Method for determining the quality of artificial intelligence and / or machine learning model input

Abstract

A method in a radio node configured to communicate with a first network node is described The first network node is configured to determine a user equipment (UE) position, and the method includes receiving a request for a measurement report, where the measurement report is associated with the position of the UE and based on an artificial intelligence (AI) model. The method also includes determining the measurement report that includes a measurement of a wireless channel and a power quality metric associated with the measurement of the wireless channel. Further, the method includes transmitting a response. The response includes the measurement report including the measurement of the wireless channel and the power quality metric associated with the measurement of the wireless channel. The measurement report triggers the first network node to determine the UE position.

Description

[0001] METHOD FOR DETERMINING THE QUALITY OF ARTIFICIAL INTELLIGENCE AND / OR MACHINE LEARNING MODEL INPUT

[0002] TECHNICAL FIELD

[0003] The present disclosure relates to wireless communications, and in particular, to methods for determining the quality of artificial intelligence / machine learning (AI / ML) model input.

[0004] BACKGROUND

[0005] The Third Generation Partnership Project (3GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile user equipments (UE), as well as communication between network nodes and between UEs. The 3GPP is also developing standards for Sixth Generation (6G) wireless communication networks.

[0006] Artificial Intelligence (Al) and Machine Learning (ML) have been investigated as promising tools to optimize the design of air-interface in wireless communication networks in both academia and industry. Example use cases include using autoencoders for channel state information (CSI) compression to reduce the feedback overhead and improve channel prediction accuracy, using deep neural networks for classifying line of sight (LOS) and non-line of sight (NLOS) conditions to enhance the positioning accuracy, and using reinforcement learning for beam selection at the network side and / or at the UE to reduce the signaling overhead and beam alignment latency. Another use case may include using deep reinforcement learning to learn an optimal precoding policy for complex multiple input-multiple output (MIMO) precoding problems.

[0007] In 3 GPP NR standardization work, the 3 GPP Release 18 study item associated with 3GPP Technical Report (TR) 38.843 V18.0.0 on AI / ML for NR air interface has been completed. This study item explores the benefits of augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead. Through studying a few selected use cases (CSI feedback, beam management and positioning), this study item aims at laying the foundation for future air-interface use cases leveraging AI / ML techniques. Building an AI / ML model includes several development steps where the actual training of the Al model is just one step in a training pipeline. One part of AI / ML development is the AI / ML model lifecycle management. This is illustrated in the example of FIG. 1. The Al model lifecycle management typically includes:

[0008] • A training (re-training) pipeline: o With data ingestion referring to gathering raw (training) data from a data storage. After data ingestion, there may also be a step that controls the validity of the gathered data; o With data pre-processing referring to some feature engineering applied to the gathered data, e.g., it may include data normalization and possibly a data transformation required for the input data to the AI / ML model; o With the actual model training steps where a model is obtained using the training dataset; o With model evaluation referring to benchmarking the performance to some baseline. The iterative steps of model training and model evaluation continues until the acceptable level of performance is achieved; and o With model registration referring to register the AI / ML model, including any corresponding AI / ML-meta data that provides information on how the AI / ML model was developed, and possibly AI / ML model evaluations performance outcomes;

[0009] • A deployment stage to make the trained (or re-trained) AI / ML model part of the inference pipeline;

[0010] • An inference pipeline: o With data ingestion referring to gathering raw (inference) data from a data storage; o With data pre-processing stage that is typically identical to corresponding processing that occurs in the training pipeline; o With model operational referring to using the trained and deployed model in an operational mode; and o With data & model monitoring referring to validate that the inference data are from a distribution that aligns well with the training data, as well as monitoring model outputs for detecting any performance, or operational, drifts; and

[0011] • A drift detection stage that informs about any drifts in the model operations. One AI / ML physical (PHY) use case is the positioning of a target UE. Both positioning approaches below have been shown to be effective in obtaining target UE's location:

[0012] • Direct AI / ML positioning, where the AI / ML model output is UE location. Direct AI / ML positioning typically refers to radio fingerprinting, where channel observation is used as the input of AI / ML model.

[0013] • AI / ML assisted positioning, where the AI / ML model output is new measurement and / or enhancement of existing measurement. The model output may be, for example, LOS / NLOS identification, timing and / or angle measurement, likelihood or reliability of the measurement. The model input is also channel observations.

[0014] For assisted AI / ML positioning, multiple constructions are possible:

[0015] (a) Assisted AI / ML positioning with multi-TRP construction;

[0016] (b) Assisted positioning with single-TRP construction and one model for N TRPs;

[0017] (c) Assisted positioning with single-TRP construction and N models for N TRPs. The following cases may be associated with applying the direct and assisted

[0018] AI / ML positioning to NR wireless communication network:

[0019] • Case 1 : UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning;

[0020] • Case 2a: UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning;

[0021] • Case 2b: UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning;

[0022] • Case 3a: NG-RAN node assisted positioning with gNB-side model, AI / ML assisted positioning;

[0023] • Case 3b: NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning.

