IMR-CMR pairing consistency across training and inference for intra-cell interference prediction
Spatial beam prediction ensures consistent IMR-CMR pairing for intra-cell interference prediction, reducing overhead and power consumption while improving prediction accuracy in wireless communication systems.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-09-25
- Publication Date
- 2026-04-02
AI Technical Summary
Existing wireless communication systems face challenges in efficiently predicting intra-cell interference and noise measurements, leading to increased overhead, power consumption, and latency due to separate measurements of channel and interference/noise using paired IMRs and CMRs.
Implementing spatial beam prediction for intra-cell interference prediction by ensuring IMR-CMR pairing consistency across training and inference, using predefined regulations and information exchange between the network and UE to reduce reference signal transmissions.
Reduces signaling overhead, power consumption, and latency by improving the accuracy of interference and noise predictions through consistent IMR-CMR pairing, enhancing beam management efficiency.
Smart Images

Figure CN2024121015_02042026_PF_FP_ABST
Abstract
Description
IMR-CMR PAIRING CONSISTENCY ACROSS TRAINING AND INFERENCE FOR INTRA-CELL INTERFERENCE PREDICTIONTECHNICAL FIELD
[0001] The present disclosure relates generally to communication systems, and more particularly, to a wireless communication that includes prediction associated with beam measurements.
[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. The apparatus is configured to receive a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter and paired with a channel measurement resource (CMR) having a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target based on prior model training for a pair that includes the CMR and an interference measurement resource (IMR) associated with the first interference prediction target. The apparatus is configured to predict the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of the IMR having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter.
[0008] In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus is configured to transmit a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter and paired with a CMR having a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target for a model trained for a pair that includes the CMR and an IMR associated with the first interference prediction target. The apparatus is configured to receive a report including a prediction of the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of the IMR having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter.
[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 communications 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 an illustrative block diagram of an example machine learning (ML) model represented by an artificial neural network (ANN) , in accordance with various aspects of the present disclosure.
[0017] FIG. 5 is an illustrative block diagram of an example ML architecture, in accordance with various aspects of the present disclosure.
[0018] FIG. 6 is an illustrative block diagram of an example ML architecture of first wireless device, in accordance with various aspects of the present disclosure.
[0019] FIG. 7 is a diagram illustrating an example of measurement resources and prediction targets, in accordance with various aspects of the present disclosure.
[0020] FIG. 8A illustrates an example of L1-SINR measurements via dedicated IMRs that are paired with CMRs, in accordance with various aspects of the present disclosure.
[0021] FIG. 8B illustrates an example of L1-SINR prediction, in accordance with various aspects of the present disclosure.
[0022] FIG. 9 illustrates an example showing Set-B beams that are a subset of Set-Abeams, in accordance with various aspects of the present disclosure.
[0023] FIG. 10 illustrates example aspects of data collection to train a model for intra-cell interference prediction procedures, in accordance with various aspects of the present disclosure.
[0024] FIG. 11 is a diagram illustrating a training portion and an inference portion using a model trained based on the training portion, in accordance with various aspects of the present disclosure.
[0025] FIG. 12 illustrates an example communication diagram showing example aspects of a network signaling possible IMR and CMR pairing hypotheses for data collection and model training, in accordance with various aspects of the present disclosure.
[0026] FIG. 13A illustrates an example in which a subset of IMR and CMR pairings are indicated, as a subset of potential IMR and CMR pairings., in accordance with various aspects of the present disclosure.
[0027] FIG. 13B illustrates an example 1350, in which CMR and IMR IDs can be used to indicate pairs of CMR and IMR for model training and reused to report interference and noise predictions for virtual IMR and CMR pairs, in accordance with various aspects of the present disclosure.
[0028] FIG. 14 illustrates an example communication diagram showing example aspects of a UE determining and signaling possible IMR and CMR pairing hypotheses for data collection and model training, in accordance with various aspects of the present disclosure.
[0029] FIG. 15 illustrates a diagram with a training portion 1502 and an inference portion 1504 showing example aspects in which a UE reports prediction information for previously indicated IMR and CMR pairing hypotheses, in accordance with various aspects of the present disclosure.
[0030] FIG. 16 illustrates an example communication flow 1600 between a UE and an example network node 1602, in accordance with various aspects of the present disclosure.
[0031] FIG. 17 is a flowchart of a method of wireless communication, in accordance with various aspects of the present disclosure.
[0032] FIG. 18 is a flowchart of a method of wireless communication, in accordance with various aspects of the present disclosure.
[0033] FIG. 19 is a diagram illustrating an example of a hardware implementation for an example apparatus and / or network entity.
[0034] FIG. 20 is a diagram illustrating an example of a hardware implementation for an example network entity.DETAILED DESCRIPTION
[0035] IMRs can be paired with CMRs for interference and noise measurements. As an example, IMRs may be time division multiplexed (TDM) with CMRs. Channel measurements and interference / noise measurements can then be carried out in different temporal occasions to provide good measurement accuracy on both components (e.g., considering both channel measurements and interference and noise measurements) . When paired IMRs and CMRs are used to perform channel measurement and interference and noise measurements at different times, the overhead for the signals increases, power consumption at the measuring device increases, and additional latency is incurred while the measurements are performed.
[0036] For example, in order to measure interference and noise from dedicated IMRs, a UE spends dedicated efforts on related measurements (e.g., using the reception beams considered for CMRs paired with the IMRs) . The added effort and related measurements causes increases in overhead, power consumption, and latency for the UE to obtain accurate interference and noise estimations.
[0037] As presented herein, spatial beam prediction can be used for intra-cell interference prediction to reduce the overhead, power consumption, and latency for paired interference and noise measurements. Various aspects relate generally to providing IMR-CMR pairing consistency across training and inference for intra-cell interference prediction. Aspects presented herein provide for rules (e.g., which may be referred to as predefined regulations) and / or further negotiation, coordination, or exchange of information between a network and UE, such that network side additional conditions (e.g., a CMR-IMR pairing pattern with respect to spatial transmission filters) can be ensured with consistency, across training and inference, e.g., as an extension of L1-RSRP based beam prediction in the related context.
[0038] For example, to predict interference and noise with respect to an IMR paired with a CMR with a model based inference, the UE may have previously measured the IMR via a TypeD-QCL identified for the CMR, when collecting data to train the AI / ML model. In some aspects, the training may be based on each potential pairing hypothesis. In some aspects, the training may be based on a subset of candidate pairing hypotheses indicated by the network. In some aspects, the training may be based on a subset of candidate pairing hypotheses indicated by the UE.
[0039] Particular aspects of the subject matter described in this disclosure can be implemented to realize one or more of the following potential advantages. The use of spatial beam prediction helps to reduce signaling overhead by enabling beam management to be performed with reduced reference signal transmissions for intra-cell interference measurements. The use of spatial beam prediction helps to reduce power consumed for intra-cell interference measurements, e.g., by reducing the number of reference signal measurements to be performed. Aspects presented herein improve the effectiveness of such predictions by providing IMR-CMR pairing consistency across training and inference for intra-cell interference prediction.
[0040] 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.
[0041] 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.
[0042] 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.
[0043] 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.
[0044] 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.
[0045] 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.
[0046] 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) .
[0047] 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.
[0048] 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.
[0049] 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.
[0050] 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.
[0051] 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.
[0052] 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.
[0053] 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.
[0054] 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.
[0055] 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) .
[0056] 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) .
[0057] 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.
[0058] 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.
[0059] 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.
[0060] 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.
[0061] 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.
[0062] 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.
[0063] 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) .
[0064] 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, 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 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 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.
[0065] 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.
[0066] Referring again to FIG. 1, in certain aspects, the UE 104 may have a prediction component 198 that may be configured to receive a first interference prediction target based on a first transmission spatial filter and paired with a channel measurement resource (CMR) having a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target based on prior model training for a pair that includes the CMR and an interference measurement resource (IMR) associated with the first interference prediction target; and predict the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of the IMR having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter. In certain aspects, the base station 102 may have a beam management component 199 that may be configured to transmit a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter and paired with a CMR having a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target for a model trained for a pair that includes the CMR and an IMR associated with the first interference prediction target; and receiving a report including a prediction of the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of the IMR having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter.
[0067] 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.
[0068] 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.
[0069] Table 1: Numerology, SCS, and CP
[0070] 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) .
[0071] 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.
[0072] 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) .
[0073] 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.
[0074] 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.
[0075] 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.
[0076] 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.
[0077] 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.
[0078] 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.
[0079] 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.
[0080] 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.
[0081] 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.
[0082] 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.
[0083] 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.
[0084] 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 prediction component 198 of FIG. 1.
[0085] 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 beam management component 199 of FIG. 1.
[0086] As used herein, the term “training stage” may refer to the process of training an AI / ML model for spatial or temporal domain DL transmit beam prediction for set-Aof beams based on measurement results of set-B of beams. As used herein, the term “measurement resources, ” “Set B beams, ” or “set-B beams” may be used interchangeably to refer to a set of measurement resources associated with one or more spatial filters (which may be referred to as “beams” and may a particular spatial filter may be based on a particular direction, a particular shape, and a particular transmit power) that may be used to train (which may be referred to as a “training stage” or “training” ) an AI / ML model at the UE to predict (which may be referred to as an “inference stage” or “inference” ) DL transmission associated with a set of “prediction targets, ” “Set A beams, ” or “set-Abeams. ” As used herein, the term “beam” may refer to a spatial filter. As used herein, the term “prediction result” may refer to predicted channel characteristics based on various information, such as information based on predicted reference signal received power (RSRP) or other measurements (e.g., a channel quality indicator (CQI) , a signal-to-noise ratio (SNR) , a signal-to-interference plus noise ratio (SINR) , a signal-to-noise-plus-distortion ratio (SNDR) , a received signal strength indicator (RSSI) , or a reference signal received quality (RSRQ) , and / or a block error rate (BLER) ) associated with prediction target (s) .
[0087] A UE may be requested by network to predict and report channel characteristics on a set of prediction targets associated with set-Anetwork node Tx beams, based on at least measurements on a set of measurement resource RSs associated with set-B network node Tx beams, through various prediction cycles and for each prediction cycle to be regarding various target temporal prediction instances.
[0088] As used herein, the term “measured characteristic” may refer to measured channel characteristic based on various information, such as information based on RSRP, CQI, SNR, SINR, SNDR, RSSI, RSRQ, BLER, that may be measured based on one or more RSs on measurements resources or one or more RSs on the prediction targets. As used herein, the term “channel characteristic” may refer to at least one of: top K targets with regard to L1-RSRP / SINR together with their predicted L1-RSRPs / SINRs, IDs of the top K targets with regard to L1-RSRP / SINR, probabilities of the target (s) being top1 / top K target (s) with regard to L1-RSRP / SINR together with their top K target IDs, or the like, where K may be a positive integer configured by the network or configured independent of signaling from the network (e.g., defined without signaling) .
[0089] The UE may be further scheduled by the network to measure a set of performance monitoring RSs associated with one or more of the set-Anetwork node Tx beams through various monitoring instances, and further calculate and feedback performance monitoring metrics and / or performance monitoring decisions based on particular performance monitoring metrics, taking measurements on the performance monitoring RSs at each monitoring instances together with the predicted channel characteristics on the prediction targets with regard to the prediction instance closest to the considered monitoring instance, into account. As used herein, RSs on the prediction targets that may allow the UE to measure the RSs to generate measured characteristic on the prediction targets may be referred to as “monitoring RS. ” The monitoring RSs may be carried in monitoring instances, which may be time instances for carrying RSs for prediction targets. In some aspects, each prediction target may be associated with a set of “monitoring instances. ” In some aspects, among all monitoring instances associated with a prediction target, a first subset of the monitoring instances may include actually transmitted RSs and a second subset of the monitoring instances may not include transmitted RSs (e.g., may be empty and there may be no RS transmitted in the monitoring instance) .
