Concurrent CSI processing unit sharing for ai / ML based CSF and beam prediction
By implementing detailed signaling mechanisms and UE capability enhancements to manage CPU occupation concurrently for AI/ML-based CSI feedback and beam prediction, the solution addresses the inefficiencies in processing and reporting CSI in current wireless communication systems, achieving improved resource allocation and performance.
Patent Information
- Application Number
- PCT/CN2023/137039
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-12-07
- Publication Date
- 2025-06-12
AI Technical Summary
Current wireless communication systems face challenges in efficiently processing and reporting channel state information (CSI) using artificial intelligence (AI)/machine learning (ML) technologies, particularly in distinguishing between AI/ML-based and conventional CSI reports to optimize hardware utilization.
The proposed solution involves detailed signaling mechanisms and UE capability enhancements to enable concurrent CPU occupation frameworks across AI/ML-based CSI feedback and beam prediction, allowing for flexible and efficient hardware utilization by separating the number of CSI processing units used for AI/ML-based tasks from those used for conventional CSI reports.
This approach enables more efficient and flexible hardware utilization, improving resource allocation and process efficiency for AI/ML-based tasks in user equipment (UE), thereby enhancing the overall performance of wireless communication systems.
Smart Images

Figure CN2023137039_12062025_PF_FP_ABST
Abstract
Description
CONCURRENT CSI PROCESSING UNIT SHARING FOR AI / ML BASED CSF AND BEAM PREDICTIONTECHNICAL FIELD
[0001] The present disclosure relates generally to communication systems, and more particularly, to concurrent channel state information (CSI) processing units (CPUs) sharing for artificial intelligence (AI) / machine learning (ML) (AI / ML) based channel state information feedback (CSF) and beam prediction in wireless communication.
[0002] INTRODUCTION
[0003] Wireless communication systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, and broadcasts. 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.
[0004] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate on a municipal, national, regional, and even global level. An example telecommunication standard is 5G New Radio (NR) . 5G NR is part of a continuous mobile broadband evolution promulgated by Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with Internet of Things (IoT) ) , and other requirements. 5G NR includes services associated with enhanced mobile broadband (eMBB) , massive machine type communications (mMTC) , and ultra-reliable low latency communications (URLLC) . Some aspects of 5G NR may be based on the 4G Long Term Evolution (LTE) standard. There exists a need for further improvements in 5G NR technology. These improvements may also be applicable to other multi-access technologies and the telecommunication standards that employ these technologies.
[0005] BRIEF SUMMARY
[0006] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects. This summary neither identifies key or critical elements of all aspects nor delineates the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
[0007] In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided for wireless communication at a user equipment (UE) . The apparatus may include at least one memory and at least one processor coupled to the at least one memory. Based at least in part on information stored in the at least one memory, the at least one processor, individually or in any combination, may be configured to transmit, to a network entity, a capability indicator of a computational capability, including an artificial intelligence (AI) / machine learning (ML) (AI / ML) capability for processing an AI / ML function; perform the AI / ML function based on the computational capability; and transmit, to the network entity based on the AI / ML function, one or more AI / ML channel station information (CSI) reports including a result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing.
[0008] In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided for wireless communication at a network entity. The apparatus may include at least one memory and at least one processor coupled to the at least one memory. Based at least in part on information stored in the at least one memory, the at least one processor, individually or in any combination, may be configured to receive, from a UE, a capability indicator of a computational capability, including an AI / ML capability for processing an AI / ML function; and receive, from the UE based on the AI / ML function, one or more AI / ML CSI reports including a result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing.
[0009] To the accomplishment of the foregoing and related ends, the one or more aspects may include the features hereinafter fully described and particularly pointed out in the claims. The following description and the drawings set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which the principles of various aspects may be employed.BRIEF DESCRIPTION OF THE DRAWINGS
[0010] FIG. 1 is a diagram illustrating an example of a wireless communication system and an access network.
[0011] FIG. 2A is a diagram illustrating an example of a first frame, in accordance with various aspects of the present disclosure.
[0012] FIG. 2B is a diagram illustrating an example of downlink (DL) channels within a subframe, in accordance with various aspects of the present disclosure.
[0013] FIG. 2C is a diagram illustrating an example of a second frame, in accordance with various aspects of the present disclosure.
[0014] FIG. 2D is a diagram illustrating an example of uplink (UL) channels within a subframe, in accordance with various aspects of the present disclosure.
[0015] FIG. 3 is a diagram illustrating an example of a base station and user equipment (UE) in an access network.
[0016] FIG. 4 is a diagram illustrating an example channel state information (CSI) processing unit (CPU) occupation for artificial intelligence (AI) and machine learning (ML) (AI / ML) based processing in accordance with various aspects of the present disclosure.
[0017] FIG. 5A is a diagram illustrating an example CPU occupation for AI / ML based processing in accordance with various aspects of the present disclosure.
[0018] FIG. 5B is a diagram illustrating an example of UE capabilities for conventional CSI reports and AI / ML CSI reports in accordance with various aspects of the present disclosure.
[0019] FIG. 6 is a diagram illustrating an example of UE capabilities for conventional CSI reports and AI / ML CSI reports in accordance with various aspects of the present disclosure.
[0020] FIG. 7 is a diagram illustrating an example of the concurrent UE capabilities on the number of CPUs occupied by the AI / ML use cases for a UE in accordance with various aspects of the present disclosure.
[0021] FIG. 8 is a call flow diagram illustrating a method of wireless communication in accordance with various aspects of the present disclosure.
[0022] FIG. 9 is a flowchart illustrating methods of wireless communication at a UE in accordance with various aspects of the present disclosure.
[0023] FIG. 10 is a flowchart illustrating methods of wireless communication at a UE in accordance with various aspects of the present disclosure.
[0024] FIG. 11 is a flowchart illustrating methods of wireless communication at a network entity in accordance with various aspects of the present disclosure.
[0025] FIG. 12 is a flowchart illustrating methods of wireless communication at a network entity in accordance with various aspects of the present disclosure.
[0026] FIG. 13 is a diagram illustrating an example of a hardware implementation for an example apparatus and / or network entity.
[0027] FIG. 14 is a diagram illustrating an example of a hardware implementation for an example network entity.DETAILED DESCRIPTION
[0028] As the implementation of artificial intelligence (AI) and machine learning (ML) (AI / ML) in wireless communication continues to grow, the deployment of dedicated hardware accelerators, such as network signal processors (NSP) and graphics processing units (GPU) , is becoming increasingly common. These hardware accelerators may be shared among various AI / ML functionalities or tasks, including AI / ML based channel state information feedback (CSF) and user equipment (UE) side beam prediction results reporting. On the other hand, conventional channel state information (CSI) reports may depend on traditional firmware / software (FW / SW) computational resources. To enhance the effectiveness of AI / ML based tasks in user equipment (UE) , it is advantageous to distinguish the number of CSI processing units (CPUs) used for AI / ML based feedback from those used for conventional type of CSI reports, also known as non-AI / ML CSI reports. The sharing of hardware for AI / ML based tasks may be tailored based on the complexities and priorities of these tasks. For example, a complex CSF model may be paired with a simple beam prediction model, or a simple CSF model may be paired with multiple beam prediction models targeting different use cases. Example aspects presented herein introduce detailed signaling mechanisms and UE capability enhancements to enable concurrent CPU occupation frameworks across AI / ML based CSF and beam prediction result reporting.
[0029] Various aspects relate generally to wireless communication. Some aspects more specifically relate to concurrent CPUs sharing for AI / ML based CSF and beam prediction in wireless communication. In some examples, a UE transmits, to a network entity, a capability indicator of the computational capability including an AI / ML capability for processing an AI / ML function. The UE further performs the AI / ML function based on the computational capability, and transmits, to the network entity based on AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing. In some aspects, the AI / ML capability may include at least one of: a first supported number of CPUs (e.g., a first maximum number of CPUs) that can be occupied by the one or more AI / ML CSI reports associated with each component carrier (CC) of a set of CCs; or a second supported number of CPUs (e.g., a second maximum number of CPUs) that can be occupied by the one or more AI / ML CSI reports for all of the set of CCs. In some aspects, the report quantity for each of the one or more AI / ML CSI reports may include one or more of: the beam prediction result, the CSI prediction result, or the CSI compression result.
[0030] Particular aspects of the subject matter described in this disclosure can be implemented to realize one or more of the following potential advantages. In some examples, by providing detailed signaling mechanisms and UE capability enhancements to enable concurrent CPU occupation frameworks across AI / ML based CSF and beam prediction results reporting, the described techniques allow for more efficient and flexible hardware utilization, including dedicated hardware accelerators like NSP and GPU. In some examples, by enabling the UE to report the maximum CPU occupation for different AI / ML based tasks like beam prediction and AI / ML based CSI prediction, the described techniques may be used to improve to the resource allocation and process efficiency for the AI / ML based tasks.
[0031] The detailed description set forth below in connection with the drawings describes various configurations and does not represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of various concepts. However, these concepts may be practiced without these specific details. In some instances, well known structures and components are shown in block diagram form in order to avoid obscuring such concepts.
[0032] Several aspects of telecommunication systems are presented with reference to various apparatus and methods. These apparatus and methods are described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as “elements” ) . These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system.
[0033] By way of example, an element, or any portion of an element, or any combination of elements may be implemented as a “processing system” that includes one or more processors. When multiple processors are implemented, the multiple processors may perform the functions individually or in combination. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs) , central processing units (CPUs) , application processors, digital signal processors (DSPs) , reduced instruction set computing (RISC) processors, systems on a chip (SoC) , baseband processors, field programmable gate arrays (FPGAs) , programmable logic devices (PLDs) , state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform the various functionality described throughout this disclosure. One or more processors in the processing system may execute software. Software, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise, shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software components, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, or any combination thereof.
[0034] Accordingly, in one or more example aspects, implementations, and / or use cases, the functions described may be implemented in hardware, software, or any combination thereof. If implemented in software, the functions may be stored on or encoded as one or more instructions or code on a computer-readable medium. Computer-readable media includes computer storage media. Storage media may be any available media that can be accessed by a computer. By way of example, such computer-readable media can include a random-access memory (RAM) , a read-only memory (ROM) , an electrically erasable programmable ROM (EEPROM) , optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of the types of computer-readable media, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer.
[0035] While aspects, implementations, and / or use cases are described in this application by illustration to some examples, additional or different aspects, implementations and / or use cases may come about in many different arrangements and scenarios. Aspects, implementations, and / or use cases described herein may be implemented across many differing platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, aspects, implementations, and / or use cases may come about via integrated chip implementations and other non-module-component based devices (e.g., end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / purchasing devices, medical devices, artificial intelligence (AI) -enabled devices, etc. ) . While some examples may or may not be specifically directed to use cases or applications, a wide assortment of applicability of described examples may occur. Aspects, implementations, and / or use cases may range a spectrum from chip-level or modular components to non-modular, non-chip-level implementations and further to aggregate, distributed, or original equipment manufacturer (OEM) devices or systems incorporating one or more techniques herein. In some practical settings, devices incorporating described aspects and features may also include additional components and features for implementation and practice of claimed and described aspect. For example, transmission and reception of wireless signals necessarily includes a number of components for analog and digital purposes (e.g., hardware components including antenna, RF-chains, power amplifiers, modulators, buffer, processor (s) , interleaver, adders / summers, etc. ) . Techniques described herein may be practiced in a wide variety of devices, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc. of varying sizes, shapes, and constitution.
[0036] Deployment of communication systems, such as 5G NR systems, may be arranged in multiple manners with various components or constituent parts. In a 5G NR system, or network, a network node, a network entity, a mobility element of a network, a radio access network (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 functionality, may be implemented in an aggregated or disaggregated architecture. For example, a BS (such as a Node B (NB) , evolved NB (eNB) , NR BS, 5G NB, access point (AP) , a transmission reception point (TRP) , or a cell, etc. ) may be implemented as an aggregated base station (also known as a standalone BS or a monolithic BS) or a disaggregated base station.
[0037] An aggregated base station may be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node. A disaggregated base station may be configured to utilize a protocol stack that is physically or logically distributed among 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, a 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 throughout one or multiple other RAN nodes. The DUs may be implemented to communicate with one or more RUs. Each of the CU, DU and RU can be implemented as virtual units, i.e., a virtual central unit (VCU) , a virtual distributed unit (VDU) , or a virtual radio unit (VRU) .
[0038] Base station operation or network design may consider aggregation characteristics of base station functionality. For example, disaggregated base stations may be utilized in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (such as the network configuration sponsored by the O-RAN Alliance) ) , or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN) ) . Disaggregation may include distributing functionality across two or more units at various physical locations, as well as distributing functionality for at least one unit virtually, which can enable flexibility in network design. The various units of the disaggregated base station, or disaggregated RAN architecture, can be configured for wired or wireless communication with at least one other unit.
[0039] FIG. 1 is a diagram 100 illustrating an example of a wireless communications system and an access network. The illustrated wireless communications system includes a disaggregated base station architecture. The disaggregated base station architecture may include one or more CUs 110 that can communicate directly with a core network 120 via a backhaul link, or indirectly with the core network 120 through one or more disaggregated base station units (such as a Near-Real Time (Near-RT) RAN Intelligent Controller (RIC) 125 via an E2 link, or a Non-Real Time (Non-RT) RIC 115 associated with a Service Management and Orchestration (SMO) Framework 105, or both) . A CU 110 may communicate with one or more DUs 130 via respective midhaul links, such as an F1 interface. The DUs 130 may communicate with one or more RUs 140 via respective fronthaul links. The RUs 140 may communicate with respective UEs 104 via one or more radio frequency (RF) access links. In some implementations, the UE 104 may be simultaneously served by multiple RUs 140.
[0040] Each of the units, i.e., the CUs 110, the DUs 130, the RUs 140, as well as the Near-RT RICs 125, the Non-RT RICs 115, and the SMO Framework 105, may include one or more interfaces or be coupled to one or more interfaces configured to receive or to transmit signals, data, or information (collectively, signals) via a wired or wireless transmission medium. Each of the units, or an associated processor or controller providing instructions to the communication interfaces of the units, can be configured to communicate with one or more of the other units via the transmission medium. For example, the units can include a wired interface configured to receive or to transmit signals over a wired transmission medium to one or more of the other units. Additionally, the units can include a wireless interface, which may include a receiver, a transmitter, or a transceiver (such as an RF transceiver) , configured to receive or to transmit signals, or both, over a wireless transmission medium to one or more of the other units.
[0041] In some aspects, the CU 110 may host one or more higher layer control functions. Such control functions can include radio resource control (RRC) , packet data convergence protocol (PDCP) , service data adaptation protocol (SDAP) , or the like. Each control function can be implemented with an interface configured to communicate signals with other control functions hosted by the CU 110. The CU 110 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 implementations, the CU 110 can be logically split into one or more CU-UP units and one or more CU-CP units. The CU-UP unit can communicate bidirectionally with the CU-CP unit via an interface, such as an E1 interface when implemented in an O-RAN configuration. The CU 110 can be implemented to communicate with the DU 130, as necessary, for network control and signaling.
[0042] The DU 130 may correspond to a logical unit that includes one or more base station functions to control the operation of one or more RUs 140. In some aspects, the DU 130 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, demodulation, or the like) depending, at least in part, on a functional split, such as those defined by 3GPP. In some aspects, the DU 130 may further host one or more low PHY layers. Each layer (or module) can be implemented with an interface configured to communicate signals with other layers (and modules) hosted by the DU 130, or with the control functions hosted by the CU 110.
[0043] Lower-layer functionality can be implemented by one or more RUs 140. In some deployments, an RU 140, controlled by a DU 130, 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, or the like) , or both, based at least in part on the functional split, such as a lower layer functional split. In such an architecture, the RU (s) 140 can be implemented to handle over the air (OTA) communication with one or more UEs 104. In some implementations, real-time and non-real-time aspects of control and user plane communication with the RU (s) 140 can be controlled by the corresponding DU 130. In some scenarios, this configuration can enable the DU (s) 130 and the CU 110 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.
[0044] The SMO Framework 105 may be configured to support RAN deployment and provisioning of non-virtualized and virtualized network elements. For non-virtualized network elements, the SMO Framework 105 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements that may be managed via an operations and maintenance interface (such as an O1 interface) . For virtualized network elements, the SMO Framework 105 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 190) to perform network element life cycle management (such as to instantiate virtualized network elements) via a cloud computing platform interface (such as an O2 interface) . Such virtualized network elements can include, but are not limited to, CUs 110, DUs 130, RUs 140 and Near-RT RICs 125. In some implementations, the SMO Framework 105 can communicate with a hardware aspect of a 4G RAN, such as an open eNB (O- eNB) 111, via an O1 interface. Additionally, in some implementations, the SMO Framework 105 can communicate directly with one or more RUs 140 via an O1 interface. The SMO Framework 105 also may include a Non-RT RIC 115 configured to support functionality of the SMO Framework 105.
