Time gap for artificial intelligence and machine learning models in wireless communications

Abstract

Aspects of the present disclosure provide apparatus and methods for providing time slots that can be used to train, verify, compile, and / or switch artificial intelligence (AI) / machine learning (ML) models for use in wireless communications. In these time slots, the wireless device can deprioritize certain normally or routinely performed processes and functions to conserve processing capabilities and / or resources for performing AI / ML model related functions. In one example, an apparatus can provide one or more time slots associated with an AI / ML model for communicating with a network entity. The apparatus can deprioritize at least one of uplink (UL) communications or downlink (DL) communications with the network entity in the one or more time slots. The apparatus is capable of performing one or more AI / ML model related processes in the one or more time slots.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to pending U.S. non-provisional application No. 17 / 855,147, filed on June 30, 2022, which is assigned to the assignee of the present application and is hereby expressly incorporated herein by reference as if fully set forth below and for all applicable purposes. Technical Field

[0003] The technology discussed below relates generally to wireless communication systems, and more specifically, to time slicing for artificial intelligence and machine learning (AI / ML) model-related functions in wireless communications. Background Art

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcast. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

[0005] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at a city, country, region, or even global level. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of the continued mobile broadband evolution promulgated by the Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT)), and other requirements. Certain aspects of 5G NR may be based on the 4G Long Term Evolution (LTE) standard. 5G NR systems may consume more power and achieve lower data rates than 4G systems.

[0006] Artificial intelligence (AI) can use machines (usually computer systems) to simulate human intelligence processes. Machine learning (ML) is a subset of AI that can create algorithms and statistical models to perform specific tasks without explicit instructions, but instead rely on patterns and inferences. In some aspects, replacing traditional wireless algorithms with AI and ML models can reduce power consumption and improve performance in wireless communications. Summary of the invention

[0007] An overview of one or more aspects of the present disclosure is presented below to provide a basic understanding of these aspects. This overview is not an extensive review of all expected features of the present disclosure, and is neither intended to identify key or important elements of all aspects of the present disclosure, nor is it intended to describe the scope of any or all aspects of the present disclosure. Its sole purpose is to present some concepts of one or more aspects of the present disclosure in a form as a preface to a more detailed description presented later.

[0008] Various aspects of the present disclosure provide apparatus and methods for providing time gaps that can be used to train, validate, compile and / or switch artificial intelligence (AI) / machine learning (ML) models for use in wireless communications. During these time gaps, the wireless device can de-prioritize certain normal or routinely executed processes and functions to save processing power and / or resources used to perform AI / ML model-related functions.

[0009] One aspect of the present disclosure provides a method for wireless communication at a user equipment (UE). The method includes providing one or more time slots associated with an artificial intelligence and machine learning (AI / ML) model for communicating with a network entity. The method also includes deprioritizing at least one of an uplink (UL) communication or a downlink (DL) communication with the network entity in the one or more time slots. The method also includes performing one or more AI / ML model-related processes in the one or more time slots.

[0010] One aspect of the present disclosure provides a user equipment (UE) for wireless communication. The UE includes a communication interface, a memory storing executable code, and a processor coupled to the communication interface and the memory. The processor is configured by the executable code to provide one or more time slots, the one or more time slots being associated with an artificial intelligence and machine learning (AI / ML) model for communicating with a network entity using the communication interface. The processor is further configured to: de-prioritize at least one of an uplink (UL) communication or a downlink (DL) communication with the network entity in the one or more time slots. The processor is further configured to perform one or more AI / ML model-related processes in the one or more time slots.

[0011] One aspect of the present disclosure provides a method for wireless communication at a network entity. The method includes providing one or more time slots to a user equipment (UE), the one or more time slots being associated with an artificial intelligence and machine learning (AI / ML) model at the UE in a radio access network associated with the network entity. The method also includes: de-prioritizing at least one of an uplink (UL) communication or a DL communication with the UE in the one or more time slots. The method also includes: performing one or more AI / ML model-related processes in the one or more time slots.

[0012] One aspect of the present disclosure provides a network entity for wireless communication. The network entity includes: a memory storing executable code; and

[0013] A processor coupled to a memory. The processor is configured by executable code to provide one or more time slots to a user equipment (UE), the one or more time slots being associated with an artificial intelligence and machine learning (AI / ML) model at the UE in a radio access network associated with a network entity. The processor is further configured to: de-prioritize at least one of uplink (UL) communications or downlink (DL) communications with the UE in the one or more time slots. The processor is further configured to perform one or more AI / ML model-related processes in the one or more time slots.

[0014] After reading the following specific embodiments, these and other aspects of the present invention will become more fully understood. After reading the following description of specific exemplary implementations in conjunction with the accompanying drawings, other aspects, features and specific implementations will become apparent to those of ordinary skill in the art. Although each feature may be discussed with respect to certain examples and drawings below, all specific implementations may include one or more advantageous features in the advantageous features discussed herein. In other words, although one or more specific implementations may be discussed as having certain advantageous features, one or more features in such features may also be used according to the various examples discussed herein. In a similar manner, although each example may be discussed as a device, system or method specific implementation below, it should be understood that such examples can be implemented in various devices, systems and methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic diagram of a wireless communication system according to some aspects.

[0016] Figure 2 is an illustration of an example of a radio access network (RAN) in accordance with some aspects.

[0017] Figure 3is a schematic diagram of organization of radio resources in an air interface utilizing orthogonal frequency division multiplexing (OFDM) according to some aspects.

[0018] Figure 4 is a diagram illustrating an example of a decomposed base station architecture in accordance with some aspects.

[0019] Figure 5 is a block diagram illustrating a wireless communication system supporting multiple-input multiple-output (MIMO) communication.

[0020] Figure 6 is a diagram illustrating an example of a multiple transmission and reception point environment according to some aspects.

[0021] Figure 7 is a diagram illustrating exemplary time slots for performing artificial intelligence and machine learning (AI / ML) related functions in accordance with some aspects.

[0022] Figure 8 is a flow diagram illustrating a process for de-prioritizing RAN functions in AI / ML model time slots according to some aspects.

[0023] Fig. 9 is a flow diagram illustrating a process for performing AI / ML model-related functions in an AI / ML model time slot according to some aspects.

[0024] Fig.10 is a signaling diagram illustrating exemplary signaling between a network entity and a user equipment (UE) for configuring AI / ML model time gaps in a wireless network according to some aspects.

[0025] Fig.11 is a block diagram illustrating an example of a hardware implementation for a UE according to some aspects.

[0026] Fig.12 is a flow chart illustrating an exemplary process for performing AI / ML model-related functions at a UE according to some aspects.

[0027] Fig.13 is a block diagram illustrating an example of a hardware implementation for a network entity according to some aspects.

[0028] Fig.14 is a flow chart illustrating an exemplary process for performing AI / ML model-related functions at a network entity according to some aspects. DETAILED DESCRIPTION

[0029] The detailed description set forth below in conjunction with the accompanying drawings is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. In order to provide a thorough understanding of the various concepts, the specific embodiments include specific details. However, it is apparent to those skilled in the art that these concepts may be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid obscuring these concepts.

[0030] Although various aspects and specific implementations are described in this application by the illustration of some examples, it will be understood by those skilled in the art that additional specific implementations and use cases may be generated in many other arrangements and scenarios. The innovation described herein can be implemented across many different platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, specific implementations and / or uses may occur via integrated chips and other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / purchase equipment, medical equipment, AI-enabled devices, etc.). Although some examples may or may not specifically point to use cases or applications, the applicability of various types of described innovations may occur. Specific implementations may have a range from chip-level or modular components to non-modular, non-chip-level specific implementations, and further to aggregated, distributed, or OEM devices or systems incorporating one or more aspects of the described innovation. In some actual settings, the device incorporating the described aspects and features may also necessarily include additional components and features for the implementation and implementation of the examples claimed and described. For example, the transmission and reception of wireless signals necessarily include multiple components for analog and digital purposes (e.g., hardware components including antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / summers, etc.). The innovations described herein are intended to be practiced in a variety of devices of different sizes, shapes, and configurations, chip-level components, systems, distributed arrangements, disaggregated arrangements (e.g., base stations and UEs), end-user devices, etc.

[0031] Various aspects of the present disclosure provide various devices and methods for providing time gaps for training, validating, compiling and / or switching artificial intelligence (AI) / machine learning (ML) models for wireless communication. During these time gaps, the UE can de-prioritize certain normally executed processes and functions to save processing power and / or resources for executing AI / ML model related functions.

[0032] The various concepts presented throughout this disclosure may be implemented across a wide variety of telecommunication systems, network architectures, and communication standards. Figure 1, various aspects of the present disclosure are illustrated with reference to a wireless communication system 100 as an illustrative example and not as a limitation. The wireless communication system 100 includes three interacting domains: a core network 102, a radio access network (RAN) 104, and a UE 106. By means of the wireless communication system 100, the UE 106 may be enabled to perform data communications with an external data network 110, such as (but not limited to) the Internet.

[0033] The RAN 104 may implement any suitable one or more wireless communication technologies to provide radio access to the UE 106. As an example, the RAN 104 may operate according to the 3rd Generation Partnership Project (3GPP) New Radio (NR) specification (commonly referred to as 5G). As another example, the RAN 104 may operate according to a hybrid of 5G NR and Evolved Universal Terrestrial Radio Access Network (eUTRAN) standards (commonly referred to as LTE). 3GPP refers to such a hybrid RAN as the Next Generation RAN or NG-RAN. Of course, many other examples may be utilized within the scope of the present disclosure.

[0034] As illustrated, RAN 104 includes multiple base stations 108. In a broad sense, a base station is a network element in a radio access network that is responsible for radio transmission and reception to or from a UE in one or more cells. In different technologies, standards or contexts, a base station may be referred to as a base transceiver station (BTS), a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), an access point (AP), a node B (NB), an evolved node B (eNB), a next generation node B (gNB), a transmit receive point (TRP) or some other suitable terminology by those skilled in the art. In some examples, a base station may include two or more TRPs that may be co-located or non-co-located. Each TRP may communicate on the same or different carrier frequencies in the same or different frequency bands.

[0035] The radio access network 104 is also illustrated as supporting wireless communications for a plurality of mobile devices. In the 3GPP standard, a mobile device may be referred to as a user equipment (UE), but those skilled in the art may also refer to it as a mobile station (MS), a user station, a mobile unit, a user unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile user station, an access terminal (AT), a mobile terminal, a wireless terminal, a remote terminal, a handset, a terminal, a user agent, a mobile client, a client, or some other suitable term. A UE may be a device (e.g., a mobile device) that provides access to network services to a user.

[0036] In this document, a "mobile" device does not necessarily need to have the ability to move, and it can be stationary. The term mobile device or mobile device refers to a wide variety of devices and technologies. A UE may include a plurality of hardware structural components whose size, shape, and arrangement facilitate communication; such components may include antennas, antenna arrays, radio frequency (RF) chains, amplifiers, one or more processors, etc. that are electrically coupled to each other. For example, some non-limiting examples of mobile devices include mobile stations, cellular (cell) phones, smart phones, session initiation protocol (SIP) phones, laptops, personal computers (PCs), notebooks, netbooks, smart books, tablet devices, personal digital assistants (PDAs), and a wide range of embedded systems, for example, corresponding to the "Internet of Things" (IoT). A mobile device may additionally be a car or other transportation vehicle, a remote sensor or actuator, a robot or robotic device, a satellite radio, a global positioning system (GPS) device, an object tracking device, a drone, a multi-axis aircraft, a quadcopter, a remote control device, a consumer and / or wearable device (such as glasses, wearable cameras, virtual reality devices, smart watches, health or fitness trackers, digital audio players (e.g., MP3 players), cameras, game consoles, etc.). The mobile device may additionally be a digital home or smart home device, such as home audio, video and / or multimedia equipment, appliances, vending machines, smart lighting, home security systems, smart meters, etc. The mobile device may additionally be a smart energy device, security device, solar panel or solar array, municipal infrastructure equipment that controls power (e.g., smart grid), lighting, water, etc.; industrial automation and enterprise equipment; logistics controller; agricultural equipment, etc. Further, the mobile device may provide connected medicine or telemedicine support, such as health care at a distance. Telemedicine devices may include telemedicine monitoring devices and telemedicine management devices, whose communications may be given priority or access over other types of information, for example, in terms of priority access for transmission of critical service data and / or associated QoS for transmission of critical service data.

[0037] Wireless communication between RAN 104 and UE 106 may be described as utilizing an air interface. Transmissions from a base station (e.g., base station 108) to one or more UEs (e.g., UE 106) over an air interface may be referred to as downlink (DL) transmissions. According to certain aspects of the present disclosure, the term downlink may refer to point-to-multipoint transmissions originating at an entity (described further below; e.g., base station 108). Another way to describe this scheme may be to use the term "broadcast channel multiplexing". Transmissions from a UE (e.g., UE 106) to a base station (e.g., base station 108) may be referred to as uplink (UL) transmissions. According to further aspects of the present disclosure, the term "uplink" may refer to point-to-point transmissions originating at a scheduled entity (described further below; e.g., UE 106).