[0090] There may be different types of performance monitoring. A first type may be network-based performance monitoring where a UE feedbacks raw monitoring metrics with regard to each monitoring instance. A second type may be hybrid performance monitoring where the UE feedbacks statistical calculations of the raw monitoring metrics with regard to various monitoring instances. A third type may be UE-based performance monitoring where the UE feedbacks whether the UE-side prediction is functioning good / bad, or may be activated / switched / deactivated, based on statistical / raw calculation (s) of the monitoring metrics.
[0091] As used herein, the term “monitoring metric” may refer to a metric that may be used for performance monitoring for prediction targets. In some aspects, a monitoring metric may be a difference between a reference measured characteristic and at least one other measured characteristic, the at least one other measured characteristic being associated with at least one prediction target of the set of prediction targets that is closest to a respective monitoring instance associated with the reference measured characteristic. In some aspects, the metric may be based on a difference between a reference measured characteristic (e.g., highest RSRP, highest SINR, highest CQI, or the like) and at least one other measured characteristic associated with at least one prediction target of the set of prediction targets that is closest to a respective monitoring instance associated with the reference measured characteristic. As an example, the monitoring metrics at a particular monitoring instance, may be calculated based at least on difference between the best actually measured channel characteristics on a monitoring RS associated with the monitoring instance, and actually measured same channel characteristics on the Top1 / K’ (K’ <K) prediction target associated with the prediction instance closest to the considered monitoring instance. Such actually measured channel characteristics include L1-RSRP, L1-SINR, BLER determined by L1-RSRP / SINR, or the like.
[0092] The measurement resources and the prediction targets, along with an AI / ML model associated with the measurement resources and the prediction targets, may be associated with an associated ID. The associated ID may be a dataset, configuration, scenario, codebook, functionality, and model identifier that identifies network side additional conditions related with UE assumptions associated with AI / ML life cycle management including data collection, training, deployment, inference, performance monitoring, activation, deactivation, and switching. In some aspects, as long as the same associated ID is identified across training and inference, network side additional conditions may be assumed to be the same by the UE across training and inference. During the training stage, reference signal (s) such as a synchronization signal block (SSB) , a channel state information (CSI) -reference signal (CSI-RS) , or a demodulation reference signal (DM-RS) , may be transmitted on the measurement resources. Reference signal (s) may also be transmitted on the prediction targets during the training stage. During the prediction stage, reference signal (s) may be transmitted on the measurement resources and the UE may output prediction result (s) on the prediction target (s) based on a set of assumptions (e.g., generated or updated during the training stage) associated with the ID. In some aspects, each prediction result may be mapped to a particular beam ID or a set of beam IDs associated with the prediction target (s) . There may be several iterations of the prediction stage and each iteration may be a “prediction cycle. ”
[0093] In some aspects, network side additional conditions may include number (e.g., quantity) , ordering, or indexing of the measurement resources and the prediction targets. In some aspects, network side additional conditions may also include absolute or relative pointing directions (e.g., with regard to boresight direction relative to the center of Tx antenna panel) . In some aspects, network side additional conditions may also include beam shapes (e.g., angular specific beam forming gains) . In some aspects, network side additional conditions may also include quasi-co-location (QCL) relationships across or within the measurement resources or the prediction targets. In some aspects, network side additional conditions may also include temporal parameters (e.g., periodicity of the measurement resources or the prediction targets, target future occasions for temporal prediction, or the like) . QCL relationships may be specified in terms of QCL types. Regarding the QCL types, QCL type A may include the Doppler shift, the Doppler spread, the average delay, and the delay spread; QCL type B may include the Doppler shift and the Doppler spread; QCL type C may include the Doppler shift and the average delay; and QCL type D may include the spatial Rx parameters (e.g., associated with beam information such as beamforming properties for finding a beam) . In some aspects, network side additional conditions may impact UE side assumptions when a same associated ID, and may be received by the UE during training and inference.
[0094] Certain aspects and techniques as described herein may be implemented, at least in part, using an AI program, such as a program that includes a ML or artificial neural network (ANN) model. An example ML model may include mathematical representations or define computing capabilities for making inferences from input data based on patterns or relationships identified in the input data. As used herein, the term “inferences” can include one or more of decisions, predictions, determinations, or values, which may represent outputs of the ML model. The computing capabilities may be defined in terms of certain parameters of the ML model, such as weights and biases. Weights may indicate relationships between certain input data and certain outputs of the ML model, and biases are offsets which may indicate a starting point for outputs of the ML model. An example ML model operating on input data may start at an initial output based on the biases and then update its output based on a combination of the input data and the weights.
[0095] In some aspects, an ML model may be configured to provide computing capabilities for wireless communications. Such an ML model may be configured with weights and biases to perform spatial domain or temporal domain DL Tx beam prediction. Thus, during operation of a device, the ML model may receive input data (such as measurements on the measurement resources) and make inferences (such as spatial domain or temporal domain DL Tx beam prediction on the prediction targets, including reference signal received power (RSRP) or other metric prediction on the prediction targets) based on the weights and biases. ML models may be deployed in one or more devices (for example, network entities and user equipments (UEs) ) and may be configured to enhance various aspects of a wireless communication system. For example, an ML model may be trained to identify patterns or relationships in data corresponding to a network, a device, an air interface, or the like. An ML model may support operational decisions relating to one or more aspects associated with wireless communications devices, networks, or services. For example, an ML model may be utilized for supporting or improving aspects such as signal coding / decoding, network routing, energy conservation, transceiver circuitry controls, frequency synchronization, timing synchronization, channel state estimation, channel equalization, channel state feedback, modulation, demodulation, device positioning, beamforming, load balancing, operations and management functions, security, or the like.
[0096] ML models may be characterized in terms of types of learning that generate specific types of learned models that perform specific types of tasks. For example, different types of machine learning include supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, etc. ML models may be used to perform different tasks such as classification or regression, where classification refers to determining one or more discrete output values from a set of predefined output values, and regression refers to determining continuous values which are not bounded by predefined output values. Some example ML models configured for performing such tasks include ANNs such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) , transformers, diffusion models, regression analysis models (such as statistical models) , large language models (LLMs) , decision tree learning (such as predictive models) , support vector networks (SVMs) , and probabilistic graphical models (such as a Bayesian network) , or the like.
[0097] The description herein illustrates, by way of some examples, how one or more tasks or problems in wireless communications may benefit from the application of one or more ML models. For example, based on aspects provided herein, performance of beams may be predicted and the UE may be able to more efficiently perform beam management. To facilitate the discussion, an ML model configured using an ANN is used, but it may be understood, that other types of ML models may be used instead of an ANN. Hence, unless expressly recited, subject matter regarding an ML model is not necessarily intended to be an ANN solution without other solutions. Further, it may be understood that, unless otherwise specifically stated, terms such “AI / ML model, ” “ML model, ” “trained ML model, ” “ANN, ” “model, ” “algorithm, ” or the like are intended to be interchangeable.
[0098] FIG. 4 is an illustrative block diagram of an example machine learning (ML) model represented by an artificial neural network (ANN) , in accordance with various aspects of the present disclosure. ANN 400 may receive input data 406 which may include one or more bits of data 402, pre-processed data output from pre-processor 404 (optional) , or some combination thereof. Here, data 402 may include training data, verification data, application-related data, or the like, based, for example, on the stage of deployment of ANN 400. Pre-processor 404 may be included within ANN 400 in some other implementations. Pre-processor 404 may, for example, process all or a portion of data 402 which may result in some of data 402 being changed, replaced, deleted, etc. In some implementations, pre-processor 404 may add additional data to data 402. In some implementations, the pre-processor 404 may be a ML model, such as an ANN.
[0099] ANN 400 includes at least one first layer 408 of artificial neurons 410 to process input data 406 and provide resulting first layer data via connections or “edges” such as edges 412 to at least a portion of at least one second layer 414. Second layer 414 processes data received via edges 412 and provides second layer output data via edges 416 to at least a portion of at least one third layer 418. Third layer 418 processes data received via edges 416 and provides third layer output data via edges 420 to at least a portion of a final layer 422 including one or more neurons to provide output data 424. All or part of output data 424 may be further processed in some manner by (optional) post-processor 426. Thus, in certain examples, ANN 400 may provide output data 428 that is based on output data 424, post-processed data output from post-processor 426, or some combination thereof.
[0100] Post-processor 426 may be included within ANN 400 in some other implementations. Post-processor 426 may, for example, process all or a portion of output data 424 which may result in output data 428 being different, at least in part, to output data 424, as result of data being changed, replaced, deleted, etc. In some implementations, post-processor 426 may be configured to add additional data to output data 424. In this example, second layer 414 and third layer 418 represent intermediate or hidden layers that may be arranged in a hierarchical or other like structure. Although not explicitly shown, there may be one or more further intermediate layers between the second layer 414 and the third layer 418. In some implementations, the post-processor 426 may be a ML model, such as an ANN.
[0101] The structure and training of artificial neurons 410 in the various layers may be tailored to specific conditions of an application. Within a given layer such as first layer 408, second layer 414, or third layer 418 of ANN 400, some or all of the neurons may be configured to process information provided to the layer and output corresponding transformed information from the layer. For example, transformed information from a layer may represent a weighted sum of the input information associated with or otherwise based on a non-linear activation function or other activation function used to “activate” artificial neurons of a next layer. Artificial neurons in such a layer may be activated by or be responsive to parameters such as the previously described weights and biases of ANN 400. The weights and biases of ANN 400 may be adjusted during a training process or during operation of ANN 400. The weights of the various artificial neurons may control a strength of connections between layers or artificial neurons, while the biases may control a direction of connections between the layers or artificial neurons. An activation function may select or determine whether an artificial neuron transmits its output to the next layer or not in response to its received data.
[0102] Different activation functions may be used to model different types of non-linear relationships. By introducing non-linearity into an ML model, an activation function allows the configuration for the ML model to change in response to identifying or detecting complex patterns and relationships in the input data 406. Some non-exhaustive example activation functions include a sigmoid based activation function, a hyperbolic tangent (tanh) based activation function, a convolutional activation function, up-sampling, pooling, and a rectified linear unit (ReLU) based activation function.
[0103] Training of an ML model, such as ANN 400, may be conducted using training data. Training data may include one or more datasets which ANN 400 may use to identify patterns or relationships. Training data may represent various types of information, including written, visual, audio, environmental context, operational properties, etc. During training, the parameters (such as the weights and biases) of artificial neurons 410 may be changed, such as to minimize or otherwise reduce a loss function or a cost function. A training process may be repeated multiple times to fine-tune ANN 400 with each iteration.
[0104] Various ANN model structures are available for consideration. For example, in a feedforward ANN structure, each artificial neuron 410 in layer 414 receives information from the previous layer (such as, one or more artificial neurons 410 in layer 408) and produces information for the next layer (such as, one or more artificial neurons 410 in layer 418) . In a convolutional ANN structure, some layers may be organized into filters that extract features from data, such as the training data or the input data. In a recurrent ANN structure, some layers may have connections that allow for processing of data across time, such as for processing information having a temporal structure, such as time series data forecasting.
[0105] ANN 400 or other ML models may be implemented in various types of processing circuits along with memory and applicable instructions therein. For example, general-purpose hardware circuits, such as, such as one or more central processing units (CPUs) , one or more graphics processing units (GPUs) , or suitable combinations thereof, may be employed to implement a model. In some implementations, one or more tensor processing units (TPUs) , neural processing units (NPUs) , or other special-purpose processors, field-programmable gate arrays (FPGAs) , application-specific integrated circuits (ASICs) , or the like may also be employed. In some implementations, the ML model may be implemented by a NPU or a TPU embedded in a system on chip (SoC) along with other components, such as one or more CPUs, GPUs, etc. A SoC includes several components manufactured on a shared semiconductor substrate. The NPU or TPU may be controlled by the one or more CPUs by configuring the ML model implemented by the NPU or TPU with weights and biases, providing certain training data to the ML model to configure the ML model, or providing input data to the ML model to obtain related inferences. The one or more CPUs may also receive the inferences and be configured to perform certain actions based on the inferences produced by the ML model. The actions performed by the one or more CPUs may include sending commands to other components of the SoC or components external to the SoC to perform certain actions. For example, the CPU may send commands to a RF transceiver based on the outputs or inferences obtained from an ML model to cause the RF transceiver to operate on a wireless network in accordance with the ML model. For example, the UE may be more inclined to use a particular set of spatial filters from the prediction targets that are associated with a better performing metric during DL reception. As another example, the UE may also predict when may the DL transmission arrive (e.g., as part of the prediction result) and adjust its RF transceiver accordingly.