[0045] The Non-RT RIC 115 may be configured to include a logical function that enables non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) / machine learning (ML) (AI / ML) workflows including model training and updates, or policy-based guidance of applications / features in the Near-RT RIC 125. The Non-RT RIC 115 may be coupled to or communicate with (such as via an A1 interface) the Near-RT RIC 125. The Near-RT RIC 125 may be configured to include a logical function that enables near-real-time control and optimization of RAN elements and resources via data collection and actions over an interface (such as via an E2 interface) connecting one or more CUs 110, one or more DUs 130, or both, as well as an O-eNB, with the Near-RT RIC 125.
[0046] In some implementations, to generate AI / ML models to be deployed in the Near-RT RIC 125, the Non-RT RIC 115 may receive parameters or external enrichment information from external servers. Such information may be utilized by the Near-RT RIC 125 and may be received at the SMO Framework 105 or the Non-RT RIC 115 from non-network data sources or from network functions. In some examples, the Non-RT RIC 115 or the Near-RT RIC 125 may be configured to tune RAN behavior or performance. For example, the Non-RT RIC 115 may monitor long-term trends and patterns for performance and employ AI / ML models to perform corrective actions through the SMO Framework 105 (such as reconfiguration via O1) or via creation of RAN management policies (such as A1 policies) .
[0047] At least one of the CU 110, the DU 130, and the RU 140 may be referred to as a base station 102. Accordingly, a base station 102 may include one or more of the CU 110, the DU 130, and the RU 140 (each component indicated with dotted lines to signify that each component may or may not be included in the base station 102) . The base station 102 provides an access point to the core network 120 for a UE 104. The base station 102 may include macrocells (high power cellular base station) and / or small cells (low power cellular base station) . The small cells include femtocells, picocells, and microcells. A network that includes both small cell and macrocells may be known as a heterogeneous network. A heterogeneous network may also include Home Evolved Node Bs (eNBs) (HeNBs) , which may provide service to a restricted group known as a closed subscriber group (CSG) . The communication links between the RUs 140 and the UEs 104 may include uplink (UL) (also referred to as reverse link) transmissions from a UE 104 to an RU 140 and / or downlink (DL) (also referred to as forward link) transmissions from an RU 140 to a UE 104. The communication links may use multiple-input and multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming, and / or transmit diversity. The communication links may be through one or more carriers. The base station 102 / UEs 104 may use spectrum up to Y MHz (e.g., 5, 10, 15, 20, 100, 400, etc. MHz) bandwidth per carrier allocated in a carrier aggregation of up to a total of Yx MHz (x component carriers) used for transmission in each direction. The carriers may or may not be adjacent to each other. Allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL than for UL) . The component carriers may include a primary component carrier and one or more secondary component carriers. A primary component carrier may be referred to as a primary cell (PCell) and a secondary component carrier may be referred to as a secondary cell (SCell) .
[0048] Certain UEs 104 may communicate with each other using device-to-device (D2D) communication link 158. The D2D communication link 158 may use the DL / UL wireless wide area network (WWAN) spectrum. The D2D communication link 158 may use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH) , a physical sidelink discovery channel (PSDCH) , a physical sidelink shared channel (PSSCH) , and a physical sidelink control channel (PSCCH) . D2D communication may be through a variety of wireless D2D communications systems, such as for example, BluetoothTM (Bluetooth is a trademark of the Bluetooth Special Interest Group (SIG) ) , Wi-FiTM (Wi-Fi is a trademark of the Wi-Fi Alliance) based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.
[0049] The wireless communications system may further include a Wi-Fi AP 150 in communication with UEs 104 (also referred to as Wi-Fi stations (STAs) ) via communication link 154, e.g., in a 5 GHz unlicensed frequency spectrum or the like. When communicating in an unlicensed frequency spectrum, the UEs 104 / AP 150 may perform a clear channel assessment (CCA) prior to communicating in order to determine whether the channel is available.
[0050] The electromagnetic spectrum is often subdivided, based on frequency / wavelength, into various classes, bands, channels, etc. In 5G NR, 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) . Although a portion of FR1 is greater than 6 GHz, FR1 is often referred to (interchangeably) as a “sub-6 GHz” band in various documents and articles. A similar nomenclature issue sometimes occurs with regard to FR2, which is often referred to (interchangeably) as a “millimeter wave” band in documents and articles, despite being different from the extremely high frequency (EHF) band (30 GHz – 300 GHz) which is identified by the International Telecommunications Union (ITU) as a “millimeter wave” band.
[0051] The frequencies between FR1 and FR2 are often referred to as mid-band frequencies. Recent 5G NR studies have identified an operating band for these mid-band frequencies as frequency range designation FR3 (7.125 GHz – 24.25 GHz) . Frequency bands falling within FR3 may inherit FR1 characteristics and / or FR2 characteristics, and thus may effectively extend features of FR1 and / or FR2 into mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operation beyond 52.6 GHz. For example, three higher operating bands have been identified as frequency range designations FR2-2 (52.6 GHz – 71 GHz) , FR4 (71 GHz – 114.25 GHz) , and FR5 (114.25 GHz – 300 GHz) . Each of these higher frequency bands falls within the EHF band.
[0052] With the above aspects in mind, unless specifically stated otherwise, the term “sub-6 GHz” or the like if used herein may broadly represent frequencies that may be less than 6 GHz, may be within FR1, or may include mid-band frequencies. Further, unless specifically stated otherwise, the term “millimeter wave” or the like if used herein may broadly represent frequencies that may include mid-band frequencies, may be within FR2, FR4, FR2-2, and / or FR5, or may be within the EHF band.
[0053] The base station 102 and the UE 104 may each include a plurality of antennas, such as antenna elements, antenna panels, and / or antenna arrays to facilitate beamforming. The base station 102 may transmit a beamformed signal 182 to the UE 104 in one or more transmit directions. The UE 104 may receive the beamformed signal from the base station 102 in one or more receive directions. The UE 104 may also transmit a beamformed signal 184 to the base station 102 in one or more transmit directions. The base station 102 may receive the beamformed signal from the UE 104 in one or more receive directions. The base station 102 / UE 104 may perform beam training to determine the best receive and transmit directions for each of the base station 102 / UE 104. The transmit and receive directions for the base station 102 may or may not be the same. The transmit and receive directions for the UE 104 may or may not be the same.
[0054] The base station 102 may include and / or be referred to as a gNB, Node B, eNB, an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS) , an extended service set (ESS) , a TRP, network node, network entity, network equipment, or some other suitable terminology. The base station 102 can be implemented as an integrated access and backhaul (IAB) node, a relay node, a sidelink node, an aggregated (monolithic) base station with a baseband unit (BBU) (including a CU and a DU) and an RU, or as a disaggregated base station including one or more of a CU, a DU, and / or an RU. The set of base stations, which may include disaggregated base stations and / or aggregated base stations, may be referred to as next generation (NG) RAN (NG-RAN) .
[0055] The core network 120 may include an Access and Mobility Management Function (AMF) 161, a Session Management Function (SMF) 162, a User Plane Function (UPF) 163, a Unified Data Management (UDM) 164, one or more location servers 168, and other functional entities. The AMF 161 is the control node that processes the signaling between the UEs 104 and the core network 120. The AMF 161 supports registration management, connection management, mobility management, and other functions. The SMF 162 supports session management and other functions. The UPF 163 supports packet routing, packet forwarding, and other functions. The UDM 164 supports the generation of authentication and key agreement (AKA) credentials, user identification handling, access authorization, and subscription management. The one or more location servers 168 are illustrated as including a Gateway Mobile Location Center (GMLC) 165 and a Location Management Function (LMF) 166. However, generally, the one or more location servers 168 may include one or more location / positioning servers, which may include one or more of the GMLC 165, the LMF 166, a position determination entity (PDE) , a serving mobile location center (SMLC) , a mobile positioning center (MPC) , or the like. The GMLC 165 and the LMF 166 support UE location services. The GMLC 165 provides an interface for clients / applications (e.g., emergency services) for accessing UE positioning information. The LMF 166 receives measurements and assistance information from the NG-RAN and the UE 104 via the AMF 161 to compute the position of the UE 104. The NG-RAN may utilize one or more positioning methods in order to determine the position of the UE 104. Positioning the UE 104 may involve signal measurements, a position estimate, and an optional velocity computation based on the measurements. The signal measurements may be made by the UE 104 and / or the base station 102 serving the UE 104. The signals measured may be based on one or more of a satellite positioning system (SPS) 170 (e.g., one or more of a Global Navigation Satellite System (GNSS) , global position system (GPS) , non-terrestrial network (NTN) , or other satellite position / location system) , LTE signals, wireless local area network (WLAN) signals, Bluetooth signals, a terrestrial beacon system (TBS) , sensor-based information (e.g., barometric pressure sensor, motion sensor) , NR enhanced cell ID (NR E-CID) methods, NR signals (e.g., multi-round trip time (Multi-RTT) , DL angle-of-departure (DL-AoD) , DL time difference of arrival (DL-TDOA) , UL time difference of arrival (UL-TDOA) , and UL angle-of-arrival (UL-AoA) positioning) , and / or other systems / signals / sensors.
[0056] Examples of UEs 104 include a cellular phone, a smart phone, a session initiation protocol (SIP) phone, a laptop, a personal digital assistant (PDA) , a satellite radio, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., MP3 player) , a camera, a game console, a tablet, a smart device, a wearable device, a vehicle, an electric meter, a gas pump, a large or small kitchen appliance, a healthcare device, an implant, a sensor / actuator, a display, or any other similar functioning device. Some of the UEs 104 may be referred to as IoT devices (e.g., parking meter, gas pump, toaster, vehicles, heart monitor, etc. ) . The UE 104 may also be referred to as a station, a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communications device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, or some other suitable terminology. In some scenarios, the term UE may also apply to one or more companion devices such as in a device constellation arrangement. One or more of these devices may collectively access the network and / or individually access the network.
[0057] Referring again to FIG. 1, in certain aspects, the UE 104 may include a CPU-sharing component 198. The CPU-sharing component 198 may be configured to transmit, to a network entity, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function; perform the AI / ML function based on the computational capability; and transmit, to the network entity based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing. In certain aspects, the base station 102 may include a CPU-sharing component 199. The CPU-sharing component 199 may be configured to receive, from a UE, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function; and receive, from the UE based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing. Although the following description may be focused on 5G NR, the concepts described herein may be applicable to other similar areas, such as LTE, LTE-A, CDMA, GSM, and other wireless technologies.
[0058] FIG. 2A is a diagram 200 illustrating an example of a first subframe within a 5G NR frame structure. FIG. 2B is a diagram 230 illustrating an example of DL channels within a 5G NR subframe. FIG. 2C is a diagram 250 illustrating an example of a second subframe within a 5G NR frame structure. FIG. 2D is a diagram 280 illustrating an example of UL channels within a 5G NR subframe. The 5G NR frame structure may be frequency division duplexed (FDD) in which for a particular set of subcarriers (carrier system bandwidth) , subframes within the set of subcarriers are dedicated for either DL or UL, or may be time division duplexed (TDD) in which for a particular set of subcarriers (carrier system bandwidth) , subframes within the set of subcarriers are dedicated for both DL and UL. In the examples provided by FIGs. 2A, 2C, the 5G NR frame structure is assumed to be TDD, with subframe 4 being configured with slot format 28 (with mostly DL) , where D is DL, U is UL, and F is flexible for use between DL / UL, and subframe 3 being configured with slot format 1 (with all UL) . While subframes 3, 4 are shown with slot formats 1, 28, respectively, any particular subframe may be configured with any of the various available slot formats 0-61. Slot formats 0, 1 are all DL, UL, respectively. Other slot formats 2-61 include a mix of DL, UL, and flexible symbols. UEs are configured with the slot format (dynamically through DL control information (DCI) , or semi-statically / statically through radio resource control (RRC) signaling) through a received slot format indicator (SFI) . Note that the description infra applies also to a 5G NR frame structure that is TDD.
[0059] FIGs. 2A-2D illustrate a frame structure, and the aspects of the present disclosure may be applicable to other wireless communication technologies, which may have a different frame structure and / or different channels. A frame (10 ms) may be divided into 10 equally sized subframes (1 ms) . Each subframe may include one or more time slots. Subframes may also include mini-slots, which may include 7, 4, or 2 symbols. Each slot may include 14 or 12 symbols, depending on whether the cyclic prefix (CP) is normal or extended. For normal CP, each slot may include 14 symbols, and for extended CP, each slot may include 12 symbols. The symbols on DL may be CP orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbols. The symbols on UL may be CP-OFDM symbols (for high throughput scenarios) or discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbols (for power limited scenarios; limited to a single stream transmission) . The number of slots within a subframe is based on the CP and the numerology. The numerology defines the subcarrier spacing (SCS) (see Table 1) . The symbol length / duration may scale with 1 / SCS.
[0060] Table 1: Numerology, SCS, and CP
[0061] For normal CP (14 symbols / slot) , different numerologies μ 0 to 4 allow for 1, 2, 4, 8, and 16 slots, respectively, per subframe. For extended CP, the numerology 2 allows for 4 slots per subframe. Accordingly, for normal CP and numerology μ, there are 14 symbols / slot and 2μ slots / subframe. The subcarrier spacing may be equal to 2μ*15 kHz, where μ is the numerology 0 to 4. As such, the numerology μ=0 has a subcarrier spacing of 15 kHz and the numerology μ=4 has a subcarrier spacing of 240 kHz. The symbol length / duration is inversely related to the subcarrier spacing. FIGs. 2A-2D provide an example of normal CP with 14 symbols per slot and numerology μ=2 with 4 slots per subframe. The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μs. Within a set of frames, there may be one or more different bandwidth parts (BWPs) (see FIG. 2B) that are frequency division multiplexed. Each BWP may have a particular numerology and CP (normal or extended) .
[0062] A resource grid may be used to represent the frame structure. Each time slot includes a resource block (RB) (also referred to as physical RBs (PRBs) ) that extends 12 consecutive subcarriers. The resource grid is divided into multiple resource elements (REs) . The number of bits carried by each RE depends on the modulation scheme.
[0063] As illustrated in FIG. 2A, some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include demodulation RS (DM-RS) (indicated as R for one particular configuration, but other DM-RS configurations are possible) and channel state information reference signals (CSI-RS) for channel estimation at the UE. The RS may also include beam measurement RS (BRS) , beam refinement RS (BRRS) , and phase tracking RS (PT-RS) .
[0064] FIG. 2B illustrates an example of various DL channels within a subframe of a frame. The physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs) , each CCE including six RE groups (REGs) , each REG including 12 consecutive REs in an OFDM symbol of an RB. A PDCCH within one BWP may be referred to as a control resource set (CORESET) . A UE is configured to monitor PDCCH candidates in a PDCCH search space (e.g., common search space, UE-specific search space) during PDCCH monitoring occasions on the CORESET, where the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs may be located at greater and / or lower frequencies across the channel bandwidth. A primary synchronization signal (PSS) may be within symbol 2 of particular subframes of a frame. The PSS is used by a UE 104 to determine subframe / symbol timing and a physical layer identity. A secondary synchronization signal (SSS) may be within symbol 4 of particular subframes of a frame. The SSS is used by a UE to determine a physical layer cell identity group number and radio frame timing. Based on the physical layer identity and the physical layer cell identity group number, the UE can determine a physical cell identifier (PCI) . Based on the PCI, the UE can determine the locations of the DM-RS. The physical broadcast channel (PBCH) , which carries a master information block (MIB) , may be logically grouped with the PSS and SSS to form a synchronization signal (SS) / PBCH block (also referred to as SS block (SSB) ) . The MIB provides a number of RBs in the system bandwidth and a system frame number (SFN) . The physical downlink shared channel (PDSCH) carries user data, broadcast system information not transmitted through the PBCH such as system information blocks (SIBs) , and paging messages.
