network entity 602 may accordingly schedule downlink data transmissions to UE 604, such as using the modulation scheme, code rate, number of transmission layers, etc., determined by the network entity based on the CSI report.

[0110] At 612, UE 604 transmits reference signals (e.g., SSB, CSI-RS, DM-RS, PT-RS, SRS, etc.) to network entity 602.

[0111] At 614, network entity 602 performs channel calculations based on reference signals, such as determining channel estimation H based on received reference signals, for example, as described herein with respect to UE performing channel calculations at 608.

[0112] In some respects, as part of channel calculation, network entity 602 may also calculate the pre-decoder (e.g., the pre-decoder matrix) V based on channel estimation H, for example, as described herein with respect to UE 604 performing such calculations. Therefore, network entity 602 may determine the H and / or V of the uplink channel between UE 604 and network entity 602 based on SRS. Furthermore, as discussed, the uplink channel between UE 604 and network entity 602 may be reciprocal with the downlink channel between UE 604 and network entity 602. Therefore, the determined H and / or V values ​​for the uplink channel between UE 604 and network entity 602 can be used for the downlink channel between UE 604 and network entity 602. In some cases, the reciprocity between the uplink channel and the downlink channel may be based on a known difference between the uplink channel and the downlink channel, such that this difference can be represented by a function. Accordingly, in some respects, in order to determine the H and / or V of the downlink channel, network entity 602 may apply a function to the H and / or V determined for the uplink channel. Example of artificial intelligence for wireless communication

[0113] Some aspects and techniques described herein can be implemented, at least in part, using some form of artificial intelligence (AI) inference, such as the process of inferring or predicting output data from input data using machine learning (ML) models. Example ML models may include mathematical representations of one or more relationships between various objects to provide outputs representing one or more decisions or inferences. Once an ML model has been trained, it can be deployed to process data that is wholly or partially similar to or related to the training data and to provide outputs representing one or more decisions or inferences based on the input data. Some example types of ML models and techniques include artificial neural networks (ANNs), regression analysis (such as statistical models), decision tree learning (such as predictive models), support vector machines (SVMs), large language models (LLMs), generative models, deep learning augmentation models, probabilistic graphical models (such as Bayesian networks), and more.

[0114] ML models can be deployed in one or more devices (e.g., base stations and / or user equipment) to support various wired and / or wireless communication aspects of a communication system. For example, ML models can be trained to identify patterns / relationships in data corresponding to networks, devices, or air interfaces. ML models can support operational decisions related to one or more aspects, such as channel state determination, device location, transceiver tuning, beamforming, signal decoding / decoding, network routing, energy saving, etc., which are associated with communication equipment (e.g., UEs and / or network entities), services (e.g., as Ultra-Reliable Low Latency (URLLC), mobile broadband, and / or Internet of Things (IoT) communications), or networks.

[0115] This paper illustrates, through examples, how one or more tasks / problems can benefit from the application of ANNs as a type of ML model. However, it should be understood that other types of ML models can be used in addition to or in place of ANNs. Therefore, unless explicitly stated otherwise, the topic of ML models is not necessarily intended to be limited to ANN solutions. Furthermore, it should be understood that, unless otherwise specified, terms such as “AI model,” “ML model,” “AI / ML model,” or “trained ML model” are intended to be used interchangeably.

[0116] Figure 7 This is a diagram illustrating an example AI architecture 700 that can be used for AI-enhanced wireless communication. As illustrated, architecture 700 includes multiple logical entities, such as a model training host 702, a model inference host 704, a data source 706, and an actor 708. The AI ​​architecture can be used in any of a variety of use cases for wireless communication, such as channel state feedback, beam management, transceiver tuning, power saving, load balancing, mobility management, and / or coverage optimization. As further described herein, the AI ​​architecture can predict the response of the UE receiver to facilitate reduced or zero-overhead high-rate tracking of the communication link between the UE and network entities.

[0117] The model inference host 704 in architecture 700 is configured to run an ML model based on inference data 712 provided by data source 706. The model inference host 704 may produce an output 714 (e.g., a prediction) based on the inference data 712 and then provide it as input to the participant 708.

[0118] Participant 708 can be a component or entity of a wireless communication system, including, for example, a radio access network (RAN), a wireless local area network, a device-to-device (D2D) communication system, etc. As an example, participant 708 can be user equipment (e.g., Figure 1 UE 104 in the base station (e.g., Figure 1The BS 102 or any of its decomposed network entities, including centralized units (CUs), distributed units (DUs) and / or radio units (RUs), access points, radio stations, RAN intelligent controllers (RICs) in cloud-based RANs, and so on. Additionally, the type of participant 708 may also depend on the type of task performed by the model inference host 704, the type of inference data 712 provided to the model inference host 704, and / or the type of output 714 generated by the model inference host 704.

[0119] For example, if the output 714 from the model inference host 704 is associated with beam management, then participant 708 may be or include a UE, DU, or RU. As another example, if the output 714 from the model inference host 704 is associated with transmit and / or receive scheduling, then participant 708 may be a CU or DU.

[0120] After participant 708 receives output 714 from model inference host 704, participant 708 may determine whether to take action based on the output. For example, if participant 708 is a DU or RU, and the output from model inference host 704 is associated with link adaptation as further described herein, participant 708 may determine whether to change / modify certain link adaptation parameters based on output 714. If participant 708 determines to take action based on output 714, participant 708 may indicate the action to at least one action subject 710. For example, if participant 708 determines to change / modify the number of MIMO layers used for communication between participant 708 and action subject 710 (e.g., UE), participant 708 may transmit an indication to action subject 710 (e.g., UE) to change / modify the number of MIMO layers.

[0121] Data source 706 can be configured to collect data that can be used as training data 716 for training an ML model or as inference data 712 for feeding ML model inference operations. Specifically, data source 706 can collect data from any of various entities that may include action subject 710 (e.g., UE and / or BS) and provide the collected data to model training host 702 for ML model training. For example, after action subject 710 (e.g., UE) receives updated link adaptation parameters from participant 708, action subject 710 can provide performance feedback associated with the link adaptation parameters to data source 706, whereby model training host 702 can use this performance feedback to monitor and / or evaluate ML model performance, such as whether the output 714 provided to participant 708 is accurate. In some examples, if the output 714 provided to participant 708 is inaccurate (or its accuracy is below an accuracy threshold), model training host 702 can determine, for example, to modify or retrain the ML model used by model inference host 704 via ML model deployment / update.

[0122] In some respects, the model training host 702 may be deployed at or on the same or different entity where the model inference host 704 is deployed. For example, to offload model training processing that may affect the performance of the model inference host 704, the model training host 702 may be deployed at a model server.

[0123] In some respects, ML models are deployed on network entities (e.g., such as...) Figure 1 The model infers the host (such as BS 102) or the network entity for communication channel adaptation. More specifically, the model infers the host (such as...) Figure 7 The model inference host (704) can be deployed at or on a network entity to simulate the response of a UE receiver, as further described herein. Aspects related to the digital representation of user equipment receivers used for communication channel adaptation

[0124] Various aspects of this disclosure provide techniques for estimating the response of a UE receiver using a digital representation of the UE receiver for link adaptation. In some cases, the digital representation of the UE receiver may include an ML model that simulates or predicts the response of the UE receiver, for example, as described herein. Figure 8 and Figure 9 To be further described, network entities can obtain indications of the ML model based on one or more characteristics associated with the ML model.

[0125] In some respects, these features can facilitate, for example, retrieving ML models from a model repository that stores multiple ML models (e.g., via model training host 702). In some cases, the features may include an identifier that identifies the ML model, and this identifier may allow network entities to access the ML model associated with the identifier from a model repository (such as model training host 702). In some cases, network entities may request and / or obtain ML models from the UE via the identifier.

[0126] In some respects, features can facilitate the reproducibility of ML models through training and / or configuration. Features may include training data used to train the ML model, such as those described in this paper. Figure 7 As described. Attributes may include coefficients and / or weights used to configure the ML model (e.g., an ANN). Attributes may include indications of the architecture or structure of the ML model, such as the connections of artificial neurons in the ANN and / or the number of layers of artificial neurons used in the ANN. In some cases, attributes may include performance indicators or metrics associated with the ML model, such as the expected or specified accuracy and / or latency of the ML model.