[0106] In example aspects, an ML model may be trained prior to, or at some point following, operation of the ML model, such as ANN 400, on input data. When training the ML model, information in the form of applicable training data may be gathered or otherwise created for use in training an ANN accordingly. For example, training data may be gathered or otherwise created regarding information associated with received / transmitted signal strengths, interference, and resource usage data, as well as any other relevant data that might be useful for training a model to address one or more problems or issues in a communication system. In certain instances, all or part of the training data may originate in a user equipment (UE) or other device in a wireless communication system, or one or more network entities, or aggregated from multiple sources (such as a UE and a network entity / entities, one or more other UEs, the Internet, or the like) . As a particular example, during the training stage, reference signals and measured metrics associated with the measurement resources or the prediction targets may be used as input for the model training. Offline training may refer to creating and using a static training dataset, such as, in a batched manner, whereas online training may refer to a real-time collection and use of training data. For example, an ML model at a network device (such as, a UE) may be trained or fine-tuned using online or offline training. For offline training, data collection and training can occur in an offline manner at the network side (such as, at a base station or other network entity) or at the UE side. For online training, the training of a UE-side ML model may be performed locally at the UE or by a server device (such as, a server hosted by a UE vendor) in a real-time or near-real-time manner based on data provided to the server device from the UE. Once an ANN has been configured by setting parameters, including weights and biases, from training data, the ANN’s performance may be evaluated. In some scenarios, evaluation / verification tests may use a validation dataset, which may include data not in the training data, to compare the model’s performance to baseline or other benchmark information. The ANN configuration may be further refined, for example, by changing its architecture, re-training it on the data, or using different optimization techniques, or the like.
[0107] As part of a training process, parameters affecting the functioning of the artificial neurons and layers may be adjusted. For example, backpropagation techniques may be used to train an ANN by iteratively adjusting weights or biases of certain artificial neurons associated with errors between a predicted output of the model and a desired output that may be known or otherwise deemed acceptable. Backpropagation may include a forward pass, a loss function, a backward pass, and a parameter update that may be performed in training iteration. The process may be repeated for a certain number of iterations for each set of training data until the weights of the artificial neurons / layers are adequately tuned. Backpropagation techniques associated with a loss function may measure how well a model is able to predict a desired output for a given input. An optimization algorithm may be used during a training process to adjust weights and biases as needed to reduce or minimize the loss function which improves the performance of the model. There are a variety of optimization algorithms that may be used along with backpropagation techniques or other training techniques. Some initial examples include a gradient descent based optimization algorithm and a stochastic gradient descent based optimization algorithm. A stochastic gradient descent technique may be used to adjust weights / biases in order to minimize or otherwise reduce a loss function. A mini-batch gradient descent technique, which is a variant of gradient descent, may involve updating weights / biases using a small batch of training data rather than the entire dataset. A momentum technique may accelerate an optimization process by adding a momentum term to update or otherwise affect certain weights / biases. An adaptive learning rate technique may adjust a learning rate of an optimization algorithm associated with one or more characteristics of the training data. A batch normalization technique may be used to normalize inputs to a model in order to stabilize a training process and potentially improve the performance of the model. A “dropout” technique may be used to randomly drop out some of the artificial neurons from a model during a training process, for example, in order to reduce overfitting and potentially improve the generalization of the model. An “early stopping” technique may be used to stop an on-going training process early, such as when a performance of the model using a validation dataset starts to degrade. Another example technique includes data augmentation to generate additional training data by applying transformations to all or part of the training information. A transfer learning technique may be used which involves using a pre-trained model as a starting point for training a new model, which may be useful when training data is limited or when there are multiple tasks that are related to each other. A multi-task learning technique may be used which involves training a model to perform multiple tasks simultaneously to potentially improve the performance of the model on one or more of the tasks. Hyperparameters or the like may be input and applied during a training process in certain instances. Another example technique that may be useful with regard to an ANN is a “pruning” technique. A pruning technique, which may be performed during a training process or after a model has been trained, involves the removal of unnecessary or less necessary, or possibly redundant features from a model. In certain instances, a pruning technique may reduce the complexity of a model or improve efficiency of a model without undermining the intended performance of the model. One or more of the example training techniques presented above may be employed as part of a training process. Some example training processes that may be used to train an ANN include supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning technique. With supervised learning, a model is trained on a labeled training dataset, where the input data is accompanied by a correct or otherwise acceptable output. With unsupervised learning, a model is trained on an unlabeled training dataset, such that the model will learn to identify patterns and relationships in the data without the explicit guidance of a labeled training dataset. With semi-supervised learning, a model is trained using some combination of supervised and unsupervised learning processes, for example, when the amount of labeled data is somewhat limited. With reinforcement learning, a model may learn from interactions with its operation / environment, such as in the form of feedback akin to rewards or penalties. Reinforcement learning may be particularly beneficial when used to improve or attempt to optimize a behavior of a model deployed in a dynamically changing environment, such as a wireless communication network. Distributed, shared, or collaborative learning techniques may be used for the training process. For example, techniques such as federated learning may be used to decentralize the training process and rely on multiple devices, network entities, or organizations for training various versions or copies of a ML model, without relying on a centralized training mechanism. Federated learning may be particularly useful in scenarios where data is sensitive or subject to privacy constraints, or where it is impractical, inefficient, or expensive to centralize data. In the context of wireless communication, for example, federated learning may be used to improve performance by allowing an ANN to be trained on data collected from a wide range of devices and environments. For example, an ANN may be trained on data collected from a large number of wireless devices in a network, such as distributed wireless communication nodes, smartphones, or internet-of-things (IoT) devices, to improve the network's performance and efficiency. With federated learning, a user equipment (UE) or other device may receive a copy of all or part of a global or shared model and perform local training on the local model using locally available training data. The UE may provide update information regarding the locally trained model to one or more other devices (such as a network entity or a server) where the updates from other-like devices (such as other UEs) may be aggregated and used to provide an update to global or shared model. A federated learning process may be repeated iteratively until all or part of a model obtains a satisfactory level of performance. Federated learning may enable devices to protect the privacy and security of local data, while supporting collaboration regarding training and updating of all or part of a shared model.
[0108] In some implementations, one or more devices or services may support processes relating to a ML model’s usage, maintenance, activation, reporting, or the like. In certain instances, all or part of a dataset or model may be shared across multiple devices, to provide or otherwise augment or improve processing. In some examples, signaling mechanisms may be utilized at various nodes of wireless network to signal the capabilities for performing specific functions related to ML model, support for specific ML models, capabilities for gathering, creating, transmitting training data, or other ML related capabilities. ML models in wireless communication systems may, for example, be employed to support decisions or improve performance relating to wireless resource allocation or selection, wireless channel condition estimation, interference mitigation, beam management, positioning accuracy, energy savings, or modulation or coding schemes, etc. In some implementations, model deployment may occur jointly or separately at various network levels, such as, a UE, a network entity such as a base station, or a disaggregated network entity such as a central unit (CU) , a distributed unit (DU) , a radio unit (RU) , or the like.
[0109] FIG. 5 is an illustrative block diagram of an example ML architecture 500 that may be used for wireless communications in any of the various implementations, processes, environments, networks, or use cases, in accordance with various aspects of the present disclosure. As illustrated, architecture 500 includes multiple logical entities, such as model training host 502, model inference host 504, data source (s) 506, and agent 508. Model inference host 504 is configured to run an ML model based on inference data 512 provided by data source (s) 506. Model inference host 504 may produce output 514, which may include a prediction or inference, such as a discrete or continuous value based on inference data 512, which may then be provided as input to the agent 508. Agent 508 may represent an element or an entity of a wireless communication system including, for example, a radio access network (RAN) , a wireless local area network, a device-to-device (D2D) communications system, etc. As an example, agent 508 may be an UE, such as the UE 104 in FIG. 1. Additionally, agent 508 also may be a type of agent that depends on the type of tasks performed by model inference host 504, the type of inference data 512 provided to model inference host 504, or the type of output 514 produced by model inference host 504. Agent 508 may perform one or more actions associated with receiving output 514 from model inference host 504. For example, if the agent 508 determines to change or modify a transmit or receive beam for a communication between agent 508 and the subject of action 510, agent 508 may adjust reception beam. As an example, agent 508 may be a UE and output 514 from model inference host 504 may one or more predicted channel characteristics for one or more beams. For example, model inference host 504 may predict channel characteristics for a set of beam based on the measurements of another set of beams. Based on the predicted channel characteristics, agent 508, the UE, may send, to the BS, a request to switch to a different beam for communications. In some cases, agent 508 and the subject of action 510 are the same entity. Data can be collected from data sources 506, and may be used as training data 516 for training an ML model, or as inference data 512 for feeding an ML model inference operation. Data sources 506 may collect data from various subject of action 510 entities (such as, the UE or the network entity) , and provide the collected data to a model training host 502 for ML model training. As an example, the data collected may include measured metrics associated with the measurement resources or the prediction targets.
[0110] Model training host 502 may be deployed at the same or a different entity than that in which model inference host 504 is deployed. For example, in order to offload model training processing, which can impact the performance of model inference host 504, model training host 502 may be deployed at a model server.
[0111] FIG. 6 is an illustrative block diagram 600 of an example ML architecture of first wireless device 602 in communication with second wireless device 604, in accordance with various aspects of the present disclosure. First wireless device 602 may be, or may include, a chip, system on chip (SoC) , chipset, package or device that includes one or more processors, processing blocks or processing elements (collectively “processor 610” ) and one or more memory blocks or elements (collectively “memory 620” ) . Processor 610 may be coupled to transceiver 640, which includes radio frequency (RF) circuitry 642 coupled to antennas 646 via interface 644, for transmitting or receiving signals.
[0112] One or more ML models 630 (collectively “ML model 630” ) may be stored in memory 620 and accessible to processor (s) 610. Individual or groups of ML models 630 may be associated with respective model identifiers. In some aspects, different ML models 630, which may optionally be associated with different model identifiers, may have different characteristics. One or more ML models 630 may be selected based on respective features, characteristics, or applications, as well as characteristics or conditions of first wireless device 602 (such as, a power state, a mobility state, a battery reserve, a temperature, etc. ) . For example, ML models 630 may have different inference data and output pairings (such as, different types of inference data produce different types of output) , different levels of accuracies associated with the predictions, different latencies associated with producing the predictions, different ML model sizes, different coefficients, different parameters, or the like.
[0113] Processor 610 may deploy ML models 630 to produce respective output data based on input data. For example, the ML models 630 may output predicted metric (s) , such as predicted reference signal received power (RSRP) or other metrics associated with prediction target (s) based on measurements on the measurement resources. In some aspects, model server 650 may perform various ML management tasks for first wireless device 602 and / or second wireless device 604. For example, model server 650 may host various types and / or versions of ML models 630 for first wireless device 602 and / or second wireless device 604 to download. Model server 650 may monitor and evaluate the performance of ML model 630. Model server 650 may transmit signals or provide indications / instructions to activate or deactivate the use of a particular ML model at first wireless device 602 or second wireless device 604. Model server 650 may switch to a different ML model being used at first wireless device 602 or second wireless device 604, and model server 650 may provide such an instruction to the respective first wireless device 602 or second wireless device 604. Model server 650 may operate as a model training host (such as model training host 502) and update ML model 630 using training data. In some cases, the model server 650 may operate as a data source (such as data source 506) to collect and host training data, inference data, performance feedback, etc., associated with ML model 630.