[0038] In some examples, access to the air interface may be scheduled, wherein a network entity (e.g., a base station 108) allocates resources for communication among some or all devices and equipment within its service area or cell. Within the present disclosure, as discussed further below, a network entity may be responsible for scheduling, assigning, reconfiguring, and releasing resources for one or more scheduled entities. That is, for scheduled communications, a UE 106 (which may be a scheduled entity) may utilize resources allocated by the network entity 108.

[0039] Base station 108 is not the only entity that can act as a scheduling entity. That is, in some examples, a UE can act as a scheduling entity, scheduling resources for one or more scheduled entities (e.g., one or more other UEs).

[0040] As in Figure 1 , the network entity 108 may broadcast downlink traffic 112 to one or more scheduled entities 106. In a broad sense, the network entity 108 is a node or device responsible for scheduling traffic in the wireless communication network, which includes downlink traffic 112 and (in some examples) uplink traffic 116 from one or more scheduled entities 106 to the network entity 108. On the other hand, the scheduled entity 106 is a node or device that receives downlink control information 114 (including but not limited to scheduling information (e.g., grant), synchronization or timing information, or other control information) from another entity in the wireless communication network (such as the network entity 108). The scheduled entity 106 may also send uplink control information 118 to the network entity 108, including but not limited to scheduling requests or feedback information or other control information.

[0041] In addition, uplink and / or downlink control information 114 and / or 118 and / or business information 112 and / or 116 may be sent on a waveform that may be divided into frames, subframes, time slots and / or symbols by time. As used herein, a symbol may refer to a time unit that carries one resource element (RE) per subcarrier in an orthogonal frequency division multiplexing (OFDM) waveform. A time slot may carry 7 or 14 OFDM symbols. A subframe may refer to a duration of 1 ms. Multiple subframes or time slots may be grouped together to form a single frame or radio frame. In the present disclosure, a frame may refer to a predetermined duration (e.g., 10 ms) for wireless transmission, wherein each frame is composed of, for example, 10 subframes of 1 ms each. Of course, these definitions are not required, and any suitable scheme for organizing waveforms may be utilized, and the various time divisions of waveforms may have any suitable duration.

[0042] Generally speaking, the base stations 108 may include a backhaul interface for communicating with a backhaul portion 120 of the wireless communication system. The backhaul 120 may provide a link between the base stations 108 and the core network 102. Furthermore, in some examples, the backhaul network may provide interconnections between the respective base stations 108. Various types of backhaul interfaces may be employed, such as a direct physical connection using any suitable transport network, a virtual network, or the like.

[0043] The core network 102 may be part of the wireless communication system 100 and may be independent of the radio access technology used in the RAN 104. In some examples, the core network 102 may be configured according to 5G standards (e.g., 5GC). In other examples, the core network 102 may be configured according to 4G Evolved Packet Core (EPC) or any other appropriate standard or configuration.

[0044] Figure 2 is an illustration of an example of a radio access network (RAN) 200 according to some aspects. In some examples, the RAN 200 can be similar to the ones described above and in Figure 1 The geographic area covered by the RAN 200 may be divided into cellular regions (cells) that may be uniquely identified by a user equipment (UE) based on an identity broadcast from an access point or base station. Figure 2 Cells 202, 204, 206, and 208 are illustrated, each of which may include one or more sectors (not shown). A sector is a sub-area of ​​a cell. All sectors within a cell are served by the same base station. A radio link within a sector may be identified by a single logical identifier belonging to the sector. In a cell divided into sectors, multiple sectors within a cell may be formed by multiple groups of antennas, each of which is responsible for communicating with a UE in a portion of the cell.

[0045] Various base station arrangements can be used. Figure 2, two base stations (base station 210 and base station 212) are shown in cells 202 and 204. A third base station (base station 214) is shown as controlling a remote radio head (RRH) 216 in cell 206. That is, the base station may have an integrated antenna, or may be connected to an antenna or RRH 216 by a feeder cable. In the illustrated example, cells 202, 204, and 206 may be referred to as macro cells because base stations 210, 212, and 214 support cells with large sizes. In addition, base station 218 is shown in cell 208, which may overlap with one or more macro cells. In this example, cell 208 may be referred to as a small cell (e.g., a micro cell, a micro cell, a femto cell, a home base station, a home node B, a home evolved node B, etc.), because base station 218 supports a cell with a relatively small range. The cell size setting may be performed according to the system design and component constraints.

[0046] It should be understood that the radio access network 200 may include any number of wireless base stations and cells. In addition, relay nodes may be deployed to extend the size or coverage area of ​​a given cell. Base stations 210, 212, 214, 218 provide wireless access points to the core network for any number of mobile devices. In some examples, base stations 210, 212, 214, and / or 218 may be similar to those described above and in Figure 1 The base station / network entity 108 is the same as that illustrated in FIG.

[0047] Figure 2 Also included is an unmanned aerial vehicle (UAV) 220, which may be a quadcopter or a drone. UAV 220 may be configured to function as a base station. That is, in some examples, the cell may not necessarily be stationary, and the geographic area of ​​the cell may move based on the location of a mobile base station (such as a quadcopter 220).

[0048] Within the RAN 200, cells may include UEs that may communicate with one or more sectors of each cell. In addition, each base station 210, 212, 214, 218, and 220 may be configured to provide access to the core network 102 (see FIG. 1 ) for all UEs in the corresponding cell. Figure 1 ) access point. For example, UEs 222 and 224 may communicate with base station 210; UEs 226 and 228 may communicate with base station 212; UEs 230 and 232 may communicate with base station 214 via RRH 216; UE 234 may communicate with base station 218; and UE 236 may communicate with mobile base station 220. In some examples, UEs 222, 224, 226, 228, 230, 232, 234, 236, 238, 240, and / or 242 may communicate with the base stations described above and Figure 1The UE / scheduled entity 106 illustrated in FIG.

[0049] In some examples, UAV 220 (e.g., a quadcopter) can be configured to function as a UE. For example, UAV 220 can operate within cell 202 by communicating with base station 210.

[0050] On the other hand of RAN 200, side link signals can be used between UEs without relying on scheduling or control information from a base station. Side link communications can be utilized in device-to-device (D2D) networks, peer-to-peer (P2P) networks, vehicle-to-vehicle (V2V) networks, vehicle-to-everything (V2X) networks, and / or other appropriate side link networks. For example, two or more UEs (e.g., UE 238, 240, and 242) can communicate with each other using side link signals 237 without relaying the communication through a base station. In some examples, UE 238, 240, and 242 can each act as a scheduling entity or a transmitting side link device and / or a scheduled entity or a receiving side link device to schedule resources and communicate side link signals 237 between them without relying on scheduling or control information from a base station. In other examples, two or more UEs (e.g., UE 226 and 228) within the coverage area of ​​a base station (e.g., base station 212) can also communicate side link signals 227 via a direct link (side link) without transmitting the communication through base station 212. In this example, base station 212 may allocate resources to UEs 226 and 228 for sidelink communications.

[0051] In some examples, a D2D relay framework may be included within a cellular network to facilitate relaying of communications to / from base station 212 via a D2D link (e.g., side link 227 or 237). For example, one or more UEs (e.g., UE 228) within the coverage area of ​​base station 212 may operate as relay UEs to extend the coverage of base station 212, improve transmission reliability to one or more UEs (e.g., UE 226), and / or allow the base station to recover from a failed UE link due to, for example, blocking or fading.

[0052] In RAN 200, the ability for a UE to communicate while moving (independent of its location) is called mobility. The various physical channels between the UE and the radio access network are typically managed by an access and mobility management function (AMF, not shown). Figure 1 The function may include a security context management function (SCMF) and a security anchor function (SEAF) for performing authentication. The SCMF may manage the security context for both the control plane functionality and the user plane functionality in whole or in part.

[0053] In various aspects of the present disclosure, the radio access network 200 can utilize DL-based mobility or UL-based mobility to implement mobility and switching (i.e., the transfer of a UE's connection from one radio channel to another). In a network configured for DL-based mobility, during a call with a scheduling entity or at any other time, the UE can monitor various parameters of the signal from its serving cell and various parameters of neighboring cells. Based on the quality of these parameters, the UE can maintain communication with one or more neighboring cells. During this time, if the UE moves from one cell to another, or if the signal quality from a neighboring cell exceeds the signal quality from the serving cell for a given amount of time, the UE can perform a handover or handover from the serving cell to the neighboring (target) cell. For example, a UE 224 (illustrated as a vehicle, although any suitable form of UE can be used) can move from a geographic area corresponding to its serving cell 202 to a geographic area corresponding to a neighboring cell 206. When the signal strength or quality from a neighboring cell 206 exceeds the signal strength and quality of its serving cell 202 for a given amount of time, the UE 224 can send a report message indicating this to its serving base station 210. In response, UE 224 may receive the handover command, and the UE may proceed with the handover to cell 206 .

[0054] In a network configured for UL-based mobility, the network can select a serving cell for each UE using a UL reference signal from each UE. In some examples, base stations 210, 212, and 214 / 216 can broadcast a unified synchronization signal (e.g., a unified primary synchronization signal (PSS), a unified secondary synchronization signal (SSS), and a unified physical broadcast channel (PBCH)). UE222, 224, 226, 228, 230, and 232 can receive a unified synchronization signal, derive a carrier frequency and a time slot timing based on the synchronization signal, and send an uplink pilot or reference signal in response to the derived timing. The uplink pilot signal sent by a UE (e.g., UE 224) can be received concurrently by two or more cells (e.g., base stations 210 and 214 / 216) within the radio access network 200. Each of the cells may measure the strength of the pilot signal, and the radio access network (e.g., one or more of the base stations 210 and 214 / 216 and / or a central node within the core network) may determine a serving cell for the UE 224. As the UE 224 moves through the radio access network 200, the network may continue to monitor the uplink pilot signal sent by the UE 224. When the signal strength or quality of the pilot signal measured by the neighboring cell exceeds the signal strength or quality measured by the serving cell, the network 200 may handover the UE 224 from the serving cell to the neighboring cell with or without notifying the UE 224.

[0055] Although the synchronization signals transmitted by base stations 210, 212 and 214 / 216 may be uniform, the synchronization signal may not identify a specific cell, but may identify a zone of multiple cells operating on the same frequency and / or using the same timing. Using zones in a 5G network or other next generation communication network implements an uplink-based mobility framework and improves the efficiency of both the UE and the network, because the number of mobility messages that need to be exchanged between the UE and the network can be reduced.

[0056] The air interface in the radio access network 200 may utilize one or more duplex algorithms. Duplex refers to a point-to-point communication link in which two endpoints can communicate with each other in two directions. Full-duplex means that two endpoints can communicate with each other at the same time. Half-duplex means that only one endpoint can transmit information to the other endpoint at a time. Half-duplex emulation is often implemented for wireless links using time division duplex (TDD). In TDD, transmissions in different directions on a given channel are separated from each other using time division multiplexing. That is, at certain times, the channel is dedicated to transmissions in one direction, while at other times, the channel is dedicated to transmissions in another direction, where the direction can change very quickly, for example, several times per time slot. In wireless links, full-duplex channels generally rely on physical isolation of transmitters and receivers and suitable interference cancellation techniques. Full-duplex emulation is often implemented for wireless links by utilizing frequency division duplex (FDD) or space division duplex (SDD). In FDD, transmissions in different directions can operate at different carrier frequencies (e.g., within a paired spectrum). In SDD, transmissions in different directions on a given channel are separated from each other using spatial division multiplexing (SDM). In other examples, full-duplex communication may be implemented within an unpaired spectrum (e.g., within a single carrier bandwidth), where transmissions in different directions occur within different sub-bands of the carrier bandwidth. This type of full-duplex communication may be referred to herein as sub-band full-duplex (SBFD), also known as flexible duplex.

[0057] In addition, the air interface in the radio access network 200 can utilize one or more multiplexing and multiple access algorithms to enable simultaneous communication of various devices. For example, the 5G NR specification provides multiple access for UL transmissions from UEs 222 and 224 to the base station 210, and multiplexing of DL transmissions from the base station 210 to one or more UEs 222 and 224 using orthogonal frequency division multiplexing (OFDM) with a cyclic prefix (CP). In addition, for UL transmissions, the 5G NR specification provides support for discrete Fourier transform spread OFDM (DFT-s-OFDM) with CP (also referred to as single carrier FDMA (SC-FDMA)). However, within the scope of the present disclosure, multiplexing and multiple access are not limited to the above schemes, and can be provided using time division multiple access (TDMA), code division multiple access (CDMA), frequency division multiple access (FDMA), sparse code multiple access (SCMA), resource extension multiple access (RSMA) or other appropriate multiple access schemes. In addition, multiplexing of DL transmissions from base station 210 to UEs 222 and 224 may be provided using time division multiplexing (TDM), code division multiplexing (CDM), frequency division multiplexing (FDM), orthogonal frequency division multiplexing (OFDM), sparse code multiplexing (SCM), or other suitable multiplexing schemes.

[0058] Reference Figure 3Various aspects of the present disclosure are described using OFDM waveforms schematically illustrated in . It should be understood by those skilled in the art that various aspects of the present disclosure can be applied to SC-FDMA waveforms in substantially the same manner as described herein below. That is, although some examples of the present disclosure may focus on OFDM links for clarity, it should be understood that the same principles can also be applied to SC-FDMA waveforms.