[0127] In some respects, network entities can obtain information that explicitly describes the architecture of the UE receiver, for example, as described in this article regarding Figure 10 Further described. This information may indicate the number of receive antennas employed at the UE. This information may identify the specific decoding operation employed at the UE, such as the channel estimation type and / or demodulator type, as described herein. Figure 10 Further described. In some cases, network entities can use this information to train, select, or configure ML models to predict the response of the UE receiver. For example, based on this information, a network entity can select an ML model that is trained to simulate a receiver architecture corresponding to a UE receiver as indicated by the information. In some cases, network entities can use this information to replicate decoding operations in simulations that estimate the response of the UE receiver. In some cases, network entities can perform other modeling techniques to estimate the performance of the UE receiver without ML. For example, in a simulation (without ML), a network entity can perform specific decoding operations (e.g., specific channel estimation and / or demodulation) as indicated by the information. Example Machine Learning UE Receiver Response Prediction

[0128] Figure 8 This is a diagram illustrating an example of UE receiver response prediction 800 performed by network entity 804. In this example, network entity 804 may communicate with the UE via a communication channel (not shown), for example, as described herein. Figures 1 to 3 and Figure 6As described. The ML model 810 is deployed at or on network entity 804 so that network entity 804 can estimate the UE receiver (e.g., based on the data input to the ML model 810) Figure 5 The response of the receiver 502). In some cases, the ML model 810 may be deployed at or on any decomposed entity associated with a network entity, including, for example, CU, DU, RU, non-RT RIC, near-RT RIC, etc.

[0129] In some respects, the ML model 810 can be trained to simulate or predict the response of a UE receiver based on certain inputs, as further described herein. In some cases, the ML model 810 may include an ANN (e.g., as described herein regarding...). Figure 9 Further descriptions include regression analysis, decision tree learning, SVM, generative models, deep learning augmentation models, etc. The ML model 810 can be an example of a digital representation of one or more operations of a UE receiver 814 (e.g., a virtual receiver of the UE), such as those described herein. Figure 5 As described, the ML model 810 can be trained to predict the response at the UE receiver 814 to certain operations used for decoding the received signal, such as specific operations for FFT, channel estimation, channel equalization, and / or demodulation.

[0130] In some respects, network entity 804 may access multiple ML models 840, and network entity 804 may select ML model 810 from ML models 840. ML model 810 may be selected based on the UE receiver being evaluated for link adaptation. In some cases, network entity 804 may select ML model 810 based on characteristics of the ML model obtained from the UE as described herein (such as model identifier, model parameters, layers, structure, neural connections, etc.). In some cases, network entity 804 may select ML model 810 based on indications of the receiver architecture used at the UE receiver, for example, as described herein regarding... Figure 10 Further description. For example, network entity 804 may be selected to be trained ML model 810 to predict the response of the receiver architecture indicated by the UE.

[0131] In some cases, ML model 840 may include a collection of ML models trained to predict the responses of different UE receivers, such as different combinations of specific types of FFT, channel estimation, channel equalization, and / or demodulation. For example, one ML model may be trained to predict the response of a UE receiver using an MMSE-based demodulator, and another ML model may be trained to predict the response of a UE receiver using a maximum likelihood-based demodulator. In some cases, ML model 810 may be trained to predict the responses of multiple types of UE receivers, and ML model 810 may output multiple predictions for such UE receiver types.

[0132] In some cases, ML model 840 may predict the UE receiver's response at different levels of accuracy (e.g., 70%, 80%, or 99% accuracy), different latency (e.g., processing time for predicting the UE's response), and / or different throughput (e.g., the ability to concurrently predict multiple responses from the UE or multiple UEs). Network entity 804 may select ML model 810 capable of predicting the UE receiver's response based on certain performance specifications (such as a certain latency and / or accuracy). The performance specifications of ML model 810 may depend on the quality of service associated with the services and / or traffic (such as URLLC, mobile broadband, and / or IoT communications) communicated between the UE and network entity 804.

[0133] In some respects, network entity 804 provides input 812 to ML model 810. Input 812 may include, for example, signals 816 and / or channel characteristics 818 associated with a communication channel between network entity 804 and the UE. Signal 816 may include signals received from the UE (e.g., SRS) and / or signals virtually received at the UE, which may be simulated based on channel characteristics 818. Network entity 804 may determine characteristics 818 associated with the communication channel between network entity 804 and the UE based on measurements of signals received from the UE (e.g., SRS), for example, as described herein. Figure 6 As described.

[0134] In some respects, input 812 may also include PMI 820, MCS 822, and / or RI 824 for simulating the response of the UE receiver. PMI 820, MCS 822, and / or RI 824 may be parameters for simulating the radio channel conditions (communication conditions) between network entity 804 and the UE. In some cases, input 812 may include different settings for PMI 820, MCS 822, and / or RI 824, such as different combinations of PMI 820, MCS 822, and / or RI 824. Different settings allow ML model 810 to simulate various responses of the UE receiver under a range of communication conditions, such as different beamforming, MCS, and / or MIMO layers. For example, different settings for PMI can simulate different transmit beamforming settings used at network entity 804, including, for example, angle of arrival (AoA), angle of departure (AoD), gain, phase, directivity, beamwidth, beam orientation in azimuth and / or elevation (relative to the reference plane), peak sidelobe ratio, and / or antenna port associated with the antenna (radiating) mode. Different settings for MCS can effectively simulate different throughput or data transfer rates for virtual transmissions from network entity 804. Different RI settings can simulate different numbers of MIMO layers for virtual transmissions from network entity 804.

[0135] The ML model 810 outputs, for example, one or more predictions of the UE receiver's response under various communication conditions. More specifically, network entity 804 obtains output 826 from the ML model 810, which may include a decodeable indicator 828 and / or an indication of mutual information 830 (e.g., channel capacity) for decoding using the UE receiver's digital representation. The decodeable indicator 828 may include an indication of whether the Cyclic Redundancy Check (CRC) at the UE receiver passes or fails under a specific communication condition (e.g., channel characteristics, PMI, MCS, and / or RI settings). In some cases, the decodeable indicator 828 may include an indication of whether a virtually received signal has been successfully decoded. For example, the ML model 810 may simulate the UE receiver decoding received signals under various communication conditions, such as those described herein. Figure 5 As described, the decodeable indicator 828 can indicate whether the received signal has been successfully decoded. Mutual information 830 can indicate the channel capacity of the communication channel between network entity 804 and the UE, for example, as described herein. Figure 5 As described.

[0136] Network entity 804 can use output 826 to determine certain link adaptation parameters (e.g., MCS, PMI, and / or RI) for the communication channel between network entity 804 and UE.

[0137] Network entity 804 may select link adaptation parameters that achieve the maximum throughput predicted by the output 826 of ML model 810 (e.g., mutual information 830). For example, ML model 810 may output first mutual information based on a first set of channel characteristics, PMI, MCS, and / or RI settings; ML model 810 may output second mutual information based on a second set of channel characteristics, PMI, MCS, and / or RI settings, wherein the second mutual information may be greater than the first mutual information. In such cases, network entity 804 may select PMI, MCS, and / or RI settings from the second set as link adaptation parameters for the communication channel. Network entity 804 may determine actions for the UE based on the predicted response of the UE receiver, as described herein. Figure 7 As described, using the ML model 810 for UE receiver response prediction can reduce signaling overhead associated with CSF reports, increase tracking rates for link adaptation, increase throughput, reduce latency, and improve spectrum efficiency.

[0138] Figure 9 This is an illustrative diagram of an example artificial neural network (ANN) 900, which can be trained to predict the response of a UE receiver, for example, as described herein. Figure 8 As described.

[0139] ANN 900 can receive input data 906, which may include one or more bits of data 902, preprocessed data (optionally) output from preprocessor 904, or some combination thereof. Here, data 902 may include training data, validation data, application-related data, etc., for example, depending on the development and / or deployment phase of ANN 900. In some other implementations, preprocessor 904 may be included within ANN 900. Preprocessor 904 may, for example, process all or part of data 902, which may result in some data in data 902 being changed, replaced, deleted, etc. In some implementations, preprocessor 904 may add additional data to data 902.

[0140] ANN 900 includes at least one first layer 908 of artificial neurons 910 to process input data 906 and provide the resulting first layer data to at least a portion of at least one second layer 914 via edge 912. The second layer 914 processes the data received via edge 912 and provides second layer output data to at least a portion of at least one third layer 918 via edge 916. The third layer 918 processes the data received via edge 916 and provides third layer output data to at least a portion of a final layer 922 comprising one or more neurons via edge 920 to provide output data 924. All or part of the output data 924 may be further processed in some way by (optionally) a post-processor 926. Thus, in some examples, ANN 900 may provide output data 928 based on output data 924, post-processed data output from post-processor 926, or some combination thereof. In some other embodiments, post-processor 926 may be included within ANN 900. Post-processor 926 may process all or part of the output data 924, which may result in output data 928 being at least partially different from output data 924, for example, due to data being altered, replaced, deleted, etc. In some implementations, post-processor 926 may be configured to add additional data to output data 924. In this example, the second layer 914 and the third layer 918 represent intermediate or hidden layers that may be arranged in a hierarchical or other similar structure. Although not explicitly shown, one or more additional intermediate layers may exist between the second layer 914 and the third layer 918.