[0114] FIG. 7 is a diagram 700 illustrating an example of measurement resources and prediction targets. As illustrated in FIG. 7, a set of measurement resources 702, which may be CSI-RS resource set or a different type of prediction resource set, may include 32 narrow beams. The set of prediction targets 704 may include SSB resource set based on 8 wide-beams. Various types of parameter consistency across training and inference with regard to a same ID may be maintained. For example, quantity consistency such that the same quantities of SSBs, CSI-RSs, or other resources configured as measurement resources and prediction targets are expected across different groups of resources during training stage and inference stage. As another example, beam consistency such that relative pointing direction and beam width difference between physical beams with regard to different resources may remain the same across different SSB resource sets for different groups of resources during training stage and inference stage, across the CSI-RS resource set for training and the prediction resource set for inference. In some aspects, a Type D QCL consistency may be used. For example, if the jth resource in a first group of resources in the training stage has a Type D QCL relationship with the kth resource in a second group of resources in the training stage, it may also be expected that the jth resource in a third group of resource in the inference stage has a Type D QCL relationship with the kth resource in the fourth group of resources in the inference stage.
[0115] For L1-SINR Measurements, when one resource setting is configured, the resource setting (e.g., given by a higher layer parameter such as resourcesForChannelMeasurement) may be used for channel and interference measurement on a non-zero power channel state information reference signal (NZP CSI-RS) for layer 1 signal to interference plus noise ratio (L1-SINR) computation. For example, a UE may assume that the same 1 port NZP CSI-RS resource (s) with a density of 3 REs / RB is used for both channel and interference measurements.
[0116] For L1-SINR Measurements, when two resource settings are configured, the first one resource setting (e.g., given by a higher layer parameter such as resourcesForChannelMeasurement) may be used for channel measurement on SSB or NZP CSI-RS and the second resource setting (e.g., given by either a higher layer parameter such as csi-IM-ResourcesForInterference or a higher layer parameter such as nzp-CSI-RS-ResourcesForInterference) may be used for interference measurement performed on CSI-IM or on 1 port NZP CSI-RS with a density of 3 REs / RB, where each SSB or NZP CSI-RS resource for channel measurement is associated with one CSI-IM resource or one NZP CSI-RS resource for interference measurement by the ordering of the SSB or NZP CSI-RS resource for channel measurement and CSI-IM resource or NZP CSI-RS resource for interference measurement in the corresponding resource sets. The number of SSB (s) or CSI-RS resources for channel measurement equals to the number of CSI-IM resources or the number of NZP CSI-RS resource for interference measurement. A resource for channel measurement may be referred to as a channel measurement resource (CMR) , and a resource for interference measurement may be referred to as an interference measurement resource (IMR) .
[0117] The UE may apply the SSB, or 'typeD'RS configured with qcl-Type set to 'typeD'to the NZP CSI-RS resource for channel measurement, as the reference RS for determining 'typeD' assumption for the corresponding CSI-IM resource or the corresponding NZP CSI-RS resource for interference measurement configured for one CSI reporting. For example, the RX beam identified for the CMR can be used for receiving the IMR.
[0118] The UE may expect that the NZP CSI-RS resource set for channel measurement and the NZP-CSI-RS resource set for interference measurement, if any, are configured with the higher layer parameter repetition, in some aspects.
[0119] In some aspects, the identifier may be referred to as an associated ID or by another name such as an AI / M functionality / model / dataset / config / codebook-ID, among other examples.
[0120] As described herein, a prediction for Set-B beams may be based on measurement of Set-Abeams. The prediction may be an L1-RSRP prediction, e.g., predicting L1-RSRPs on Set-Abeams, or predicting the Top-K Set-Abeams (e.g., a subset of K beams from the Set-Abeams that are predicted to have the best measurements) in terms of L1-RSRP. In some aspects, the L1-RSRP prediction may include predicting the Top-K Set-Abeams in terms of probabilities being the Top-1 / Top-K Set-Abeams with respect to L1-RSRP. The Top-1 / Top-K Set-Abeam is the beam predicted to have the best (or top) measurement from the subset of K beams that are predicted to have the best measurements with respect to L1-RSRP or L1-SINR among the Set-Abeams.
[0121] Aspects presented herein provide for rules (e.g., which may be referred to as predefined regulations) and / or further negotiation, coordination, or exchange of information between a network and UE, such that network side additional conditions (e.g., a CMR-IMR pairing pattern with respect to spatial transmission filters) can be ensured with consistency, across training and inference, e.g., as an extension of L1-RSRP based beam prediction in the related context.
[0122] The use of spatial beam prediction helps to reduce signaling overhead by enabling beam management to be performed with reduced reference signal transmissions for intra-cell interference measurements. The use of spatial beam prediction helps to reduce power consumed for intra-cell interference measurements, e.g., by reducing the number of reference signal measurements to be performed.
[0123] As discussed above, IMRs are paired with CMRs for interference and noise measurements. As an example, IMRs may be time division multiplexed (TDM) with CMRs. Channel measurements and interference / noise measurements can then be carried out in different temporal occasions to provide good measurement accuracy on both components (e.g., considering both channel measurements and interference and noise measurements) . In some aspects, a direct interference and noise estimate may be performed from CMRs. However, a channel estimate accuracy may be low when interference and noise are strong.
[0124] When paired IMRs and CMRs are used to perform channel measurement and interference / noise measurements at different times, the overhead for the signals increases, power consumption at the measuring device increases, and additional latency is incurred while the measurements are performed.
[0125] In order to measure interference and noise from dedicated IMRs, a UE spends dedicated efforts on related measurements (e.g., using the Rx beams considered for CMRs paired with the IMRs) . The added effort and related measurements causes increases in overhead, power consumption, and latency for the UE to obtain accurate interference and noise estimations.
[0126] Spatial beam prediction can be used for intra-cell interference prediction and may also be used for interference prediction to reduce the overhead, power consumption, and latency for paired interference and noise measurements.
[0127] For example, a UE may more frequently measure CMRs as Set-B beams for channel measurements, and may measure IMRs less frequently as Set-A / Set-B beams for interference measurement and / or prediction. In some aspects, the network may completely skip transmission of IMRs, so that interference and noise measurements are predicted (e.g., pure prediction) without actual measurements of the IMRs. In this example, the IMRs that are not transmitted may be the Set-Abeams for spatial beam prediction. In other aspects, the device (e.g., UE) may perform a mixture of measurement and prediction for the IMRs. In such aspects, the network may continue transmit at least a subset of the IMRs, and the transmitted IMRs may correspond to both Set-Abeams and Set-B beams.
[0128] In some aspects, the UE may be requested to provide feedback to the network, e.g., such as feedback that is based on or comprises L1-SINR, RI, CQI, PMI, and / or layer indicator (LI) (e.g., a strongest layer if there are more than one) , regarding occasions wherein CMRs are transmitted and IMRs are not transmitted (e.g., interference and noise are predicted rather than measured) .
[0129] During such prediction occasions, the QCL of the interference and noise prediction target IMRs, as Set-Abeams, can be based on a QCL of the paired CMRs.
[0130] FIG. 8A illustrates an example 800 of spatial resources for L1-SINR measurements via dedicated IMRs that are paired with CMRs. FIG. 8A shows the paired IMRs and CMRs in multiple occasions or instances (e.g., 802, 804, 806, 808, 810, 812, and 814) over a period of time that allows for paired measurements of both CMRs and IMRs (e.g., measurement of the IMRs without interference and noise prediction) . As illustrated in FIG. 8A, the IMRs (e.g., IMR #1, IMR #2, and IMR #3) are transmitted with the same time periodicity (e.g., frequency over time) as the CMRs (e.g., CMR #1, CMR #2, and CMR #3) . As an example, CMR transmission may refer to a signal transmission associated with a particular spatial filter or beam. For CMR #1, a CSI-RS may be transmitted based on a first spatial filter. For CMR #2, the CSI-RS may be transmitted based on a second spatial filter. For CMR #3, the CSI-RS may be transmitted based on a third spatial filter. The CMR and IMR pairing may be configured, e.g., as a CSI report setting. FIG. 8A illustrates that IMR #1 is paired with CMR #1, IMR #2 is paired with CMR #2, and IMR #3 is paired with CMR #3. The UE may perform the channel measurements on the CMRs (e.g., CMR #1, CMR #2, and CMR #3) , and perform the interference and noise measurements on the IMRs (e.g., IMR #1, IMR #2, IMR #3) . The UE may report the measurements (e.g., transmit a report based on actual measurements without predictions) at each reporting occasion, in some aspects. For example, the UE may measure the IMRs and CMRs at occasion 802 and send a first report, measure the IMRs and CMRs at occasion 804 and send a second report, measure the IMRs and CMRs at occasion 806 and send a report. As an example, the UE may transmit a report with a first L1-SINR for the pair of CMR #1 and IMR #2, a second L1-SINR for the pair of CMR #2 and IMR #2, and a third L1-SINR for the pair of CMR #3 and IMR #3. In some aspects, a time restriction may be configured for interference measurements (e.g., by a parameter such as timeRestrictionForInterferenceMeasurements being set to configured) . In response to the time restriction configuration, the UE may derive the L1-SINR based on instantaneously measured interference and noise.
[0131] FIG. 8B illustrates an example 850 of CMR and IMR resources for L1-SINR prediction and having different transmission periodicities, as presented herein. FIG. 8B illustrates that the IMRs may be transmitted less frequently than the associated CMRs, and the UE may predict interference and noise measurements on at least some of the IMRs. In this example, the UE can predict interference and noise for an IMR in a time occasion when the IMR is not measurable (e.g., is not transmitted) . The UE can report the L1-SINR (measured and / or predicted) for the corresponding time occasion. As shown in FIG. 8B, the CMRs (e.g., CMR #1, CMR #2, and CMR #3) may be transmitted in each of the occasions, e.g., 852, 854, 856, 858, 860, 862, and 864. In contrast, IMR #1 is transmitted at occasions 852 and 864, but not at the other occasions. The dashed arrows show that IMR #2 and IMR #3 may be a prediction target at the occasions 852 and 864. Similarly, IMR #2 is transmitted at occasion 856, but not at the other occasions, and IMR #3 is transmitted at occasion 860, but not at the other occasions. In some occasions, no IMRs may be transmitted, e.g., as shown at occasions 854, 858, and 862.
[0132] FIG. 9 illustrates an example 900 showing Set-B beams that are a subset of Set-Abeams. For example, the spatial and / or temporal density of the Set-B beams may be lower compared to the prediction instances of the Set-Abeams. Similar to FIG. 8B, IMR #1 may be transmitted at occasion 902 and 914. At other occasions, the interference and noise may be predicted rather than measured. The IMR #2 may be transmitted at occasion 906, and the IMR #3 may be transmitted at occasion 910. If a particular IMR is not transmitted at an occasion, an interference prediction may be performed for the IMR at that occasion. At occasions 904, 908, and 912, the interference and noise may be predicted for each of IMR #1, IMR #2, and IMR #3. The UE may provide reports with measurements at each reporting occasion. The report may include the Top-K Set-Abeams, plus their measured and / or predicted L1-RSRPs with respect to the reporting occasion. The example in FIG. 10 may be for an L1-RSRP based spatial beam prediction, e.g., which may be referred to as narrow-to-narrow spatial beam predictions.
[0133] As shown in FIG. 8B and 9, the IMRs may be transmitted (or measured) less frequently compared to the corresponding (e.g., paired) CMRs. The UE may predict the interference and noise with respect to an IMR for an occasion where the IMR is not measurable, and the UE can report the L1-SINR (e.g., either measured or predicted) corresponding to the report occasion.