[0059] Reference now Figure 3 , illustrates an expanded view of an exemplary subframe 302 showing an OFDM resource grid. However, as will be readily apparent to one skilled in the art, the PHY transmit structure for any particular application may differ from the examples described herein, depending on any number of factors. Here, time is in units of OFDM symbols in the horizontal direction; and frequency is in units of subcarriers of a carrier in the vertical direction.

[0060] Resource grid 304 can be used to schematically represent the time-frequency resources for a given antenna port. That is, in a multiple-input multiple-output (MIMO) implementation with multiple available antenna ports, a corresponding plurality of resource grids 304 may be available for communication. Resource grid 304 is divided into a plurality of resource elements (REs) 306. RE (which is 1 subcarrier × 1 symbol) is the smallest discrete portion of the time-frequency grid and contains a single complex value representing data from a physical channel or signal. Depending on the modulation utilized in a particular implementation, each RE can represent one or more bits of information. In some examples, a block of REs may be referred to as a physical resource block (PRB), or more simply a resource block (RB) 308, which may contain any suitable number of consecutive subcarriers in the frequency domain. In one example, an RB may include 12 subcarriers (a number independent of the parameter set used). In some examples, depending on the parameter set, an RB may include any suitable number of consecutive OFDM symbols in the time domain. Within the present disclosure, it is assumed that a single RB (such as RB 308) corresponds entirely to communication in a single direction (transmission or reception for a given device).

[0061] A collection of contiguous or discontinuous resource blocks may be referred to herein as a resource block group (RBG), a subband, or a bandwidth part (BWP). A collection of subbands or BWPs may span the entire bandwidth. Scheduling a scheduled entity (e.g., a UE) for downlink, uplink, or sidelink transmission typically involves scheduling one or more resource elements 306 within one or more subbands or bandwidth parts (BWPs). Therefore, a UE generally utilizes only a subset of a resource grid 304. In some examples, an RB may be the smallest resource unit that may be allocated to a UE. Therefore, the more RBs scheduled for a UE, and the higher the modulation scheme selected for the air interface, the higher the data rate for the UE. The RBs may be scheduled by a scheduling entity such as a base station (e.g., a gNB, eNB, etc.), or may be self-scheduled by a UE implementing D2D sidelink communication.

[0062] In this illustration, RB 308 is shown as occupying less than the entire bandwidth of subframe 302, with some subcarriers illustrated above and below RB 308. In a given implementation, subframe 302 may have a bandwidth corresponding to any number of one or more RBs 308. Furthermore, in this illustration, RB 308 is shown as occupying less than the entire duration of subframe 302, but this is merely one possible example.

[0063] Each 1 ms subframe 302 may consist of one or more adjacent time slots. Figure 3 In the example shown in, as an illustrative example, a subframe 302 includes four time slots 310. In some examples, a time slot may be defined according to a specified number of OFDM symbols with a given cyclic prefix (CP) length. For example, a time slot may include 7 or 14 OFDM symbols with a nominal CP. Additional examples may include micro-slots (sometimes referred to as shortened transmission time intervals (TTIs)) with shorter durations (e.g., one to three OFDM symbols). These micro-slots or shortened transmission time intervals (TTIs) may be transmitted in some cases by occupying resources scheduled for ongoing time slot transmissions for the same UE or different UEs. Any number of resource blocks may be utilized within a subframe or time slot.

[0064] An expanded view of one of the time slots 310 illustrates the time slot 310 including a control region 312 and a data region 314. In general, the control region 312 may carry control channels, and the data region 314 may carry data channels. Of course, a time slot may contain full DL, full UL, or at least one DL portion and at least one UL portion. Figure 3 The structures illustrated in are merely exemplary in nature, and different slot structures may be utilized, and these slot structures may include one or more of each of the control region or the data region.

[0065] Despite Figure 3 Although not illustrated in the figure, each RE 306 within the RB 308 may be scheduled to carry one or more physical channels, including a control channel, a shared channel, a data channel, etc. Other REs 306 within the RB 308 may also carry pilot signals or reference signals. These pilot signals or reference signals may be provided to a receiving device to perform channel estimation of the corresponding channel, which may enable coherent demodulation / detection of the control channel and / or the data channel within the RB 308.

[0066] In some examples, time slot 310 may be used for broadcast, multicast, groupcast, or unicast communications. For example, broadcast, multicast, or groupcast communications may refer to point-to-multipoint transmissions from one device (e.g., a base station, UE, or other similar device) to other devices. Here, broadcast communications are delivered to all devices, while multicast or groupcast communications are delivered to multiple intended receiving devices. Unicast communications may refer to point-to-point transmissions from one device to a single other device.

[0067] In an example of cellular communication via a cellular carrier via a Uu interface, for DL ​​transmission, a scheduling entity (e.g., a base station) may allocate one or more REs 306 (e.g., within a control region 312) to one or more scheduled entities (e.g., UEs) to carry DL control information including one or more DL control channels (e.g., a physical downlink control channel (PDCCH)). The PDCCH carries downlink control information (DCI), including, but not limited to, power control commands (e.g., one or more open-loop power control parameters and / or one or more closed-loop power control parameters), scheduling information, grants, and / or assignments of REs for DL ​​transmission and UL transmission. The PDCCH may also carry hybrid automatic repeat request (HARQ) feedback transmissions, such as acknowledgements (ACKs) or negative acknowledgements (NACKs). HARQ is a technique well known to those of ordinary skill in the art, in which the integrity of packet transmissions may be checked for accuracy at the receiving side, for example, using any appropriate integrity check mechanism, such as a checksum or a cyclic redundancy check (CRC). If the integrity of the transmission is confirmed, an ACK may be sent, and if it is not confirmed, a NACK may be sent. In response to the NACK, the sending device may transmit a HARQ retransmission, which may implement trace combining, incremental redundancy, and the like.

[0068] The base station may further allocate one or more REs 306 (e.g., in the control region 312 or the data region 314) to carry other DL signals, such as a demodulation reference signal (DMRS); a phase tracking reference signal (PT-RS); a channel state information (CSI) reference signal (CSI-RS); and a synchronization signal block (SSB). The SSB may be broadcast at regular intervals based on a periodicity (e.g., 5ms, 10ms, 20ms, 40ms, 80ms, or 160ms). The SSB includes a primary synchronization signal (PSS), a secondary synchronization signal (SSS), and a physical broadcast control channel (PBCH). The UE may use the PSS and SSS to achieve radio frame, subframe, time slot, and symbol synchronization in the time domain, identify the center of the channel (system) bandwidth in the frequency domain, and identify the physical cell identity (PCI) of the cell.

[0069] The PBCH in the SSB may also include a master information block (MIB) containing various system information and parameters for decoding a system information block (SIB). The SIB may be, for example, SystemInformationType 1 (SIB1), which may include various additional system information. The MIB and SIB1 together provide minimum system information (SI) for initial access. Examples of system information sent in the MIB may include, but are not limited to, subcarrier spacing (e.g., default downlink parameter set), system frame number, configuration of the PDCCH control resource set (CORESET) (e.g., PDCCH CORESET0), cell barring indicator, cell reselection indicator, grid offset, and search space for SIB1. Examples of remaining minimum system information (RMSI) sent in SIB1 may include, but are not limited to, random access search space, paging search space, downlink configuration information, and uplink configuration information. The base station may also send other system information (OSI).

[0070] In an UL transmission, a scheduled entity (e.g., a UE) may utilize one or more REs 306 to carry UL control information (UCI) including one or more UL control channels (such as a physical uplink control channel (PUCCH)) to a scheduling entity. UCI may include various packet types and categories, including pilots, reference signals, and information configured to enable or assist in decoding uplink data transmissions. Examples of uplink reference signals may include sounding reference signals (SRS) and uplink DMRS. In some examples, UCI may include a scheduling request (SR), i.e., a request for a scheduling entity to schedule an uplink transmission. In this document, in response to the SR sent on the UCI, the scheduling entity may send downlink control information (DCI), which may schedule resources for uplink packet transmissions. UCI may also include HARQ feedback, channel state feedback (CSF) (such as a CSI report), or any other appropriate UCI.

[0071] In addition to control information, one or more REs 306 (e.g., within the data region 314) may also be allocated for data services. Such data services may be carried on one or more service channels, such as on a physical downlink shared channel (PDSCH) for DL ​​transmissions, or on a physical uplink shared channel (PUSCH) for UL transmissions. In some examples, one or more REs 306 within the data region 314 may be configured to carry other signals, such as one or more SIBs and DMRS. In some examples, the PDSCH may carry multiple SIBs, not limited to the SIB1 discussed above. For example, OSI may be provided in these SIBs (e.g., SIB2 and above).

[0072] In an example of sidelink communication via a ProSe PC5 interface over a sidelink carrier, a control region 312 of a time slot 310 may include a physical sidelink control channel (PSCCH) including sidelink control information (SCI) sent by an initiating (transmitting) sidelink device (e.g., a Tx V2X device or other Tx UE) toward a set of one or more other receiving sidelink devices (e.g., an Rx V2X device or other Rx UE). A data region 314 of the time slot 310 may include a physical sidelink shared channel (PSSCH) including sidelink data traffic sent by the initiating (transmitting) sidelink device within resources reserved by the transmitting sidelink device via the SCI over the sidelink carrier. Other information may be further sent via various REs 306 within the time slot 310. For example, HARQ feedback information may be sent from a receiving sidelink device to a transmitting sidelink device in a physical sidelink feedback channel (PSFCH) within the time slot 310. Additionally, one or more reference signals may be sent within slot 310, such as a sidelink SSB, a sidelink CSI-RS, a sidelink SRS, and / or a sidelink positioning reference signal (PRS).

[0073] These physical channels described above are typically multiplexed and mapped to transport channels for processing at the medium access control (MAC) layer. The transport channels carry information blocks called transport blocks (TBs). Based on the modulation and coding scheme (MCS) and the number of RBs in a given transmission, the transport block size (TBS), which may correspond to the number of information bits, may be a controlled parameter.

[0074] Figure 3 The channels or carriers illustrated in the drawings are not necessarily all channels or carriers that may be utilized between devices, and one of ordinary skill in the art will recognize that other channels or carriers may be utilized in addition to the channels or carriers illustrated, such as other traffic, control, and feedback channels.

[0075] The deployment of a communication system (such as a 5G new NR system) can be arranged with various components or constituent parts in a variety of ways. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a RAN node, a core network node, a network element or a network equipment (such as a base station (BS), or one or more units (or one or more components) performing base station functions) can be implemented in an aggregated or decomposed architecture. For example, a BS (such as an NB, an eNB, an NR BS, a 5G NB, an access point (AP), a TRP or a cell, etc.) can be implemented as an aggregated base station (also called an independent BS or a monolithic BS) or a decomposed base station.

[0076] The aggregated base station may be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node (e.g., network entity 108). The decomposed base station may be configured to utilize a protocol stack physically or logically distributed between two or more units, such as one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs). In some aspects, the CU may be implemented within a RAN node, and one or more DUs may be co-located with the CU, or alternatively, may be geographically or virtually distributed in one or more other RAN nodes. The DU may be implemented to communicate with one or more RUs. Each of the CU, DU, and RU may also be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0077] Base station type operations or network designs may take into account the aggregated nature of base station functionality. For example, a disaggregated base station may be used in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (network configurations such as those initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which may enable flexibility in network design. Various units of a disaggregated base station or disaggregated RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0078] Figure 4 A diagram illustrating an example of a disaggregated base station architecture 400 is shown. The disaggregated base station architecture may include one or more central units (CUs) 410 that may communicate directly with a core network 420 via a backhaul link, or indirectly with the core network 420 through one or more disaggregated base station units, such as a near real-time (near-RT) RAN intelligent controller (RIC) 425 via an E2 link, or a non-real-time (non-RT) RIC 415 associated with a service management and orchestration (SMO) framework 405, or both. The CU 410 may communicate with one or more distributed units (DUs) 430 via respective midhaul links, such as an F1 interface. The DU 430 may communicate with one or more radio units (RUs) 440 via respective fronthaul links. The RU 440 may communicate with respective UEs 120 via one or more radio frequency (RF) access links. In some implementations, a UE 120 may be served simultaneously by multiple RUs 440.

[0079] Each of the units (i.e., CU 410, DU 430, RU 440, and near-RT RIC 425, non-RT RIC 415, and SMO framework 405) may include or be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of the units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, these units may include a wired interface configured to receive or send signals to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (such as a radio frequency (RF) transceiver) configured to receive or send signals or receive and send signals to one or more of the other units via a wireless transmission medium.

[0080] In some aspects, CU 410 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface configured to communicate signals with other control functions hosted by CU 410. CU 410 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, CU 410 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). As needed, CU 410 may be implemented to communicate with DU 430 for network control and signaling.

[0081] DU 430 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 440. In some aspects, DU 430 may host one or more of a radio link control (RLC) layer, a 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 a functional split, such as a functional split defined by the 3rd Generation Partnership Project (3GPP). In some aspects, DU 430 may further host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 430 or with control functions hosted by CU 410.