[0141] The structure and training of the artificial neurons 910 in each layer can be customized to meet the specific requirements of the application. Within a given layer of an ANN, some or all of the neurons can be configured to process the information provided to that layer and output corresponding transformed information from that layer. For example, the transformed information from a layer can represent a weighted sum of input information associated with a nonlinear activation function or another activation function used to “activate” the artificial neurons in the next layer, or otherwise based on that nonlinear activation function or the other activation function used to “activate” the artificial neurons in the next layer. Artificial neurons in such layers can be activated by or in response to weights and biases that can be adjusted during the training process. The weights of various artificial neurons can act as parameters controlling the connection strength between layers or between artificial neurons, while the biases can act as parameters controlling the connection direction between layers or between artificial neurons. Activation functions can select or determine whether an artificial neuron sends its output to the next layer in response to the data received by the artificial neuron. Different activation functions can be used to model different types of nonlinear relationships. By introducing nonlinearity into the ML model, activation functions allow the ML model to “learn” complex patterns and relationships in the input data 906. Some non-exhaustive examples of activation functions include sigmoid-based activation functions, tanh-based activation functions, convolutional activation functions, upsampling, pooling, and rectified linear unit (ReLU)-based activation functions.

[0142] Design tools (such as computer applications, programs, etc.) can be used to select the appropriate structure and number of layers for the ANN 900, as well as the number of artificial neurons in each layer, and to select activation functions, loss functions, training procedures, etc. Once the initial model is designed, it can be trained using training data. Training data may include one or more datasets within which the ANN 900 can detect, determine, identify, or discover patterns. Training data can represent various types of information, including written, visual, audio, environmental context, operational attributes, etc. During training, the parameters of the artificial neurons 910 can be changed, such as minimizing or otherwise reducing the loss function or cost function. The training process can be repeated multiple times to fine-tune the ANN 900 with each iteration.

[0143] Various ANN model architectures are available for consideration. For example, in a feedforward ANN architecture, each artificial neuron 910 in a layer receives information from the previous layer and similarly generates information for the next layer. In a convolutional ANN architecture, some layers can be organized as filters that extract features from data (e.g., training data and / or input data). In a recursive ANN architecture, some layers may have connections that allow data to be processed across time, such as for processing information with temporal structure (e.g., time series data prediction). In an autoencoder ANN architecture, compact representations of data can be processed, and the model is trained to make predictions from a reduced set of features or potentially reconstruct the original data. Autoencoder ANN architectures can be used for tasks related to dimensionality reduction and data compression. Generative adversarial ANN architectures may include generator ANNs and discriminator ANNs trained to compete with each other. Generative adversarial networks (GANs) are ANN architectures that can be used for tasks related to generating synthetic data or improving the performance of other models. Transformer ANN architectures utilize attention mechanisms, which enable the model to process input sequences in a parallel and efficient manner. Attention mechanisms allow a model to focus on different parts of an input sequence at different times. Attention mechanisms can be implemented using a series of layers called attention layers to compute, operate on, determine, or select a weighted sum of input features based on the similarity between different elements of the input sequence. Transformer ANN structures can include a series of feedforward ANN layers that “learn” a non-linear relationship between the input and output sequences. The output of a transformer ANN structure can be obtained by applying a linear transformation to the output of the final attention layer. Transformer ANN structures are particularly useful for tasks involving sequence modeling or other similar processing. Another example type of ANN structure is a model with one or more invertible layers. This type of model can be inverted or “unfolded” to reveal the input data used to generate the output of the layers. Other example types of ANN model structures include fully connected neural networks (FCNNs) and long short-term memory (LSTM) networks.

[0144] ANN 900 or other ML models can be implemented in various types of processing circuits, along with their memory and applicable instructions. For example, models can be implemented using general-purpose hardware circuits such as one or more central processing units (CPUs) and one or more graphics processing units (GPUs). They can also be implemented using one or more tensor processing units (TPUs), embedded neural processing units (eNPUs), or other similar dedicated processors, and / or field-programmable gate arrays (FPGAs), or application-specific integrated circuits (ASICs). Various programming tools are available for developing ANN models. For example, some open-source tools include TensorFlow, provided by Google. ® PyTorch provided by Facebook ® and by Apache® MXNet provided by the Software Foundation (ASF) ™ Additionally, a variety of other tools may or may not be considered open-source tools.

[0145] There are various model training techniques and processes that can be used at some point before or after deploying an ML model (such as ANN 900).

[0146] As part of the model development process, information may be collected or otherwise created in a suitable training data format for training the ML model accordingly. For example, training data may be collected or otherwise created relating to data on received / transmitted signal strength, interference, and resource usage, as well as any other relevant data that can be used to train the model to solve one or more problems or challenges in a communication system. In some cases, all or part of the training data may originate from one or more user equipment (UEs), one or more network entities, or one or more other devices in a wireless communication system. In some cases, all or part of the training data may be aggregated from multiple sources, such as one or more UEs, one or more network entities, the Internet, etc. For example, wireless network architectures (such as self-organizing networks (SONs) or mobile-driven test (MDT) networks) may be adapted to support data collection for ML model applications. In another example, training data may be generated or collected online, offline, or both online and offline by UEs, network entities, or other devices, and all or part of such training data may be transmitted or shared (real-time or near real-time), such as through store-and-forward functions. Offline training may refer to, for example, creating and using a static training dataset in a batch manner, while online training may refer to collecting and using training data in real-time or near real-time. For example, online or offline training can be used to train and / or fine-tune the ML model at a wireless communication device (e.g., a UE). For offline training, data collection and training can occur offline at the network side (e.g., at a base station or other network entity) or at the UE side. Regarding ML models deployed at or on a network entity (e.g., as discussed herein), Figure 8 As described, offline training can occur at a separate computing device, such as an edge computing device, core network, and / or RAN controller (e.g., near-RT RIC and / or non-RT RIC). For online training, training of the ML model can be performed locally at the UE or on a separate computing device (e.g., a server hosted by the UE vendor and / or network operator) in real-time or near real-time, based on data provided from the UE to the server device. Regarding ML models deployed at or on a network entity (e.g., as described herein...), Figure 8As described, online training can occur locally at network entities or at individual computing devices, such as edge computing devices, core networks, and / or RAN controllers (e.g., near-RT RIC and / or non-RT RIC).

[0147] In some cases, all or part of the training data may be shared within the wireless communication system, or even shared (or obtained from outside) the wireless communication system.

[0148] Once the ML model has been "trained" with the training data, its performance can be evaluated. In some scenarios, evaluation / validation tests can use a validation dataset, which may include data not in the training data, to compare the model's performance against a baseline or other benchmark information. If the model's performance is considered unsatisfactory, it may be beneficial to fine-tune the model, for example, by changing its architecture, retraining it on the data, or using different optimization techniques. Once the model's performance is deemed satisfactory, it can be deployed accordingly. In some cases, the model can be updated in some way, for example, all or part of the model can be changed or replaced, or it can undergo further training, to name just a few examples.

[0149] As part of the training process for an ANN, parameters affecting the operation of artificial neurons and layers can be tuned. For example, backpropagation can be used to train an ANN by iteratively adjusting the weights or biases of certain artificial neurons associated with the error between the model's predicted output and the expected output, which may be known or otherwise considered acceptable. Backpropagation may include forward propagation, loss function, backward propagation, and parameter updates that can be performed during training iterations. This process can be repeated a certain number of times for each training dataset until the weights of the artificial neurons / layers are properly tuned. Backpropagation, associated with the loss function, measures how well the model can predict the expected output for a given input. Optimization algorithms can be used during the training process to tune the weights / biases to reduce or minimize the loss function, which will improve the model's performance. Various optimization algorithms exist that can be used with backpropagation or other training techniques. Some initial examples include gradient descent-based optimization algorithms and stochastic gradient descent-based optimization algorithms. Stochastic gradient descent can be used to tune the weights / biases to minimize or otherwise reduce the loss function. Mini-batch gradient descent, a variant of gradient descent, may involve updating the weights / biases using mini-batch training data instead of the entire dataset. Momentum techniques can accelerate the optimization process by adding momentum terms to update or otherwise influence certain weights / biases. Adaptive learning rate techniques adjust the learning rate of an optimization algorithm associated with one or more characteristics of the training data. Batch normalization techniques can be used to normalize the input to a model to stabilize the training process and potentially improve the model's performance. "Dropout" techniques can be used to randomly drop some artificial neurons from the model during training, for example, to reduce overfitting and potentially improve the model's generalization. "Early stopping" techniques can be used to stop an ongoing training process early, such as when the performance of a model using a validation dataset begins to degrade. Another example technique includes data augmentation to generate additional training data by applying transformations to all or part of the training information. Transfer learning techniques can be used, which involve using a pre-trained model as a starting point for training a new model; this can be useful when training data is limited or when there are multiple tasks that are related to each other. Multi-task learning techniques can be used, which involve training a model to perform multiple tasks simultaneously to potentially improve the model's performance on one or more of these tasks. In some cases, hyperparameters can be input and applied during the training process.