[0134] The prediction of the interference and noise may be based on historically measured power of interference and noise with respect to different IMRs (e.g., TypeD-QCL based on the paired CMRs’ TypeD-QCL) , as shown at 1002 in FIG. 10, and / or historically measured power of signal (S) with respect to different CMRs (e.g., TypeD-QCL based on the paired CMRs’ TypeD-QCL) , as shown at 1004 in FIG. 10. For example, the historical measurements may be used as input to a model (such as an AI / ML model 1006 described in connection with any of FIGs. 4-6) to obtain an output of a predicted power of interference and noise on non-measurable IMRs (e.g., which may be referred to as interference prediction targets) for the current reporting occasion (e.g., a “virtual” TypeD-QCL based on the paired CMRs’ TypeD-QCL) , e.g., as shown at 1008 in FIG. 10. The term “virtual” may be used for the IMR that is predicted rather than measured (and / or not actually transmitted) . In some aspects, the
[0135] Aspects may be performed to help ensure consistency of network side parameters between model training &model inference for UE-side beam prediction, e.g., for L1-RSRP types of beam prediction. For example, it may be helpful to maintain consistency between the use of antenna panel structures, number (s) (e.g. number of Set-Abeams or Set-B beams or their corresponding RSs) , order (s) , codebook (s) , and / or EPRE ratio between Set-Abeams and the corresponding Set-B beams in order to have future occasions considered using temporal beam prediction.
[0136] As an example, a same model DI, configuration ID, or dataset ID may be identified, and used, during both model training and model inference in order to help maintain consistency and help to ensure prediction accuracy.
[0137] As presented herein, the prediction targets may be L1-SINR for IMRs, where the IMRs can be a mixture of Set-Abeams and Set-B beams, while the paired CMRs can be considered as Set-B beams. Although aspects are described herein for IMRs as the Set-Abeams, in some aspects, the prediction targets for Set-Abeams may also include CMR(s) .
[0138] As a first example consideration for consistency, predictable IMR and CMR pairs may be pair-wise measured during data collection for model training (e.g., for the training shown at 516 in FIG. 5) . To predict, at 514, interference and noise with respect to a particular IMR paired with a CMR (such as IMR #1 paired with CMR #1) with AI / ML inference with the model (e.g., 504) , the UE may measure the IMR via TypeD-QCL identified for the CMR, when collecting data to train the AI / ML model. For example, in order to perform the inference, the UE may not use inference to predict the IMR paired with a CMR if the UE has not previously measured the IMR via TypeD-QCL identified for the CMR when collecting training data for the model.
[0139] FIG. 10 illustrates an example 1000 of data collection for IMR and CMR to train a model to intra-cell interference prediction procedures. For example, to train the AI / ML model (s) (e.g., 504) , the UE may first collect a dataset comprising powers of interference and noise measured from IMRs, using the TypeD-QCL identified from their pairing CMRs. The measured powers of interference and noise can be used as ground-truth labels to train the AI / ML model (s) (e.g., 504) , as shown at 516 and 502. FIG. 10 similarly shows the historical measurements (e.g., 1002 and 1004) used to train the model 1006.
[0140] For example, FIG. 10 illustrates that both the Set-Abeams and the Set-B beams (e.g., signals on the Set-Abeams and Set-B beams) may be transmitted and / or measured to obtain a training dataset. The collected training dataset may then be input for model training. FIG. 10 shows an example of CMR and IMR pairing that may be considered during data collection for model training. The example candidate CMR and IMR pairs in FIG. 10 include: IMR #1 paired with CMR #1, as shown with the arrow 1020; IMR #2 paired with CMR #2, as shown with the arrow 1022; and IMR #3 paired with CMR #3, as shown with the arrow 1024. For example, the Type-D QCL for the IMR #1 corresponds to the Type-D QCL of CMR #1. Similarly, the Type-D QCL for the IMR #2 corresponds to the Type-D QCL of CMR #2, and the Type-D QCL for the IMR #3 corresponds to the Type-D QCL of CMR #3. In FIG. 10, the model is trained on the indicated three pairings, e.g., the indicated CMR and IMR pairing hypotheses. Then, the interference and noise prediction, at 1008 and 1010, can be based on the CMR and IMR pairing hypotheses used for training, e.g., and not for untrained pairing hypotheses.
[0141] As an example, a network may transmit a {1st, 2nd} NZP-CSI-RS based on the {1st, 2nd} Tx spatial filter defined respectively as {IMR, CMR} . The UE identifies a TypeD-QCL of the IMR based on TypeD-QCL with respect to the QCL source RS of the CMR. The UE measures and stores (e.g., logs) the measured amount (e.g., power or level) of interference and noise from the IMR and the measured (e.g., power or level) of S from the CMR, respectively. The logged information may then be used as components of a training dataset to train the model 1006.
[0142] During model inference (e.g., an inferred prediction as output 514 based on inference data 512) , the AI / ML model (e.g., 504) may predict powers of interference and noise regarding those IMR and CMR pairs that have been measured during data collection for model training (e.g., and may not predict interference and noise for IMR and CMR pairs without training data) . If an unseen IMR and CMR pair (e.g., a pair without training data) is requested for prediction of interference and noise, more data collection may be carried out in real-time to refine and / or retrain the model (s) (e.g., 504) .
[0143] For example, the network may request the UE to predict and report an L1-SINR with respect to a time occasion. In the occasion, the CMR may be transmitted based on the 2nd Tx spatial filter, but the paired IMR is not transmitted (or not measured) for the occasion, such that the power of (e.g., amount of) interference and noise is to be predicted. As the IMR is not transmitted (or not measured) , the IMR may be referred to as a virtual IMR. The UE may expect that the transmission spatial filter associated with the non-transmitted, virtual IMR is associated with the first transmission spatial filter (s) that have been measured during data collection for model training.
[0144] The IMR and CMR pairing consistency is maintained across training and inference. During interference and noise prediction (e.g., AI / ML inference) via a certain AI / ML model for L1-SINR based UE-side beam prediction, the UE may be requested to predict characteristics of interference and noise at a certain occasion (e.g., time occasion) for a non-transmitted, virtual IMR associated with a first transmission spatial filter, where the virtual IMR is paired with a certain CMR associated with a second transmission spatial filter for deriving L1-SINR with respect to the same occasion. The UE performs the prediction based on the training dataset associated with the AI / ML model having been trained based on measurements of interference and noise characteristics with respect to the first transmission spatial filter associated with the virtual IMR, and interference and noise measurements obtained based on a TypeD QCL determined based on a QCL source RS associated with the second transmission spatial filter.
[0145] In some aspects, in order to enable the training data to be obtained for IMR and CMR beam pairs, potential the potential IMR beams and CMR beams may be included together in an umbrella set of beams in a cell, where the umbrella set of claims is transmitted toward the UE (s) during an over-the-air data collection period. If candidate transmission spatial filters, which can be associated with a CMR or a virtual IMR, can be identified during data collection for training an AI / ML model associated with the L1-SINR based beam prediction, various aspects may be employed to ensure that training data is provided for potential IMR beams and CMR beams to enable later interference and noise predictions (or inferences) .
[0146] In some aspects, brute-force pairing hypotheses can be used. When carrying out model training and inference, the UE may assume that any two beams among the umbrella set of beams, can be paired as an IMR and CMR pair or a CMR and IMR pair for the prediction procedures. For example, a set of candidate pairings may be identified for each potential combination of two transmission spatial filters among the candidate transmission spatial filters identified during data collection for model training. Each combination of two transmission spatial filters is measured for a pair of CMR and IMR and used to train a model that can later perform inference for the pair of CMR and virtual IMR. In some aspects, this assumption may lead to heavy UE side efforts to consider each hypothesis, whereas many hypotheses may not be applicable.
[0147] FIG. 11 shows a diagram 1100 including a training portion 1102 and an inference portion 1104 using a model trained based on the training portion 1102. As shown with the arrows at 1106, a hypothesis is assumed for each candidate IMR and CMR pairing. Then, training data (e.g., for a particular AI / ML functionality, model, dataset, configuration, and / or codebook, which may be identified by an associated ID) is collected for each of the hypotheses (e.g., 1108) . As an example, for beam #1, there are potential pairings 1110, 1112, 1114, 1116, and 1118. Similarly, each of beams #2 to #6 also have a set of five potential pairings (e.g., hypotheses) . For each potential hypothesis, the UE measures IMR based on the Type-D QCL relationship with the corresponding. The network may transmit (e.g., contiguously transmit) various NZP-CSI-RSs (e.g., via periodic or semi-persistent CSI-RSs) based on different transmission spatial filters. The candidate transmission spatial filter IDs corresponding to the model being trained (e.g., AI / ML model-ID) , may be 1-to-1 mapped with the transmitted NZP-CSI-RS resource IDs. For example, candidate transmission spatial filter IDs may be in ascending order of the NZP-CSI-RS resource entry-IDs) . In some aspects, the UE may decide how and / or when to receive and measure the reference signals to obtain the training data for each IMR and CMR pairing hypothesis. As an example, the measurement may be of a periodic or semi-persistent NZP-CSI-RS. As each potential pairing is included in the training, each hypothesis may be considered for an inference or prediction, at 1104. The AI / ML functionality, model, dataset, configuration, and / or codebook for the inference or prediction may be indicated (e.g., explicitly indicated or implicitly identified through CSI report setting with respect to the L1-SINR reporting) . Each CMR / IMR may be signaled (e.g., reported) with the candidate transmission spatial filter ID assumed during data collection for model training. FIG. 11 shows an inference example for a CMR and IMR pairing in which the CMR is associated with beam #3, and the IMR is associated with beam #5.
[0148] In some aspects, a set of pairing hypotheses may be configured. For example, a network may configure pairing hypotheses to signal the candidate hypotheses that can be considered as an IMR and CMR pair or a CMR and IMR pair for the prediction procedures. As an example, for carrying out data-collection, the network may signal the candidate hypotheses on which beam-pairs can be considered as IMR and CMR pairs. Possible combinations of two transmission spatial filters associated with a pair including a CMR and a virtual IMR for later inference can be identified to collect data for model training. Then, the UE can expect such network signaled pairs to be requested for the prediction procedures. As an example, inference may be expected for the identified combinations and not for unidentified combinations.
[0149] FIG. 12 illustrates an example communication diagram 1200 showing example aspects of a network signaling possible IMR and CMR pairing hypotheses for data collection and model training. At 1206, an initialization is sent to trigger data collection for model training (e.g., for interference and noise prediction for a virtual IMR) . In some aspects, the network node 1202 may send a message, at 1206, that indicates for the UE to collect data and train a model. The UE 1204 may send a reply to the network. In some aspects, the UE 1204 may send a message, at 1206, indicating that the UE will collect data for model training, and the network node 1202 may send a reply. As shown at 1208, the network may indicate IMR and CMR beam pairing hypotheses for the UE 1204 to collect training data. In some aspects, the indication may include a configuration of IMR and CMR beam pairing candidates. The UE may collect training data for the indicated IMR and CMR beam pairing hypotheses (e.g., by performing and logging measurements for the IMR and CMR hypotheses) . As shown at 1210, the intra-cell L1-SINR prediction procedures may be performed using the model trained based on the IMR and CMR pairing hypotheses indicated at 1208. For example, the network may request an L1-SINR prediction, and / or the UE may report an L1-SINR prediction for at least one virtual IMR based on the IMR and CMR pairing hypotheses indicated by the network. The UE may not infer or predict for unidentified IMR and CMR pairing hypotheses that were not indicated by the network, for example.
[0150] For data collection for a particular AI / ML functionality, model, dataset, configuration, and / or codebook (which may be identified by or associated with an identifier) , the network may transmit (e.g., contiguously transmit) various reference signals (such as periodic or semi-persistent NZP-CSI-RSs) based on different transmission spatial filters. The candidate transmission spatial filter IDs corresponding to the AI / ML model-ID may be 1-to-1 mapped with the transmitted NZP-CSI-RS resource IDs. As an example, the candidate Tx spatial filter IDs may be associated in an ascending order with the NZP-CSI-RS resource entry-IDs. The network may further signal the possible transmission spatial filter pairs to be considered as IMR and CMR pairs. As an example, the network may indicate the NZP-CSI-RS resource pairs (e.g., with ordering to represent IMR in contrast to CMR) .
[0151] In some aspects, the UE may decide how to receive the NZP-CSI-RSs to perform the measurements for data collection and training of the model based on the indicated IMR and CMR pairs.
[0152] In some aspects, the network may directly schedule CMR and IMR pairs for L1-SINR measurements. In such aspects the UE uses a TypeD-QCL relationship with respect to the CMR to receive the paired IMR.