[0082] The lower layer functionality may be implemented by one or more RUs 440. In some deployments, a RU 440 controlled by a DU 430 may correspond to a logical node that hosts 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, based at least in part on a functional split (such as a lower layer functional split). In such an architecture, the RU 440 may be implemented to handle over-the-air (OTA) communications with one or more UEs 412. In some implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU 440 may be controlled by the corresponding DU 430. In some scenarios, this configuration may enable the implementation of the DU 430 and the CU 410 in a cloud-based RAN architecture (such as a vRAN architecture).

[0083] The SMO framework 405 may be configured to support RAN deployment and provisioning of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 405 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 405 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 490) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 410, DU 430, RU 440, and near-RT RIC 425. In some specific implementations, the SMO framework 405 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) 411) via the O1 interface. Additionally, in some specific implementations, the SMO framework 405 may communicate directly with one or more RUs 440 via the O1 interface. The SMO framework 405 may also include a non-RT RIC 415 configured to support the functionality of the SMO framework 405 .

[0084] The non-RT RIC 415 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence / machine learning (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 425. The non-RT RIC 415 may be coupled to or in communication with the near-RT RIC 425 (such as via an A1 interface). The near-RT RIC 425 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 410, one or more DUs 430, or both, and the O-eNB with the near-RT RIC 425.

[0085] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 425, the non-RT RIC 415 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 425 and may be received from a non-network data source or from a network function at the SMO framework 405 or the non-RT RIC 415. In some examples, the non-RT RIC 415 or the near-RT RIC 425 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 415 may monitor long-term trends and patterns for performance and employ AI / ML models to perform corrective actions via the SMO framework 405 (such as via reconfiguration of O1) or via creation of RAN management policies (such as A1 policies).

[0086] In some aspects of the present disclosure, a network entity (eg, a base station) and / or a scheduled entity (eg, a UE) may be configured for beamforming and / or multiple-input multiple-output (MIMO) techniques. Figure 5 An example of a wireless communication system 500 supporting MIMO is illustrated. In a MIMO system, a transmitter 502 includes multiple transmit antennas 504 (e.g., N transmit antennas), and a receiver 506 includes multiple receive antennas 508 (e.g., M receive antennas). Therefore, there are N×M signal paths 510 from the transmit antennas 504 to the receive antennas 508. Each of the transmitter 502 and the receiver 506 can be implemented, for example, within a network entity 108, a scheduled entity 106 (e.g., a UE), or any other suitable wireless communication device.

[0087] The use of such multi-antenna technology enables wireless communication systems to exploit the spatial domain to support spatial multiplexing, beamforming, and transmit diversity. Spatial multiplexing can be used to simultaneously send different data streams (also referred to as layers) on the same time-frequency resources. These data streams can be sent to a single UE to increase the data rate or to multiple UEs to increase the total system capacity, the latter of which is called multi-user MIMO (MU-MIMO). This can be achieved by spatially precoding each data stream (i.e., multiplying the data stream by different weights and phase shifts) and then sending each spatially precoded stream through multiple transmit antennas on the downlink. The spatially precoded data streams arrive at UEs with different spatial characteristics, and the different spatial characteristics enable each UE in the UE to recover one or more data streams destined for the UE. On the uplink, each UE sends a spatially precoded data stream, which enables the base station to identify the source of each spatially precoded data stream.

[0088] The number of data streams or layers corresponds to the rank of transmission. In general, the rank of the MIMO system 500 is limited to the lower of the number of transmit or receive antennas 504 or 508. In addition, the channel conditions at the UE and other considerations (such as the available resources at the base station) can also affect the transmission rank. For example, the rank assigned to a specific UE on the downlink (and therefore the number of data streams) can be determined based on a rank indicator (RI) sent from the UE to the base station. The RI can be determined based on the antenna configuration (e.g., the number of transmit antennas and receive antennas) on each receive antenna in the receive antenna and the measured signal to interference and noise ratio (SINR). For example, the RI can indicate the number of layers that can be supported under the current channel conditions. The base station can use the RI and resource information (e.g., the available resources and amount of data to be scheduled for the UE) to assign the rank of transmission to the UE.

[0089] In a time division duplex (TDD) system, UL and DL are reciprocal because they each use different time slots of the same frequency bandwidth. Therefore, in a TDD system, the base station can allocate a rank for DL ​​MIMO transmission based on UL SINR measurements (e.g., based on a sounding reference signal (SRS) or other pilot signal sent from the UE). Based on the assigned rank, the base station can then send a CSI-RS with a separate C-RS sequence for each layer to provide multi-layer channel estimation. The UE can measure the channel quality across each layer and each resource block based on the CSI-RS, and feed back the RI and channel quality indicator (CQI) (which indicates to the base station the modulation and coding scheme (MCS) to be used for transmission to the UE) to the base station for updating the rank and allocating REs for future downlink transmissions.

[0090] In the simplest case, Figure 5 As shown in , rank 2 spatial multiplexing transmission on a 2x2 MIMO antenna configuration, one data stream is sent from each transmit antenna 504. Each data stream follows a different signal path 510 to each receive antenna 508. The receiver 506 can then use the received signal from each receive antenna 508 to reconstruct the data stream.

[0091] Beamforming is a signal processing technique that can be used at a transmitter 502 or a receiver 506 to shape or direct an antenna beam (e.g., a transmit beam or a receive beam) along a spatial path between the transmitter 502 and the receiver 506. Beamforming can be achieved by combining signals communicated via antennas 504 or 508 (e.g., antenna elements of an antenna array module) so that some of the signals experience constructive interference and other signals experience destructive interference. In order to produce the desired constructive / destructive interference, the transmitter 502 or the receiver 506 may apply an amplitude and / or phase offset to the signal transmitted or received from each of the antennas 504 or 508 associated with the transmitter 502 or the receiver 506.

[0092] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5GNR, two initial operating bands have been identified as frequency range designations FR1 (410 MHz–7.125 GHz) and FR2 (24.25 GHz–52.6 GHz). It should be understood that, although portions of FR1 are greater than 6 GHz, FR1 is often (interchangeably) referred to as the “below 6 GHz” band in various documents and articles. A similar naming problem sometimes occurs with respect to FR2, which is often (interchangeably) referred to as the “millimeter wave” band in documents and articles, although different from the extremely high frequency (EHF) band (30 GHz–300 GHz) identified as the “millimeter wave” band by the International Telecommunication Union (ITU).

[0093] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as frequency range designation FR3 (7.125GHz–24.25GHz). The bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, and therefore the features of FR1 and / or FR2 can be effectively extended to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to more than 52.6GHz. For example, three higher operating bands have been identified as frequency range designations FR4-a or FR4-1 (52.6GHz-71GHz), FR4 (52.6GHz-114.25GHz) and FR5 (114.25GHz-300GHz). Each of these higher frequency bands falls within the EHF band.

[0094] In view of the above aspects, unless otherwise specifically stated, it should be understood that if the term "below 6 GHz" or the like is used herein, it can be broadly referred to as a frequency that may be less than 6 GHz, may be within FR1, or may include mid-band frequencies. In addition, unless otherwise specifically stated, it should be understood that if the term "millimeter wave" or the like is used herein, it can be broadly referred to as a frequency that may include mid-band frequencies, may be within FR2, FR4, FR4-a or FR4-1 and / or FR5, or may be within the EHF band.

[0095] In 5G NR systems, especially for FR2 (millimeter wave) systems, beamformed signals can be used for most downlink channels, including PDCCH and PDSCH. In addition, broadcast control information (such as synchronization signal blocks (SSBs), slot format indicators (SFIs), and paging information) can be sent in a beam scanning manner so that all UEs in the coverage area of ​​the network entity (e.g., TRP, gNB) can receive the broadcast control information. In addition, for UEs configured with beamforming antenna arrays, beamformed signals can also be used for uplink channels (including PUCCH and PUSCH). In addition, beamformed signals can also be used in D2D systems (such as NR sidelink (SL) or V2X, which utilize FR2).

[0096] Figure 6 is a diagram illustrating an example of a multi-TRP environment 600 according to some aspects. The multi-TRP environment 600 includes multiple cells 602 and 606a-606d. In some examples, one of the cells 602 can be considered a primary serving cell (PCell) 602, and the remaining cells 606a, 606b, 606c, and 306d can be considered secondary serving cells (SCells). The PCell 602 can be referred to as an anchor cell that provides a radio resource control (RRC) connection with a UE. In some examples, the PCell and the SCell can be co-located (e.g., different TRPs at the same geographic location and coupled to the same antenna tower / pole).

[0097] When carrier aggregation is configured, one or more of the SCells 606a to 606d may be activated or added to the PCell 602 to form a serving cell serving the UE 610. Each serving cell corresponds to a component carrier (CC). The CC of the PCell 602 may be referred to as a primary CC, and the CCs of the SCells 606a to 606d may be referred to as secondary CCs. The PCell 602 and one or more of the SCells 606a to 606d may be composed of Figure 2 and Figure 4Any TRP in the TRPs illustrated in FIG. 6A is served by a similar corresponding TRP 604 and 608a to 608c. Figure 6 In the example shown in , SCells 606a to 606c are each served by a corresponding non-co-located TRP 608a to 608c. However, SCell 606d is co-located with PCell 602. Therefore, TRP 604 may include two co-located TRPs, each supporting a different carrier. For example, TRP 604 may correspond to a base station including multiple co-located TRPs. The coverage of PCell 602 and SCell 606d may be different because different component carriers (which may be in different frequency bands) may experience different path losses.

[0098] In some examples, PCell 602 may add or remove one or more of SCells 606a-606d to improve reliability and / or increase data rates of a connection with UE 610. PCell 602 may be changed when handing over to another PCell.

[0099] In some examples, one of the cells (e.g., cell 602) may be a low-band cell, and the other cell (e.g., cell 606d) may be a high-band cell. The low-band cell uses a carrier frequency in a frequency band lower than that of the high-band cell. For example, a high-band cell may use a high-band millimeter wave carrier (e.g., FR4-a or FR4-1 or above), while a low-band cell may use a low-band millimeter wave carrier (e.g., FR2). In this example, depending on whether cross-band carrier aggregation is supported, carrier aggregation may not be performed between cells 602 and 606d. In addition, when a millimeter wave carrier (e.g., FR2 or above) is used, beamforming may be used to send and receive signals.

[0100] Artificial Intelligence and Machine Learning (AI / ML) for Air Interfaces

[0101] In some aspects, artificial intelligence and machine learning (AI / ML) can be used for wireless communications, such as the operation of the air interface between the network (e.g., RAN200) and the UE. In some aspects, the AI / ML enhanced air interface can have enhanced performance and / or reduced complexity and overhead. For example, an air interface (e.g., 5G NR) using AI / ML can have improved throughput, robustness, accuracy, reliability, etc. In one aspect, AI / ML models can be used for CSI feedback enhancement, such as reduced overhead, improved accuracy, and prediction. In one aspect, AI / ML models can be used for beam management, such as beam prediction in the time domain and / or spatial domain, reduced overhead and latency, improved beam selection accuracy, etc. In one aspect, AI / ML models can be used for positioning accuracy enhancement in various scenarios, including, for example, conditions with significant non-line-of-sight conditions.

[0102] The application of AI / ML models in wireless communications may involve various processes, such as model training, model inference, model verification, model testing, model activation, model deactivation, and model switching. In some aspects, in different use cases of AI / ML models, UE and network entities (e.g., base stations, gNBs, etc.) may have different levels of collaboration. In one aspect, no collaboration occurs between the UE and the network entity to use the AI / ML model. In this case, the UE and / or the network entity may implement the corresponding AI / ML model or algorithm without information exchange. In one aspect, signaling-based collaboration may be used without model transfer. For example, the UE may use signaling with a network entity to support training, inference, and / or verification of a predetermined AI / ML model without transferring or downloading the AI / ML model from the network. In one aspect, signaling-based collaboration may be used in the case of AI / ML model transfer.

[0103] AI / ML model training is a process for training an AI / ML model in a data-driven manner (e.g., by learning the input / output relationship of the model) and obtaining a trained AI / ML model for inference. AI / ML model inference is the process of using a trained AI / ML model to produce a set of outputs based on a set of inputs. AI / ML verification is the process of evaluating the quality of an AI / ML model using a dataset different from the one used for model training. This process can help select model parameters that generalize beyond the dataset used for model training.

[0104] AI / ML model testing is a process for evaluating the performance of an applied AI / ML model using a dataset different from the one used for model training and verification. Unlike the AI / ML model verification process, model testing may not perform post-tuning of the model. AI / ML model activation is a process for enabling an AI / ML model. AI / ML model deactivation is a process for disabling an AI / ML model. AI / ML model switching is a process for deactivating a currently active AI / ML model and activating a different AI / ML model.

[0105] When the UE and the network entity (e.g., base station, gNB, CU, DU, TRP) collaborate to select an AI / ML model for wireless communication, the UE may perform various processes and collect data at the request of the network entity. The collected data may be reported to the network entity. Before applying an AI / ML model (e.g., a model downloaded from a network entity or pre-configured), the UE may perform various processes, such as model training and / or verification. For example, the UE and the network entity may check the performance of a newly updated / downloaded AI / ML model before applying it to normal operations.