[0065] As illustrated in FIG. 2C, some of the REs carry DM-RS (indicated as R for one particular configuration, but other DM-RS configurations are possible) for channel estimation at the base station. The UE may transmit DM-RS for the physical uplink control channel (PUCCH) and DM-RS for the physical uplink shared channel (PUSCH) . The PUSCH DM-RS may be transmitted in the first one or two symbols of the PUSCH. The PUCCH DM-RS may be transmitted in different configurations depending on whether short or long PUCCHs are transmitted and depending on the particular PUCCH format used. The UE may transmit sounding reference signals (SRS) . The SRS may be transmitted in the last symbol of a subframe. The SRS may have a comb structure, and a UE may transmit SRS on one of the combs. The SRS may be used by a base station for channel quality estimation to enable frequency-dependent scheduling on the UL.
[0066] FIG. 2D illustrates an example of various UL channels within a subframe of a frame. The PUCCH may be located as indicated in one configuration. The PUCCH carries uplink control information (UCI) , such as scheduling requests, a channel quality indicator (CQI) , a precoding matrix indicator (PMI) , a rank indicator (RI) , and hybrid automatic repeat request (HARQ) acknowledgment (ACK) (HARQ-ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACK and / or negative ACK (NACK) ) . The PUSCH carries data, and may additionally be used to carry a buffer status report (BSR) , a power headroom report (PHR) , and / or UCI.
[0067] FIG. 3 is a block diagram of a base station 310 in communication with a UE 350 in an access network. In the DL, Internet protocol (IP) packets may be provided to a controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functionality. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting of system information (e.g., MIB, SIBs) , RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release) , inter radio access technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (ciphering, deciphering, integrity protection, integrity verification) , and handover support functions; RLC layer functionality associated with the transfer of upper layer packet data units (PDUs) , error correction through ARQ, concatenation, segmentation, and reassembly of RLC service data units (SDUs) , re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs) , demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.
[0068] The transmit (TX) processor 316 and the receive (RX) processor 370 implement layer 1 functionality associated with various signal processing functions. Layer 1, which includes a physical (PHY) layer, may include error detection on the transport channels, forward error correction (FEC) coding / decoding of the transport channels, interleaving, rate matching, mapping onto physical channels, modulation / demodulation of physical channels, and MIMO antenna processing. The TX processor 316 handles mapping to signal constellations based on various modulation schemes (e.g., binary phase-shift keying (BPSK) , quadrature phase-shift keying (QPSK) , M-phase-shift keying (M-PSK) , M-quadrature amplitude modulation (M-QAM) ) . The coded and modulated symbols may then be split into parallel streams. Each stream may then be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., pilot) in the time and / or frequency domain, and then combined together using an Inverse Fast Fourier Transform (IFFT) to produce a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially precoded to produce multiple spatial streams. Channel estimates from a channel estimator 374 may be used to determine the coding and modulation scheme, as well as for spatial processing. The channel estimate may be derived from a reference signal and / or channel condition feedback transmitted by the UE 350. Each spatial stream may then be provided to a different antenna 320 via a separate transmitter 318Tx. Each transmitter 318Tx may modulate a radio frequency (RF) carrier with a respective spatial stream for transmission.
[0069] At the UE 350, each receiver 354Rx receives a signal through its respective antenna 352. Each receiver 354Rx recovers information modulated onto an RF carrier and provides the information to the receive (RX) processor 356. The TX processor 368 and the RX processor 356 implement layer 1 functionality associated with various signal processing functions. The RX processor 356 may perform spatial processing on the information to recover any spatial streams destined for the UE 350. If multiple spatial streams are destined for the UE 350, they may be combined by the RX processor 356 into a single OFDM symbol stream. The RX processor 356 then converts the OFDM symbol stream from the time-domain to the frequency domain using a Fast Fourier Transform (FFT) . The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier, and the reference signal, are recovered and demodulated by determining the most likely signal constellation points transmitted by the base station 310. These soft decisions may be based on channel estimates computed by the channel estimator 358. The soft decisions are then decoded and deinterleaved to recover the data and control signals that were originally transmitted by the base station 310 on the physical channel. The data and control signals are then provided to the controller / processor 359, which implements layer 3 and layer 2 functionality.
[0070] The controller / processor 359 can be associated with at least one memory 360 that stores program codes and data. The at least one memory 360 may be referred to as a computer-readable medium. In the UL, the controller / processor 359 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, and control signal processing to recover IP packets. The controller / processor 359 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.
[0071] Similar to the functionality described in connection with the DL transmission by the base station 310, the controller / processor 359 provides RRC layer functionality associated with system information (e.g., MIB, SIBs) acquisition, RRC connections, and measurement reporting; PDCP layer functionality associated with header compression / decompression, and security (ciphering, deciphering, integrity protection, integrity verification) ; RLC layer functionality associated with the transfer of upper layer PDUs, error correction through ARQ, concatenation, segmentation, and reassembly of RLC SDUs, re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.
[0072] Channel estimates derived by a channel estimator 358 from a reference signal or feedback transmitted by the base station 310 may be used by the TX processor 368 to select the appropriate coding and modulation schemes, and to facilitate spatial processing. The spatial streams generated by the TX processor 368 may be provided to different antenna 352 via separate transmitters 354Tx. Each transmitter 354Tx may modulate an RF carrier with a respective spatial stream for transmission.
[0073] The UL transmission is processed at the base station 310 in a manner similar to that described in connection with the receiver function at the UE 350. Each receiver 318Rx receives a signal through its respective antenna 320. Each receiver 318Rx recovers information modulated onto an RF carrier and provides the information to a RX processor 370.
[0074] The controller / processor 375 can be associated with at least one memory 376 that stores program codes and data. The at least one memory 376 may be referred to as a computer-readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover IP packets. The controller / processor 375 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.
[0075] At least one of the TX processor 368, the RX processor 356, and the controller / processor 359 may be configured to perform aspects in connection with the CPU-sharing component 198 of FIG. 1.
[0076] At least one of the TX processor 316, the RX processor 370, and the controller / processor 375 may be configured to perform aspects in connection with the CPU-sharing component 199 of FIG. 1.
[0077] Example aspects presented herein propose new UE capabilities reporting for processing CSI using AI / ML functionalities, including AI / ML based beam prediction and CSI compression or prediction. The UE capabilities that involve AI / ML CSI or beam prediction may be reported separately so that different types of hardware (e.g., dedicated GPU / NSP) may be allocated for the UE when AI / ML features kick in.
[0078] The deployment of AI / ML technologies in wireless communication has been growing steadily. Examples of these technologies include the AI / ML frameworks for air-interface corresponding to various target use cases regarding aspects such as their performance, complexity, and their potential impact on existing wireless communication specifications. Examples of the use cases may include the enhancement of channel state information (CSI) feedback, which includes efforts to reduce overhead, improve the accuracy of feedback, and enhance prediction capabilities. Another example of the use cases includes beam management, which includes beam prediction in the time domain, spatial domain, or both to reduce overhead and latency and to improve the accuracy of beam selection. Examples of the use cases may further include positioning accuracy enhancements for various scenarios, such as those with heavy non-line-of-sight (NLOS) conditions and AI / ML based CSI prediction.
[0079] In a wireless network, a UE may possess specific capabilities and behaviors for managing channel state information (CSI) reports. For example, the UE may possess two types of CSI report capabilities: the first type may be related to the reported number of simultaneous CSI calculations per component carrier (CC) that the UE can support, denoted by the parameter SimultaneousCSI-ReportsPerCC, and the second type may be related to the reported number of simultaneous CSI calculations for all of the CCs that the UE can support, denoted by the parameter SimultaneousCSI-ReportsAllCC. As used herein, the number of simultaneous CSI calculations the UE can support may be represented by the number of CSI processing units (CPUs) the UE supports.
[0080] These CPUs may be in an occupied state or an unoccupied state. An occupied CPU is a CPU that is currently engaged in calculating a CSI report, while an unoccupied CPU is a CPU that is not currently engaged in calculating a CSI report and is available for such a task. The number of available CPUs indicates the UE’s capacity to process CSI reports. For example, if a UE is using L CPUs for calculating the CSI reports for a given orthogonal frequency division multiplexing (OFDM) symbol (i.e., the L CPUs are occupied) , the UE has NCPU - L unoccupied CPUs available for other CSI report calculations, where NCPU represents the total number of CPUs the UE can support.
[0081] In some examples, the UE may have the flexibility to refrain from updating a subset of requested CSI reports (e.g., N – M CSI reports) with the lowest priority. For example, in a scenario N CSI reports start to occupy their respective CPUs on the same OFDM symbol, on which NCPU - L CPUs are in the unoccupied state. Each such CSI report, denoted as CSI report n (n=0, ..., N-1) , may occupy CPUs, with M being the largest value, such as the condition of is met. The number of different CSI report settings included by a single aperiodic CSI (AP CSI) triggering state may not exceed NCPU.
[0082] The specific number of occupied CPUs, denoted as OCPU, may vary depending on the report quantity of the CSI report, denoted as reportQuantity. As used herein, the report quantity of a CSI report may refer to the content of the CSI report. For example, OCPU may be equal to zero if reportQuantity of the corresponding CSI report setting is set to “none” and the CSI resource set associated with the CSI report setting is configured with parameter trs-Info; OCPU may be equal to 1 if reportQuantity of the corresponding CSI report setting is set to the value of parameters cri-RSRP, ssb-Index-RSRP, cri-SINR, or ssb-Index-SINR, or “none, ” while the CSI resource set associated with the CSI report setting is not configured with trs-Info; and OCPU may be equal to Ks, if reportQuantity of the corresponding CSI report setting is set to the value of parameters cri-RI-PMI-CQI, cri-RI-i1, cri-RI-i1-CQI, cri-RI-CQI, or cri-RI-LI-PMI-CQI, where Ks is the number of CSI-RS resources in the associated channel measurement resource (CMR) set.
[0083] The duration for which a CPU is occupied may vary based on the type of CSI report, reportQuantity of the CSI report, and trs-Info. In some examples, the reportQuantity may not be set to “none. ” In these scenarios, for persistent (P) or semi-persistent (SP) (P / SP) CSI reports (excluding the initial SP CSI report on the PUSCH after the PDCCH triggering the report) , the duration may span from the first symbol of the earliest of each CMR or interference measurement report (IMR) on the latest occasion no later than the corresponding CSI reference resource to the last symbol of the PUSCH / PUCCH carrying the CSI report. For AP CSI reports or the initial SP CSI report on the PUSCH triggered by DCI, the duration may span from the first symbol after the PDCCH triggering the CSI report to the last symbol of the scheduled PUSCH carrying the report.
[0084] In some examples, the reportQuantity may be set to “none” and trs-Info may not be configured for the CMR set. In these scenarios, for SP CSI reports (excluding the initial SP CSI report on the PUSCH after the PDCCH triggering the report) , the duration may span from the first symbol of the earliest one of each persistent or semi-persistent CSI-RS or synchronization signal block (SSB) occasions for CMR of layer 1 (L1) - reference signal received power (L1-RSRP) computation to a specific number of symbols (denoted as Z3’) after the last symbol of the latest one of the CSI-RS / SSB resource used for CMR for L1-RSRP computation in each transmission occasion. For AP CSI reports, the duration may span from the first symbol after the PDCCH triggering the CSI report to the last symbols between Z3’ symbols after the last symbol of the latest one of each CSI-RS / SSB resource for CMR for L1-RSRP computation, where Z3’ is a predefined number.
[0085] In some examples, the number of CPUs occupied by conventional CSI reports (or non-AI / ML CSI reports) and those occupied by AI / ML CSI reports may be separated. The computation of the report quantity of a conventional CSI report (or non-AI / ML CSI report) may not involve AI / ML based processing, while the computation of the report quantity of an AI / ML CSI report may be associated with AI / ML based processing. For example, the number of CPUs occupied by CSI reports carrying channel characteristic prediction results (which is associated with AI / ML based processing) may be separated from the number of CPUs occupied by CSI reports carrying a conventional type of reportQuantity, whose computation does not involve AI / ML based processing. In these scenarios, UE may report two types of capabilities: a per-CC capability and a cross-CC capability. The per-CC capability may be represented by the parameter SimultaneousCSI-ReportsPerCC-Prediction, and the cross-CC capability may be represented by the parameter SimultaneousCSI-ReportsAllCC-Prediction. The per-CC capability may indicate the maximum number of simultaneous active number of CPUs that can be engaged in processing such CSI reports with channel prediction results for each CC, and the cross-CC capability may indicate the maximum number of simultaneous active number of CPUs that can be engaged in processing such CSI reports across all of the CCs.
[0086] For a CSI report whose reportQuantity includes both conventional type of quantities and the quantities associated with AI / ML based processing, such as predicted channel characteristics, the CPU occupation may be counted differently. FIG. 4 is a diagram 400 illustrating an example CPU occupation for AI / ML based processing in accordance with various aspects of the present disclosure. In FIG. 4, the reportQuantity of a CSI report may include conventional non-AI / ML quantities or measurements (at 402) and the quantities associated with AI / ML based processing, such as AI / ML based prediction (at 404) . In this scenario, the number of CPUs occupied by such a CSI report may be defined as the CPUs used for a CSI report with reportQuantity being the conventional type of quantities, plus a certain number of additional CPUs (denoted as P) occupied for determining the predicted channel characteristics.
[0087] In one configuration, as shown in FIG. 4, these CPUs (e.g., P CPUs) may be counted toward the total number of occupied CPUs associated with SimultaneousCSI-ReportsPerCC-Prediction and SimultaneousCSI-ReportsAllCC-Prediction. The remaining CPUs occupied for conventional type of quantities may be counted towards the total number of occupied CPUs associated with SimultaneousCSI-ReportsPerCC and SimultaneousCSI-ReportsAllCC. For example, if the prediction involves L1-RSRP, L1 signal-to-interference-plus-noise ratios (L1-SINR) , or top-k-resources (i.e., the selection of the best k resources) , a certain additional number of CPUs (e.g., one additional CPU) may be counted for the corresponding CSI report.
[0088] In another configuration, the value of P may be predefined and, in some examples, may vary based on different prediction conditions. For example, if the prediction is in the time domain (TD) for T future time occasions, P may be increased proportionally with a larger T (e.g., P=pTT, where pT is a predefined number) . Similarly, if the prediction is related to the R prediction target resources, P may increase proportionally with a greater R (e.g., P=pRR, where pR is a predefined number) .
[0089] For a CSI report whose reportQuantity solely includes quantities associated with AI / ML capabilities, such as predicted channel characteristics, the CPU occupation may be counted differently. FIG. 5A is a diagram 500 illustrating an example of CPU occupation for AI / ML based processing in accordance with various aspects of the present disclosure. As shown in FIG. 5A, in one configuration, the number of CPUs occupied by such reports may be defined as P (at 504) , irrespective of any calculations related to measurement resources. In another configuration, the number of CPUs occupied by such reports may be defined as P+P’, where P’ is accounted for calculations associated with the measurement resources (at 502) . For example, if the predicted channel characteristic involves L1-RSRP, L1-SINR, or top-K-resources, P’ may be set to 1 to accommodate the UE’s calculation of L1-RSRPs or L1-SINRs of the measurement resources. If the predicted channel characteristics involve the precoding matrix indicator (PMI) , P’ may be set to be equal to the number of CMRs necessary for the UE to calculate the PMI of these CMRs. In these scenarios, P is the number of CPUs counted towards the total number of CPUs associated with SimultaneousCSI-ReportsPerCC-Prediction and SimultaneousCSI-ReportsAllCC-Prediction, while P’ is the number of CPUs occupied for measuring the measurement resources and are counted towards the number of occupied CPUs associated with SimultaneousCSI-ReportsPerCC and SimultaneousCSI-ReportsAllCC.
[0090] In another configuration, the value of P may be predefined and, in some examples, may vary based on different prediction conditions. For example, if the prediction is in the time domain (TD) for T future time occasions, P may be increased proportionally with a larger T (e.g., P=pTT, where pT is a predefined number) . Similarly, if the prediction is related to the R prediction target resources, P may increase proportionally with a greater R (e.g., P=pRR, where pR is a predefined number) .
[0091] In some examples, the UE may report the values of P, P’ , or both, as part of its capabilities. The reported values may differ depending on the T or R values.
[0092] In the AI / ML based channel state information feedback (CSF) and beam prediction, the CPUs may be concurrently occupied by the AI / ML based CSF and beam prediction due to the sharing of hardware accelerators, such as network signal processors (NSP) and graphics processing units (GPU) , across these applications. For example, dedicated hardware accelerators (e.g., NSP or GPU) may be shared for completing AI / ML based CSF and UE-side beam prediction tasks, while conventional CSI reports may typically rely on traditional firmware / software (FW / SW) computational resources. Hence, the occupied number of CPUs for AI / ML based feedback may be separated from those used for conventional (non-AI / ML) CSI reporting. This separation may allow for flexible allocation of hardware among different use cases (e.g., AI / ML based CSF and beam prediction) based on the complexity of the AI / ML models involved and the priorities of the related CSF and beam prediction problems. For example, a more complex CSF model may be paired with a simpler beam prediction model, or a simpler CSF mode may be paired with multiple beam prediction models targeting different sub-use cases like spatial and temporal domain predictions.