[0150] Another example technique that can be useful for ML models is some form of "pruning" technique. Pruning techniques, which can be performed during the training process or after the model has been trained, involve removing unnecessary, less necessary, or potentially redundant features from the model. In some cases, pruning techniques can reduce the complexity of the model or improve its efficiency without compromising its expected performance. Pruning techniques can be particularly useful in the context of wireless communication, where available resources, such as power and bandwidth, may be limited. Some example pruning techniques include weight pruning, neuron pruning, layer pruning, structural pruning, and dynamic pruning. Pruning techniques can, for example, reduce the amount of data corresponding to the model that may need to be sent or stored. Weight pruning may involve removing some weights from the model. Neuron pruning may involve removing some neurons from the model. Layer pruning may involve removing some layers from the model. Structural pruning may involve removing some connections between neurons in the model. Dynamic pruning may involve adapting a pruning strategy for the model to one or more characteristics of the data or environment. For example, in some wireless communication devices, dynamic pruning techniques can more aggressively prune models used in low-power or low-bandwidth environments and less aggressively prune models used in high-power or high-bandwidth environments. In some example implementations, pruning techniques can also be applied to training data, for example, to remove outliers. In some implementations, preprocessing techniques on all or part of the training dataset can improve model performance or facilitate faster model convergence. For example, training data can be preprocessed to alter or remove unnecessary, irrelevant, incorrect, or otherwise identifiable data. Such preprocessing of training data can, for example, reduce potential overfitting or otherwise improve the performance of the trained model.

[0151] One or more of the example training techniques presented above can be used as part of the training process. Some example training processes that can be used to train ML models include supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning techniques. Supervised learning involves training the model on a labeled training dataset, where the input data is accompanied by correct or otherwise acceptable outputs. Unsupervised learning involves training the model on an unlabeled training dataset, so that the model will need to learn to identify patterns and relationships in the data without explicit guidance from the labeled training dataset. Semi-supervised learning is used, for example, when the amount of labeled data is somewhat limited, using some combination of supervised and unsupervised learning processes to train the model. Reinforcement learning allows the model to learn from interactions with its operation / environment, such as learning in the form of feedback similar to rewards or punishments. Reinforcement learning can be particularly beneficial when used to improve or attempt to optimize the behavior of models deployed in dynamically changing environments, such as wireless communication networks.

[0152] Distributed or shared learning, such as federated learning, enables training on data distributed across multiple devices or organizations without the need for centralized data or training. Federated learning can be particularly useful in data-sensitive or privacy-constrained situations, or when centralized data is impractical, inefficient, or expensive. For example, in the context of wireless communications, federated learning can be used to improve performance by allowing ML models to be trained on data collected from a wide range of devices and environments. For instance, ML models can be trained on data collected from a large number of wireless devices in a network, such as distributed wireless communication nodes, smartphones, or Internet of Things (IoT) devices, to improve network performance and efficiency. With federated learning, a user equipment (UE) or other device can receive a full or partial copy of the model and perform local training on such a copy of the model using locally available training data. Such a device can then provide updated information about the locally trained model (e.g., coefficients, weights, number of layers, kernel size or dimension, zero-padding, linear operations, etc.) to one or more other devices (such as network entities or servers), where updates from other similar devices (such as other UEs) can be aggregated and used to provide updates to shared models, etc. The federated learning process can be iteratively repeated until all or part of the model achieves a satisfactory performance level. Federated learning enables devices to protect the privacy and security of local data while supporting collaboration on training and updating all or part of a shared model.

[0153] In some implementations, one or more devices or services may support processes related to the use, maintenance, activation, or reporting of ML models. In some cases, all or part of a dataset or model may be shared across multiple devices, for example, to provide or otherwise enhance or improve processing. In some examples, signaling mechanisms may be used at various nodes in a wireless network to signal capabilities for performing specific functions related to the ML model, support for a particular ML model, capabilities for collecting, creating, and transmitting training data, or other ML-related capabilities. ML models in wireless communication systems may, for example, support decisions related to wireless resource allocation or selection, wireless channel condition estimation, interference mitigation, beam management, positioning accuracy, energy saving, or modulation or decoding schemes. In some implementations, model deployment may be conducted jointly or individually at various network levels, such as CU, DU, RU, non-RT RIC, RT-RIC, SMO, or core network. Example receiver architecture mapping

[0154] In some respects, network entities can obtain indications of a UE receiver via a receiver architecture map that identifies one or more signal decoding operations and / or the number of receive antennas used at the UE receiver. As an example, a receiver architecture index may correspond to one or more decoding operations of the UE receiver, such as those described herein. Figure 5 The described operations. In some cases, network entities may use indications of the receiver architecture to train, configure, or select an ML model, which is trained to predict the response of the indicated receiver architecture. In some cases, during simulations (such as when no ML model is available), network entities may perform decoding operations associated with the indicated receiver architecture to estimate the response of the UE receiver.

[0155] Figure 10 This is a diagram illustrating an example mapping scheme 1000 that maps receiver architecture to various types of signal decoding operations used at the UE receiver. In this example, mapping scheme 1000 defines multiple receiver architecture indices 1002a, 1002b, and 1002c (collectively referred to as receiver architecture indices 1002). Each receiver architecture index in receiver architecture indices 1002 corresponds to one or more decoding operations (e.g., 1004 to 1010) and / or the number 1012 of receive antennas employed at the UE receiver. As an example, the first receiver architecture index 1002a maps to FFT type 1004 (e.g., radix-2, radix-4, or radix-8 FFT architecture), channel estimation type 1006 (e.g., frequency domain MMSE, time domain MMSE, etc.), channel equalization type 1008 (e.g., MMSE, blind equalization, adaptive median filtering, etc.), and / or demodulation type 1010 (e.g., MMSE, maximum likelihood, etc.). Note that, except for... Figure 10 In addition to or in lieu of the decoding operation types described herein, other decoding operations may be associated with the receiver architecture index. In some aspects, the UE may transmit an indication of the UE receiver used at the UE to a network entity via mapping scheme 1000. For example, the UE may transmit an indication to the network entity of a first receiver architecture index 1002a corresponding to the receiver architecture implemented at the UE. Example operations of entities in a communication network

[0156] Figure 11 A process flow 1100 for communication between network entity 1102 and UE 1104 in a network is described. In some aspects, network entity 1102 can be about Figure 1 and Figure 3 The BS 102 depicted and described or related to Figure 2 Examples of decomposed base stations depicted and described. Similarly, UE 1104 could be about... Figure 1 and Figure 3 The example of UE 104 depicted and described herein. However, in other respects, UE 1104 may be another type of wireless communication device, and network entity 1102 may be another type of network entity or network node, such as those network entities or network nodes described herein.

[0157] At 1106, network entity 1102 obtains an indication of the UE receiver used at UE 1104. In some cases, network entity 1102 may obtain capability information including an indication of the UE receiver. The indication of the UE receiver may include an indication of the ML model trained to predict the response of the UE receiver, for example, as described herein. Figure 8 and Figure 9 As described herein. In some cases, the indication of the UE receiver may include an indication of the receiver architecture associated with the UE receiver used at UE 1104, for example, as described herein regarding Figure 10 As described, the indication of the ML model may include parameters associated with the ANN, such as weights, coefficients, neuron connections, and / or the number of layers in the ANN. In some respects, network entity 1102 may obtain indication to the UE receiver when UE 1104 is in idle or inactive mode.

[0158] At 1108, UE 1104 establishes an RRC connection with network entity 1102. For example, an RRC establishment procedure can be performed to establish an RRC connection. In the RRC connection state, UE 1104 can communicate with network entity 1102 via a data radio bearer, for example, to transfer application data between UE 1104 and network entity 1102.