[0106] However, some UEs may have limited processing power, memory and / or resources. In some cases, when performing the above-mentioned AI / ML model-related functions or processes (e.g., data collection, training, verification, compilation, switching, etc.), the UE may not be able to perform wireless communication operations (e.g., DL reception and / or UL transmission). For example, UE constraints (e.g., time / frequency resources, physical channel / signal usage, communication direction (DL / UL), etc.) may depend on the AI / ML model and / or the purpose or use of the AI / ML model (e.g., L1 and / or L3 measurements, beam management, CSI reporting, positioning, etc.). In some aspects, the UE may deprioritize some processes or operations commonly used for wireless communication at the UE in order to perform some AI / ML model-related functions (e.g., training, inference, verification, testing, activation, deactivation, switching, compilation, etc.). To this end, the UE or scheduled entity may perform AI / ML model-related functions ("model functions") in one or more configured time slots, in which the UE may deprioritize some normally performed wireless communication functions.

[0107] Time slots for AI / ML model operations

[0108] Figure 7 is a diagram illustrating exemplary time slots configured for performing AI / ML model-related functions according to some aspects of the present disclosure. Figure 7A timeline 700 is illustrated in which a UE may communicate with a network entity (e.g., a base station, gNB, TRP, CU, DU, etc.) in a RAN (e.g., RAN 200, NG-RAN, O-RAN, etc.) using normally executed or scheduled RAN functions 702 (e.g., DL and / or UL communications, measurements and reporting, etc.) or an air interface. In some aspects, the UE may communicate with a network entity (e.g., a base station, gNB, TRP, CU, DU, etc.) in one or more AI / ML model time slots 704 (e.g., Figure 7 In some aspects, the UE may be configured with one or more aperiodic and / or periodic AI / ML model time slots 704.

[0109] Examples of AI / ML model functions include model training, model inference, model verification, model testing, model compilation, model activation, model deactivation, and model switching. In some cases, due to UE limitations (e.g., UE data / signal processing capabilities and / or resource limitations), the UE may deprioritize some normally executed or scheduled RAN functions (e.g., PDCCH / PDSCH reception, PUCCH / PUSCH transmission, channel / beam / signal measurement, CSI reporting, etc.) in one or more AI / ML model time slots. Deprioritizing certain RAN functions can reduce resources and / or processing requirements at the UE, so that the UE can save processing power and / or resources to perform one or more AI / ML model functions as described above. Unlike measurement gaps typically used for cell measurements (e.g., legacy measurement gaps), each AI / ML model time slot 704 can be selectively configured for one or more specific carriers, SCells, BWPs, and / or RAN functions. That is, if the AI / ML model time gap 704 is configured for a subset of carriers, BWPs, or RAN functions used by the UE, the UE may use the carriers / BWPs and / or perform RAN functions that are not configured with the AI / ML model time gap.

[0110] In some aspects, an AI / ML model time gap (e.g., a training gap) may be defined by a gap pattern including a gap offset, a gap duration, and a gap periodicity (for periodic time gaps). The gap offset is the first subframe of each time gap occurring at the system frame number (SFN) and the subframe that satisfies the following conditions: SFN mod T = FLOOR (gap offset / L); subframe = gap offset mod L; where T = gap periodicity / L. L may be 10 or any preconfigured value. The gap offset and gap duration for non-periodic AI / ML time gaps may be dynamically scheduled by the network using DCI and / or MAC CE signaling.

[0111] Figure 8800 is a flowchart illustrating a process of deprioritizing RAN functions in an AI / ML model time gap according to some aspects. At 802, the UE may temporarily deactivate one or more SCells (or associated CCs) in an AI / ML model time gap. In one aspect, the deactivated SCell may not include an SCell associated with a PUCCH or an SCell associated with a PRACH configuration. At 804, the UE may temporarily change the BWP configuration to reduce processing and / or resource usage. For example, the UE may switch from an active BWP to a dormant BWP or a narrower BWP. In a dormant BWP, some RAN operations may be restricted, suspended, or subject to one or more constraints. For example, the UE may not receive a PDCCH and / or PDSCH from a deactivated SCell, and the UE may not send a PUCCH or PUSCH to a deactivated SCell. In addition, using a dormant BWP or a narrower BWP, the UE may reduce the need for processing power and / or resources (e.g., time, frequency, and / or spatial resources). Therefore, the UE can reuse available processing power (e.g., computing power and / or memory) and communication resources (e.g., time, frequency and / or space resources) for AI / ML model related functions.

[0112] In other aspects, the UE may Figure 8 1. The UE may deactivate the SCell and / or change the BWP configuration in various orders and manners different from the order and manner illustrated in . In one example, the UE may first change the BWP configuration and then deactivate the SCell. In one example, the UE may only change the BWP configuration or deactivate the SCell. After the time gap has passed, the UE may resume normal RAN operation. For example, the UE may reactivate the deactivated SCell and / or restore the previous BWP configuration.

[0113] Fig. 9 is a flow chart illustrating a process 900 of performing AI / ML model related functions in an AI / ML model time gap. In an AI / ML model time gap, a network entity (e.g., a base station, a gNB) may transmit certain signals (e.g., a PDCCH, a PDSCH, and / or reference signals) to a UE to facilitate various AI / ML model related functions performed at the UE and / or the network entity.

[0114] At 902, the network entity may transmit a PDCCH / PDSCH transmission and / or DL ​​signal configured for AI / ML model-related functions (e.g., model training, model compilation, model validation, and / or model switching). In some aspects, the network entity may configure and transmit PDCCH / PDSCH transmissions in specific or predetermined formats that can be recognized and used by the UE to perform AI / ML model-related functions (e.g., model training, model testing, model verification, etc.) during the AI / ML model time gap. In some aspects, the network entity may transmit specific reference signals (e.g., non-cell defined SSB (NCD-SSB), CSI-RS, etc.) that can be used by the UE for AI / ML model-related functions. These AI / ML model-related PDCCH / PDSCH and / or DL ​​signals can be used by all UEs for, for example, AI / ML model training (e.g., learning, parameter tuning) and / or model validation and testing.

[0115] In the AI / ML model time gaps, the network entity may discard or ignore UE feedback that may be sent by the UE in response to AI / ML related DL signals or PDCCH / PDSCH transmissions, such as ACK / NACK feedback, measurement reports, CSI reports, etc. However, in legacy or normal measurement gaps not related to the AI / LM model, the UE may not receive PDCCH / PDSCH and may skip UL transmissions.

[0116] In some aspects, the UE may be configured not to transmit corresponding feedback (e.g., ACK / NACK) to a PDCCH / PDSCH specifically configured for AI / ML model-related functions. In some aspects, the UE may be configured not to transmit reports (e.g., measurements, CSI reports, etc.) corresponding to DL signals configured for AI / ML model-related functions. In some aspects, at 904, the network entity may configure the UE to transmit a report for AI / ML model-related functions performed in the time slot, for example, based on the PDCCH / PDSCH and / or DL ​​signals received in the time slot. For example, the report may include data for facilitating certain AI / ML model functions (e.g., model selection, training results (e.g., reliability level of the model), verification, etc.).

[0117] In some aspects, during the AI / ML model-related time gap, the UE may be configured to perform AI / ML model-related functions in a specific cell (e.g., a serving cell). That is, the UE may select certain cells (i.e., not all cells) to perform AI / ML-related functions. In one example, the UE may be configured not to monitor the PDCCH in the cell used for the AI / ML model-related functions. To this end, the PDCCH may be scrambled by an identifier (e.g., a radio network temporary identifier (RNTI)) or allocated in a specific search space resource set. In one example, the UE may be configured not to demodulate the PDSCH in the cell used for the AI / ML model-related functions. The PDSCH may have a rank higher than a predetermined rank (e.g., rank 2 or greater) and / or more RBs than a predetermined number of RBs. In some aspects, during the AI / ML model-related time gap, the UE may demodulate the PDSCH using a rank lower than a predetermined rank and / or a predetermined number of RBs. In one example, in a cell used for AI / ML model-related functions, the UE may be configured not to send uplink channels / signals (e.g., PUCCH / PUSCH) other than channels / signals used for AI / ML model functions (e.g., AI / ML model compilation report, model switching completion, etc.).

[0118] In some aspects, the above-described behavior of the UE and / or network entity in the AI / ML model time slot may be different in different time slots (e.g., training time slots, compilation time slots, and model switching time slots). In one example, if the UE downloads the AI / ML model from the network, the UE may have to compile the AI / ML model into executable code. In this case, the UE may be configured to use the model compilation time slot. In one example, the UE may be configured to use the model switching time slot to switch between AI / ML models or replace a previously activated AI / ML model.

[0119] AI / ML model time gap configuration

[0120] Fig.10 is a signaling diagram illustrating an exemplary signaling process 1000 for configuring AI / ML model time slots in a wireless network between a network entity 1002 and a UE 1004. In some aspects, the network entity 1002 may configure one or more AI / ML model time slots (e.g., a model training time slot, a model compilation time slot, and a model switching time slot) to the UE 1004.

[0121] At 1006, the network entity 1002 may transmit the AI / ML time gap configuration to the UE 1004, for example, using RRC signaling. The network entity 1002 may configure one or more aperiodic and / or periodic AI / ML model time gaps (e.g., Figure 7 The UE may use multiple AI / ML models, and each AI / ML model may be associated with one or more configured AI / ML model time slots. For example, the UE may use the time slots for various AI / ML model related processing or AI / ML model related functions (e.g., training, validation, compilation, and / or switching).

[0122] At 1008, the UE may use the configured AI / ML model time slot to perform AI / ML model related functions. The association between the AI / ML model and the time slot may be pre-configured (e.g., by an original equipment manufacturer (OEM) based on one or more standards or specifications) or configured by a network entity. For example, at 1010, the network entity 1002 may select an AI / ML model time slot for performing AI / ML model related functions by transmitting a time slot selection message (e.g., a MAC control element (MAC-CE) or a DCI) to the UE. In some aspects, when multiple AI / ML model time slots are configured for an associated AI / ML model, the UE may select an AI / ML model time slot without receiving an indication from the network entity.

[0123] At 1012, after performing AI / ML model related functions (e.g., model training, validation, testing, etc.), the UE may transmit an AI / ML report to the network entity 1002. For example, the AI / ML report may include data used to facilitate certain AI / ML model functions (e.g., model selection, training results (e.g., reliability level of the model), verification, etc.). For example, the UE may transmit the AI / ML report in a PUCCH or PUSCH transmission. In some aspects, the UE may not transmit the AI / ML report after performing some AI / ML model related functions (e.g., model compilation and model switching, etc.).

[0124] At 1014, the UE may explicitly request a time gap by transmitting a message to the network entity. For example, the UE may transmit a request (e.g., Need for Gap) using UCI or MAC CE. At 1016, the network entity may query the UE whether the UE requires a time gap (e.g., a non-periodic time gap) and / or a time gap pattern (e.g., a periodic time gap) to perform AI / ML model related functions. For example, the query may indicate conditions under which the UE may require a time gap to perform the AI / ML model function. For example, the condition may indicate an AI / ML model and memory / computational complexity related parameters required to perform the AI / ML function, such as carrier aggregation, BWP, MIMO configuration, etc. Based on the indicated conditions, the UE may decide whether a time gap will be required to perform the AI / ML model related functions.

[0125] In some aspects, the network entity 1002 may provide a set of parameters (e.g., RRC parameters) to the UE for use in the AI / ML model time gap while performing AI / ML model related functions at 1018. For example, the RRC parameter set may include a discontinuous reception (DRX) configuration, a MIMO configuration, a CSI measurement and reporting configuration, etc. that enables the UE to deprioritize some normally performed RAN related or air interface functions (e.g., skip PDCCH monitoring, reduce processing power for MIMO decoding and / or CSI calculation, etc.).

[0126] Fig.11 1 is a block diagram illustrating an example of a hardware implementation for a user equipment (UE) 1100 that employs a processing system 1114. For example, the UE 1100 may be Figure 1 , Figure 2 , Figure 4 , Figure 6 and / or Fig.10 A user equipment (UE) is illustrated in any one or more of the embodiments.

[0127] The UE 1100 may be implemented using a processing system 1114 including one or more processors 1104. Examples of the processor 1104 include a microprocessor, a microcontroller, a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a state machine, a gated logic element, a discrete hardware circuit, and other suitable hardware configured to perform various functionalities described throughout the present disclosure. In various examples, the UE 1100 may be configured to perform any one or more of the functions described herein. That is, the processor 1104 as utilized in the UE 1100 may be used to implement the various functions described in the present disclosure. Figures 7 to 10 and Fig.12 Any one or more of the processes and procedures described and illustrated in .

[0128] In some instances, the processor 1104 may be implemented via a baseband or modem chip, and in other implementations, the processor 1104 may include multiple devices distinct and different from the baseband or modem chip (e.g., in scenarios such as those that may work together to implement the examples discussed herein). And as mentioned above, various hardware arrangements and components outside of the baseband modem processor may be used in implementations, including RF chains, power amplifiers, modulators, buffers, interleavers, adders / summers, etc.

[0129] In this example, the processing system 1114 may be implemented using a bus architecture (roughly represented by bus 1102). The bus 1102 may include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the processing system 1114. The bus 1102 communicatively couples various circuits including one or more processors (roughly represented by processor 1104), memory 1105, and computer-readable media (roughly represented by computer-readable media 1106). The bus 1102 may also link various other circuits, such as timing sources, peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further. The bus interface 1108 provides an interface between the bus 1102 and the transceiver 1110. The transceiver 1110 and the antenna array 1120 (e.g., one or more antennas) provide a communication interface or component for communicating with various other devices through a transmission medium. Depending on the nature of the device, a user interface 1112 (e.g., a keypad, display, speaker, microphone, joystick, touch screen) may also be provided. Of course, such a user interface 1112 is optional and may be omitted in some examples (such as a base station).