[0093] In some examples, UE capabilities and CPU occupation frameworks may be provided for the UE to report different aspects of its CPU usage. For example, the UE may report the number of CPUs for beam prediction use cases. In some examples, to more efficiently determine the hardware sharing among different AI / ML use cases, the UE capabilities and CPU occupation frameworks may consider both AI / ML based CSF and beam prediction. Example aspects presented herein introduce detailed signaling mechanisms and UE capability enhancements that enable a more efficient and concurrent CPU occupation framework across these AI / ML based tasks, such as the AI / ML based CSF and beam prediction.
[0094] In some aspects, the UE may report concurrent UE capabilities regarding the number of CPUs that can be occupied by AI / ML use cases. FIG. 5B is a diagram 550 illustrating an example of UE capabilities for conventional CSI reports and AI / ML CSI reports in accordance with various aspects of the present disclosure. In FIG. 5B, assuming that UEs may continue to report conventional capabilities on the number of CPUs (e.g., the supported number of CPUs that can be occupied for conventional non-AI / ML CSI reports at 552) , such as SimultaneousCSI-ReportsPerCC and SimultaneousCSI-ReportsAllCC, the UE may further report, at 554, on the joint capabilities on the maximum number of CPUs (or the supported number of CPUs) that can be occupied by AI / ML based CSI reports (e.g., the CSI reports the calculation of the associated report quantity is associated with AI / ML based processing) .
[0095] In some examples, such report quantity may include at least one of AI / ML based beam prediction 562, a CSI compression result or a CSI prediction result (at 560) . In some aspects, the beam prediction results (at 562) may include one or more of the following: a predicted L1-RSRP, a predicted L1-SINR, or a predicted top-K-resources in terms of predicted L1-RSRP / SINR for a set of SSB / CSI-RS / virtual resources (which may be referred to as “Set-A beams” ) without actual measurements for them. These predictions may be based on real measurements from a different set of SSB / CSI-RS resources (which may be referred to as “Set-B beams” ) . The beam prediction results may include different types of predictions, such as spatial prediction, where there are non-overlapping resources between Set-A and Set-B beams, temporal prediction, where the predicted quantities regarding Set-A are with respect to future temporal occasions, and frequency or mobility prediction, where the resources for Set-A and Set-B beams are defined in different Bandwidth Parts (BWPs) , CCs, or frequency ranges (FRs) , or cells.
[0096] In some aspects, the AI / ML based CSI compression or prediction (at 560) may include two-sided model based CSI compression and decompression. For example, the raw PMI for the CSI compression and decompression may be compressed by the UE using a first AI / ML model and then packed into the uplink control information (UCI) payload sent to the network. Upon receiving the UCI payload, the network may decompress the received UCI payload using a second AI / ML model. In some examples, the AI / ML based CSI compression or prediction may include a predicted PMI associated with future temporal occasions, which may be compressed or decompressed using these two-sided models. The concurrent UE capabilities on the number of CPUs that can be occupied by AI / ML use cases may include a first capability defined per CC and a second capability defined across all of the CCs. For example, the first capability may be a first supported number of CPUs that can be occupied by the AI / ML based CSI reports for each CC and may be represented by the parameter SimultaneousCSI-ReportsPerCC-AIML. The second capability may be a second supported number of CPUs that can be occupied by the AI / ML based CSI reports for all of the CCs and may be presented by the parameter SimultaneousCSI-ReportsAllCC-AIML.
[0097] In some aspects, in addition to the concurrent UE capabilities on the number of CPUs occupied by AI / ML use cases, as described above, the UE capabilities may further include a set of capabilities related to the maximum number of CPUs (or the supported number of CPUs) that can be occupied by UE for each respective use cases. For example, the UE may report the maximum number of CPUs that can be occupied by CSI reports whose reportQuantity is associated with beam prediction results reporting, and the maximum number of CPUs that can be occupied by CSI reports whose reportQuantity is associated with AI / ML based CSI compression or prediction. Each of these capabilities may include a first capability defined per CC and a second capability defined across all CCs. For example, for AI / ML based CSI compression or prediction, the UE’s capabilities for each individual CC may be represented by the parameter SimultaneousCSI-ReportsPerCC-AIML-CSI, and the UE’s capability across all CCs may be represented by the parameter SimultaneousCSI-ReportsAllCC-CSI. Similarly, for beam prediction results reporting, the UE’s capabilities for each individual CC may be presented by the parameter SimultaneousCSI-ReportsPerCC-AIML-BM, and the UE’s capability across all CCs may be represented by the parameter SimultaneousCSI-ReportsAllCC-BM.
[0098] In some aspects, certain limitations or restrictions may be placed on the UE’s capabilities related to individual use cases in relation to the broader, cross-use case capabilities. In some examples, for any given use case, functionality, or model, the maximum number of CPUs that can be occupied may not exceed the overall maximum number of CPUs designated for all use cases, functionalities, or models. Hence, the capabilities such as SimultaneousCSI-ReportsPerCC-AIML-CSI and SimultaneousCSI-ReportsPerCC-AIML-BM may be less than or equal to SimultaneousCSI-ReportsPerCC-AIML, and similarly, the capabilities SimultaneousCSI-ReportsAllCC-AIML-CSI and SimultaneousCSI-ReportsAllCC-AIML-BM may be less than or equal to SimultaneousCSI-ReportsAllCC-AIML.
[0099] On the other hand, the sum of these specific capabilities may or may not have restrictions when compared to the overall capacity for all use cases. For example, in one configuration, there may be no restrictions, allowing the sum of the maximum number of CPUs for different use cases, functionalities, or models to be less than, equal to, or greater than the maximum number of CPUs across all use cases, functionalities, or models. That is, the sum of SimultaneousCSI-ReportsPerCC-AIML-CSI and SimultaneousCSI-ReportsPerCC-AIML-BM may be less than, equal to, or greater than SimultaneousCSI-ReportsPerCC-AIML, and the sum of SimultaneousCSI-ReportsAllCC-AIML-CSI and SimultaneousCSI-ReportsAllCC-AIML-BM may be less than, equal to, or greater-than SimultaneousCSI-ReportsAllCC-AIML.
[0100] In another configuration, the sum of the maximum number of CPUs for different use cases, functionalities, or models may be restricted to be less than or equal to the overall maximum number of CPUs allocated for all use cases, functionalities, or models. That is, the sum of SimultaneousCSI-ReportsPerCC-AIML-CSI and SimultaneousCSI-ReportsPerCC-AIML-BM may be less than or equal to SimultaneousCSI-ReportsPerCC-AIML, and the sum of SimultaneousCSI-ReportsAllCC-AIML-CSI and SimultaneousCSI-ReportsAllCC-AIML-BM may be less than or equal to SimultaneousCSI-ReportsAllCC-AIML.
[0101] The relationships between the conventional (non-AI / ML) capabilities on the maximum number of CPUs that may be occupied by the conventional (non-AI / ML) CSI reports and the concurrent UE capabilities on the maximum number of CPUs that are occupied by the AI / ML CSI reports may be set according to specific conditions.
[0102] In some aspects, the CPU occupations for AI / ML based CSI reports may be separated from those for conventional (non-AI / ML) CSI reports. Under this arrangement, the number of CPUs occupied for conventional (non-AI / ML) CSI reports, whose reportQuantity is not associated with AI / ML use cases, may count towards the maximum number of CPUs for conventional (non-AI / ML) CSI reports. On the other hand, the number of CPUs occupied by AI / ML CSI reports, whose reportQuantity is associated with AI / ML use cases such as AI / ML based CSI compression or prediction, or beam prediction, may count towards the maximum number of CPUs that are designated for AI / ML use cases. This setup may be a default mechanism without further signaling or instructions from the base station (e.g., a gNB) .
[0103] In some aspects, AI / ML CSI reports may be allowed to occupy CPUs reserved for conventional (non-AI / ML) CSI reports. In this scenario, while conventional (non-AI / ML) CSI reports whose reportQuantity is not associated with AI / ML use cases may still occupy CPUs associated with the maximum number of conventional (non-AI / ML) CPU numbers, certain AI / ML CSI reports whose reportQuantity associated with AI / ML use cases (e.g., AI / ML based CSI compression or prediction or beam prediction) may alternatively occupy CPUs associated with the maximum number of CPUs for conventional (non-AI / ML) CSI reports.
[0104] FIG. 6 is a diagram 600 illustrating an example of UE capabilities for conventional CSI reports and AI / ML CSI reports in accordance with various aspects of the present disclosure. In FIG. 6, hardware accelerators (e.g., NSP or GPU at 604 or 606) may be shared with AI / ML based positioning use cases (at 614) , which may not be operated as frequently as beam prediction (at 614) or CSI compression or prediction 610. During urgent positioning tasks (at 614) , the UE might move some AI / ML calculations, such as low-complexity beam predictions (at 612) , to conventional firmware / software (at 602) , thereby occupying CPUs associated with conventional type of CSI reports (whose reportQuantity is not associated with AI / ML based processing) .
[0105] In some examples, UEs may use a medium access control (MAC) – control element (MAC-CE) to request that CSI reports associated with certain AI / ML functionalities or models (e.g., the AI / ML based positioning use cases at 614) , along with associated conditions (e.g., narrow-to-narrow beam prediction where the number of Set-A beams is below 24) , may alternatively occupy the conventional maximum number of CPUs (at 602) instead of the CPUs dedicated to AI / ML use cases (e.g., at 604) . In some examples, the UE may further request a reduction in the maximum number of CPUs for certain AI / ML use cases, functionalities, or models. In some examples, after the UE requested the CSI reports associated with certain AI / ML functionalities or models to occupy the conventional maximum number of CPUs, the UE may further request that certain AI / ML use cases, functionalities, or models switch back to occupy the CPUs dedicated for AI / ML. For example, during an urgent positioning task (at 614) , the UE may move the AI / ML beam prediction 612 to conventional FW / SW (e.g., at 602) to allow the positioning use cases (at 614) to occupy dedicated hardware for AI / ML use cases. After the positioning task is completed, the UE may switch the AI / ML beam prediction 612 back to occupy the CPUs for the AI / ML use cases. In these examples, UEs may await confirmations from the base station (e.g., a gNB) before proceeding with these CPU occupation adjustments.
[0106] In some aspects, a UE may refrain from updating certain CSI reports based on the CPU occupation, for example, in scenarios involving the concurrent use of CPUs for both conventional non-AI / ML tasks and AI / ML based tasks. In some aspects, UEs may identify and manage CSI reports that should be refrained based on the maximum number of CPUs allocated for both conventional non-AI / ML tasks and AI / ML based tasks. For example, if the scheduled CSI reports associated with the maximum number of CPUs for AI / ML use cases exceeds the UE’s reported capabilities for AI / ML use cases (in terms of the maximum CPU occupation) , the UE may either drop or stop updating the CSI reports that are exclusively associated with the maximum number of CPUs for AI / ML use cases. This decision may be based on the inter-CSI priority rules, which involve comparing the predefined inter-CSI report priorities of the scheduled CSI reports associated with the maximum number of CPUs for AI / ML use cases. This approach may also be applicable to conventional types of CSI reports.
[0107] In some examples, a CSI report associated with AI / ML functionalities or models may temporarily occupy conventional non-AI / ML CPUs. In such situations, the decision on whether to drop or stop updating a CSI report may be based on an inter-CSI priority comparison with other CSI reports that are also occupying the conventional CPUs. This means that if an AI / ML CSI report is temporarily occupying conventional CPUs, its priority may be compared with other CSI reports in the same CPU category or CPU occupation to determine if its updating process should be refrained or completely discontinued.
[0108] FIG. 7 is a diagram 700 illustrating an example of the concurrent UE capabilities on the number of CPUs occupied by the AI / ML use cases for a UE in accordance with various aspects of the present disclosure. As shown in FIG. 7, the UE 752 may support different numbers of CPUs for conventional non-AI / ML CSI reports (whose reportQuantity is not based on AI / ML based processing) and AI / ML CSI reports (whose reportQuantity is based on AI / ML based processing) . In the example in FIG. 7, the maximum number of CPUs (or the supported number of CPUs) for non-AI / ML CSI reports may be four (e.g., CPUs 702, 704, 706, and 708) , and the maximum number of CPUs for AI / ML CSI reports may be three for each individual CC (e.g., CPUs 712, 714, and 716 for CC1 710, and CPUs 722, 724, and 726 for CC2 720) and six for all of the CCs. The UE 752 may transmit a capability indicator of its computational capability to the base station 754. The indicator may indicate to the network the maximum numbers of CPUs the UE can support for non-AI / ML and AI / ML CSI reports (e.g., four CPUs for non-AI / ML CSI reports, three per-CC CPUs, and six cross-CC CPUs for AI / ML CSI reports) . The UE 752 may utilize (or occupy) the number of CPUs for non-AI / ML CSI reports (e.g., CPU 702) to transmit the non-AI / ML CSI reports to the base station 754 at 740, and utilize (or occupy) the number of CPUs for AI / ML CSI reports (e.g., CPU 712) to transmit the AI / ML CSI reports to the base station 754 at 750. The reportQuantity in the AI / ML CSI reports sent at 750 may include, for example, the beam prediction result, the CSI prediction result, or the CSI compression result. In some examples, the UE 752 may send a CPU occupation request to the base station 754 to allow an AI / ML CSI report to occupy a non-AI / ML CPU (e.g., CPU 702) , for example, when a more urgent AI / ML CSI report needs to occupy available AI / ML CPUs. In some examples, when the number of AI / ML CSI reports exceeds the maximum number of CPUs for the AI / ML CSI reports (e.g., three per-CC CPUs or six cross-CC CPUs) , the UE 752 may refrain from updating one or more AI / ML CSI reports based on, for example, the priorities of these AI / ML CSI reports.
[0109] FIG. 8 is a call flow diagram 800 illustrating a method of wireless communication in accordance with various aspects of this present disclosure. Various aspects are described in connection with a UE 802 and a base station 804. The aspects may be performed by the UE 802 or the base station 804 in aggregation and / or by one or more components of a base station 804 (e.g., a CU 110, a DU 130, and / or an RU 140) .
[0110] As shown in FIG. 8, a UE 802 may, at 806, transmit a capability indicator to the base station 804. The capability indicator may indicate the computational capability of the UE 802. In some examples, the computational capability may include an AI / ML capability for processing an AI / ML function (at 830) . The AI / ML capability may include the maximum number of CSI processing units (CPUs) that can be occupied by the CSI reports that carry report quantities associated with AI / ML functions. For example, referring to FIG. 5B, these report quantities may include AI / ML based channel state information feedback, such as CSI compression / prediction (at 560) , or AI / ML based beam prediction results (at 562) , or both. The AI / ML capability may include the first capability defined per CC and the second capability defined across all of the CCs. For example, the AI / ML capability may include a first maximum number of CPUs (or a first support number of CPUs) that can be occupied by the AI / ML CSI reports for each CC of a set of CC (at 834) , and a second maximum number of CPUs (or a second supported number of CPUs) that can be occupied by the AI / ML CSI report across all of the CCs (at 836) .
[0111] In some examples, the computational capability may include a non-AI / ML capability that includes a non-AI / ML number of CPUs for one or more non-AI / ML CSI reports (at 832) . For example, referring to FIG. 5B, the conventional (non-AI / ML) capability may include a non-AI / ML number of CPUs (at 552) that can be occupied by the CSI reports whose report quantities are not associated with the AI / ML functions.
[0112] At 808, the UE 802 may transmit, to the base station 804 via a MAC-CE, a CPU occupation request for the CPU occupation of the at least one AI / ML CSI report on the non-AI / ML number of CPUs. For example, the CPU occupation request may include one or more of: the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, or the condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs. For example, referring to FIG. 6, during an urgent positioning task (at 614) , the UE may request that the AI / ML beam prediction (at 612) to occupy the non-AI / ML number of CPUs (at 602) .
[0113] If the base station 804 confirms the CPU occupation request, the UE 802 may, at 810, receive a first confirmation of the CPU occupation request.