[0159] At 1110, network entity 1102 may transmit a CSF configuration to UE 1104 indicating when to report CSFs to network entity 1102. The CSF configuration may facilitate a reduction in signaling overhead for CSF reporting. The CSF configuration may reduce the rate at which CSFs are communicated to network entity 1102. For example, the CSF configuration may increase the periodicity of CSF reporting or indicate that only non-periodic CSFs are reported to network entity 1102. In some cases, the CSF configuration may disable the reporting of periodic or semi-persistent CSFs. In some cases, the CSF configuration may enable the reporting of non-periodic CSFs based on certain non-periodic triggers (such as DCI triggers). The CSF configuration may be transmitted in response to obtaining UE capability information indicating support for digital representations of the UE receiver at 1106.

[0160] At 1112, network entity 1102 obtains a reference signal (e.g., SRS) from UE 1104, for example, as described herein. Figure 5As described, the reference signal may be obtained on a periodic basis (e.g., a periodic or semi-persistent reference signal) and / or on an aperiodic basis (e.g., triggered by control signaling or another event). Network entity 1102 determines the channel characteristics of the communication channel between network entity 1102 and UE 1104 based on measurements of signals received from UE 1104. The channel characteristics of the communication channel allow network entity 1102 to estimate the impact of the channel on signals transmitted from network entity 1102 and received at UE 1104.

[0161] At 1114, network entity 1102 determines parameters (e.g., MCS, PMI, and / or RI) for one or more communication channels between UE 1104 and network entity 1102 based on simulations of the UE receiver's performance. In some cases, network entity 1102 uses an ML model trained to predict the UE receiver's response to estimate the UE receiver's response, for example, as described herein. Figure 8 As described. Network entity 1102 may configure, select, and / or train an ML model based on parameters or characteristics associated with the ML model obtained at 1106. In some cases, under simulation, network entity 1102 performs various decoding operations (e.g., specific types of channel estimation, channel equalization, demodulation, etc.) used at the UE receiver, as indicated by the receiver architecture obtained at 1106.

[0162] At 1116, network entity 1102 transmits parameters for the communication channel to UE 1104. For example, parameters may include MCS, beamforming, and / or the number of MIMO layers to be used on the communication channel. It should be noted that these parameters are examples, and other link adaptation parameters may be used as alternatives to or supplements to these parameters described herein. For example, parameters may include code rate (e.g., the proportion of non-redundant data streams), the number of aggregated carriers, channel bandwidth, subcarrier spacing, frequency range (e.g., FR1 or FR2 under 5G NR), etc.

[0163] At 1118, UE 1104 communicates with network entity 1102 via adaptive communication. For example, the operations at 1112, 1114, and 1116 can be repeated to adapt to the time-varying channel conditions between UE 1104 and network entity 1102. It should be understood that the simulated response of the UE receiver as described herein can facilitate a reduction in CSF overhead (improving spectral, temporal, and spatial efficiency) and / or a higher tracking rate for link adaptation. Example operations of network entities

[0164] Figure 12 It shows a device (such as) Figure 1 and Figure 3BS 102 or about Figure 2 The method 1200 for wireless communication using the decomposed base station under discussion.

[0165] Method 1200 begins at box 1205: Obtain the UE receiver from the UE (e.g., Figure 5 One or more parameters of the receiver 502. These parameters may include those as described herein. Figure 8 The described ML model refers to one or more characteristics associated with it. For example, these parameters may include coefficients and / or weights used in an ANN, indications of the architecture or structure of the ML model (e.g., connections for artificial neurons and / or the number of layers for artificial neurons), training data used to train the ML model, and / or identifiers used for the ML model. In some cases, these parameters may include indications of the architecture of the UE receiver, for example, as described herein. Figure 10 As described. As an example, these parameters may include a receiver architecture index that maps to one or more decoding operations and / or the number of receive antennas used at the UE receiver.

[0166] Method 1200 then proceeds to box 1210: determining one or more channel characteristics of the communication channel between the device and the UE based on measurements of signals received from the UE, for example, as described herein. Figure 6 As described. As an example, a network entity may receive SRS from a UE, and the network entity may determine the channel characteristics of the communication channel based on the SRS measurement.

[0167] Method 1200 then proceeds to box 1215: estimating the response of the UE receiver to communicate on a communication channel having one or more channel characteristics based on the digital representation of the UE receiver, wherein the digital representation of the UE receiver is based on one or more parameters of the UE receiver, such as those referenced herein. Figure 8 As described. The estimated response may include, for example, an indicator 828 that can be decoded and / or a pair of... Figure 8 The mutual information 830 is an indication. As an example, the network entity may obtain from the ML model a prediction (e.g., an indicator 828 indicating that the received signal can be decoded at the UE receiver under channel conditions such as those represented by one or more channel characteristics and using a certain combination of PMI, RI and / or MCS for communication between the network entity and the UE).

[0168] Method 1200 then proceeds to block 1220: determining at least one parameter for communicating with the UE on the communication channel based on the estimated response, for example, as described herein. Figure 8 As described. At least one parameter may include link adaptation parameters such as PMI, RI, and / or MCS.

[0169] Method 1200 then proceeds to box 1225: transmitting to the UE an indication of at least one parameter, for example, as described herein. Figure 11 As described. In some respects, network entities may transmit at least one parameter via control signaling such as RRC signaling, MAC signaling, DCI, sidelink control information (SCI), and / or system information.

[0170] Method 1200 then proceeds to box 1230: communicating with the UE based on at least one parameter, for example, as described herein. Figure 11 As described. For example, a network entity may use the number of MCS, transmit beamforming and / or MIMO layers indicated by at least one parameter to transmit signals (e.g., carrying data and / or control information) to the UE over a communication channel.

[0171] In some respects, the numerical representation includes a machine learning model configured (e.g., trained) to estimate the response of a UE receiver, and one or more parameters therein include one or more coefficients used for the machine learning model, for example, as described herein. Figure 8 As described. In some aspects, box 1215 includes: providing an input to a machine learning model comprising one or more channel characteristics; and obtaining an output from the machine learning model comprising an estimated response. In some aspects, the estimated response includes an indication of mutual information decoded via a digital representation of the UE receiver. In some aspects, box 1215 includes: providing an input to a machine learning model comprising one or more input combinations, each of the one or more input combinations comprising one or more channel characteristics and one or more of the following: a corresponding MCS, a corresponding PMI, or a corresponding RI; and obtaining an output from the machine learning model as an estimated response for each of the one or more input combinations, the output including an indication of whether the corresponding input combination passes the CRC. In some aspects, at least one parameter includes one or more of the corresponding MCS, corresponding PMI, or corresponding RI of one of the one or more input combinations that will pass the CRC.

[0172] In some respects, one or more parameters include a receiver index that indicates the receiver architecture of the UE receiver, for example, as described in this article regarding... Figure 10 As described. In some aspects, the receiver architecture includes one or more of the following: channel estimation type or demodulator type. In some aspects, the channel estimation type includes one or more of the following: frequency-domain MMSE-based channel estimation or time-domain MMSE-based channel estimation. In some aspects, the demodulator type includes one or more of the following: MMSE-based demodulator or maximum likelihood-based demodulator.

[0173] In some respects, one or more parameters also include the number of receive antennas for the UE, for example, as discussed in this article. Figure 10 As described.

[0174] In some respects, box 1205 includes obtaining one or more parameters prior to the establishment of an RRC connection between the device and the UE, for example, as described herein. Figure 11 As described.

[0175] In some respects, method 1200 also includes, in response to obtaining one or more parameters, an indication to the UE to reduce the rate of CSF transmission, for example, as described herein. Figure 11 As described.

[0176] In some respects, at least one parameter includes: MCS, PMI, RI, or a combination thereof, for example, as discussed in this article. Figure 11 As described.

[0177] In some respects, method 1200 or any aspect thereof may be made possible by means of a device (such as...) Figure 14 The communication device 1400 performs the method, which includes various components operable to, configured to, or adapted to perform the method 1200. The communication device 1400 is described in more detail below.

[0178] It should be noted that Figure 12 This is merely one example of a method, and other methods that include fewer, additional, or alternative operations may also be consistent with this disclosure. Example operation of user equipment

[0179] Figure 13 It shows a device (such as) Figure 1 and Figure 3 Method 1300 for wireless communication of UE 104.