[0130] The processor 1104 is responsible for managing the bus 1102 and general processing, which includes executing software stored on a computer-readable medium 1106. The software, when executed by the processor 1104, causes the processing system 1114 to perform the various functions described herein for any particular device. The computer-readable medium 1106 and memory 1105 may also be used to store data (e.g., AI / ML models 1122 and associated data 1123) that are manipulated by the processor 1104 when executing the software.

[0131] One or more processors 1104 in the processing system can execute software. Software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language or other. Software can reside on computer-readable media 1106. Computer-readable media 1106 can be non-transient computer-readable media. By way of example, non-transient computer-readable media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips), optical disks (e.g., compact discs (CDs) or digital versatile discs (DVDs)), smart cards, flash memory devices (e.g., cards, sticks or key drives), random access memory (RAM), read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), registers, removable disks, and any other suitable media for storing software and / or instructions that can be accessed and read by a computer. The computer readable medium 1106 may reside in the processing system 1114, be external to the processing system 1114, or be distributed across multiple entities including the processing system 1114. The computer readable medium 1106 may be embodied in a computer program product. By way of example, a computer program product may include a computer readable medium in packaging materials. Those skilled in the art will recognize how to best implement the described functionality presented throughout this disclosure, depending on the specific application and the overall design constraints imposed on the overall system.

[0132] In some aspects of the present disclosure, the processor 1104 may include circuitry configured for various functions, including, for example, AI / ML model-related functions for wireless communications in a RAN (e.g., RAN 200 and RAN 400). For example, the circuitry may be configured to implement the present disclosure with respect to Figures 7 to 10 and Fig.12 One or more of the functions described.

[0133] In some aspects of the present disclosure, the processor 1104 may include communication and processing circuitry 1140 configured for various functions, including, for example, communicating with a network entity (e.g., a base station, gNB, CU, DU, RU, TRP) or any other entity. In some examples, the communication and processing circuitry 1140 may include one or more hardware components that provide a physical structure that performs processes related to wireless communication (e.g., signal reception and / or signal transmission) and signal processing (e.g., processing received signals and / or processing signals for transmission). For example, the communication and processing circuitry 1140 may include one or more transmit / receive chains. In addition, the communication and processing circuitry 1140 may be configured to send and process uplink traffic and uplink control messages (e.g., with Figure 1 The communication and processing circuit 1140 may be configured to receive and process downlink traffic and downlink control messages (e.g., similar to downlink traffic 112 and downlink control 114) and receive and process downlink traffic and downlink control messages (e.g., similar to downlink traffic 112 and downlink control 114). The communication and processing circuit 1140 may be further configured to execute communication and processing software 1150 stored on the computer-readable medium 1106 to implement one or more functions described herein.

[0134] In some implementations where the communication involves receiving information, the communication and processing circuit 1140 may obtain information from a component of the UE 1100 (e.g., from a transceiver 1110 that receives information via radio frequency signaling or some other type of signaling suitable for an applicable communication medium), process (e.g., decode) the information, and output the processed information. For example, the communication and processing circuit 1140 may output the information to another component of the processor 1104, to the memory 1105, or to the bus interface 1108. In some examples, the communication and processing circuit 1140 may receive one or more of a signal, a message, other information, or any combination thereof. In some examples, the communication and processing circuit 1140 may receive information via one or more channels. In some examples, the communication and processing circuit 1140 may include functionality for components for receiving. In some examples, the communication and processing circuit 1140 may include functionality for components for processing, including components for demodulation, components for decoding, and the like.

[0135] In some implementations where the communication involves transmitting (e.g., sending) information, the communication and processing circuitry 1140 may obtain the information (e.g., from another component of the processor 1104, the memory 1105, or the bus interface 1108), process (e.g., modulate, encode, etc.) the information, and output the processed information. For example, the communication and processing circuitry 1140 may output the information to the transceiver 1110 (e.g., it transmits the information via radio frequency signaling or some other type of signaling suitable for the applicable communication medium). In some examples, the communication and processing circuitry 1140 may transmit one or more of a signal, a message, other information, or any combination thereof. In some examples, the communication and processing circuitry 1140 may transmit information via one or more channels. In some examples, the communication and processing circuitry 1140 may include functionality for components for transmitting (e.g., components for sending). In some examples, the communication and processing circuitry 1140 may include functionality for components for generating, including components for modulating, components for encoding, and the like.

[0136] In some aspects, the communication and processing circuit 1140 may be configured to deprioritize wireless communication or RAN functions to increase available resources and / or processing power for performing AI / ML model-related functions as described herein. For example, AI / ML model-related functions may include model compilation, model training, model inference, model verification, model testing, model activation, model deactivation, model switching, etc. In one aspect, the communication and processing circuit 1140 may deprioritize UL and / or DL ​​communications, for example, by deactivating communications with one or more SCells during an AI / ML model time gap. In one aspect, the communication and processing circuit 1140 may temporarily change the BWP configuration to reduce processing and / or resource usage. For example, the UE may switch from an active BWP to a dormant BWP or a narrower BWP.

[0137] In some aspects of the present disclosure, the processor 1104 may include an AI / ML model circuit 1142, which may be configured to perform various AI / ML model-related functions in one or more AI / ML model time slots. For example, the AI / ML model circuit 1142 may be configured to perform model compilation, model training, model inference, model verification, model testing, model activation, model deactivation, model switching, etc. of one or more AI / ML models. For example, one or more AI / ML models 1122 and associated AI / ML data 1123 may be stored in the memory 1105. The AI / ML model 1122 may be downloaded and / or predefined from a network entity. The UE may perform AI / ML model-related functions ("model functions") in one or more time slots, in which the UE may de-prioritize some wireless communication functions to save additional resources and / or processing power. The AI / ML model circuit 1142 may be further configured to execute the AI / ML model software 1152 stored on the computer-readable medium 1106 to implement one or more functions described herein.

[0138] Fig.12 is a flow chart illustrating an exemplary process 1200 for performing AI / ML model-related functions at a UE according to some aspects. As described below, some or all of the illustrated features may be omitted in certain implementations within the scope of the present disclosure, and some of the illustrated features may not be required for all example implementations. In some examples, the process 1200 may be performed by Fig.11 In some examples, process 1200 may be implemented by any suitable device or component for implementing the functions or algorithms described below.

[0139] At block 1202, the UE may provide one or more time slots associated with an artificial intelligence and machine learning (AI / ML) model for communicating with a network entity. For example, the one or more time slots may be associated with the above-described Figure 7 The AI / ML model circuit 1142 may be configured to provide one or more time slots. The time slot 704 enables the UE to communicate with the network entity using the AI / ML model. In one example, the AI / ML model may be used for CSI feedback enhancements, such as overhead reduction, improved accuracy, and prediction. In one example, the AI / ML model may be used for beam management, such as beam prediction in the time domain and / or spatial domain, overhead and latency reduction, improved beam selection accuracy, etc. In one example, the AI / ML model may be used for positioning accuracy enhancement in various scenarios, including, for example, conditions with significant non-line-of-sight conditions.

[0140] At box 1204, the UE may deprioritize at least one of UL communications or DL ​​communications with the network entity in one or more time slots. In one aspect, the communication and processing circuit 1140 may be configured as a component for deprioritizing UL and / or DL ​​communications with the network entity. In one example, deprioritizing UL and / or DL ​​communications may include deactivating communications with one or more SCells in the AI / ML model time slot. In one example, the deactivated SCell may not include an SCell associated with a PUCCH or an SCell with a PRACH configuration. In one example, deprioritizing UL and / or DL ​​communications may include temporarily changing the BWP configuration to reduce processing and / or resource usage. For example, the UE may switch from an active BWP to a dormant BWP or a narrower BWP.

[0141] At box 1206, the UE may perform one or more AI / ML model-related processes in one or more time slots. In one aspect, the AI / ML model circuit 1142 may be configured as a component for performing one or more AI / ML model-related processes. In one example, the UE may receive a PDCCH / PDSCH transmission and / or a specific DL signal configured for an AI / ML model-related process (e.g., compilation, training, compilation, verification, switching, etc.). In some aspects, a network entity (e.g., a base station, a gNB, a TRP) may configure and transmit a PDCCH / PDSCH signal in a predetermined format that may be recognized by the UE and used to perform AI / ML model-related functions in an AI / ML model time slot. In one example, the UE may receive a non-cell-defined SSB (NCD-SSB), CSI-RS, etc. that may be used for AI / ML model-related functions. These PDCCH / PDSCH and / or DL ​​signals may be used, for example, for AI / ML model training (e.g., learning, parameter tuning) and / or model verification and testing.

[0142] In one configuration, the UE 1100 for wireless communication includes components for performing AI / ML model related processes and functions in the configured AI / ML model time slot. In one aspect, the aforementioned components may be Fig.11 The processor 1104 shown in FIG. 1 is configured to perform the functions recited by the aforementioned components. On the other hand, the aforementioned components may be a circuit or any device configured to perform the functions recited by the aforementioned components.

[0143] Of course, in the above examples, the circuits included in the processor 1104 are provided only as examples, and other components for implementing the described functions may be included in various aspects of the present disclosure, including but not limited to storage in the computer-readable storage medium 1106 or in Figure 1 , Figure 2 , Figure 4 , Figure 6 and / or Fig.10 In any other suitable device or component described in any of the foregoing and utilizing, for example, Figures 7 to 10 and / or Fig.12 Instructions that describe a process and / or algorithm.

[0144] Fig.13 1304 is a diagram illustrating an example of a hardware implementation for an exemplary network entity 1300 employing a processing system 1314. According to various aspects of the present disclosure, an element or any portion of an element or any combination of elements may be implemented using a processing system 1314 including one or more processors 1304. For example, the network entity 1300 may be such as Figure 1 , Figure 2 , Figure 4 , Figure 6 and / or Fig.10 A network entity exemplified in any one or more of .

[0145] Processing system 1314 can be used with Fig.11 The processing system 1114 illustrated in FIG. 1 is substantially the same as that in FIG. 1 , including a bus interface 1308, a bus 1302, a memory 1305, a processor 1304, and a computer-readable medium 1306. In addition, the network entity 1300 may include the same as that described above in FIG. Fig.11 The user interface 1312 (optional) and transceiver 1310 are substantially similar to the user interface and transceiver described in . The transceiver 1310 and antenna array 1320 (e.g., one or more antennas) provide communication interfaces or components for communicating with various other devices over a transmission medium. The processor 1304, as utilized in the network entity 1300, may be used to implement the methods described herein and in, for example, Figures 7 to 10 and Fig.14 Any one or more of the processes illustrated in .

[0146] In some aspects of the present disclosure, processor 1304 may include circuitry configured for various functions, including, for example, AI / ML model-related functions in wireless communications. For example, the circuitry may be configured to implement Figures 7 to 10 and Fig.14 One or more of the functions described.

[0147] In some aspects of the present disclosure, the processor 1304 may include communication and processing circuitry 1340 configured for various functions, including, for example, communicating with a UE, another network entity (e.g., a base station, gNB, CU, DU, RU, TRP), or any other entity. In some examples, the communication and processing circuitry 1340 may include one or more hardware components that provide a physical structure that performs processes related to wireless communication (e.g., signal reception and / or signal transmission) and signal processing (e.g., processing received signals and / or processing signals for transmission). For example, the communication and processing circuitry 1340 may include one or more transmit / receive chains. In addition, the communication and processing circuitry 1340 may be configured to receive and process uplink traffic and uplink control messages (e.g., with Figure 1 The communication and processing circuit 1340 may be configured to execute communication and processing software 1350 stored on the computer-readable medium 1306 to implement one or more functions described herein.

[0148] In some implementations where the communication involves receiving information, the communication and processing circuitry 1340 may obtain information from a component of the network entity 1300 (e.g., from a transceiver 1310 that receives information via radio frequency signaling or some other type of signaling suitable for an applicable communication medium), process (e.g., decode) the information, and output the processed information. For example, the communication and processing circuitry 1340 may output the information to another component of the processor 1304, to the memory 1305, or to the bus interface 1308. In some examples, the communication and processing circuitry 1340 may receive one or more of a signal, a message, other information, or any combination thereof. In some examples, the communication and processing circuitry 1340 may receive information via one or more channels. In some examples, the communication and processing circuitry 1340 may include functionality for components for receiving. In some examples, the communication and processing circuitry 1340 may include functionality for components for processing, including components for demodulating, components for decoding, and the like.

[0149] In some implementations where the communication involves transmitting (e.g., sending) information, the communication and processing circuit 1340 may obtain the information (e.g., from another component of the processor 1304, the memory 1305, or the bus interface 1308), process (e.g., modulate, encode, etc.) the information, and output the processed information. For example, the communication and processing circuit 1340 may output the information to the transceiver 1310 (e.g., it transmits the information via radio frequency signaling or some other type of signaling suitable for the applicable communication medium). In some examples, the communication and processing circuit 1340 may transmit one or more of a signal, a message, other information, or any combination thereof. In some examples, the communication and processing circuit 1340 may transmit information via one or more channels. In some examples, the communication and processing circuit 1340 may include functionality for components for transmitting (e.g., components for sending). In some examples, the communication and processing circuit 1340 may include functionality for components for generating, including components for modulating, components for encoding, and the like.