[0114] At 812, the UE 802 may transmit, to the base station 804 via the MAC-CE, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report to the first supported number of CPUs or the second supported number of CPUs. For example, when an AI / ML CSI report occupies one of the non-AI / ML number of CPUs based on the CPU occupation request the UE 802 sent on 808, the UE 802 may transmit a switch request at 812 to request that AI / ML CSI report to occupy the AI / ML capability (e.g., to occupy the first supported number of CPUs or the second supported number of CPUs) . For example, referring to FIG. 6, if the AI / ML beam prediction (at 612) occupies the non-AI / ML number of CPUs (at 602) due to an urgent positioning task (at 614) , after the urgent positioning task (at 614) is completed, the UE may send a switch request to change of the CPU occupation of the AI / ML beam prediction (at 612) back to the number of CPUs for the AI / ML CSI reports (e.g., at 604) .
[0115] If the base station 804 confirms the switch request, the UE 802 may, at 814, receive a second confirmation of the switch request.
[0116] At 816, the UE 802 may perform the AI / ML function based on the computational capability. For example, the AI / ML function may include the AI / ML based CSF, the AI / ML based beam prediction on the UE side.
[0117] In some aspects, the UE 802 may move at least one of the AI / ML CSI reports to occupy non-AI / ML number of CPUs. For example, at 818, the UE 802 may select the at least one AI / ML CSI report based on the urgency of the report quantity for the at least one AI / ML CSI report, or the complexity for the computation of the report quantity for the at least one AI / ML CSI report, or both. For example, the report quantities of the AI / ML CSI reports may include AI / ML based positioning results (at 614) . Assuming the AI / ML based positioning result is more urgent than the AI / ML based beam prediction, the UE 802 may select the AI / ML CSI reports for the beam prediction to occupy the non-AI / ML number of CPUs (at 602) , to allow more urgent AI / ML based positioning (at 614) to occupy the CPUs associated with AI / ML functions (at 606) .
[0118] In some aspects, the UE 802 may refrain from updating or transmitting the CSI reports. For example, at 820, when the number of the one or more AI / ML CSI reports exceeds the first supported number, the second supported number, or both the UE 802 may identify one or more refrained CSI reports from the one or more AI / ML CSI reports. The choice of the CSI reports to be refrained may be based on the inter-CSI priorities of the one or more AI / ML CSI reports.
[0119] At 822, the UE 802 may refrain from updating the one or more refrained CSI reports the UE 802 identified at 820.
[0120] At 824, the UE 802 may transmit, to the base station 804 based on the computational capability (at 806) , one or more AI / ML CSI reports. The one or more AI / ML CSI may include the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. For example, the report quantities of the AI / ML CSI reports may include AI / ML based beam prediction result (e.g., at 562, 612) , AI / ML based CSI prediction result or compression result (e.g., at 560, 610) .
[0121] FIG. 9 is a flowchart 900 illustrating methods of wireless communication at a UE in accordance with various aspects of the present disclosure. The method may be performed by a UE. The UE may be the UE 104, 350, 752, 802, or the apparatus 1304 in the hardware implementation of FIG. 13. The methods provide detailed signaling mechanisms and UE capability enhancements to enable concurrent CPU occupation frameworks across AI / ML based CSF and beam prediction results reporting, thereby allowing for more efficient and flexible hardware utilization, including dedicated hardware accelerators like NSP and GPU.
[0122] As shown in FIG. 9, at 902, the UE may transmit, to a network entity, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function. The network entity may be a base station, or a component of a base station, in the access network of FIG. 1 or a core network component (e.g., base station 102, 310, 754, 804; or the network entity 1302 in the hardware implementation of FIG. 13) . FIGs. 5A, 5B, 6, 7, and 8 illustrate various aspects of the steps in connection with flowchart 900. For example, referring to FIG. 8, the UE 802 may, at 806, transmit to a network entity (base station 804) a capability indicator of a computational capability. The computation capability may include an AI / ML capability for processing an AI / ML function (at 830) . In some aspects, 902 may be performed by the CPU-sharing component 198.
[0123] At 904, the UE may perform the AI / ML function based on the computational capability. For example, referring to FIG. 8, the UE 802 may, at 816, perform the AI / ML function based on the computational capability. In some aspects, 904 may be performed by the CPU-sharing component 198.
[0124] At 906, the UE may transmit, to the network entity based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. For example, referring to FIG. 8, the UE 802 may, at 824, transmit to the network entity (base station 804) based on the AI / ML function (at 830) one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. Referring to FIG. 7, the UE 752 may transmit the one or more AI / ML CSI reports at 750 to the base station 754. In some aspects, 906 may be performed by the CPU-sharing component 198.
[0125] FIG. 10 is a flowchart 1000 illustrating methods of wireless communication at a UE in accordance with various aspects of the present disclosure. The method may be performed by a UE. The UE may be the UE 104, 350, 752, 802, or the apparatus 1304 in the hardware implementation of FIG. 13. The methods provide detailed signaling mechanisms and UE capability enhancements to enable concurrent CPU occupation frameworks across AI / ML based CSF and beam prediction results reporting, thereby allowing for more efficient and flexible hardware utilization, including dedicated hardware accelerators like NSP and GPU.
[0126] As shown in FIG. 10, at 1002, the UE may transmit, to a network entity, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function. The network entity may be a base station, or a component of a base station, in the access network of FIG. 1 or a core network component (e.g., base station 102, 310, 754, 804; or the network entity 1302 in the hardware implementation of FIG. 13) . FIGs. 5A, 5B, 6, 7, and 8 illustrate various aspects of the steps in connection with flowchart 1000. For example, referring to FIG. 8, the UE 802 may, at 806, transmit to a network entity (base station 804) a capability indicator of a computational capability. The computation capability may include an AI / ML capability for processing an AI / ML function (at 830) . Referring to FIG. 7, the UE 752 may transmit the one or more AI / ML CSI reports at 750 to the base station 754. In some aspects, 1002 may be performed by the CPU-sharing component 198.
[0127] At 1008, the UE may perform the AI / ML function based on the computational capability. For example, referring to FIG. 8, the UE 802 may, at 816, perform the AI / ML function based on the computational capability. In some aspects, 1008 may be performed by the CPU-sharing component 198.
[0128] At 1014, the UE may transmit, to the network entity based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. For example, referring to FIG. 8, the UE 802 may, at 824, transmit to the network entity (base station 804) based on the AI / ML function (at 830) one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. In some aspects, 1014 may be performed by the CPU-sharing component 198.
[0129] In some aspects, the AI / ML capability may include at least one of: a first supported number of CPUs occupied by the one or more AI / ML CSI reports associated with each CC of a set of CCs (at 1020) , or a second supported number of CPUs occupied by the one or more AI / ML CSI reports for all of the set of CCs (at 1022) . For example, referring to FIG. 8, the AI / ML capability (at 830) may include at least one of: a first supported number of CPUs occupied by the one or more AI / ML CSI reports associated with each CC of a set of CCs (at 834) , or a second supported number of CPUs occupied by the one or more AI / ML CSI reports for all of the set of CCs (at 836) . For example, the first supported number of CPUs may be represented by the parameter SimultaneousCSI-ReportsPerCC-AIML, and the second supported number of CPUs may be represented by the parameter SimultaneousCSI-ReportsAllCC-AIML. Referring to FIG. 7, the first supported number of CPUs may be three (e.g., CPUs 712, 714, 716 for CC1 710) , and the second supported number of CPUs may be six.
[0130] In some aspects, the report quantity for each of the one or more AI / ML CSI reports may include one or more of: a beam prediction result (at 1030) , a CSI prediction result, or a CSI compression result (at 1034) . For example, referring to FIG. 5B, the report quantity for each of the one or more AI / ML CSI reports may include one or more of: a beam prediction result (at 562) , a CSI prediction result or a CSI compression result (at 560) .
[0131] In some aspects, the beam prediction result (at 1030) may include one or more of: a predicted L1 RSRP or L1 SINR for each of a first set of beams based on measurements for a second set of beams, a predicted number of beams for the first set of beams based on the measurements for the second set of beams, a spatial prediction for the first set of beams based on the measurements for the second set of beams, where first resources for the first set of beams do not overlap with second resources for the second set of beams, a temporal prediction for the first set of beams for one or more future temporal occasions, or a frequency or mobility prediction for the first set of beams based on the measurements for the second set of beams, where the first set of beams and the second set of beams are associated with different BWPs, CCs, FRs, or cells. For example, referring to FIG. 5B, beam prediction result (at 562) may include one or more of: the predicted L1-RSRP or L1-SINR for each of the first set of beams based on measurements for a second set of beams, the predicted number of beams for the first set of beams based on the measurements for the second set of beams, a spatial prediction for the first set of beams based on the measurements for the second set of beams, where first resources for the first set of beams do not overlap with second resources for the second set of beams, a temporal prediction for the first set of beams for one or more future temporal occasions, or a frequency or mobility prediction for the first set of beams based on the measurements for the second set of beams, where the first set of beams and the second set of beams are associated with different BWPs, CCs, FRs, or cells.
[0132] In some aspects, the CSI prediction result (at 1032) may include one or more of: a model for CSI compression and decompression, or a predicted PMI associated with one or more future temporal occasions. The PMI associated with the CSI compression and decompression may be compressed using a first AI / ML model and decompressed using a second AI / ML model. For example, referring to FIG. 5B, the CSI prediction result (at 560) may include one or more of: a model for CSI compression and decompression, or a predicted PMI associated with one or more future temporal occasions. The PMI associated with the CSI compression and decompression may be compressed using a first AI / ML model and decompressed using a second AI / ML model.
[0133] In some aspects, the AI / ML capability may further include one or more of: a beam prediction capability associated with a first portion of the one or more AI / ML CSI reports (at 1024) , where the report quantity for each of the one or more AI / ML CSI reports in the first portion of the one or more AI / ML CSI reports includes the beam prediction result, or a CSI capability associated with a second portion of the one or more AI / ML CSI reports (at 1026) , where the report quantity for each of the one or more AI / ML CSI reports in the second portion of the one or more AI / ML CSI reports includes the CSI prediction result or the CSI compression result. For example, referring to FIG. 8, the AI / ML capability (at 830) may further include one or more of: a beam prediction capability associated with a first portion of the one or more AI / ML CSI reports, where the report quantity for each of the one or more AI / ML CSI reports in the first portion of the one or more AI / ML CSI reports includes the beam prediction result. The AI / ML capability (at 830) may further include a CSI capability associated with a second portion of the one or more AI / ML CSI reports, where the report quantity for each of the one or more AI / ML CSI reports in the second portion of the one or more AI / ML CSI reports includes the CSI prediction result or the CSI compression result.
[0134] In some aspects, the beam prediction capability (at 1024) may include: a third supported number of CPUs occupied by the first portion of the one or more AI / ML CSI reports associated with each CC of the set of CCs; and a fourth supported number of CPUs occupied by the first portion of the one or more AI / ML CSI reports for all of the set of CCs. The CSI capability (at 1026) may include: a fifth supported number of CPUs occupied by the second portion of the one or more AI / ML CSI reports associated with each CC of the set of CCs; and a sixth supported number of CPUs occupied by the second portion of the one or more AI / ML CSI reports for all of the set of CCs. For example, the third supported number of CPUs occupied by the first portion of the one or more AI / ML CSI reports associated with each CC may be represented by the parameter SimultaneousCSI-ReportsPerCC-AIML-BM, the fourth supported number of CPUs occupied by the first portion of the one or more AI / ML CSI reports for all of the set of CCs may be represented by the parameter SimultaneousCSI-ReportsAllCC-AIML-BM. The fifth supported number of CPUs occupied by the second portion of the one or more AI / ML CSI reports associated with each CC may be represented by the parameter SimultaneousCSI-ReportsPerCC-AIML-CSI, and the sixth supported number of CPUs occupied by the second portion of the one or more AI / ML CSI reports for all of the set of CCs may be represented by the parameter SimultaneousCSI-ReportsAllCC-AIML-CSI.
[0135] In some aspects, the third supported number of CPUs may be less than or equal to the first supported number of CPUs, the fifth supported number of CPUs may be less than or equal to the first supported number of CPUs, the fourth supported number of CPUs may be less than or equal to the second supported number of CPUs, and the sixth supported number of CPUs may be less than or equal to the second supported number of CPUs. For example, the following restriction may apply to the parameters: SimultaneousCSI-ReportsPerCC-AIML-CSI ≤ SimultaneousCSI-ReportsPerCC-AIML, SimultaneousCSI-ReportsPerCC-AIML-BM≤ SimultaneousCSI-ReportsPerCC-AIML, SimultaneousCSI-ReportsAllCC-AIML-CSI ≤ SimultaneousCSI-ReportsAllCC-AIML, and SimultaneousCSI-ReportsAllCC-AIML-BM ≤ SimultaneousCSI-ReportsAllCC-AIML.
[0136] In some aspects, the first sum of the third supported number of CPUs and the fifth supported number of CPUs may be less than or equal to the first supported number of CPUs, and the second sum of the fourth supported number of CPUs and the sixth supported number of CPUs may be less than or equal to the second supported number of CPUs. For example, the following restrictions may apply to the parameters: SimultaneousCSI-ReportsPerCC-AIML-CSI+SimultaneousCSI-ReportsPerCC-AIML-BM≤SimultaneousCSI-ReportsPerCC-AIML, and SimultaneousCSI- ReportsAllCC-AIML-CSI+SimultaneousCSI-ReportsAllCC-AIML-BM ≤ SimultaneousCSI-ReportsAllCC-AIML.
[0137] In some aspects, the computational capability (at 1002) may further include a non-AI / ML capability (at 1028) including a non-AI / ML number of CPUs for one or more non-AI / ML CSI reports. The report quantity for each of the one or more non-AI / ML CSI reports may not be associated with the AI / ML based processing, and the one or more non-AI / ML CSI reports may not occupy the first supported number of CPUs or the second supported number of CPUs. For example, referring to FIG. 8, the computational capability (at 806) may further include a non-AI / ML capability (at 832) including a non-AI / ML number of CPUs for one or more non-AI / ML CSI reports. The report quantity for each of the one or more non-AI / ML CSI reports may not be associated with the AI / ML based processing, and the one or more non-AI / ML CSI reports may not occupy the first supported number of CPUs or the second supported number of CPUs.
[0138] In some aspects, the one or more AI / ML CSI reports may not occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports. For example, referring to FIG. 5B, the one or more AI / ML CSI reports (e.g., the CSI report for beam prediction at 562) may not occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports (at 552) .
[0139] In some aspects, at least one AI / ML CSI report of the one or more AI / ML CSI reports may occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports. For example, referring to FIG. 6, at least one AI / ML CSI report of the one or more AI / ML CSI reports (e.g., the CSI report for beam prediction at 612) may occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports (at 602) . Referring to FIG. 7, at least one AI / ML CSI report of the one or more AI / ML CSI reports may occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports (e.g., CPU 702) .
[0140] In some aspects, at 1010, the UE may select the at least one AI / ML CSI report based on one or more of: the urgency of the report quantity for the at least one AI / ML CSI report, or the complexity for a computation of the report quantity for the at least one AI / ML CSI report. For example, referring to FIG. 8, the UE 802 may, at 818, select the at least one AI / ML CSI report based on one or more of: the urgency of the report quantity for the at least one AI / ML CSI report, or the complexity for a computation of the report quantity for the at least one AI / ML CSI report. Referring to FIG. 6, the UE may select the AI / ML beam prediction (at 612) to occupy the non-AI / ML number of CPUs (at 602) based on the urgency of the beam prediction report (e.g., the beam prediction may be less urgent than the positioning task at 614) , or the complexity for the computation of the beam prediction results (e.g., the beam prediction may involve a relatively low computational complexity) . In some aspects, 1010 may be performed by the CPU-sharing component 198.
[0141] In some aspects, at 1004, the UE may transmit, to the network entity via a MAC-CE, a CPU occupation request for a CPU occupation of the at least one AI / ML CSI report on the non-AI / ML number of CPUs; and receive a first confirmation of the CPU occupation request. The CPU occupation request may include one or more of: the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, or the condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs. To perform the AI / ML function based on the computational capability (at 1008) , the UE may perform the AI / ML function based on the computational capability and the CPU occupation of the at least one AI / ML CSI report. For example, referring to FIG. 6 and FIG. 8, the UE 802 may transmit, at 808, to the network entity (base station 804) via a MAC-CE, a CPU occupation request for a CPU occupation of the at least one AI / ML CSI report (e.g., beam prediction at 612) on the non-AI / ML number of CPUs (at 602) ; and, at 810, receive a first confirmation of the CPU occupation request. The CPU occupation request may include one or more of: the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, or the condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs. To perform the AI / ML function based on the computational capability (at 816) , the UE 802 may perform the AI / ML function based on the computational capability and the CPU occupation of the at least one AI / ML CSI report. In some aspects, 1004 may be performed by the CPU-sharing component 198.