[0153] The UE may then perform inference or prediction using the particular AI / ML functionality, model, dataset, configuration, and / or codebook, e.g., based on an implicit or explicit indication of the particular AI / ML functionality, model, dataset, configuration, and / or codebook to be used. As an example, the particular AI / ML functionality, model, dataset, configuration, and / or codebook for the inference may be explicitly indicated to the UE or implicitly identified through a CSI report setting with respect to L1-SINR reporting.
[0154] In some aspects, the UE may report, or indicate, each CMR / IMR pair with the candidate transmission spatial filter ID assumed during data collection for model training. For example, the CMR / IMR may be signaled with the candidate transmission spatial filter ID assumed during data collection for model training, e.g., whether the UE determines how to obtain the measurements and / or the network schedules CMR and IMR pairs for measurement. FIG. 13A illustrates an example 1300 in which a subset of IMR and CMR pairings are indicated, as a subset of potential IMR and CMR pairings. The table 1306 shows a “yes” for a candidate IMR and CMR pairing and a “no” for potential pairings that are not indicated for model training. NA indicates that the combination is not a potential CMR and IMR pairing, and is not considered applicable. The UE may train the model with measurements for each of the indicates IMR and CMR pairings (e.g., IMR on beam #1 paired with CMR on beam #2, IMR on beam #1 paired with CMR on beam #3, IMR on beam #2 paired with CMR on beam #1, IMR on beam #3 paired with CMR on beam #1, IMR on beam #3 paired with CMR on beam #4, and IMR on beam #4 paired with CMR on beam #1. An inference can later be obtained for one of the indicated IMR and CMR pairings using the trained model. For example, an interference and noise for a virtual IMR 1304 on beam #1 may be predicted based on a paired CMR 1302 on beam #2.
[0155] In some aspects, the UE may report the CMR and IMR information reusing CMR and IMR IDs from IDs identified during the data collection for model training. In some aspects, the CMR and IMR IDs may be provided from the network to the UE, and the UE may use the provided IDs to report the inferred information.
[0156] FIG. 13B illustrates an example 1350, in which CMR and IMR IDs can be used to ensure consistency of resource pairing CMR and IMR (1356) for model training and reused to report interference and noise predictions for virtual IMR and CMR pairs 1358. In FIG. 13B, the TypeD-QCL of the CMR may be used for the receiving IMR for training purposes, at 1352, and similarly for the IMR prediction during the inference stage 1354.
[0157] In some aspects, the UE may assist in the determination of the candidate hypotheses for IMR and CMR pairs or CMR and IMR pairs. For example, the UE may determine and report such pairing hypotheses. When carrying out data collection for training, the UE may determine the candidate hypotheses on which beam-pairs can be considered as an IMR+CMR or a CMR+IMR pair. The UE reports such hypotheses before carrying prediction procedures (e.g., that may be limited based on the previously reported candidate hypotheses) . For example, possible combinations of two transmission spatial filters may be associated with a pair of CMR and virtual IMR for inference. The possible combinations may be determined by UE during data collection for model training, and the UE may report, or otherwise indicate, the determined combinations to the network before inference / prediction. In this example, the UE reported combinations may be expected during inference and not unreported combinations.
[0158] FIG. 14 illustrates an example communication diagram 1400 showing example aspects of a UE determining and signaling possible IMR and CMR pairing hypotheses for data collection and model training. At 1406, an initialization is sent to trigger data collection for model training (e.g., for interference and noise prediction for a virtual IMR) . In some aspects, the network node 1402 may send a message, at 1406, that indicates for the UE to collect data and train a model. The UE 1404 may send a reply to the network. In some aspects, the UE 1404 may send a message, at 1406, indicating that the UE will collect data for model training, and the network node 1402 may send a reply. As shown at 1408, the UE may indicate IMR and CMR beam pairing hypotheses for which the UE 1404 intends to collect training data. The UE may collect training data for the indicated IMR and CMR beam pairing hypotheses (e.g., by performing and logging measurements for the IMR and CMR hypotheses) . As shown at 1410, the intra-cell L1-SINR prediction procedures may be performed using the model trained based on the IMR and CMR pairing hypotheses indicated at 1408. For example, the network may request an L1-SINR prediction, and / or the UE may report an L1-SINR prediction for at least one virtual IMR based on the IMR and CMR pairing hypotheses previously indicated by the UE. As an example, the UE may not expect to infer a prediction for unidentified IMR and CMR pairing hypotheses that were not indicated by the UE to the network, for example.
[0159] FIG. 15 illustrates a diagram 1500 with a training portion 1502 and an inference portion 1504 showing example aspects in which a UE reports prediction information for previously indicated IMR and CMR pairing hypotheses.
[0160] For data collection for a particular AI / ML functionality, model, dataset, configuration, and / or codebook (which may be identified by or associated with an identifier) , the network may transmit (e.g., contiguously transmit) various reference signals (such as periodic or semi-persistent NZP-CSI-RSs) based on different transmission spatial filters. The candidate transmission spatial filter IDs corresponding to the AI / ML model-ID can be 1-to-1 mapped with the transmitted reference signal resource IDs (e.g., NZP-CSI-RS resource IDs) . As an example, the candidate transmission spatial filter IDs may be 1-to-1 mapped in ascending order of the NZP-CSI-RS resource entry-IDs. The UE may determine, as shown at 1506, the possible transmission spatial filter pairs to be considered as IMR+CMR pairs (from the set of all potential pairings of two spatial filters shown at 1508) . In some aspects, the UE may also decide how to receive the NZP-CSI-RSs to obtain the measurements for training the model.
[0161] For inference, at 1504, the particular AI / ML functionality, model, dataset, configuration, and / or codebook may be indicated to the UE for inference and prediction. The indication may be explicitly signaled to the UE or implicitly indicated through a CSI report setting with respect to L1-SINR reporting.
[0162] Before the network configures, activates, and / or triggers L1 reports for the L1-SINR based beam prediction from the UE, the UE reports the transmission spatial filter pairs for the determined IMR and CMR pairs. In some aspects, the IMR and CMR pairs or the spatial filter pairs may be referred to as self-determined transmission spatial filter pairing decisions. The indicated pairs may be indicated with an association to associated with an identifier for the particular AI / ML functionality, model, dataset, configuration, and / or codebook. The pairs may be indicated in one or more of UE capability reporting, RRC signaling, a medium access control-control element (MAC-CE) , and / or uplink control information UCI) .
[0163] After the UE receives the configuration or indication to report the L1-SINR based beam prediction, the CMR / IMR may be signaled with the candidate transmission spatial filter ID that is assumed during the data collection for model training. The UE reports based on the pairing options that it supports and reported, and does not expect to report predictions for other pairing options that the UE did not indicate.
[0164] FIG. 16 illustrates an example communication flow 1600 between a UE and an example network node 1602. The network node may correspond to a base station in aggregation or may correspond to one or more components of a base station, such as a CU, DU and / or RU. Although aspects are described for a network node and a UE, in some aspects, the communication flow may be performed between a UE and a UE. For example, the aspects performed by the network node 1602 may be performed by a first UE, and the aspects performed by the UE 1604 may be performed by a second UE. In some aspects, the exchanged communication may include sidelink communication between the first UE and the second UE.
[0165] As illustrated at 1613, the UE 1604 trains a model based on measurements collected for candidate IMR and CMR pairs. As shown at 1610 and 1612, the network node 1602 transmits various reference signals (e.g., NZP CSI-RSs) using different spatial filters. The UE 1604 receives the signals, and performs measurements for the candidate IMR and CMR pairs (e.g., measurements for combinations of two transmission spatial filters) . The UE then uses the collected measurements to train the model at 1613. The model may correspond to the model described in connection with 504, 630, or 1006, for example. The candidate IMR and CMR pairs may include each possible combination of spatial filters, such as described in connection with FIG. 11. The training data may include any of 1002, 1004, 1108, or information obtained at 1502, for example. In some aspects the candidate IMR and CMR pairs may be indicated by the network node 1602, as shown at 1608. In some aspects the candidate IMR and CMR pairs may be indicated by the UE 1604, as shown at 1606.
[0166] As shown at 1614, the network node 1602 may configure, or otherwise indicate for the UE 1604, to perform L1-SINR beam prediction and / or reporting. The network may indicate a particular AI / ML functionality, model, dataset, configuration, and / or codebook for the UE to use. The UE 1604 measures the reference signals 1616 for the CMR (s) , at 1618. Then, using the measurement for the CMR and the model trained at 1613, the UE 1604 predicts interference and noise for one or more virtual IMRs (or prediction targets) , at 1620. The UE may provide a report, at 1622, based on the L1-SINR based beam prediction (s) . The training, prediction, and / or reporting may include any of the aspects described in connection with FIGs. 4-15, for example.
[0167] FIG. 17 is a flowchart 1700 of a method of wireless communication. The method may be performed by a UE (e.g., the UE 104, 350, 1204, 1404, 1604; the apparatus 1904) . The method enables a reduction in latency, overhead, and power consumption by enabling the UE to provide an interference prediction based on a paired CMR, e.g., without reception, measurement, and / or transmission of the IMR in an occasion corresponding to the interference prediction target. Aspects of the method may be performed, e.g., by the prediction component 198, as described in connection with FIG. 1 or FIG. 19.
[0168] At 1702, the UE receives a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter, where the first interference prediction target is paired with a CMR having a second transmission spatial filter and paired with a CMR having a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target based on prior model training for a pair that includes the CMR and an IMR associated with the first interference prediction target. In some aspects, the interference prediction target may be referred to as a virtual IMR, an unmeasurable IMR, an IMR that is not measured, or an IMR that is not transmitted. Example aspects of IMR and CMR resources are described in connection with FIG. 8A, 8B, 9, and 10, for example. In some aspects, the indication may correspond to an initialization of data collection for model training, such as shown at 1206 or 1406. FIG. 16 illustrates an example in which the UE receives a configuration for L1-SINR beam prediction, at 1614. The reception may be performed, e.g., by the prediction component 198.
[0169] At 1704, the UE predicts the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of the IMR having the first transmission spatial filter and obtained based on a Type D QCL relationship with the second transmission spatial filter. In some aspects, the UE may perform a measurement based on the CMR, and the characteristics of interference and noise for the first interference prediction target may be predicted based on the measurement of the CMR. The model may include any of the aspects described in connection with the model in FIGs. 4-6, or the model 1006. The model may be trained based on any of the aspects described in connection with FIGs. 7-16. In some aspects, the model comprises an artificial intelligence or machine learning model trained for interference and noise prediction. The prediction may be performed, e.g., by the prediction component 198.
[0170] In some aspects, the UE may identify an error based on a request to predict a second interference prediction target associated with a candidate IMR and CMR pair for which the model has not been trained. The identification may be performed, e.g., by the prediction component 198.
[0171] In some aspects, the model is trained based on hypotheses pairings for each potential candidate pair of two transmission spatial filters among a set of multiple transmission spatial filters. FIG. 11 illustrates an example of training based on each potential pair. In some aspects, such training may be referred to as brute force training (e.g., training for all potential pairings) rather than training for a more targeted subset of potential pairings.
[0172] In some aspects, the UE may receive a second indication of one or more combinations of spatial filter pairs associated with a paired CMR and IMR, where the model is trained based on the one or more combinations of spatial filters in the second indication. The reception may be performed, e.g., by the prediction component 198. The UE may receive scheduling for the one or more combinations of the spatial filter pairs for L1-SINR measurements. The reception may be performed, e.g., by the prediction component 198. FIG. 12 and FIG. 16 illustrates examples in which the network may indicate a set of hypotheses to the UE. The UE may measure the L1-SINR measurements, and the model may be trained on the L1-SINR measurements. The measurement may be performed, e.g., by the prediction component 198. In some aspects, the UE may receive a third indication of a candidate transmission spatial filter identifiers for each CMR and IMR for model training. The reception may be performed, e.g., by the prediction component 198. In some aspects, the UE may report a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and IMR for model training and the prediction of the characteristics of interference and noise. The reporting may be performed, e.g., by the prediction component 198. FIG. 13A and 13B illustrate example aspects that the UE may use for identifying the resources for training and reporting.