[0180] Method 1300 begins at box 1305: transmitting data to the UE receiver (e.g., Figure 5 One or more parameters of the receiver (508) indicate a digital representation of the UE receiver, which represents the response used to estimate the UE receiver's communication on a communication channel having one or more channel characteristics. These parameters may include those described herein. Figure 8 The described ML model refers to one or more characteristics associated with it. For example, these parameters may include coefficients and / or weights used in an ANN, indications of the architecture or structure of the ML model (e.g., connections for artificial neurons and / or the number of layers for artificial neurons), training data used to train the ML model, and / or identifiers used for the ML model. In some cases, these parameters may include indications of the architecture of the UE receiver, for example, as described herein. Figure 10As described. As an example, these parameters may include a receiver architecture index that maps to one or more decoding operations and / or the number of receive antennas used at the UE receiver.

[0181] Method 1300 then proceeds to block 1310: receiving at least one parameter for communicating on a communication channel, the at least one parameter being based at least in part on one or more parameters and one or more channel characteristics of the communication channel, for example, as referenced herein. Figure 11 As described. At least one parameter may include link adaptation parameters such as PMI, RI, and / or MCS. In some respects, the UE may receive at least one parameter via control signaling such as RRC signaling, MAC signaling, DCI, sidelink control information (SCI), and / or system information.

[0182] Method 1300 then proceeds to box 1315: communicating on a communication channel based on at least one parameter, for example, as referenced herein. Figure 11 As described. For example, a UE may use the number of MCS, transmit beamforming and / or MIMO layers indicated by at least one parameter to receive signals (e.g., carrying data and / or control information) from network entities on a communication channel.

[0183] In some respects, the numerical representation includes a machine learning model configured to estimate the response of the UE receiver, and one or more parameters therein include one or more coefficients for the machine learning model, for example, as referenced herein. Figure 8 As described.

[0184] In some respects, one or more parameters include a receiver index that indicates the receiver architecture of the UE receiver, for example, as described in this article regarding... Figure 10 As described. In some aspects, the receiver architecture includes one or more of the following: channel estimation type or demodulator type. In some aspects, the channel estimation type includes one or more of the following: frequency-domain MMSE-based channel estimation or time-domain MMSE-based channel estimation. In some aspects, the demodulator type includes one or more of the following: MMSE-based demodulator or maximum likelihood-based demodulator. In some aspects, one or more parameters also include the number of receive antennas of the UE.

[0185] In some respects, method 1300 also includes transmitting a reference signal over a communication channel, for example, as described herein. Figure 11 As described.

[0186] In some respects, box 1305 includes transmitting one or more parameters prior to the establishment of an RRC connection between the device and the UE, for example, as described herein. Figure 11 As described.

[0187] In some respects, method 1300 also includes an indication to reduce the rate of CSF transmission in response to transmitting one or more parameters, for example, as described herein. Figure 11 As described.

[0188] In some respects, at least one parameter includes: MCS, PMI, RI, or a combination thereof, for example, as discussed in this article. Figure 11 As described.

[0189] In some respects, method 1300 or any aspect thereof may be made by means of a device (such as...) Figure 15 The communication device 1500 performs the method, which includes various components operable to, configured to, or adapted to perform the method 1300. The communication device 1500 is described in more detail below.

[0190] It should be noted that Figure 13 This is merely one example of a method, and other methods that include fewer, additional, or alternative operations may also be consistent with this disclosure. Example communication device

[0191] Figure 14 Various aspects of the example communication device 1400 are described. In some aspects, the communication device 1400 is a network entity, such as... Figure 1 and Figure 3 BS 102 or about Figure 2 The decomposed base station under discussion.

[0192] Communication device 1400 includes a processing system 1405 coupled to a transceiver 1485 (e.g., a transmitter and / or receiver) and / or a network interface 1495. Transceiver 1485 is configured to transmit and receive signals for communication device 1400 via antenna 1490, such as various signals as described herein. Network interface 1495 is configured to transmit and receive signals for communication device 1400 via a communication link (such as those described herein). Figure 2 The described backhaul link, midhaul link, and / or fronthaul link acquire and transmit signals for the communication device 1400. The processing system 1405 can be configured to perform the processing functions of the communication device 1400, including processing signals received by the communication device 1400 and / or to be transmitted by the communication device.

[0193] Processing system 1405 includes one or more processors 1410. In various aspects, the one or more processors 1410 may represent one or more of a receive processor 338, a transmit processor 320, a TX MIMO processor 330, and / or a controller / processor 340, as per [reference to...]. Figure 3As described. One or more processors 1410 are coupled to a computer-readable medium / memory 1445 via a bus 1480. In some aspects, the computer-readable medium / memory 1445 is configured to store instructions (e.g., computer-executable code) that, when executed by the one or more processors 1410, enable the one or more processors 1410 to execute and cause the one or more processors to perform actions related to... Figure 12 The described method 1200 or any aspect thereof, including regarding Figure 12 Any additional operations described. Note that references to the processor of the communication device 1400 performing the function may include one or more processors of the communication device 1400, such as those performing the function in a distributed manner.

[0194] In the depicted example, computer-readable medium / memory 1445 stores code 1450 for obtaining, code 1455 for determining, code 1460 for estimating, code 1465 for transmitting, code 1470 for communicating, and code 1475 for providing. Processing of codes 1450 to 1475 enables communication device 1400 to perform and allows the communication device to perform actions related to... Figure 12 The method 1200 described or any aspect thereof.

[0195] One or more processors 1410 include circuitry configured to implement (e.g., execute) code stored in a computer-readable medium / memory 1445. This circuitry includes circuitry 1415 for acquisition, circuitry 1420 for determination, circuitry 1425 for estimation, circuitry 1430 for transmission, circuitry 1435 for communication, and circuitry 1440 for provision. Processing using circuitry 1415 to 1440 enables communication device 1400 to perform and allow the communication device to perform actions related to… Figure 12 The method 1200 described or any aspect thereof.

[0196] More generally, components used for communication, sending, transmitting, or outputting for transmission may include Figure 3 The BS102 illustrated includes a transceiver 332, an antenna 334, a transmit processor 320, a TX MIMO processor 330, and / or a controller / processor 340. Figure 14 The transceiver 1485 and / or antenna 1490 of the communication device 1400 in the middle Figure 14 One or more processors 1410 of the communication device 1400. Components for communicating, receiving, or acquiring may include... Figure 3 The BS 102 illustrated includes transceiver 332, antenna 334, receiver processor 338, and / or controller / processor 340. Figure 14The transceiver 1485 and / or antenna 1490 of the communication device 1400 in the middle Figure 14 One or more processors 1410 of the communication device 1400 in the middle.

[0197] Figure 15 Various aspects of the example communication device 1500 are described. In some aspects, the communication device 1500 is user equipment, such as those described above. Figure 1 and Figure 3 The UE 104 described.

[0198] Communication device 1500 includes a processing system 1505 coupled to a transceiver 1565 (e.g., a transmitter and / or receiver). Transceiver 1565 is configured to transmit and receive signals for communication device 1500 via antenna 1570, such as the various signals described herein. Processing system 1505 may be configured to perform processing functions of communication device 1500, including processing signals received by and / or to be transmitted by communication device 1500.

[0199] Processing system 1505 includes one or more processors 1510. In various aspects, the one or more processors 1510 may represent one or more of a receive processor 358, a transmit processor 364, a TX MIMO processor 366, and / or a controller / processor 380, as per [reference to...]. Figure 3 As described. One or more processors 1510 are coupled to a computer-readable medium / memory 1535 via a bus 1560. In some aspects, the computer-readable medium / memory 1535 is configured to store instructions (e.g., computer-executable code) that, when executed by one or more processors 1510, enable one or more processors 1510 to execute and cause the one or more processors to perform actions related to... Figure 13 The described method 1300 or any aspect thereof, including regarding Figure 13 Any additional operations described. Note that references to processors performing the functions of communication device 1500 may include one or more processors, such as performing the functions of communication device 1500 in a distributed manner.

[0200] In the depicted example, computer-readable medium / memory 1535 stores code 1540 for transmission, code 1545 for reception, code 1550 for communication, and code 1555 for acquisition. Processing of codes 1540 to 1555 enables communication device 1500 to perform and allow the communication device to perform actions related to... Figure 13 The method described 1300 or any aspect thereof.

[0201] One or more processors 1510 include circuitry configured to implement (e.g., execute) code stored in a computer-readable medium / memory 1535, including circuitry 1515 for transmission, circuitry 1520 for reception, circuitry 1525 for communication, and circuitry 1530 for acquisition. Processing using circuitry 1515 to 1530 enables communication device 1500 to execute and perform actions related to... Figure 13 The method described 1300 or any aspect thereof.