[0142] In some aspects, at 1006, the UE may transmit, to the network entity via a MAC-CE, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report to the first supported number of CPUs or the second supported number of CPUs; and receive, from the network entity, a second confirmation of the switch request. For example, referring to FIG. 6 and FIG. 8, the UE 802 may, at 812, transmit, to the network entity (base station 804) via a MAC-CE, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report (e.g., beam prediction at 612) to the first supported number of CPUs or the second supported number of CPUs (e.g., at 604) ; and receive, at 814, from the network entity (base station 804) , a second confirmation of the switch request. For example, if the AI / ML beam prediction (at 612) occupies the non-AI / ML number of CPUs (at 602) due to an urgent positioning task (at 614) , after the urgent positioning task (at 614) is completed, the UE may send a switch request to change of the CPU occupation of the AI / ML beam prediction (at 612) back to the number of CPUs for the AI / ML CSI reports (e.g., at 604) . In some aspects, 1006 may be performed by the CPU-sharing component 198.
[0143] In some aspects, at 1012, the UE may identify, based on the number of the one or more AI / ML CSI reports that exceeds one or more of the first supported number of CPUs or the second supported number of CPUs, one or more refrained CSI reports of the one or more AI / ML CSI reports; and refrain from updating the one or more refrained CSI reports. For example, referring to FIG. 8, the UE 802 may, at 820, identify, based on the number of the one or more AI / ML CSI reports that exceeds one or more of the first supported number of CPUs or the second supported number of CPUs, one or more refrained CSI reports of the one or more AI / ML CSI reports; and, at 822, refrain from updating the one or more refrained CSI reports. For example, if the number of the AI / ML CSI reports has exceeded SimultaneousCSI-ReportsPerCC-AIML (for any individual CC) or SimultaneousCSI-ReportsAllCC-AIML (for all of the CCs combined) , the UE may refrain from updating one or more selected AI / ML CSI reports. In some aspects, 1012 may be performed by the CPU-sharing component 198.
[0144] In some aspects, each of the one or more AI / ML CSI reports has an inter-CSI priority. To identify the one or more refrained CSI reports of the one or more AI / ML CSI reports (at 1012) , the UE may identify the refrained CSI reports based on a comparison of the inter-CSI priority for the one or more AI / ML CSI reports. For example, referring to FIG. 8, to identify the one or more refrained CSI reports of the one or more AI / ML CSI reports (at 820) , the UE 802 may identify the refrained CSI reports based on a comparison of the inter-CSI priority for the one or more AI / ML CSI reports.
[0145] In some aspects, each of the one or more AI / ML CSI reports and the one or more non-AI / ML CSI reports may have an inter-CSI priority. To identify the one or more refrained CSI reports of the one or more AI / ML CSI reports (at 1012) , the UE may identify the refrained CSI reports based on a comparison of the inter-CSI priority associated with the one or more AI / ML CSI reports and the one or more non-AI / ML CSI reports having a same CPU occupation. For example, referring to FIG. 8, to identify the one or more refrained CSI reports of the one or more AI / ML CSI reports (at 820) , the UE 802 may identify the refrained CSI reports based on a comparison of the inter-CSI priority associated with the one or more AI / ML CSI reports and the one or more non-AI / ML CSI reports having the same CPU occupation.
[0146] FIG. 11 is a flowchart 1100 illustrating methods of wireless communication at a network entity in accordance with various aspects of the present disclosure. The method may be performed by a network entity. The network entity may be a base station, or a component of a base station, in the access network of FIG. 1 or a core network component (e.g., base station 102, 310, 754, 804; or the network entity 1302 in the hardware implementation of FIG. 13) . The methods provide detailed signaling mechanisms and UE capability enhancements to enable concurrent CPU occupation frameworks across AI / ML based CSF and beam prediction results reporting, thereby allowing for more efficient and flexible hardware utilization, including dedicated hardware accelerators like NSP and GPU.
[0147] As shown in FIG. 11, at 1102, the network entity may receive, from a UE, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function. The UE may be the UE 104, 350, 752, 802, or the apparatus 1304 in the hardware implementation of FIG. 13. FIGs. 5A, 5B, 6, 7, and 8 illustrate various aspects of the steps in connection with flowchart 1100. For example, referring to FIG. 8, the network entity (base station 804) may, at 806, receive, from a UE 802, a capability indicator of a computational capability. The computation capability may include an AI / ML capability for processing an AI / ML function (at 830) . In some aspects, 1102 may be performed by the CPU-sharing component 199.
[0148] At 1104, the network entity may receive, from the UE based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. For example, referring to FIG. 8, the network entity (base station 804) may, at 824, receive, from the UE 802 based on the AI / ML function (at 830) , one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. Referring to FIG. 7, the network entity (base station 754) may receive, from the UE 752 based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function at 750. In some aspects, 1104 may be performed by the CPU-sharing component 199.
[0149] FIG. 12 is a flowchart 1200 illustrating methods of wireless communication at a network entity in accordance with various aspects of the present disclosure. The method may be performed by a network entity. The network entity may be a base station, or a component of a base station, in the access network of FIG. 1 or a core network component (e.g., base station 102, 310, 754, 804; or the network entity 1302 in the hardware implementation of FIG. 13) . The methods provide detailed signaling mechanisms and UE capability enhancements to enable concurrent CPU occupation frameworks across AI / ML based CSF and beam prediction results reporting, thereby allowing for more efficient and flexible hardware utilization, including dedicated hardware accelerators like NSP and GPU.
[0150] As shown in FIG. 12, at 1202, the network entity may receive, from a UE, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function. The UE may be the UE 104, 350, 752, 802, or the apparatus 1304 in the hardware implementation of FIG. 13. FIGs. 5A, 5B, 6, 7, and 8 illustrate various aspects of the steps in connection with flowchart 1200. For example, referring to FIG. 8, the network entity (base station 804) may, at 806, receive, from a UE 802, a capability indicator of a computational capability. The computation capability may include an AI / ML capability for processing an AI / ML function (at 830) . In some aspects, 1202 may be performed by the CPU-sharing component 199.
[0151] At 1212, the network entity may receive, from the UE based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. For example, referring to FIG. 8, the network entity (base station 804) may, at 824, receive, from the UE 802 based on the AI / ML function (at 830) , one or more AI / ML CSI reports including the result of the AI / ML function. The calculation of the report quantity for each of the one or more AI / ML CSI reports may be associated with AI / ML based processing. Referring to FIG. 7, the network entity (base station 754) may receive, from the UE 752 based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function at 750. In some aspects, 1212 may be performed by the CPU-sharing component 199.
[0152] In some aspects, the AI / ML capability (at 1202) may include at least one of: a first supported number of CPUs occupied by the one or more AI / ML CSI reports associated with each CC of a set of CCs (at 1220) ; and a second supported number of CPUs occupied by the one or more AI / ML CSI reports for all of the set of CCs (at 1222) . For example, referring to FIG. 8, the AI / ML capability (at 830) may include at least one of: a first supported number of CPUs occupied by the one or more AI / ML CSI reports associated with each CC of a set of CCs (at 834) , or a second supported number of CPUs occupied by the one or more AI / ML CSI reports for all of the set of CCs (at 836) . For example, the first supported number of CPUs may be represented by the parameter SimultaneousCSI-ReportsPerCC-AIML, and the second supported number of CPUs may be represented by the parameter SimultaneousCSI-ReportsAllCC-AIML.
[0153] In some aspects, the report quantity (at 1212) for each of the one or more AI / ML CSI reports may include one or more of: a beam prediction result (at 1230) , a CSI prediction result or a CSI compression result (at 1232) . For example, referring to FIG. 5B, the report quantity for each of the one or more AI / ML CSI reports may include one or more of: a beam prediction result (at 562) , a CSI prediction result or a CSI compression result (at 560) .
[0154] In some aspects, the beam prediction result (at 1230) may include one or more of: a predicted L1 RSRP or L1 SINR for each of a first set of beams based on measurements for a second set of beams, a predicted number of beams for the first set of beams based on the measurements for the second set of beams, a spatial prediction for the first set of beams based on the measurements for the second set of beams, where first resources for the first set of beams do not overlap with second resources for the second set of beams, a temporal prediction for the first set of beams for one or more future temporal occasions, or a frequency or mobility prediction for the first set of beams based on the measurements for the second set of beams, where the first set of beams and the second set of beams are associated with different BWP, CCs, FRs, or cells. For example, referring to FIG. 5B, beam prediction result (at 562) may include one or more of: the predicted L1-RSRP or L1-SINR for each of the first set of beams based on measurements for a second set of beams, the predicted number of beams for the first set of beams based on the measurements for the second set of beams, a spatial prediction for the first set of beams based on the measurements for the second set of beams, where first resources for the first set of beams do not overlap with second resources for the second set of beams, a temporal prediction for the first set of beams for one or more future temporal occasions, or a frequency or mobility prediction for the first set of beams based on the measurements for the second set of beams, where the first set of beams and the second set of beams are associated with different BWPs, CCs, FRs, or cells.
[0155] In some aspects, the CSI prediction result (at 1232) may include one or more of: a model for CSI compression and decompression or a predicted PMI associated with one or more future temporal occasions. The PMI associated with the CSI compression and decompression may be compressed using a first AI / ML model and decompressed using a second AI / ML model. For example, referring to FIG. 5B, the CSI prediction result (at 560) may include one or more of: a model for CSI compression and decompression, or a predicted PMI associated with one or more future temporal occasions. The PMI associated with the CSI compression and decompression may be compressed using a first AI / ML model and decompressed using a second AI / ML model.
[0156] In some aspects, the computational capability (at 1202) further include a non-AI / ML capability including a non-AI / ML number of CPUs for one or more non-AI / ML CSI reports (at 1224) . The report quantity for each of the one or more non-AI / ML CSI reports may not be associated with the AI / ML based processing, and the one or more non-AI / ML CSI reports may not occupy the first supported number of CPUs or the second supported number of CPUs. For example, referring to FIG. 8, the computational capability (at 806) may further include a non-AI / ML capability (at 832) including a non-AI / ML number of CPUs for one or more non-AI / ML CSI reports. The report quantity for each of the one or more non-AI / ML CSI reports may not be associated with the AI / ML based processing, and the one or more non-AI / ML CSI reports may not occupy the first supported number of CPUs or the second supported number of CPUs.
[0157] In some aspects, the one or more AI / ML CSI reports may not occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports. For example, referring to FIG. 5B, the one or more AI / ML CSI reports (e.g., the CSI report for beam prediction at 562) may not occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports (at 552) .
[0158] In some aspects, at least one AI / ML CSI report of the one or more AI / ML CSI reports may occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports. For example, referring to FIG. 6, at least one AI / ML CSI report of the one or more AI / ML CSI reports (e.g., the CSI report for beam prediction at 612) may occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports (at 602) .
[0159] In some aspects, the network entity may, at 1204, receive, from the UE via a MAC-CE, a CPU occupation request for a CPU occupation of the at least one AI / ML CSI report on the non-AI / ML number of CPUs. The CPU occupation request may include one or more of: the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, or the condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs. For example, referring to FIG. 8, the network entity (base station 804) may, at 808, receive from the UE 802 via a MAC-CE a CPU occupation request for a CPU occupation of the at least one AI / ML CSI report on the non-AI / ML number of CPUs. The CPU occupation request may include one or more of: the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, or the condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs. In some aspects, 1204 may be performed by the CPU-sharing component 199.
[0160] In some aspects, the network entity may, at 1206, transmit, for the UE, a first confirmation of the CPU occupation request. For example, referring to FIG. 8, the network entity (base station 804) may, at 810, transmit, for the UE 802, a first confirmation of the CPU occupation request. In some aspects, 1206 may be performed by the CPU-sharing component 199.
[0161] In some aspects, the network entity may, at 1208, receive, from the UE via the MAC-CE, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report to the first supported number of CPUs or the second supported number of CPUs. For example, referring to FIG. 8, the network entity (base station 804) may, at 812, receive, from the UE 802 via the MAC-CE, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report to the first supported number of CPUs or the second supported number of CPUs. In some aspects, 1208 may be performed by the CPU-sharing component 199.
[0162] In some aspects, the network entity may, at 1210, transmit, for the UE, a second confirmation of the switch request. For example, referring to FIG. 8, the network entity (base station 804) may, at 814, transmit, for the UE 802, a second confirmation of the switch request. In some aspects, 1210 may be performed by the CPU-sharing component 199.
[0163] FIG. 13 is a diagram 1300 illustrating an example of a hardware implementation for an apparatus 1304. The apparatus 1304 may be a UE, a component of a UE, or may implement UE functionality. In some aspects, the apparatus 1304 may include at least one cellular baseband processor (or processing circuitry) 1324 (also referred to as a modem) coupled to one or more transceivers 1322 (e.g., cellular RF transceiver) . The cellular baseband processor (s) (or processing circuitry) 1324 may include at least one on-chip memory (or memory circuitry) 1324'. In some aspects, the apparatus 1304 may further include one or more subscriber identity modules (SIM) cards 1320 and at least one application processor (or processing circuitry) 1306 coupled to a secure digital (SD) card 1308 and a screen 1310. The application processor (s) (or processing circuitry) 1306 may include on-chip memory (or memory circuitry) 1306'. In some aspects, the apparatus 1304 may further include a Bluetooth module 1312, a WLAN module 1314, an SPS module 1316 (e.g., GNSS module) , one or more sensor modules 1318 (e.g., barometric pressure sensor / altimeter; motion sensor such as inertial measurement unit (IMU) , gyroscope, and / or accelerometer (s) ; light detection and ranging (LIDAR) , radio assisted detection and ranging (RADAR) , sound navigation and ranging (SONAR) , magnetometer, audio and / or other technologies used for positioning) , additional memory modules 1326, a power supply 1330, and / or a camera 1332. The Bluetooth module 1312, the WLAN module 1314, and the SPS module 1316 may include an on-chip transceiver (TRX) (or in some cases, just a receiver (RX) ) . The Bluetooth module 1312, the WLAN module 1314, and the SPS module 1316 may include their own dedicated antennas and / or utilize the antennas 1380 for communication. The cellular baseband processor (s) (or processing circuitry) 1324 communicates through the transceiver (s) 1322 via one or more antennas 1380 with the UE 104 and / or with an RU associated with a network entity 1302. The cellular baseband processor (s) (or processing circuitry) 1324 and the application processor (s) (or processing circuitry) 1306 may each include a computer-readable medium / memory (or memory circuitry) 1324', 1306', respectively. The additional memory modules 1326 may also be considered a computer-readable medium / memory (or memory circuitry) . Each computer-readable medium / memory (or memory circuitry) 1324', 1306', 1326 may be non-transitory. The cellular baseband processor (s) (or processing circuitry) 1324 and the application processor (s) (or processing circuitry) 1306 are each responsible for general processing, including the execution of software stored on the computer-readable medium / memory (or memory circuitry) . The software, when executed by the cellular baseband processor (s) (or processing circuitry) 1324 / application processor (s) (or processing circuitry) 1306, causes the cellular baseband processor (s) (or processing circuitry) 1324 / application processor (s) (or processing circuitry) 1306 to perform the various functions described supra. The cellular baseband processor (s) (or processing circuitry) 1324 and the application processor (s) (or processing circuitry) 1306 are configured to perform the various functions described supra based at least in part of the information stored in the memory (or memory circuitry) . That is, the cellular baseband processor (s) (or processing circuitry) 1324 and the application processor (s) (or processing circuitry) 1306 may be configured to perform a first subset of the various functions described supra without information stored in the memory and may be configured to perform a second subset of the various functions described supra based on the information stored in the memory. The computer-readable medium / memory (or memory circuitry) may also be used for storing data that is manipulated by the cellular baseband processor (s) (or processing circuitry) 1324 / application processor (s) (or processing circuitry) 1306 when executing software. The cellular baseband processor (s) (or processing circuitry) 1324 / application processor (s) (or processing circuitry) 1306 may be a component of the UE 350 and may include the at least one memory 360 and / or at least one of the TX processor 368, the RX processor 356, and the controller / processor 359. In one configuration, the apparatus 1304 may be at least one processor chip (modem and / or application) and include just the cellular baseband processor (s) (or processing circuitry) 1324 and / or the application processor (s) (or processing circuitry) 1306, and in another configuration, the apparatus 1304 may be the entire UE (e.g., see UE 350 of FIG. 3) and include the additional modules of the apparatus 1304.