[0173] In some aspects, the UE may report one or more combinations of spatial filters associated with a paired CMR and IMR, and the model may be trained based on the one or more combinations of spatial reported by the UE. The reporting may be performed, e.g., by the prediction component 198. In some aspects, the one or more combinations of spatial filters may be reported using candidate transmission spatial identifiers that map to reference signal resource identifiers. FIG. 14, FIG. 15, and FIG. 16 illustrate example aspects in which a UE indicates a set of hypotheses. In some aspects, the UE may further report a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and IMR for model training and the prediction of the characteristics of interference and noise. In some aspects, the one or more combinations of spatial filters may be indicated with an associated identifier associated with one or more of a model functionality, the model, a dataset, a configuration, or a codebook.
[0174] FIG. 18 is a flowchart 1800 of a method of wireless communication. The method may be performed by a network node or network entity, which may include a base station in aggregation or one or more components of a base station (e.g., the base station 102, 310; CU 110; DU 130; RU 140; the network entity 2002; the network node 1202, 1402, 1602) . The method enables a reduction in latency, overhead, and power consumption by enabling the UE to provide an interference prediction based on a paired CMR, e.g., which may be done without transmission of the IMR in an occasion corresponding to the interference prediction target.
[0175] At 1802, the network node transmits a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter and paired with a CMR having a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target for a model trained for a pair that includes the CMR and an IMR associated with the first interference prediction target. The transmission may be performed, e.g., by the beam management component 199. In some aspects, the interference prediction target may be referred to as a virtual IMR, an unmeasurable IMR, an IMR that is not measured, or an IMR that is not transmitted. Example aspects of IMR and CMR resources are described in connection with FIG. 8A, 8B, 9, and 10, for example. In some aspects, the indication may correspond to an initialization of data collection for model training, such as shown at 1206 or 1406. FIG. 16 illustrates an example in which the UE receives a configuration for L1-SINR beam prediction, at 1614.
[0176] At 1804, the network node receives a report including a prediction of the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of the IMR having the first transmission spatial filter and obtained based on a Type D QCL relationship with the second transmission spatial filter. The reception may be performed, e.g., by the beam management component 199. The model may include any of the aspects described in connection with the model in FIGs. 4-6, or the model 1006. The model may be trained based on any of the aspects described in connection with FIGs. 7-16. In some aspects, the model comprises an artificial intelligence or machine learning model trained for interference and noise prediction.
[0177] In some aspects, the model is trained based on hypotheses pairings for each potential candidate pair of two transmission spatial filters among a set of multiple transmission spatial filters. FIG. 11 illustrates an example of training based on each potential pair. In some aspects, such training may be referred to as brute force training (e.g., training for all potential pairings) rather than training for a more targeted subset of potential pairings.
[0178] In some aspects, the network node transmits a second indication of one or more combinations of spatial filter pairs associated with a paired CMR and IMR, where the model is trained based on the one or more combinations of spatial filters in the second indication. The transmission may be performed, e.g., by the beam management component 199. The network node may transmit scheduling for the one or more combinations of the spatial filter pairs for L1-SINR measurements. The transmission may be performed, e.g., by the beam management component 199.
[0179] In some aspects, the network node may transmit a third indication of a candidate transmission spatial filter identifiers for each CMR and IMR for model training. The transmission may be performed, e.g., by the beam management component 199. FIG. 12 and FIG. 16 illustrates examples in which the network may indicate a set of hypotheses to the UE. The model may be trained on the L1-SINR measurements for the indicated pairs. In some aspects, the network node may receive a report including a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and IMR for model training and the prediction of the characteristics of interference and noise. The reception may be performed, e.g., by the beam management component 199. FIG. 13A and 13B illustrate example aspects that may be used for identifying the resources for training and reporting.
[0180] In some aspects, the network node may receive a second indication of one or more combinations of spatial filters associated with a paired CMR and IMR, and the model may be trained based on the one or more combinations of spatial in the second indication. The reception may be performed, e.g., by the beam management component 199. In some aspects, the one or more combinations of spatial filters may be reported using candidate transmission spatial identifiers that map to reference signal resource identifiers. FIG. 14, FIG. 15, and FIG. 16 illustrate example aspects in which a UE indicates a set of hypotheses. In some aspects, the network node may further receive a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and IMR for model training and the prediction of the characteristics of interference and noise. The reception may be performed, e.g., by the beam management component 199. In some aspects, the one or more combinations of spatial filters may be indicated with an associated identifier associated with one or more of a model functionality, the model, a dataset, a configuration, or a codebook.
[0181] FIG. 19 is a diagram 1900 illustrating an example of a hardware implementation for an apparatus 1904. The apparatus 1904 may be a UE, a component of a UE, or may implement UE functionality. In some aspects, the apparatus1904 may include at least one cellular baseband processor 1924 (also referred to as a modem) coupled to one or more transceivers 1922 (e.g., cellular RF transceiver) . The cellular baseband processor (s) 1924 may include at least one on-chip memory 1924'. In some aspects, the apparatus 1904 may further include one or more subscriber identity modules (SIM) cards 1920 and at least one application processor 1906 coupled to a secure digital (SD) card 1908 and a screen 1910. The application processor (s) 1906 may include on-chip memory 1906'. In some aspects, the apparatus 1904 may further include a Bluetooth module 1912, a WLAN module 1914, an SPS module 1916 (e.g., GNSS module) , one or more sensor modules 1918 (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 1926, a power supply 1930, and / or a camera 1932. The Bluetooth module 1912, the WLAN module 1914, and the SPS module 1916 may include an on-chip transceiver (TRX) (or in some cases, just a receiver (RX) ) . The Bluetooth module 1912, the WLAN module 1914, and the SPS module 1916 may include their own dedicated antennas and / or utilize the antennas 1980 for communication. The cellular baseband processor (s) 1924 communicates through the transceiver (s) 1922 via one or more antennas 1980 with the UE 104 and / or with an RU associated with a network entity 1902. The cellular baseband processor (s) 1924 and the application processor (s) 1906 may each include a computer-readable medium / memory 1924', 1906', respectively. The additional memory modules 1926 may also be considered a computer-readable medium / memory. Each computer-readable medium / memory 1924', 1906', 1926 may be non-transitory. The cellular baseband processor (s) 1924 and the application processor (s) 1906 are each responsible for general processing, including the execution of software stored on the computer-readable medium / memory. The software, when executed by the cellular baseband processor (s) 1924 / application processor (s) 1906, causes the cellular baseband processor (s) 1924 / application processor (s) 1906 to perform the various functions described supra. The cellular baseband processor (s) 1924 and the application processor (s) 1906 are configured to perform the various functions described supra based at least in part of the information stored in the memory. That is, the cellular baseband processor (s) 1924 and the application processor (s) 1906 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 may also be used for storing data that is manipulated by the cellular baseband processor (s) 1924 / application processor (s) 1906 when executing software. The cellular baseband processor (s) 1924 / application processor (s) 1906 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 1904 may be at least one processor chip (modem and / or application) and include just the cellular baseband processor (s) 1924 and / or the application processor (s) 1906, and in another configuration, the apparatus 1904 may be the entire UE (e.g., see UE 350 of FIG. 3) and include the additional modules of the apparatus 1904.
[0182] As discussed supra, the component 198 may be configured to receive a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter, wherein the first interference prediction target is paired with a channel measurement resource (CMR) having a second transmission spatial filter; and predict the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of a first interference measurement resource (IMR) having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter. The apparatus 1904 may be configured to perform any of the aspects described in connection with the flowchart in FIG. 17, aspects performed by the UE in any of the communication flows in FIG. 12, 14, or 16, or any of the aspects described in connection with interference prediction in any of FIGs. 4-17. The component 198 may be within the cellular baseband processor (s) 1924, the application processor (s) 1906, or both the cellular baseband processor (s) 1924 and the application processor (s) 1906. 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 1904 may include a variety of components configured for various functions. In one configuration, the apparatus 1904, and in particular the cellular baseband processor (s) 1924 and / or the application processor (s) 1906, may include means for receiving a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter, wherein the first interference prediction target is paired with a channel measurement resource (CMR) having a second transmission spatial filter; and means for predicting the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of a first interference measurement resource (IMR) having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter. The apparatus 1904 may further include means for identifying an error based on a request to predict a second interference prediction target associated with a candidate IMR and CMR pair for which the model has not been trained. The apparatus 1904 may further include means for performing a measurement based on the CMR, wherein the characteristics of interference and noise for the first interference prediction target are predicted based on the measurement of the CMR. The apparatus 1904 may further include means for receiving a second indication of one or more combinations of spatial filter pairs associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial filters in the second indication. The apparatus 1904 may further include means for receiving scheduling for the one or more combinations of the spatial filter pairs for Layer 1 signal to interference plus noise ratio (L1-SINR) measurements; and means for measuring the L1-SINR measurements, wherein the model is trained on the L1-SINR measurements. The apparatus 1904 may further include means for receiving a third indication of a candidate transmission spatial filter identifier for each CMR and IMR for model training. The apparatus 1904 may further include means for reporting a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and IMR for model training and the prediction of the characteristics of interference and noise. The apparatus 1904 may further include means for reporting one or more combinations of spatial filters associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial reported by the UE. The apparatus 1904 may further include means for reporting a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and IMR for model training and the prediction of the characteristics of interference and noise. The apparatus 1904 may include means for performing may any of the aspects described in connection with the flowchart in FIG. 17, aspects performed by the UE in any of the communication flows in FIG. 12, 14, or 16, or any of the aspects described in connection with interference prediction in any of FIGs. 4-17. . The means may be the component 198 of the apparatus 1904 configured to perform the functions recited by the means. As described supra, the apparatus 1904 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.
[0183] FIG. 20 is a diagram 2000 illustrating an example of a hardware implementation for a network entity 2002. The network entity 2002 may be a BS, a component of a BS, or may implement BS functionality. The network entity 2002 may include at least one of a CU 2010, a DU 2030, or an RU 2040. For example, depending on the layer functionality handled by the component 199, the network entity 2002 may include the CU 2010; both the CU 2010 and the DU 2030; each of the CU 2010, the DU 2030, and the RU 2040; the DU 2030; both the DU 2030 and the RU 2040; or the RU 2040. The CU 2010 may include at least one CU processor 2012. The CU processor (s) 2012 may include on-chip memory 2012'. In some aspects, the CU 2010 may further include additional memory modules 2014 and a communications interface 2018. The CU 2010 communicates with the DU 2030 through a midhaul link, such as an F1 interface. The DU 2030 may include at least one DU processor 2032. The DU processor (s) 2032 may include on-chip memory 2032'. In some aspects, the DU 2030 may further include additional memory modules 2034 and a communications interface 2038. The DU 2030 communicates with the RU 2040 through a fronthaul link. The RU 2040 may include at least one RU processor 2042. The RU processor (s) 2042 may include on-chip memory 2042'. In some aspects, the RU 2040 may further include additional memory modules 2044, one or more transceivers 2046, antennas 2080, and a communications interface 2048. The RU 2040 communicates with the UE 104. The on-chip memory 2012', 2032', 2042'a nd the additional memory modules 2014, 2034, 2044 may each be considered a computer-readable medium / memory. Each computer-readable medium / memory may be non-transitory. Each of the processors 2012, 2032, 2042 is responsible for general processing, including the execution of software stored on the computer-readable medium / memory. The software, when executed by the corresponding processor (s) causes the processor (s) to perform the various functions described supra. The computer-readable medium / memory may also be used for storing data that is manipulated by the processor (s) when executing software.