[0202] More generally, components used for communication, sending, transmitting, or outputting for transmission may include Figure 3 The UE104 illustrated includes a transceiver 354, an antenna 352, a transmit processor 364, a TX MIMO processor 366, and / or a controller / processor 380. Figure 15 The transceiver 1565 and / or antenna 1570 of the communication equipment 1500 in the middle. Figure 15 One or more processors 1510 of the communication device 1500. Components for communicating, receiving, or acquiring may include... Figure 3 The UE 104 illustrated includes a transceiver 354, an antenna 352, a receiver processor 358, and / or a controller / processor 380. Figure 15 The transceiver 1565 and / or antenna 1570 of the communication equipment 1500 in the middle. Figure 15 One or more processors 1510 of the communication device 1500 in the middle. Example Terms

[0203] Specific implementation examples are described in the following numbered clauses.

[0204] Clause 1: A method for wireless communication by a device, the method comprising: obtaining one or more parameters of a UE receiver from a UE; determining one or more channel characteristics of a communication channel between the device and the UE based on measurements of a signal received from the UE; estimating a response of the UE receiver to communicate on the communication channel having the one or more channel characteristics based on a digital representation of the UE receiver, wherein the digital representation of the UE receiver is based on the one or more parameters of the UE receiver; determining at least one parameter for communicating with the UE on the communication channel based on the estimated response; transmitting an indication of the at least one parameter to the UE; and communicating with the UE according to the at least one parameter.

[0205] Clause 2: The method according to Clause 1, wherein the number represents a machine learning model configured to estimate the response of the UE receiver, and wherein the one or more parameters include one or more coefficients for the machine learning model.

[0206] Clause 3: The method according to Clause 2 further includes: providing the machine learning model with input including the one or more channel characteristics; and obtaining from the machine learning model an output including the estimated response.

[0207] Clause 4: The method according to Clause 3, wherein the estimated response includes an indication of mutual information decoded via the digital representation of the UE receiver.

[0208] Clause 5: The method according to Clause 2, wherein estimating the response of the UE receiver comprises providing the machine learning model with an input comprising one or more input combinations, each of the one or more input combinations comprising the one or more channel characteristics and one or more of the following: a corresponding MCS, a corresponding PMI, or a corresponding RI; and for each of the one or more input combinations, obtaining an output from the machine learning model as the estimated response, the output comprising an indication of whether the corresponding input combination passes the CRC.

[0209] Clause 6: The method according to Clause 5, wherein the at least one parameter includes one or more of the corresponding MCS, the corresponding PMI, or the corresponding RI of the one or more input combinations that will pass through the CRC.

[0210] Clause 7: The method according to any one of Clauses 1 to 6, wherein one or more parameters include a receiver index indicating the receiver architecture of the UE receiver.

[0211] Clause 8: The receiver architecture described in Clause 7 includes one or more of the following: channel estimation type or demodulator type.

[0212] Clause 9: The channel estimation type described in accordance with Clause 8 includes one or more of the following: channel estimation based on frequency domain MMSE or channel estimation based on time domain MMSE.

[0213] Clause 10: The method described in Clause 8, wherein the demodulator type includes one or more of the following: an MMSE-based demodulator or a maximum likelihood-based demodulator.

[0214] Clause 11: The method described in Clause 7, wherein one or more parameters further include the number of receiving antennas of the UE.

[0215] Clause 12: The method according to any one of Clauses 1 to 11, wherein obtaining the one or more parameters includes obtaining the one or more parameters prior to the establishment of an RRC connection between the device and the UE.

[0216] Clause 13: The method according to any one of Clauses 1 to 12, the method further comprising: in response to obtaining the one or more parameters, transmitting to the UE an instruction to reduce the rate of CSF transmission.

[0217] Clause 14: The method according to any one of Clauses 1 to 13, wherein the at least one parameter includes: MCS, PMI, RI, or a combination thereof.

[0218] Clause 15: A method for wireless communication by a device, the method comprising: transmitting one or more parameters of a UE receiver, the one or more parameters indicating a digital representation of the UE receiver, the digital representation being used to estimate a response of the UE receiver to communicate on a communication channel having one or more channel characteristics; receiving at least one parameter for communicating on the communication channel, the at least one parameter being based at least in part on the one or more parameters and the one or more channel characteristics of the communication channel; and communicating on the communication channel according to the at least one parameter.

[0219] Clause 16: The method according to Clause 15, wherein the number represents a machine learning model configured to estimate the response of the UE receiver, and wherein the one or more parameters include one or more coefficients for the machine learning model.

[0220] Clause 17: The method according to any one of Clauses 15 to 16, wherein one or more parameters include a receiver index indicating the receiver architecture of the UE receiver.

[0221] Clause 18: The receiver architecture described in accordance with Clause 17 includes one or more of the following: channel estimation type or demodulator type.

[0222] Clause 19: The method of Clause 18, wherein the channel estimation type includes one or more of the following: channel estimation based on frequency domain MMSE or channel estimation based on time domain MMSE.

[0223] Clause 20: The method described in Clause 18, wherein the demodulator type includes one or more of the following: an MMSE-based demodulator or a maximum likelihood-based demodulator.

[0224] Clause 21: The method according to Clause 17, wherein one or more parameters further include the number of receiving antennas of the UE.

[0225] Clause 22: The method according to any one of Clauses 15 to 21 further includes transmitting a reference signal on the communication channel.

[0226] Clause 23: The method according to any one of Clauses 15 to 22, wherein transmitting the one or more parameters includes transmitting the one or more parameters prior to the establishment of an RRC connection between the device and the UE.

[0227] Clause 24: The method according to any one of Clauses 15 to 23, the method further comprising: obtaining an indication to reduce the rate of CSF transmission in response to transmitting the one or more parameters.

[0228] Clause 25: The method according to any one of Clauses 15 to 24, wherein the at least one parameter includes: MCS, PMI, RI, or a combination thereof.

[0229] Clause 26: One or more means comprising: one or more memories including executable instructions; and one or more processors configured to execute the executable instructions and cause the one or more means to perform the method according to any one of Clauses 1 to 25.

[0230] Clause 27: One or more apparatuses, said apparatuses comprising components for performing the method according to any one of Clauses 1 to 25.

[0231] Clause 28: One or more non-transitory computer-readable media, the one or more non-transitory computer-readable media comprising executable instructions that, when executed by one or more processors of one or more devices, cause the one or more devices to perform the method according to any one of Clauses 1 to 25.

[0232] Clause 29: One or more computer program products embodied on one or more computer-readable storage media, the one or more computer program products including code for performing the method according to any one of Clauses 1 to 25.

[0233] Additional Notes The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. The examples discussed herein do not limit the scope, applicability, or aspects set forth in the claims. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. For example, the function and arrangement of the elements discussed may be changed without departing from the scope of this disclosure. Various processes or components may be omitted, substituted, or added as appropriate in various examples. For example, the described methods may be performed in a different order than described, and various actions may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined in some other examples. For example, any number of aspects set forth herein may be used to implement an apparatus or practice. Additionally, the scope of this disclosure is intended to cover such apparatuses or methods practiced using other structures, functionalities, or structures and functionalities that complement or replace the various aspects of this disclosure set forth herein. It should be understood that any aspect of this disclosure disclosed herein may be embodied by one or more elements of these claims.

[0234] The various exemplary logic blocks, modules, and circuits described in this disclosure can be implemented or executed using a general-purpose processor, AI processor, digital signal processor (DSP), ASIC, field-programmable gate array (FPGA) or other programmable logic device (PLD), discrete gate or transistor logic unit, discrete hardware component, or any combination thereof designed to perform the functions described herein. While the general-purpose processor may be a microprocessor, in alternative embodiments, the processor may be any commercially available processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors working in conjunction with a DSP core, a system-on-a-chip (SoC), or any other such configuration.

[0235] As used in this article, the phrase “at least one of the items” refers to any combination of these items, including a single member. As an example, “at least one of a, b, or c” is intended to cover: a, b, c, ab, ac, bc, and abc, as well as any combination with multiple identical elements (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbb, cc, and ccc, or any other ordering of a, b, and c).

[0236] As used herein, the term "determine" encompasses a wide variety of actions. For example, "determine" can include calculation, computation, processing, derivation, investigation, searching (e.g., looking in a table, database, or other data structure), assertion, and so on. Additionally, "determine" can include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), and so on. Furthermore, "determine" can include parsing, selecting, picking, building, and so on.

[0237] As used herein, unless otherwise stated, “coupled to” and “coupled with” generally encompass both direct and indirect coupling (e.g., including intermediate aspects of coupling). For example, stating that a processor is coupled to memory allows for direct coupling or coupling via an intermediate aspect such as a bus.