[0164] As discussed supra, the component 198 may be configured to transmit, to a network entity, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function; perform the AI / ML function based on the computational capability; and transmit, to the network entity based on AI / ML function, one or more AI / ML CSI reports including a result of the AI / ML function, where the calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing. The component 198 may be further configured to perform any of the aspects described in connection with the flowcharts in FIG. 9 and FIG. 10, and / or performed by the UE 802 in FIG. 8. The component 198 may be within the cellular baseband processor (s) (or processing circuitry) 1324, the application processor (s) (or processing circuitry) 1306, or both the cellular baseband processor (s) (or processing circuitry) 1324 and the application processor (s) (or processing circuitry) 1306. The component 198 may be one or more hardware components specifically configured to carry out the stated processes / algorithm, implemented by one or more processors configured to perform the stated processes / algorithm, stored within a computer-readable medium for implementation by one or more processors, or some combination thereof. When multiple processors are implemented, the multiple processors may perform the stated processes / algorithm individually or in combination. As shown, the apparatus 1304 may include a variety of components configured for various functions. In one configuration, the apparatus 1304, and in particular the cellular baseband processor (s) (or processing circuitry) 1324 and / or the application processor (s) (or processing circuitry) 1306, includes means for transmitting, to a network entity, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function, means for performing the AI / ML function based on the computational capability, and means for transmitting, to the network entity based on the AI / ML function, one or more AI / ML CSI reports including a result of the AI / ML function, where the calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing. The apparatus 1304 may further include means for performing any of the aspects described in connection with the flowcharts in FIG. 9 and FIG. 10, and / or aspects performed by the UE 802 in FIG. 8. The means may be the component 198 of the apparatus 1304 configured to perform the functions recited by the means. As described supra, the apparatus 1304 may include the TX processor 368, the RX processor 356, and the controller / processor 359. As such, in one configuration, the means may be the TX processor 368, the RX processor 356, and / or the controller / processor 359 configured to perform the functions recited by the means.
[0165] FIG. 14 is a diagram 1400 illustrating an example of a hardware implementation for a network entity 1402. The network entity 1402 may be a BS, a component of a BS, or may implement BS functionality. The network entity 1402 may include at least one of a CU 1410, a DU 1430, or an RU 1440. For example, depending on the layer functionality handled by the component 199, the network entity 1402 may include the CU 1410; both the CU 1410 and the DU 1430; each of the CU 1410, the DU 1430, and the RU 1440; the DU 1430; both the DU 1430 and the RU 1440; or the RU 1440. The CU 1410 may include at least one CU processor (or processing circuitry) 1412. The CU processor (s) (or processing circuitry) 1412 may include on-chip memory (or memory circuitry) 1412'. In some aspects, the CU 1410 may further include additional memory modules 1414 and a communications interface 1418. The CU 1410 communicates with the DU 1430 through a midhaul link, such as an F1 interface. The DU 1430 may include at least one DU processor (or processing circuitry) 1432. The DU processor (s) (or processing circuitry) 1432 may include on-chip memory (or memory circuitry) 1432'. In some aspects, the DU 1430 may further include additional memory modules 1434 and a communications interface 1438. The DU 1430 communicates with the RU 1440 through a fronthaul link. The RU 1440 may include at least one RU processor (or processing circuitry) 1442. The RU processor (s) (or processing circuitry) 1442 may include on-chip memory (or memory circuitry) 1442'. In some aspects, the RU 1440 may further include additional memory modules 1444, one or more transceivers 1446, antennas 1480, and a communications interface 1448. The RU 1440 communicates with the UE 104. The on-chip memory (or memory circuitry) 1412', 1432', 1442' and the additional memory modules 1414, 1434, 1444 may each be considered a computer-readable medium / memory (or memory circuitry) . Each computer-readable medium / memory (or memory circuitry) may be non-transitory. Each of the processors (or processing circuitry) 1412, 1432, 1442 is responsible for general processing, including the execution of software stored on the computer-readable medium / memory (or memory circuitry) . The software, when executed by the corresponding processor (s) (or processing circuitry) causes the processor (s) (or processing circuitry) to perform the various functions described supra. The computer-readable medium / memory (or memory circuitry) may also be used for storing data that is manipulated by the processor (s) (or processing circuitry) when executing software.
[0166] As discussed supra, the component 199 may be configured to receive, from a UE, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function; and receive, from the UE based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function, where the calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing. The component 199 may be further configured to perform any of the aspects described in connection with the flowcharts in FIG. 11 and FIG. 12, and / or performed by the base station 804 in FIG. 8. The component 199 may be within one or more processors (or processing circuitry) of one or more of the CU 1410, DU 1430, and the RU 1440. The component 199 may be one or more hardware components specifically configured to carry out the stated processes / algorithm, implemented by one or more processors configured to perform the stated processes / algorithm, stored within a computer-readable medium for implementation by one or more processors, or some combination thereof. When multiple processors are implemented, the multiple processors may perform the stated processes / algorithm individually or in combination. The network entity 1402 may include a variety of components configured for various functions. In one configuration, the network entity 1402 includes means for receiving, from a UE, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function, and means for receiving, from the UE based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function, where the calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing. The network entity 1402 may further include means for performing any of the aspects described in connection with the flowcharts in FIG. 11 and FIG. 12, and / or aspects performed by the base station 804 in FIG. 8. The means may be the component 199 of the network entity 1402 configured to perform the functions recited by the means. As described supra, the network entity 1402 may include the TX processor 316, the RX processor 370, and the controller / processor 375. As such, in one configuration, the means may be the TX processor 316, the RX processor 370, and / or the controller / processor 375 configured to perform the functions recited by the means.
[0167] This disclosure provides a method for wireless communication at a UE. The method may include transmitting, to a network entity, a capability indicator of a computational capability including an AI / ML capability for processing an AI / ML function; performing the AI / ML function based on the computational capability; and transmitting, to the network entity based on the AI / ML function, one or more AI / ML CSI reports including the result of the AI / ML function, where the calculation of the report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing. The methods provide detailed signaling mechanisms and UE capability enhancements to enable concurrent CPU occupation frameworks across AI / ML based CSF and beam prediction results reporting, thereby allowing for more efficient and flexible hardware utilization, including dedicated hardware accelerators like NSP and GPU.
[0168] It is understood that the specific order or hierarchy of blocks in the processes / flowcharts disclosed is an illustration of example approaches. Based upon design preferences, it is understood that the specific order or hierarchy of blocks in the processes / flowcharts may be rearranged. Further, some blocks may be combined or omitted. The accompanying method claims present elements of the various blocks in a sample order, and are not limited to the specific order or hierarchy presented.
[0169] The previous 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 readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not limited to the aspects described herein, but are to be accorded the full scope consistent with the language claims. Reference to an element in the singular does not mean “one and only one” unless specifically so stated, but rather “one or more. ” Terms such as “if, ” “when, ” and “while” do not imply an immediate temporal relationship or reaction. That is, these phrases, e.g., “when, ” do not imply an immediate action in response to or during the occurrence of an action, but simply imply that if a condition is met then an action will occur, but without requiring a specific or immediate time constraint for the action to occur. The word “exemplary” is used herein to mean “serving as an example, instance, or illustration. ” Any aspect described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other aspects. Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C, ” “one or more of A, B, or C, ” “at least one of A, B, and C, ” “one or more of A, B, and C, ” and “A, B, C, or any combination thereof” include any combination of A, B, and / or C, and may include multiples of A, multiples of B, or multiples of C. Specifically, combinations such as “at least one of A, B, or C, ” “one or more of A, B, or C, ” “at least one of A, B, and C, ” “one or more of A, B, and C, ” and “A, B, C, or any combination thereof” may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, where any such combinations may contain one or more member or members of A, B, or C. Sets should be interpreted as a set of elements where the elements number one or more. Accordingly, for a set of X, X would include one or more elements. When at least one processor is configured to perform a set of functions, the at least one processor, individually or in any combination, is configured to perform the set of functions. Accordingly, each processor of the at least one processor may be configured to perform a particular subset of the set of functions, where the subset is the full set, a proper subset of the set, or an empty subset of the set. A processor may be referred to as processor circuitry. A memory / memory module may be referred to as memory circuitry. If a first apparatus receives data from or transmits data to a second apparatus, the data may be received / transmitted directly between the first and second apparatuses, or indirectly between the first and second apparatuses through a set of apparatuses. A device configured to “output” data or “provide” data, such as a transmission, signal, or message, may transmit the data, for example with a transceiver, or may send the data to a device that transmits the data. A device configured to “obtain” data, such as a transmission, signal, or message, may receive, for example with a transceiver, or may obtain the data from a device that receives the data. Information stored in a memory includes instructions and / or data. All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are encompassed by the claims. Moreover, nothing disclosed herein is dedicated to the public regardless of whether such disclosure is explicitly recited in the claims. The words “module, ” “mechanism, ” “element, ” “device, ” and the like may not be a substitute for the word “means. ” As such, no claim element is to be construed as a means plus function unless the element is expressly recited using the phrase “means for. ”
[0170] As used herein, the phrase “based on” shall not be construed as a reference to a closed set of information, one or more conditions, one or more factors, or the like. In other words, the phrase “based on A” (where “A” may be information, a condition, a factor, or the like) shall be construed as “based at least on A” unless specifically recited differently.
[0171] The following aspects are illustrative only and may be combined with other aspects or teachings described herein, without limitation.
[0172] Aspect 1 is a method of wireless communication at a UE. The method includes transmitting, to a network entity, a capability indicator of a computational capability comprising an artificial intelligence (AI) / machine learning (ML) (AI / ML) capability for processing an AI / ML function; performing the AI / ML function based on the computational capability; and transmitting, to the network entity based on the AI / ML function, one or more AI / ML channel station information (CSI) reports comprising a result of the AI / ML function, wherein a calculation of a report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing.
[0173] Aspect 2 is the method of aspect 1, wherein the AI / ML capability includes at least one of: a first supported number of channel state information (CSI) processing units (CPUs) occupied by the one or more AI / ML CSI reports associated with each component carrier (CC) of a set of CCs; or a second supported number of CPUs occupied by the one or more AI / ML CSI reports for all of the set of CCs.
[0174] Aspect 3 is the method of any of aspects 1 to 2, wherein the report quantity for each of the one or more AI / ML CSI reports includes one or more of: a beam prediction result, a CSI prediction result, or a CSI compression result.
[0175] Aspect 4 is the method of aspect 3, wherein the beam prediction result includes one or more of: a predicted layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) for each of a first set of beams based on measurements for a second set of beams, a predicted number of beams for the first set of beams based on the measurements for the second set of beams, a spatial prediction for the first set of beams based on the measurements for the second set of beams, wherein first resources for the first set of beams do not overlap with second resources for the second set of beams, a temporal prediction for the first set of beams for one or more future temporal occasions, or a frequency or mobility prediction for the first set of beams based on the measurements for the second set of beams, wherein the first set of beams and the second set of beams are associated with different bandwidth parts (BWP) , component carriers (CCs) , frequency ranges (FRs) , or cells.
[0176] Aspect 5 is the method of aspect 3, wherein the CSI prediction result includes one or more of: a model for CSI compression and decompression, wherein a precoding matrix indicator (PMI) associated with the CSI compression and decompression is compressed using a first AI / ML model and decompressed using a second AI / ML model, or a predicted PMI associated with one or more future temporal occasions.
[0177] Aspect 6 is the method of aspect 3, wherein the AI / ML capability further includes one or more of: a beam prediction capability associated with a first portion of the one or more AI / ML CSI reports, wherein the report quantity for each of the one or more AI / ML CSI reports in the first portion of the one or more AI / ML CSI reports includes the beam prediction result, or a CSI capability associated with a second portion of the one or more AI / ML CSI reports, wherein the report quantity for each of the one or more AI / ML CSI reports in the second portion of the AI / ML CSI reports includes the CSI prediction result or the CSI compression result.
[0178] Aspect 7 is the method of aspect 6, wherein the beam prediction capability includes: a third supported number of CPUs occupied by the first portion of the one or more AI / ML CSI reports associated with each CC of the set of CCs; and a fourth supported number of CPUs occupied by the first portion of the one or more AI / ML CSI reports for all of the set of CCs, and wherein the CSI capability includes: a fifth supported number of CPUs occupied by the second portion of the one or more AI / ML CSI reports associated with each CC of the set of CCs; and a sixth supported number of CPUs occupied by the second portion of the one or more AI / ML CSI reports for all of the set of CCs.
[0179] Aspect 8 is the method of aspect 7, wherein the third supported number of CPUs is less than or equal to the first supported number of CPUs, wherein the fifth supported number of CPUs is less than or equal to the first supported number of CPUs, wherein the fourth supported number of CPUs is less than or equal to the second supported number of CPUs, and wherein the sixth supported number of CPUs is less than or equal to the second supported number of CPUs.
[0180] Aspect 9 is the method of aspect 8, wherein a first sum of the third supported number of CPUs and the fifth supported number of CPUs is less than or equal to the first supported number of CPUs, and a second sum of the fourth supported number of CPUs and the sixth supported number of CPUs is less than or equal to the second supported number of CPUs.
[0181] Aspect 10 is the method of any of aspects 1 to 2, wherein the computational capability further comprises a non-AI / ML capability comprising a non-AI / ML number of CPUs for one or more non-AI / ML CSI reports, wherein the report quantity for each of the one or more non-AI / ML CSI reports is not associated with the AI / ML based processing, and wherein the one or more non-AI / ML CSI reports do not occupy the first supported number of CPUs or the second supported number of CPUs.
[0182] Aspect 11 is the method of aspect 10, wherein the one or more AI / ML CSI reports do not occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports.
[0183] Aspect 12 is the method of aspect 10, wherein at least one AI / ML CSI report of the one or more AI / ML CSI reports occupies the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports.
[0184] Aspect 13 is the method of aspect 12, where the method further includes selecting the at least one AI / ML CSI report based on one or more of: an urgency of the report quantity for the at least one AI / ML CSI report, or a complexity for a computation of the report quantity for the at least one AI / ML CSI report.
[0185] Aspect 14 is the method of any of aspects 1 to 12, where the method further includes transmitting, to the network entity via a medium access control (MAC) – control element (MAC-CE) , a CPU occupation request for a CPU occupation of the at least one AI / ML CSI report on the non-AI / ML number of CPUs, wherein the CPU occupation request comprises one or more of: the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, or a condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs; and receiving, from the network entity, a first confirmation of the CPU occupation request, and wherein performing the AI / ML function based on the computational capability comprises: performing the AI / ML function based on the computational capability and the CPU occupation of the at least one AI / ML CSI report.
[0186] Aspect 15 is the method of aspect 14, where the method further includes: transmitting, to the network entity via the MAC-CE and based on the first confirmation, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report to the first supported number of CPUs or the second supported number of CPUs; and receiving, from the network entity, a second confirmation of the switch request.
[0187] Aspect 16 is the method of any of aspects 1 to 10, where the method further includes identifying, based on a number of the one or more AI / ML CSI reports that exceeds one or more of the first supported number of CPUs or the second supported number of CPUs, one or more refrained CSI reports of the one or more AI / ML CSI reports; and refraining from updating the one or more refrained CSI reports.
[0188] Aspect 17 is the method of aspect 16, wherein each of the one or more AI / ML CSI reports has an inter-CSI priority, and identifying the one or more refrained CSI reports of the one or more AI / ML CSI reports comprises: identifying the refrained CSI reports based on a comparison of the inter-CSI priority for the one or more AI / ML CSI reports.
[0189] Aspect 18 is the method of aspect 16, wherein each of the one or more AI / ML CSI reports and the one or more non-AI / ML CSI reports has an inter-CSI priority, and identifying the one or more refrained CSI reports of the one or more AI / ML CSI reports comprises: identifying the refrained CSI reports based on a comparison of the inter-CSI priority associated with the one or more AI / ML CSI reports and the one or more non-AI / ML CSI reports having a same CPU occupation.
[0190] Aspect 19 is an apparatus for wireless communication at a UE, comprising: a processing system that includes processor circuitry and memory circuitry that stores code and is coupled with the processor circuitry, the processing system configured to cause the UE to perform the method of one or more of aspects 1-18.
[0191] Aspect 20 is an apparatus for wireless communication at a UE, comprising: at least one memory; and at least one processor coupled to the at least one memory and, where the at least one processor, individually or in any combination, is configured to perform the method of any of aspects 1-18.