[0184] As discussed supra, the component 199 may be configured to transmit a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter, wherein the first interference prediction target is paired with a channel measurement resource (CMR) having a second transmission spatial filter; and receive a report including a prediction of the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of a first interference measurement resource (IMR) having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter. The network entity, or the component 199, may be configured to perform any of the aspects described in connection with the flowchart in FIG. 18, aspects performed by the network in any of the communication flows in FIG. 12, 14, or 16, or any of the aspects described in connection with beam management based on interference prediction in any of FIGs. 4-17. The component 199 may be within one or more processors of one or more of the CU 2010, DU 2030, and the RU 2040. 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 2002 may include a variety of components configured for various functions. In one configuration, the network entity 2002 may include means for transmitting a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter, wherein the first interference prediction target is paired with a channel measurement resource (CMR) having a second transmission spatial filter; and means for receiving a report including a prediction of the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of a first interference measurement resource (IMR) having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter. The network entity 2002 may further include means for transmitting a second indication of one or more combinations of spatial filter pairs associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial filters in the second indication. The network entity 2002 may further include means for transmitting scheduling for the one or more combinations of the spatial filter pairs for Layer 1 signal to interference plus noise ratio (L1-SINR) measurements for model training. The network entity 2002 may further include means for transmitting a third indication of a candidate transmission spatial filter identifier for each CMR and IMR for model training. The network entity 2002 may further include means for receiving a second indication of one or more combinations of spatial filters associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial in the second indication. The network entity 2002 may include means for performing any of the aspects described in connection with the flowchart in FIG. 18, aspects performed by the network in any of the communication flows in FIG. 12, 14, or 16, or any of the aspects described in connection with beam management based on interference prediction in any of FIGs. 4-17. The means may be the component 199 of the network entity 2002 configured to perform the functions recited by the means. As described supra, the network entity 2002 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.
[0185] 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.
[0186] 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. ”
[0187] 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.
[0188] The following aspects are illustrative only and may be combined with other aspects or teachings described herein, without limitation.
[0189] Aspect 1 is a method of wireless communication at a user equipment (UE) , comprising: receiving a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter and paired with a channel measurement resource (CMR) having a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target based on prior model training for a pair that includes the CMR and an interference measurement resource (IMR) associated with the first interference prediction target; and predicting the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of the IMR having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter.
[0190] In aspect 2, the method of aspect 1 further includes identifying an error based on a request to predict a second interference prediction target associated with a candidate IMR and CMR pair for which the model has not been trained.
[0191] In aspect 3, the method of aspect 1 or aspect 2 further comprises performing a measurement based on the CMR, wherein the characteristics of interference and noise for the first interference prediction target are predicted based on the measurement of the CMR.
[0192] In aspect 4, the method of any of aspects 1-3 further includes that the model comprises an artificial intelligence or machine learning model trained for interference and noise prediction.
[0193] In aspect 5, the method of any of aspects 1-4 further includes that the model is trained based on hypotheses pairings for each potential candidate pair of two transmission spatial filters among a set of multiple transmission spatial filters.
[0194] In aspect 6, the method of any of aspects 1-4 further includes receiving a second indication of one or more combinations of spatial filter pairs associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial filters in the second indication.
[0195] In aspect 7, the method of aspect 6 further includes receiving scheduling for the one or more combinations of the spatial filter pairs for Layer 1 signal to interference plus noise ratio (L1-SINR) measurements; and measuring the L1-SINR measurements, wherein the model is trained on the L1-SINR measurements.
[0196] In aspect 8, the method of aspect 6 further includes receiving a third indication of a candidate transmission spatial filter identifier for each CMR and each IMR for model training.
[0197] In aspect 9, the method of aspect 6 further includes reporting a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and each IMR for model training and the prediction of the characteristics of interference and noise.
[0198] In aspect 10, the method of any of aspects 1-4 further includes reporting one or more combinations of spatial filters associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial reported by the UE.
[0199] In aspect 11, the method of aspect 10 further includes that the one or more combinations of spatial filters are reported using candidate transmission spatial identifiers that map to reference signal resource identifiers.
[0200] In aspect 12, the method of aspect 10 or aspects 11 further includes reporting a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and each IMR for model training and the prediction of the characteristics of interference and noise.
[0201] In aspect 13, the method of any of aspects 10-12 further includes that the one or more combinations of spatial filters are indicated with an associated identifier associated with one or more of a model functionality, the model, a dataset, a configuration, or a codebook.
[0202] Aspect 14 is a method of wireless communication at a network node, comprising: transmitting a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter and paired with a channel measurement resource (CMR) having a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target for a model trained for a pair that includes the CMR and an interference measurement resource (IMR) associated with the first interference prediction target; and receiving a report including a prediction of the characteristics of interference and noise for the first interference prediction target using the model that is trained with a first measurement of the IMR having the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter.
[0203] In aspect 15, the method of aspect 14 further includes that the model is trained based on hypotheses pairings for each potential candidate pair of two transmission spatial filters among a set of multiple transmission spatial filters.
[0204] In aspect 16, the method of aspect 14 or 15 further includes transmitting a second indication of one or more combinations of spatial filter pairs associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial filters in the second indication.
[0205] In aspect 17, the method of aspect 16 further includes transmitting scheduling for the one or more combinations of the spatial filter pairs for Layer 1 signal to interference plus noise ratio (L1-SINR) measurements for model training.
[0206] In aspect 18, the method of aspect 16 further includes transmitting a third indication of a candidate transmission spatial filter identifier for each CMR and each IMR for model training.
[0207] In aspect 19, the method of aspect 16 further includes that the prediction included in the report uses a same candidate transmission spatial filter identifier for each CMR and each IMR for model training and the prediction of the characteristics of interference and noise.
[0208] In aspect 20, the method of any of aspects 14-16 further includes receiving a second indication of one or more combinations of spatial filters associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial in the second indication.
[0209] In aspect 21, the method of aspect 20 further includes that the one or more combinations of spatial filters are indicated using candidate transmission spatial identifiers that map to reference signal resource identifiers.
[0210] In aspect 22, the method of aspect 21 further includes that the report of the prediction uses a same candidate transmission spatial filter identifier for each CMR and each IMR for model training and the prediction of the characteristics of interference and noise.
[0211] In aspect 23, the method of aspect 20 further includes that the one or more combinations of spatial filters are indicated with an associated identifier associated with one or more of a model functionality, the model, a dataset, a configuration, or a codebook 1.
[0212] Aspect 24 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, the at least one processor, individually or in any combination, is configured to perform the method of any of aspects 1-13.
[0213] Aspect 25 is an apparatus for wireless communication at a UE, comprising means for performing each step in the method of any of aspects 1-13.
[0214] Aspect 26 is the apparatus of any of aspects 24 to 25, further comprising a transceiver configured to receive or to transmit in association with the method of any of aspects 1-13.
[0215] Aspect 27 is a computer-readable medium (e.g., non-transitory computer-readable storage medium) storing computer executable code at a UE, the code when executed by at least one processor causes the at least one processor to perform the method of any of aspects 1-13.
[0216] Aspect 28 is an apparatus for wireless communication at a network node, comprising: at least one memory; and at least one processor coupled to the at least one memory, the at least one processor, individually or in any combination, is configured to perform the method of any of aspects 14-23.
[0217] Aspect 29 is an apparatus for wireless communication at a network node, comprising means for performing each step in the method of any of aspects 14-23.
[0218] Aspect 30 is the apparatus of any of aspects 28 to 29, further comprising a transceiver configured to receive or to transmit in association with the method of any of aspects 14-23.
[0219] Aspect 31 is a computer-readable medium (e.g., non-transitory computer-readable storage medium) storing computer executable code at a network node, the code when executed by at least one processor causes the at least one processor to perform the method of any of aspects 14-23.
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:receive a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter and paired with a channel measurement resource (CMR) that has a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target based on prior model training for a pair that includes the CMR and an interference measurement resource (IMR) associated with the first interference prediction target; andpredict the characteristics of interference and noise for the first interference prediction target using a model that is trained with a first measurement of the IMR that has the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter.2.The apparatus of claim 1, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:identify an error based on a request to predict a second interference prediction target associated with a candidate IMR and CMR pair for which the model has not been trained.3.The apparatus of claim 1, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:perform a measurement based on the CMR, wherein the characteristics of interference and noise for the first interference prediction target are predicted based on the measurement of the CMR.4.The apparatus of claim 1, wherein the model comprises an artificial intelligence or machine learning model trained for interference and noise prediction.5.The apparatus of claim 1, wherein the model is trained based on hypotheses pairings for each potential candidate pair of two transmission spatial filters among a set of multiple transmission spatial filters.6.The apparatus of claim 1, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:receive a second indication of one or more combinations of spatial filter pairs associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial filters in the second indication.7.The apparatus of claim 6, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:receive scheduling for the one or more combinations of the spatial filter pairs for Layer 1 signal to interference plus noise ratio (L1-SINR) measurements; andmeasure the L1-SINR measurements, wherein the model is trained on the L1-SINR measurements.8.The apparatus of claim 6, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:receive a third indication of a candidate transmission spatial filter identifier for each CMR and each IMR for model training.9.The apparatus of claim 6, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:report a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and each IMR for model training and the prediction of the characteristics of interference and noise.10.The apparatus of claim 1, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:report one or more combinations of spatial filters associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial reported by the UE.11.The apparatus of claim 10, wherein the one or more combinations of spatial filters are reported using candidate transmission spatial identifiers that map to reference signal resource identifiers.12.The apparatus of claim 11, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:report a prediction of the characteristics of interference and noise for the first interference prediction target using a same candidate transmission spatial filter identifier for each CMR and each IMR for model training and the prediction of the characteristics of interference and noise.13.The apparatus of claim 10, wherein the one or more combinations of spatial filters are indicated with an associated identifier associated with one or more of a model functionality, the model, a dataset, a configuration, or a codebook.14.An apparatus for wireless communication at a network node, 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 a first indication to predict characteristics of interference and noise for a first interference prediction target based on a first transmission spatial filter and paired with a channel measurement resource (CMR) that has a second transmission spatial filter, wherein the first interference prediction target is a valid prediction target for a model trained for a pair that includes the CMR and an interference measurement resource (IMR) associated with the first interference prediction target; andreceive a report that includes a prediction of the characteristics of interference and noise for the first interference prediction target using the model that is trained with a first measurement of the IMR that has the first transmission spatial filter and obtained based on a Type D quasi co-location (QCL) relationship with the second transmission spatial filter.15.The apparatus of claim 14, wherein the model is trained based on hypotheses pairings for each potential candidate pair of two transmission spatial filters among a set of multiple transmission spatial filters.16.The apparatus of claim 14, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:transmit a second indication of one or more combinations of spatial filter pairs associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial filters in the second indication.17.The apparatus of claim 16, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to perform one of:transmit scheduling for the one or more combinations of the spatial filter pairs for Layer 1 signal to interference plus noise ratio (L1-SINR) measurements for model training,transmit a third indication of a candidate transmission spatial filter identifier for each CMR and each IMR for the model training, orwherein the prediction included in the report uses a same candidate transmission spatial filter identifier for each CMR and each IMR for the model training and the prediction of the characteristics of interference and noise.18.The apparatus of claim 14, wherein, based at least in part on the information stored in the at least one memory, the at least one processor is further configured to:receive a second indication of one or more combinations of spatial filters associated with a paired CMR and IMR, wherein the model is trained based on the one or more combinations of spatial in the second indication.19.The apparatus of claim 18, wherein the one or more combinations of spatial filters are indicated using candidate transmission spatial identifiers that map to reference signal resource identifiers.20.The apparatus of claim 19, wherein the report of the prediction uses a same candidate transmission spatial filter identifier for each CMR and each IMR for model training and the prediction of the characteristics of interference and noise, wherein the one or more combinations of spatial filters are indicated with an associated identifier associated with one or more of a model functionality, the model, a dataset, a configuration, or a codebook.
Citation Information
Patent Citations
Channel state information report using interference measurement resources
WO2024060121A1
Methods and apparatuses for reporting CSI prediction for a set of beams
WO2024065372A1
Wireless communication method and device
WO2024130739A1
Method and apparatus for transmitting and receiving signal in wireless communication system
WO2024172431A1