[0238] The methods disclosed herein include one or more actions for implementing the methods. These actions may be interchanged without departing from the scope of the claims. In other words, unless a specified order of actions is given, the order and / or use of a particular action may be modified without departing from the scope of the claims. Furthermore, the various operations of the methods described above can be performed by any suitable component capable of performing the corresponding function. This component may include various hardware and / or software components and / or modules, including but not limited to circuits, application-specific integrated circuits (ASICs), or processors.

[0239] The following claims are not intended to be limited to the aspects shown herein, but should be given the full scope consistent with the language of the claims. References to singular elements are not intended to mean “only one” (unless specifically stated as “only one”), but rather “one or more”. Unless otherwise expressly stated, definite articles (e.g., “the” or “described”) subsequently used with elements (e.g., “processor”) are not intended to invoke the singular meaning of the element (e.g., “only one”). For example, unless specifically stated otherwise, references to elements (e.g., “processor”, “controller”, “memory”, “transceiver”, “antenna”, “the processor”, “the controller”, “the memory”, “the transceiver”, “the antenna”, etc.) should be understood to refer to one or more elements (e.g., “one or more processors”, “one or more controllers”, “one or more memories”, “one or more transceivers”, etc.). The terms “set” and “group” are intended to include one or more elements and are used interchangeably with “one or more”. In the case of references to one or more elements performing a function (e.g., steps of a method), one element may perform all the functions, or more than one element may collectively perform those functions. When more than one element performs these functions together, each function does not need to be performed by every single element (e.g., different functions can be performed by different elements), and / or each function does not need to be performed by only one element as a whole (e.g., different elements can perform different sub-functions of a function). Similarly, when referring to one or more elements configured to cause another element (e.g., a device) to perform a function, one element may be configured to cause another element to perform all functions, or more than one element may be jointly configured to cause another element to perform these functions. Unless otherwise specifically stated, the term "some" refers to one or more. All structural and functional equivalents of the various aspects described throughout this disclosure that are currently or hereafter known to those skilled in the art are intended to be covered by the claims. Furthermore, nothing disclosed herein is intended to be offered to the public, whether or not such disclosure is explicitly recited in the claims.

Claims

1. An apparatus configured for wireless communication, the apparatus comprising: One or more memory units; and One or more processors, said one or more processors coupled to said one or more memories, said one or more processors being configured to cause the device to: Obtain one or more parameters of the UE receiver from the user equipment (UE); One or more channel characteristics of the communication channel between the device and the UE are determined based on measurements of signals received from the UE. The response of the UE receiver to communicate on the communication channel having the one or more channel characteristics is estimated based on the digital representation of the UE receiver, wherein the digital representation of the UE receiver is based on the one or more parameters of the UE receiver; Based on the estimated response, at least one parameter for communicating with the UE on the communication channel is determined; Transmit an indication of the at least one parameter to the UE; as well as The communication with the UE is based on at least one parameter.

2. The apparatus of claim 1, wherein the digital representation includes a machine learning model configured to estimate the response of the UE receiver, and wherein the one or more parameters include one or more coefficients for the machine learning model.

3. The apparatus according to claim 2, wherein, In order to estimate the response of the UE receiver, the one or more processors are configured to further enable the device to: Provide the machine learning model with input including one or more of the channel characteristics; and The machine learning model produces an output that includes the estimated response.

4. The apparatus of claim 3, wherein the estimated response includes an indication of mutual information decoded via the digital representation of the UE receiver.

5. The apparatus according to claim 2, wherein, In order to estimate the response of the UE receiver, the one or more processors are configured to further enable the device to: The machine learning model is provided with input comprising one or more input combinations, each of the one or more input combinations including the one or more channel characteristics and one or more of the following: a corresponding modulation and decoding scheme (MCS), a corresponding pre-decoding matrix indicator (PMI), or a corresponding rank indicator (RI); and For each of the one or more input combinations, an output is obtained from the machine learning model as an estimated response, the output including an indication of whether the corresponding input combination passes the cyclic redundancy check (CRC).

6. The apparatus of claim 5, wherein the at least one parameter comprises one or more of the corresponding MCS, the corresponding PMI, or the corresponding RI of the one or more input combinations that will pass through the CRC.

7. The apparatus of claim 1, wherein one or more parameters include a receiver index indicating the receiver architecture of the UE receiver.

8. The apparatus of claim 7, wherein the receiver architecture comprises one or more of the following: a channel estimation type or a demodulator type.

9. The apparatus of claim 8, wherein the channel estimation type includes one or more of the following: Channel estimation based on minimum mean square error (MMSE) in the frequency domain, or Channel estimation based on time-domain MMSE.

10. The apparatus of claim 8, wherein the demodulator type includes one or more of the following: Demodulators based on minimum mean square error (MMSE), or Maximum likelihood-based demodulator.

11. The apparatus of claim 7, wherein the one or more parameters further include the number of receiving antennas of the UE.

12. The apparatus of claim 1, wherein, in order to obtain the one or more parameters, the one or more processors are configured to further enable the apparatus to obtain the one or more parameters prior to the establishment of a radio resource control (RRC) connection between the apparatus and the UE.

13. The apparatus of claim 1, wherein the one or more processors are further configured to cause the apparatus to: In response to obtaining the one or more parameters, an indication is sent to the UE to reduce the rate of communication channel state feedback (CSF).

14. The apparatus of claim 1, wherein the at least one parameter comprises: Modulation and decoding scheme (MCS). Predecoding matrix indicator (PMI) Rank indicator (RI), or Their combination.

15. An apparatus configured for wireless communication, the apparatus comprising: One or more memory units; and One or more processors, said one or more processors coupled to said one or more memories, said one or more processors being configured to cause the device to: Transmit one or more parameters of a user equipment (UE) receiver, the one or more parameters indicating a digital representation of the UE receiver, the digital representation being used to estimate the response of the UE receiver to communicate on a communication channel having one or more channel characteristics; Receive at least one parameter for communicating on the communication channel, the at least one parameter being based at least in part on the one or more parameters and the one or more channel characteristics of the communication channel; as well as Communication is performed on the communication channel according to at least one of the parameters.

16. The apparatus of claim 15, wherein the digital representation includes a machine learning model configured to estimate the response of the UE receiver, and wherein the one or more parameters include one or more coefficients for the machine learning model.

17. The apparatus of claim 15, wherein one or more parameters include a receiver index indicating the receiver architecture of the UE receiver.

18. The apparatus of claim 17, wherein the receiver architecture comprises one or more of the following: a channel estimation type or a demodulator type.

19. The apparatus of claim 18, wherein the channel estimation type includes one or more of the following: Channel estimation based on minimum mean square error (MMSE) in the frequency domain, or Channel estimation based on time-domain MMSE.

20. The apparatus of claim 18, wherein the demodulator type includes one or more of the following: Demodulators based on minimum mean square error (MMSE), or Maximum likelihood-based demodulator.

21. The apparatus of claim 17, wherein the one or more parameters further include the number of receiving antennas of the UE.

22. The apparatus of claim 15, wherein the one or more processors are further configured to cause the apparatus to transmit a reference signal on the communication channel.

23. The apparatus of claim 15, wherein, in order to transmit the one or more parameters, the one or more processors are configured to further enable the apparatus to transmit the one or more parameters prior to the establishment of a radio resource control (RRC) connection between the apparatus and the UE.

24. The apparatus of claim 15, wherein the one or more processors are further configured to cause the apparatus to: In response to transmitting one or more of the parameters, an indication is obtained to reduce the rate of communication channel state feedback (CSF).

25. The apparatus of claim 15, wherein the at least one parameter comprises: Modulation and decoding scheme (MCS). Predecoding matrix indicator (PMI) Rank indicator (RI), or Their combination.

26. A method for wireless communication by a device, the method comprising: Obtain one or more parameters of the UE receiver from the user equipment (UE); One or more channel characteristics of the communication channel between the device and the UE are determined based on measurements of signals received from the UE. The response of the UE receiver to communicate on the communication channel having the one or more channel characteristics is estimated based on the digital representation of the UE receiver, wherein the digital representation of the UE receiver is based on the one or more parameters of the UE receiver; Based on the estimated response, at least one parameter for communicating with the UE on the communication channel is determined; Transmit an indication of the at least one parameter to the UE; as well as The communication with the UE is based on at least one parameter.

27. A method for wireless communication by a device, the method comprising: Transmit one or more parameters of a user equipment (UE) receiver, the one or more parameters indicating a digital representation of the UE receiver, the digital representation being used to estimate the response of the UE receiver to communicate on a communication channel having one or more channel characteristics; Receive at least one parameter for communicating on the communication channel, the at least one parameter being based at least in part on the one or more parameters and the one or more channel characteristics of the communication channel; as well as Communication is performed on the communication channel according to at least one of the parameters.

Images