[0192] Aspect 21 is the apparatus for wireless communication at a UE, comprising means for performing each step in the method of any of aspects 1-18.
[0193] Aspect 22 is an apparatus of any of aspects 19-21, further comprising a transceiver configured to receive or to transmit in association with the method of any of aspects 1-18.
[0194] Aspect 23 is a computer-readable medium (e.g., a non-transitory computer-readable medium) storing computer executable code at a UE, the code when executed by at least one processor causes the at least one processor to, individually or in any combination, perform the method of any of aspects 1-18.
[0195] Aspect 24 is a method of wireless communication at a network entity. The method includes receiving, from a user equipment (UE) , a capability indicator of a computational capability comprising an artificial intelligence (AI) / machine learning (ML) (AI / ML) capability for processing an AI / ML function; and receiving, from the UE based on the AI / ML function, one or more AI / ML channel station information (CSI) reports comprising a result of the AI / ML function, wherein a calculation of a report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing.
[0196] Aspect 25 is the method of aspect 24, wherein the AI / ML capability includes at least one of: a first supported number of channel state information (CSI) processing units (CPUs) occupied by the one or more AI / ML CSI reports associated with each component carrier (CC) of a set of CCs; or a second supported number of CPUs occupied by the one or more AI / ML CSI reports for all of the set of CCs.
[0197] Aspect 26 is the method of any of aspects 24 to 25, wherein the report quantity for each of the one or more AI / ML CSI reports includes one or more of: a beam prediction result, a CSI prediction result, or a CSI compression result.
[0198] Aspect 27 is the method of aspect 26, wherein the beam prediction result includes one or more of: a predicted layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) for each of a first set of beams based on measurements for a second set of beams, a predicted number of beams for the first set of beams based on the measurements for the second set of beams, a spatial prediction for the first set of beams based on the measurements for the second set of beams, wherein first resources for the first set of beams do not overlap with second resources for the second set of beams, a temporal prediction for the first set of beams for one or more future temporal occasions, or a frequency or mobility prediction for the first set of beams based on the measurements for the second set of beams, wherein the first set of beams and the second set of beams are associated with different bandwidth parts (BWPs) , component carriers (CCs) , frequency ranges (FRs) , or cells.
[0199] Aspect 28 is the method of aspect 26, wherein the CSI prediction result includes one or more of: a model for CSI compression and decompression, wherein a precoding matrix indicator (PMI) associated with the CSI compression and decompression is compressed using a first AI / ML model and decompressed using a second AI / ML model, or a predicted PMI associated with one or more future temporal occasions.
[0200] Aspect 29 is the method of any of aspects 24 to 25, wherein the computational capability further comprises a non-AI / ML capability comprising a non-AI / ML number of CPUs for one or more non-AI / ML CSI reports, wherein the report quantity for each of the one or more non-AI / ML CSI reports is not associated with the AI / ML based processing, and wherein the one or more non-AI / ML CSI reports do not occupy the first supported number of CPUs or the second supported number of CPUs.
[0201] Aspect 30 is the method of aspect 29, wherein the one or more AI / ML CSI reports do not occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports.
[0202] Aspect 31 is the method of aspect 29, wherein at least one AI / ML CSI report of the one or more AI / ML CSI reports occupies the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports.
[0203] Aspect 32 is the method of any of aspects 24 to 31, where the method further includes receiving, from the UE via a medium access control (MAC) – control element (MAC-CE) , a CPU occupation request for a CPU occupation of the at least one AI / ML CSI report on the non-AI / ML number of CPUs, wherein the CPU occupation request comprises one or more of: the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, or a condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs; and transmitting, for the UE, a first confirmation of the CPU occupation request.
[0204] Aspect 33 is the method of aspect 32, where the method further includes: receiving, from the UE via the MAC-CE and based on the first confirmation, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report to the first supported number of CPUs or the second supported number of CPUs; and transmitting, for the UE, a second confirmation of the switch request.
[0205] Aspect 34 is an apparatus for wireless communication at a network entity, comprising: a processing system that includes processor circuitry and memory circuitry that stores code and is coupled with the processor circuitry, the processing system configured to cause the network entity to perform the method of one or more of aspects 24-33.
[0206] Aspect 35 is an apparatus for wireless communication at a network entity, comprising: at least one memory; and at least one processor coupled to the at least one memory and, where the at least one processor, individually or in any combination, is configured to perform the method of any of aspects 24-33.
[0207] Aspect 36 is the apparatus for wireless communication at a network entity, comprising means for performing each step in the method of any of aspects 24-33.
[0208] Aspect 37 is an apparatus of any of aspects 34-36, further comprising a transceiver configured to receive or to transmit in association with the method of any of aspects 24-33.
[0209] Aspect 38 is a computer-readable medium (e.g., a non-transitory computer-readable medium) storing computer executable code at a network entity, the code when executed by at least one processor causes the at least one processor to, individually or in any combination, perform the method of any of aspects 24-33.
Claims
1.An apparatus for wireless communication at a user equipment (UE) , comprising:at least one memory; andat least one processor coupled to the at least one memory and, based at least in part on information stored in the at least one memory, the at least one processor, individually or in any combination, is configured to:transmit, to a network entity, a capability indicator of a computational capability comprising an artificial intelligence (AI) / machine learning (ML) (AI / ML) capability for processing an AI / ML function;perform the AI / ML function based on the computational capability; andtransmit, to the network entity based on the AI / ML function, one or more AI / ML channel station information (CSI) reports comprising a result of the AI / ML function, wherein a calculation of a report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing.2.The apparatus of claim 1, further comprising a transceiver coupled to the at least one processor, wherein, to transmit the capability indicator, the at least one processor, individually or in any combination, is configured to transmit the capability indicator via the transceiver, and wherein the AI / ML capability includes at least one of:a first supported number of CSI processing units (CPUs) occupied by the one or more AI / ML CSI reports associated with each component carrier (CC) of a set of CCs; ora second supported number of CPUs occupied by the one or more AI / ML CSI reports for all of the set of CCs.3.The apparatus of claim 2, wherein the report quantity for each of the one or more AI / ML CSI reports includes one or more of:a beam prediction result,a CSI prediction result, ora CSI compression result.4.The apparatus of claim 3, wherein the beam prediction result includes one or more of:a predicted layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) for each of a first set of beams based on measurements for a second set of beams,a predicted number of beams for the first set of beams based on the measurements for the second set of beams,a spatial prediction for the first set of beams based on the measurements for the second set of beams, wherein first resources for the first set of beams do not overlap with second resources for the second set of beams,a temporal prediction for the first set of beams for one or more future temporal occasions, ora frequency or mobility prediction for the first set of beams based on the measurements for the second set of beams, wherein the first set of beams and the second set of beams are associated with different bandwidth parts (BWPs) , component carriers (CCs) , frequency ranges (FRs) , or cells.5.The apparatus of claim 3, wherein the CSI prediction result includes one or more of:a mode for CSI compression and decompression, wherein a precoding matrix indicator (PMI) associated with the CSI compression and decompression is compressed using a first AI / ML model and decompressed using a second AI / ML model, ora predicted PMI associated with one or more future temporal occasions.6.The apparatus of claim 3, wherein the AI / ML capability further includes one or more of:a beam prediction capability associated with a first portion of the one or more AI / ML CSI reports, wherein the report quantity for each of the one or more AI / ML CSI reports in the first portion of the one or more AI / ML CSI reports includes the beam prediction result, ora CSI capability associated with a second portion of the one or more AI / ML CSI reports, wherein the report quantity for each of the one or more AI / ML CSI reports in the second portion of the one or more AI / ML CSI reports includes the CSI prediction result or the CSI compression result.7.The apparatus of claim 6, wherein the beam prediction capability includes:a third supported number of CPUs occupied by the first portion of the one or more AI / ML CSI reports associated with each CC of the set of CCs; anda fourth supported number of CPUs occupied by the first portion of the one or more AI / ML CSI reports for all of the set of CCs, andwherein the CSI capability includes:a fifth supported number of CPUs occupied by the second portion of the one or more AI / ML CSI reports associated with each CC of the set of CCs; anda sixth supported number of CPUs occupied by the second portion of the one or more AI / ML CSI reports for all of the set of CCs.8.The apparatus of claim 7, wherein the third supported number of CPUs is less than or equal to the first supported number of CPUs,wherein the fifth supported number of CPUs is less than or equal to the first supported number CPUs,wherein the fourth supported number of CPUs is less than or equal to the second supported number of CPUs, andwherein the sixth supported number of CPUs is less than or equal to the second supported number of CPUs.9.The apparatus of claim 8, wherein a first sum of the third supported number of CPUs and the fifth supported number of CPUs is less than or equal to the first supported number of CPUs, andwherein a second sum of the fourth supported number of CPUs and the sixth supported number of CPUs is less than or equal to the second supported number of CPUs.10.The apparatus of claim 2, wherein the computational capability further comprises a non-AI / ML capability comprising a non-AI / ML number of CPUs for one or more non- AI / ML CSI reports, the report quantity for each of the one or more non-AI / ML CSI reports is not associated with the AI / ML based processing, and wherein the one or more non-AI / ML CSI reports do not occupy the first supported number of CPUs or the second supported number of CPUs.11.The apparatus of claim 10, wherein the one or more AI / ML CSI reports do not occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports.12.The apparatus of claim 10, wherein at least one AI / ML CSI report of the one or more AI / ML CSI reports occupies the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports.13.The apparatus of claim 12, wherein the at least one processor, individually or in any combination, is further configured to:select the at least one AI / ML CSI report based on one or more of:an urgency of the report quantity for the at least one AI / ML CSI report, ora complexity for a computation of the report quantity for the at least one AI / ML CSI report.14.The apparatus of claim 12, wherein the at least one processor, individually or in any combination, is further configured to:transmit, to the network entity via a medium access control (MAC) –control element (MAC-CE) , a CPU occupation request for a CPU occupation of the at least one AI / ML CSI report on the non-AI / ML number of CPUs, wherein the CPU occupation request comprises one or more of:the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, ora condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs; andreceive, from the network entity, a first confirmation of the CPU occupation request, and wherein to perform the AI / ML function based on the computational capability, the at least one processor, individually or in any combination, is configured to: perform the AI / ML function based on the computational capability and the CPU occupation of the at least one AI / ML CSI report.15.The apparatus of claim 14, wherein the at least one processor, individually or in any combination, is further configured to:transmit, to the network entity via the MAC-CE and based on the first confirmation, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report to the first supported number of CPUs or the second supported number of CPUs; andreceive, from the network entity, a second confirmation of the switch request.16.The apparatus of claim 10, wherein the at least one processor, individually or in any combination, is further configured to:identify, based on a number of the one or more AI / ML CSI reports that exceeds one or more of the first supported number of CPUs or the second supported number of CPUs, one or more refrained CSI reports of the one or more AI / ML CSI reports; andrefrain from updating the one or more refrained CSI reports.17.The apparatus of claim 16, wherein each of the one or more AI / ML CSI reports has an inter-CSI priority, and wherein to identify the one or more refrained CSI reports of the one or more AI / ML CSI reports, the at least one processor, individually or in any combination, is configured to:identify the refrained CSI reports based on a comparison of the inter-CSI priority for the one or more AI / ML CSI reports.18.The apparatus of claim 16, wherein each of the one or more AI / ML CSI reports and the one or more non-AI / ML CSI reports has an inter-CSI priority, and wherein to identify the one or more refrained CSI reports of the one or more AI / ML CSI reports, the at least one processor, individually or in any combination, is configured to:identify the refrained CSI reports based on a comparison of the inter-CSI priority associated with the one or more AI / ML CSI reports and the one or more non-AI / ML CSI reports having a same CPU occupation.19.An apparatus for wireless communication at a network entity, comprising:at least one memory; andat least one processor coupled to the at least one memory and, based at least in part on information stored in the at least one memory, the at least one processor, individually or in any combination, is configured to:receive, from a user equipment (UE) , a capability indicator of a computational capability comprising an artificial intelligence (AI) / machine learning (ML) (AI / ML) capability for processing an AI / ML function; andreceive, from the UE based on the AI / ML function, one or more AI / ML channel station information (CSI) reports comprising a result of the AI / ML function, wherein a calculation of a report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing.20.The apparatus of claim 19, further comprising a transceiver coupled to the at least one processor, wherein, to receive the capability indicator, the at least one processor, individually or in any combination, is configured to receive the capability indicator via the transceiver, and wherein the AI / ML capability includes at least one of:a first supported number of channel state information (CSI) processing units (CPUs) occupied by the one or more AI / ML CSI reports associated with each component carrier (CC) of a set of CCs; ora second supported number of CPUs occupied by the one or more AI / ML CSI reports for all of the set of CCs.21.The apparatus of claim 20, wherein the report quantity for each of the one or more AI / ML CSI reports includes one or more of:a beam prediction result,a CSI prediction result, ora CSI compression result.22.The apparatus of claim 21, wherein the beam prediction result includes one or more of:a predicted layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) for each of a first set of beams based on measurements for a second set of beams,a predicted number of beams for the first set of beams based on the measurements for the second set of beams,a spatial prediction for the first set of beams based on the measurements for the second set of beams, wherein first resources for the first set of beams do not overlap with second resources for the second set of beams,a temporal prediction for the first set of beams for one or more future temporal occasions, ora frequency or mobility prediction for the first set of beams based on the measurements for the second set of beams, wherein the first set of beams and the second set of beams are associated with different bandwidth parts (BWPs) , component carriers (CCs) , frequency ranges (FRs) , or cells.23.The apparatus of claim 21, wherein the CSI prediction result includes one or more of:a model for CSI compression and decompression, wherein a precoding matrix indicator (PMI) associated with the CSI compression and decompression is compressed using a first AI / ML model and decompressed using a second AI / ML model, ora predicted PMI associated with one or more future temporal occasions.24.The apparatus of claim 20, wherein the computational capability further comprises a non-AI / ML capability comprising a non-AI / ML number of CPUs for one or more non-AI / ML CSI reports, the report quantity for each of the one or more non-AI / ML CSI reports is not associated with the AI / ML based processing, and wherein the one or more non-AI / ML CSI reports do not occupy the first supported number of CPUs or the second supported number of CPUs.25.The apparatus of claim 24, wherein the one or more AI / ML CSI reports do not occupy the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports.26.The apparatus of claim 24, wherein at least one AI / ML CSI report of the one or more AI / ML CSI reports occupies the non-AI / ML number of CPUs for the one or more non-AI / ML CSI reports.27.The apparatus of claim 26, wherein the at least one processor, individually or in any combination, is further configured to:receive, from the UE via a medium access control (MAC) –control element (MAC-CE) , a CPU occupation request for a CPU occupation of the at least one AI / ML CSI report on the non-AI / ML number of CPUs, wherein the CPU occupation request comprises one or more of:the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs, ora condition associated with the report quantity for each of the at least one AI / ML CSI report occupying the non-AI / ML number of CPUs; andtransmit, for the UE, a first confirmation of the CPU occupation request.28.The apparatus of claim 27, wherein the at least one processor, individually or in any combination, is further configured to:receive, from the UE via the MAC-CE and based on the first confirmation, a switch request for a change of the CPU occupation of the at least one AI / ML CSI report to the first supported number of CPUs or the second supported number of CPUs; andtransmit, for the UE, a second confirmation of the switch request.29.A method of wireless communication at a user equipment (UE) , comprising:transmitting, to a network entity, a capability indicator of a computational capability comprising an artificial intelligence (AI) / machine learning (ML) (AI / ML) capability for processing an AI / ML function;performing the AI / ML function based on the computational capability; andtransmitting, to the network entity based on the AI / ML function, one or more AI / ML channel station information (CSI) reports comprising a result of the AI / ML function, wherein a calculation of a report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing.30.A method of wireless communication at a network entity, comprising:receiving, from a user equipment (UE) , a capability indicator of a computational capability comprising an artificial intelligence (AI) / machine learning (ML) (AI / ML) capability for processing an AI / ML function; andreceiving, from the UE based on the AI / ML function, one or more AI / ML channel station information (CSI) reports comprising a result of the AI / ML function, wherein a calculation of a report quantity for each of the one or more AI / ML CSI reports is associated with AI / ML based processing.
Citation Information
Patent Citations
Qualification of csi prediction based on machine learning
CN116210181A
Method and device for sending or receiving capability information and readable storage medium
CN116868604A
Apparatus and method for transmission and reception of channel state information based on artificial intelligence
US20230370885A1
Terminal, radio communication method, and base station
WO2023218657A1