[0150] In some aspects, the communication and processing circuit 1340 may be configured to deprioritize some communication or RAN functions and processes at the UE to increase the resources and / or processing capabilities available at the UE to perform one or more AI / ML model-related functions as described herein. For example, AI / ML model-related functions may include compilation, training, inference, verification, model testing, activation, deactivation, switching, etc. In one aspect, the communication and processing circuit 1340 may deprioritize UL and / or DL ​​communications at the UE, for example, by deactivating communications between the UE and one or more SCells during one or more AI / ML model time gaps. In one aspect, the communication and processing circuit 1340 may temporarily change the BWP configuration of the UE to reduce the processing and / or resource usage of the UE. For example, the network entity may configure the UE to switch from an active BWP to a dormant BWP or a narrower BWP.

[0151] In some aspects of the present disclosure, the processor 1304 may include an AI / ML model circuit 1342, which may be configured to perform various AI / ML model-related functions in one or more AI / ML model time slots. For example, the AI / ML model circuit 1342 may be configured to coordinate with the UE to perform model training, model inference, model verification, model testing, model activation, model deactivation, model switching, etc. of one or more AI / ML models. For example, one or more AI / ML models 1322 and associated AI / ML data 1323 may be stored in the memory 1305. The AI / ML model may be downloaded and / or predefined from a network entity. The network entity may perform AI / ML model-related functions ("model functions") in one or more time slots, in which the network may de-prioritize some wireless communication functions at the UE. The AI / ML model circuit 1342 may be further configured to execute the AI / ML model software 1352 stored on the computer-readable medium 1306 to implement one or more functions described herein.

[0152] Fig.14 is a flow chart illustrating an exemplary process 1400 for performing AI / ML model-related functions at a network entity according to some aspects of the present disclosure. As described below, some or all of the illustrated features may be omitted in certain implementations within the scope of the present disclosure, and some of the illustrated features may not be required for all example implementations. In some examples, process 1400 may consist of Fig.13 In some examples, process 1400 may be performed by any suitable device or component for performing the functions or algorithms described below.

[0153] At block 1402, the network entity may provide one or more time slots to the UE, the one or more time slots being associated with an AI / ML model used at the UE in a RAN associated with the network entity (e.g., RAN 200). For example, the one or more time slots may be associated with the AI / ML model used at the UE in a RAN associated with the network entity (e.g., RAN 200). Figure 7The same as the time gap 704 described. In one aspect, the AI / ML model circuit 1342 can be configured as a component for providing one or more time gaps. The time gap enables the UE to use the AI / ML model in the RAN associated with the network entity. In one example, the UE can use the AI / ML model for CSI feedback enhancement, such as overhead reduction, improved accuracy and prediction. In one example, the UE can use the AI / ML model for beam management, such as beam prediction in the time domain and / or spatial domain, overhead and latency reduction, improved beam selection accuracy, etc. In one example, the UE can use the AI / ML model for positioning accuracy enhancement in various scenarios, including, for example, conditions with significant non-line-of-sight conditions.

[0154] At box 1404, the network entity may deprioritize at least one of UL communications or DL ​​communications with the UE in one or more time slots. In one aspect, the communication and processing circuit 1340 may be configured as a component for deprioritizing UL and / or DL ​​communications with the UE. In one example, deprioritizing UL and / or DL ​​communications may include deactivating communications between the UE and one or more SCells in the AI / ML model time slot. In one example, the deactivated SCell may not include an SCell associated with a PUCCH or an SCell with a PRACH configuration. In one example, deprioritizing UL and / or DL ​​communications may include temporarily changing the BWP configuration of the UE to reduce processing and / or resource usage at the UE. For example, the network entity may configure the UE to switch from an active BWP to a dormant BWP or a narrower BWP.

[0155] At box 1406, the network entity may perform one or more AI / ML model-related processes in one or more time slots. In one aspect, the AI / ML model circuit 1342 may be configured as a component for performing one or more AI / ML model-related processes. In one example, the network entity may send a PDCCH / PDSCH transmission and / or a DL signal configured for AI / ML model-related functions (e.g., training, compilation, verification, switching, etc.). In some aspects, the network entity (e.g., base station, gNB, TRP) may configure and transmit a PDCCH / PDSCH signal in a predetermined format that can be recognized by the UE and used to perform AI / ML model-related functions (e.g., model training, testing, verification, etc.) in a time slot. In one example, the network entity may transmit a DL reference signal (e.g., non-cell defined SSB (NCD-SSB), CSI-RS, etc.) that can be used by the UE for AI / ML model-related functions. These PDCCH / PDSCH and / or DL ​​signals may be specifically configured for, for example, AI / ML model training (e.g., learning, parameter tuning) and / or model validation and testing, and the UE may not send normal (e.g., not related to AI / ML functions) feedback and / or reports in response to these PDCCH / PDSCH and / or DL ​​signals.

[0156] In one configuration, the network entity 1300 includes components for performing AI / ML related processes in the configured time slots as described above. In one aspect, the aforementioned components may be Fig.13 The processor 1304 shown in FIG. 1 is configured to perform the functions recited by the aforementioned components. On the other hand, the aforementioned components may be a circuit or any device configured to perform the functions recited by the aforementioned components.

[0157] Of course, in the above examples, the circuits included in the processor 1304 are provided only as examples, and other components for implementing the described functions may be included in various aspects of the present disclosure, including but not limited to storage in the computer-readable storage medium 1306 or in Figure 1 , Figure 2 , Figure 4 , Figure 6 and / or Fig.10 In any other suitable device or component described in any of the foregoing and utilizing, for example, Figures 7 to 10 and / or Fig.14 Instructions that describe a process and / or algorithm.

[0158] In a first aspect, a method of wireless communication at a user equipment (UE) is provided. The method includes: providing one or more time slots, the one or more time slots being associated with an artificial intelligence and machine learning (AI / ML) model for communicating with a network entity; deprioritizing at least one of uplink (UL) communications or downlink (DL) communications with the network entity in the one or more time slots; and performing one or more AI / ML model-related processes in the one or more time slots.

[0159] In a second aspect, alone or in combination with the first aspect, the one or more AI / ML model-related processes include at least one of model training, model inference, model verification, model testing, model activation, model deactivation, or model switching.

[0160] In a third aspect, either alone or in combination with the first aspect, the method further comprises at least one of: using the AI / ML model to perform channel measurement and reporting; using the AI / ML model to perform beam management; or using the AI / ML model to perform positioning.

[0161] In a fourth aspect, alone or in combination with any one of the first to third aspects, the deprioritization comprises at least one of the following operations: deactivating data transmission with one or more secondary serving cells (SCells); or switching an active bandwidth part (BWP) to a dormant BWP or a narrower BWP.

[0162] In the fifth aspect, alone or in combination with any one of the first to third aspects, the one or more AI / ML model-related processes include: training the AI / ML model based on at least one of a physical downlink control channel (PDCCH) transmission, a physical downlink shared channel (PDSCH) transmission, or a downlink reference signal; suppressing sending an acknowledgment of the PDCCH transmission or the PDSCH transmission; suppressing sending a measurement report based on the downlink reference signal; or sending a report indicating at least one of a selection of an AI / ML model or the reliability of an AI / ML model.

[0163] In a sixth aspect, alone or in combination with any one of the first to third aspects, the one or more time slots are associated with a subset of a currently configured carrier or bandwidth part of the UE.

[0164] In a seventh aspect, alone or in combination with any one of the first to third aspects, the method further comprises at least one of the following operations: receiving a query for the one or more time slots or transmitting a request for the one or more time slots.

[0165] In the eighth aspect, alone or in combination with any one of the first to third aspects, the method also includes: receiving a radio resource control (RRC) configuration associated with the one or more time slots, wherein the RRC configuration includes at least one of a DRX configuration, a MIMO configuration, or a measurement and reporting configuration.

[0166] In a ninth aspect, a user equipment (UE) for wireless communication is provided. The UE includes a communication interface, a memory storing executable code, and a processor coupled to the communication interface and the memory. The processor is configured by the executable code to provide one or more time slots, the one or more time slots being associated with an artificial intelligence and machine learning (AI / ML) model for communicating with a network entity using the communication interface. The processor is further configured to: de-prioritize at least one of an uplink (UL) communication or a downlink (DL) communication with the network entity in the one or more time slots. The processor is further configured to perform one or more AI / ML model-related processes in the one or more time slots.

[0167] In the tenth aspect, alone or in combination with the ninth aspect, the one or more AI / ML model-related processes include at least one of model training, model inference, model verification, model testing, model activation, model deactivation, or model switching.

[0168] In the eleventh aspect, alone or in combination with the ninth aspect, the processor is further configured to: use the AI / ML model to perform channel measurement and reporting; use the AI / ML model to perform beam management; or use the AI / ML model to perform positioning.

[0169] In the twelfth aspect, alone or in combination with any one of the ninth to eleventh aspects, in order to deprioritize the at least one of the UL communication or the DL communication, the processor is further configured to perform at least one of the following operations: deactivating data transmission with one or more secondary service cells (SCells); or switching an active bandwidth part (BWP) to a dormant BWP or a narrower BWP.

[0170] In the thirteenth aspect, alone or in combination with any one of the ninth to eleventh aspects, the one or more AI / ML model-related processes include at least one of the following operations: training the AI / ML model based on at least one of a physical downlink control channel (PDCCH) transmission, a physical downlink shared channel (PDSCH) transmission, or a downlink reference signal; suppressing sending an acknowledgment of the PDCCH transmission or the PDSCH transmission; suppressing sending a measurement report based on the downlink reference signal; or sending a report indicating at least one of a selection of an AI / ML model or the reliability of an AI / ML model.

[0171] In a fourteenth aspect, alone or in combination with any one of the ninth to eleventh aspects, wherein the one or more time slots are associated with a subset of a currently configured carrier or bandwidth part of the UE.

[0172] In the fifteenth aspect, alone or in combination with any one of the ninth to eleventh aspects, the processor is further configured to perform at least one of the following operations: receiving a query for the one or more time slots; or transmitting a request for the one or more time slots.

[0173] In the sixteenth aspect, alone or in combination with any one of the ninth to eleventh aspects, the processor is further configured to: receive a radio resource control (RRC) configuration associated with the one or more time slots, wherein the RRC configuration includes at least one of a DRX configuration, a MIMO configuration, or a measurement and reporting configuration.

[0174] In a seventeenth aspect, a method of wireless communication at a network entity is provided. The method includes providing one or more time slots to a user equipment (UE), the one or more time slots being associated with an artificial intelligence and machine learning (AI / ML) model at the UE in a radio access network associated with the network entity. The method also includes: de-prioritizing at least one of uplink (UL) communications or DL ​​communications with the UE in the one or more time slots. The method also includes: performing one or more AI / ML model-related processes in the one or more time slots.

[0175] In the eighteenth aspect, alone or in combination with the seventeenth aspect, the one or more AI / ML model-related processes include at least one of model training, model inference, model verification, model testing, model activation, model deactivation, or model switching.

[0176] In the nineteenth aspect, alone or in combination with the seventeenth aspect, the deprioritization comprises at least one of the following operations: deactivating data transmission with the UE via one or more secondary serving cells (SCells); or switching the active bandwidth part (BWP) of the UE to a dormant BWP or a narrower BWP.

[0177] In the twentieth aspect, alone or in combination with any one of aspects seventeen to nineteen, the one or more AI / ML model-related processes include at least one of the following operations: training the AI / ML model based on at least one of a physical downlink control channel (PDCCH) transmission, a physical downlink shared channel (PDSCH) transmission, or a downlink reference signal; ignoring, by the UE, confirmation of the PDCCH transmission or the PDSCH transmission; ignoring, by the UE, measurement reports based on the downlink reference signal; or receiving a report indicating at least one of a selection of an AI / ML model or the reliability of an AI / ML model.

[0178] In a twenty-first aspect, alone or in combination with any one of aspects seventeen to nineteen, wherein the one or more time slots are associated with a subset of a currently configured carrier or bandwidth portion of the UE.

[0179] In the twenty-second aspect, alone or in combination with any one of the seventeenth to nineteenth aspects, the method further comprises: sending a query for the one or more time slots; or receiving a request for the one or more time slots.

[0180] In aspect twenty-third, alone or in combination with any one of aspects seventeen to nineteen, the method further comprises: sending a radio resource control (RRC) configuration associated with the one or more time slots, wherein the RRC configuration comprises at least one of a DRX configuration, a MIMO configuration, or a measurement and reporting configuration.

[0181] In a twenty-fourth aspect, a network entity for wireless communication is provided. The network entity includes a memory storing executable code and a processor coupled to the memory. The processor is configured by the executable code to provide one or more time slots to a user equipment (UE), the one or more time slots being associated with an artificial intelligence and machine learning (AI / ML) model at the UE in a radio access network associated with the network entity. The processor is further configured to: de-prioritize at least one of an uplink (UL) communication or a downlink (DL) communication with the UE in the one or more time slots. The processor is further configured to perform one or more AI / ML model-related processes in the one or more time slots.

[0182] In the twenty-fifth aspect, alone or in combination with the twenty-fourth aspect, the one or more AI / ML model-related processes include at least one of model training, model inference, model verification, model testing, model activation, model deactivation, or model switching.

[0183] In the twenty-sixth aspect, alone or in combination with the twenty-fourth aspect, in order to deprioritize the UL communication or at least one of the DL communication, the processor is further configured to perform at least one of the following operations: deactivating data transmission with the UE via one or more secondary service cells (SCells); or switching the active bandwidth part (BWP) of the UE to a dormant BWP or a narrower BWP.

[0184] In aspect 27, alone or in combination with any one of aspects 24 to 26, the one or more AI / ML model-related processes include at least one of the following operations: training the AI / ML model based on at least one of a physical downlink control channel (PDCCH) transmission, a physical downlink shared channel (PDSCH) transmission, or a downlink reference signal; ignoring, by the UE, confirmation of the PDCCH transmission or the PDSCH transmission; ignoring, by the UE, measurement reports based on the downlink reference signal; or receiving a report indicating at least one of a selection of an AI / ML model or the reliability of an AI / ML model.

[0185] In a twenty-eighth aspect, alone or in combination with any one of aspects twenty-four to twenty-six, wherein the one or more time slots are associated with a subset of a currently configured carrier or bandwidth portion of the UE.

[0186] In a twenty-ninth aspect, alone or in combination with any one of aspects twenty-four to twenty-six, wherein the processor is further configured to: send a query for the one or more time slots; or receive a request for the one or more time slots.

[0187] In the thirtieth aspect, alone or in combination with any one of aspects twenty-four to twenty-six, the processor is further configured to: send a radio resource control (RRC) configuration associated with the one or more time slots, wherein the RRC configuration includes at least one of a DRX configuration, a MIMO configuration, or a measurement and reporting configuration.

[0188] Several aspects of wireless communication networks have been presented with reference to exemplary implementations. As those skilled in the art will readily appreciate, various aspects described throughout this disclosure may be extended to other telecommunication systems, network architectures and communication standards.

[0189] By way of example, various aspects may be implemented within other systems defined by 3GPP, such as Long Term Evolution (LTE), Evolved Packet System (EPS), Universal Mobile Telecommunications System (UMTS), and / or Global System for Mobile (GSM). Various aspects may also be extended to systems defined by the Third Generation Partnership Project 2 (3GPP2), such as CDMA2000 and / or Evolution-Data Optimized (EV-DO). Other examples may be implemented within systems employing IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE802.20, Ultra Wideband (UWB), Bluetooth, and / or other suitable systems. The actual telecommunication standard, network architecture, and / or communication standard employed will depend on the specific application and the overall design constraints imposed on the system.

[0190] Within the present disclosure, the word "exemplary" is used to mean "serving as an example, instance, or illustration". Any specific implementation or aspect described herein as "exemplary" is not necessarily to be construed as superior or superior to other aspects of the present disclosure. Likewise, the term "aspect" does not require that all aspects of the present disclosure include the discussed features, advantages, or modes of operation. The term "coupled" is used herein to refer to a direct or indirect coupling between two objects. For example, if object A physically contacts object B, and object B contacts object C, objects A and C may still be considered to be coupled to each other, even if they are not in direct physical contact with each other. For example, a first object may be coupled to a second object, even if the first object has never been in direct physical contact with the second object. The terms "circuit" and "circuitry" are used broadly, and they are intended to include both hardware implementations of electronic devices and conductors (where these electronic devices and conductors, when connected and configured, implement the execution of the functions described in the present disclosure, without limitation on the type of electronic circuits) and software implementations of information and instructions (where these information and instructions, when executed by a processor, implement the execution of the functions described in the present disclosure).

[0191] Figures 1 to 14 One or more of the components, steps, features, and / or functions illustrated in the present invention may be rearranged and / or combined into a single component, step, feature, or function or may be embodied in several components, steps, or functions. Additional elements, components, steps, and / or functions may also be added without departing from the novel features disclosed herein. Figures 1 to 14 The apparatus, device and / or components illustrated in the can be configured to perform one or more of the methods, features or steps described herein. The novel algorithms described herein can also be effectively implemented in software and / or embedded in hardware.

[0192] It should be understood that the specific order or hierarchy of steps in the disclosed methods is an illustration of an exemplary process. It should be understood that the specific order or hierarchy of steps in these methods can be rearranged based on design preferences. The attached method claims present elements of various steps in a sample order, but are not intended to be limited to the specific order or hierarchy presented unless explicitly stated herein.

[0193] The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. 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. Therefore, the claims are not intended to be limited to the various aspects shown herein, but to conform to the full scope consistent with the text of the claims, wherein unless explicitly stated otherwise, reference to an element in the singular form is not intended to mean "one and only one", but "one or more". Unless otherwise specified, the term "some" refers to one or more. The phrase "at least one" referring to a list of items refers to any combination of those items, including a single member. As an example, "at least one of a, b or c" is intended to cover: a; b; c; a and b; a and c; b and c; and a, b and c. All structural and functional equivalents of the elements of the various aspects described throughout the present disclosure that are known or will be known later to a person of ordinary skill in the art are expressly incorporated herein by reference and are intended to be covered by the claims. In addition, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is explicitly stated in the claims. No claim element is to be construed under 35 USC §112(f) unless the element is expressly recited using the phrase “means for” or, in the case of a method claim, the phrase “step for.”

Claims

1. A method for wireless communication at a user equipment (UE), comprising: providing one or more time slots associated with an artificial intelligence and machine learning (AI / ML) model for communicating with a network entity; deprioritizing at least one of uplink (UL) communications or downlink (DL) communications with the network entity in the one or more time slots; as well as One or more AI / ML model-related processes are performed in the one or more time slots.

2. The method of claim 1, wherein the one or more AI / ML model-related processes include at least one of model training, model inference, model verification, model testing, model activation, model deactivation, or model switching.

3. The method according to claim 1, further comprising at least one of the following operations: Using the AI / ML model to perform channel measurement and reporting; Use the AI / ML model to perform beam management; or Positioning is performed using the AI / ML model.

4. The method of claim 1 , wherein the de-prioritization comprises at least one of the following operations: Deactivating data transmission to one or more secondary serving cells (SCells); or Switches the active bandwidth part (BWP) to a dormant BWP or a narrower BWP.

5. The method of claim 1, wherein the one or more AI / ML model-related processes include: training the AI / ML model based on at least one of a physical downlink control channel (PDCCH) transmission, a physical downlink shared channel (PDSCH) transmission, or a downlink reference signal; refraining from sending an acknowledgement of the PDCCH sending or the PDSCH sending; refraining from sending measurement reports based on the downlink reference signal; or Sending a report indicating at least one of the selection of the AI / ML model or the reliability of the AI / ML model.

6. The method of claim 1, wherein the one or more time slots are associated with a subset of a currently configured carrier or bandwidth portion of the UE.

7. The method according to claim 1, further comprising at least one of the following operations: receiving a query for the one or more time slots; or A request for the one or more time slots is transmitted.

8. The method according to claim 1, further comprising: A radio resource control (RRC) configuration associated with the one or more time slots is received, wherein the RRC configuration comprises at least one of a DRX configuration, a MIMO configuration, or a measurement and reporting configuration.

9. A user equipment (UE) for wireless communication, comprising: Communication interface; A memory storing executable code; as well as a processor coupled to the communication interface and the memory, wherein the processor is configured by the executable code to: providing one or more time slots associated with an artificial intelligence and machine learning (AI / ML) model for communicating with a network entity using the communication interface; deprioritizing at least one of uplink (UL) communications or downlink (DL) communications with the network entity in the one or more time slots; as well as One or more AI / ML model-related processes are performed in the one or more time slots.

10. The UE of claim 9, wherein the one or more AI / ML model-related processes include at least one of model training, model inference, model verification, model testing, model activation, model deactivation, or model switching.

11. The UE according to claim 9, wherein the processor is further configured to perform at least one of the following operations: Using the AI / ML model to perform channel measurement and reporting; Use the AI / ML model to perform beam management; or Positioning is performed using the AI / ML model.

12. The UE of claim 9, wherein in order to deprioritize the at least one of the UL communication or the DL communication, the processor is further configured to perform at least one of the following operations: Deactivating data transmission to one or more secondary serving cells (SCells); or Switches the active bandwidth part (BWP) to a dormant BWP or a narrower BWP.

13. The UE according to claim 9, wherein the one or more AI / ML model-related processes include at least one of the following operations: training the AI / ML model based on at least one of a physical downlink control channel (PDCCH) transmission, a physical downlink shared channel (PDSCH) transmission, or a downlink reference signal; refraining from sending an acknowledgement of the PDCCH sending or the PDSCH sending; refraining from sending measurement reports based on the downlink reference signal; or Sending a report indicating at least one of the selection of the AI / ML model or the reliability of the AI / ML model.

14. The UE of claim 9, wherein the one or more time slots are associated with a subset of a currently configured carrier or bandwidth portion of the UE.

15. The UE according to claim 9, wherein the processor is further configured to perform at least one of the following operations: receiving a query for the one or more time slots; or A request for the one or more time slots is transmitted.

16. The UE according to claim 9, wherein the processor is further configured to: A radio resource control (RRC) configuration associated with the one or more time slots is received, wherein the RRC configuration comprises at least one of a DRX configuration, a MIMO configuration, or a measurement and reporting configuration.

17. A method for wireless communication at a network entity, comprising: providing one or more time slots to a user equipment (UE), the one or more time slots associated with an artificial intelligence and machine learning (AI / ML) model at the UE in a radio access network associated with the network entity; deprioritize at least one of uplink (UL) communications or DL ​​communications with the UE in the one or more time slots; as well as One or more AI / ML model-related processes are performed in the one or more time slots.

18. The method of claim 17, wherein the one or more AI / ML model-related processes include at least one of model training, model inference, model verification, model testing, model activation, model deactivation, or model switching.

19. The method of claim 17, wherein the de-prioritization comprises at least one of the following operations: deactivating data transmission with the UE via one or more secondary serving cells (SCells); or The active bandwidth part (BWP) of the UE is switched to a dormant BWP or a narrower BWP.

20. The method of claim 17, wherein the one or more AI / ML model-related processes include at least one of the following operations: training the AI / ML model based on at least one of a physical downlink control channel (PDCCH) transmission, a physical downlink shared channel (PDSCH) transmission, or a downlink reference signal; Ignoring, by the UE, an acknowledgement of the PDCCH transmission or the PDSCH transmission; Ignoring, by the UE, a measurement report based on the downlink reference signal; or A report is received indicating at least one of a selection of the AI / ML model or a reliability of the AI / ML model.

21. The method of claim 17, wherein the one or more time slots are associated with a subset of a currently configured carrier or bandwidth portion of the UE.

22. The method of claim 17, further comprising: sending a query for the one or more time slots; or A request for the one or more time slots is received.

23. The method of claim 17, further comprising: A radio resource control (RRC) configuration associated with the one or more time slots is transmitted, wherein the RRC configuration comprises at least one of a DRX configuration, a MIMO configuration, or a measurement and reporting configuration.

24. A network entity for wireless communication, comprising: A memory storing executable code; as well as a processor coupled to the memory, wherein the processor is configured by the executable code to: providing one or more time slots to a user equipment (UE), the one or more time slots associated with an artificial intelligence and machine learning (AI / ML) model at the UE in a radio access network associated with the network entity; deprioritizing at least one of uplink (UL) communications or downlink (DL) communications with the UE in the one or more time slots; as well as One or more AI / ML model-related processes are performed in the one or more time slots.

25. The network entity of claim 24, wherein the one or more AI / ML model-related processes include at least one of model training, model inference, model verification, model testing, model activation, model deactivation, or model switching.

26. The network entity of claim 24, wherein to deprioritize the at least one of the UL communications or the DL communications, the processor is further configured to perform at least one of the following operations: deactivating data transmission with the UE via one or more secondary serving cells (SCells); or The active bandwidth part (BWP) of the UE is switched to a dormant BWP or a narrower BWP.

27. The network entity of claim 24, wherein the one or more AI / ML model-related processes include at least one of the following operations: training the AI / ML model based on at least one of a physical downlink control channel (PDCCH) transmission, a physical downlink shared channel (PDSCH) transmission, or a downlink reference signal; Ignoring, by the UE, an acknowledgement of the PDCCH transmission or the PDSCH transmission; Ignoring, by the UE, a measurement report based on the downlink reference signal; or A report is received indicating at least one of a selection of the AI / ML model or a reliability of the AI / ML model.

28. The network entity of claim 24, wherein the one or more time slots are associated with a subset of a currently configured carrier or bandwidth portion of the UE.

29. The network entity of claim 24, wherein the processor is further configured to: sending a query for the one or more time slots; or A request for the one or more time slots is received.

30. The network entity of claim 24, wherein the processor is further configured to: A radio resource control (RRC) configuration associated with the one or more time slots is transmitted, wherein the RRC configuration comprises at least one of a DRX configuration, a MIMO configuration, or a measurement and reporting configuration.

Images