[0024] The term “LMF” may refer to Location Management Function. The term RAN may refer to Radio Access Network.

[0025] For radio signal based positioning methods, conventional methods rely on a sufficient number of line-of-sight (LoS) links, typically at least three to five LOS links depending on the positioning method, and whether vertical position is estimated in addition to horizontal position. In a cluttered environment, there is often a low probability of line-of-sight for a radio link between a UE and a transmission / reception point (TRP). For example, for InF- DH (Indoor Factory with Dense clutter and High base station height (transmission (Tx) or reception (Rx) elevated above the clutter)) environment, the LoS probability may be poor, e.g., ranging from 44.9% in a mildly cluttered environment to only 0.8% in a heavily cluttered environment.

[0026] Thus, conventional positioning methods struggle to locate a target UE in a heavily cluttered environment. Evaluations show that the 90%-tile positioning accuracy of conventional positioning methods is more than 15 meters in an InF-DH {60%, 6m, 2m} environment, due to the unavailability of sufficient LoS links.

[0027] Measurement quality in positioning

[0028] Legacy solution for positioning, e.g., in 3GPP radio, may support the reporting of various measurements which are subject to requirements in terms of accuracy / quality. These requirements are specified in RAN4 Technical Specification (TS) 38.133 V18.4.0 and are expressed in the unit of the measurements, e.g., reference signal received power (RSRP) requirements are in dB, Reference Signal Time Difference (RSTD) are in unit of samples (Tc, the basic timing unit defined in 3GPP Technical TS 38.211 V18.1.0).

[0029] Additionally, the measurement reports may be completed with an indication of the estimated accuracy. Timing measurements may optionally be associated with an estimate of uncertainty of the timing value via the IE NR-TimingQuality, provided in units of meters and with resolution ranging from 0.1 to 30 meters. The rational for these indicators is that the RAN4 requirements are meant to be a minimum requirement to qualify a device to enter the market as 5G certified, and therefore there is a need for additional information beyond requirements to assess the reliability of a measurement report toward the end accuracy target, which may be much higher than the basic requirements.

[0030] The IE NR-TimingQuality defines the quality of a timing value (e.g., of a TOA measurement).

[0031] - ASN1 START

[0032] NR-TimingQuality-rl6 ::= SEQUENCE { timingQualityValue-rl6 INTEGER (0..31), timingQualityResolution-rl6 ENUMERATED {mdotl, ml, mlO, m30,

[0033] ...},

[0034] } - ASN1STOP

[0035] NR-TimingQuality field descriptions timingQuality Value

[0036] This field provides an estimate of uncertainty of the timing value for which the IE NR-TimingQuality is provided in units of metres. timingQualityResolution This field provides the resolution used in the timingQuality Value field.

[0037] Enumerated values mdotl, ml, mlO, m30 correspond to 0.1, 1, 10, 30 metres, respectively.

[0038] Table 1. NR-TimingQuality field descriptions

[0039] The IE NR-PhaseQuality defines the quality of the RSCP / RSCPD measurement.

[0040] - ASN1 START

[0041] NR-PhaseQuality-rl8 ::= SEQUENCE { phaseQualityValue-rl8 INTEGER (0..179), phaseQualityResolution-rl 8 ENUMERATED {mdotl, ml,...}, }

[0042] - ASN1STOP Table 2. NR-PhaseQuality field descriptions

[0043] A TRP may also indicate the measurement quality associated to the positioning measurement to higher layers. In Fl AP, TRPs are located in gNB distributed unit (DU) and the gNB-DU may report the TRP Positioning Measurement Quality to gNB central unit (CU) in the TRP measurement result. In NRPPa, the NG-RAN provides the Measurement Quality to LMF in the measurement result.

[0044] Table 3. Measurement information

[0045] The current 3 GPP specification allows a UE or TRP to convey quality information on phase or timing measurements but omits power information quality. The rationale behind this omission stems from the fact that in legacy solution, a power measurement was in itself a measure of the quality of the signal. The higher the power received, the more useful the signal was considered. This approach for legacy positioning focused on identifying line-of-sight (LOS) path with no obstruction and may not be usable in communication where line LOS paths may encounter obstruction or in other circumstances.

[0046] SUMMARY

[0047] For Al ML positioning and other machine learning based methods in NR, the signal strength or weakness is not necessarily a sign of good or poor quality in the measurement. The quality of the ML model input is based on how close the model input is to the actual channel condition. One simple example is the case of a direct path with a wall obstructing the radio signal. The direct path signal strength will be very weak. Still, if the measuring device may extract the path signal strength accurately, the path strength will contribute to establishing a “signature” the ML model may compare to training data. Hence, a very low reference signal received power (RSRP) value may not be the sign of an unreliable measurement, e.g., as long as that RSRP value has been acquired reliably.

[0048] Some embodiments advantageously provide methods, systems, and apparatuses for determining the quality of artificial intelligence / machine learning (AI / ML) model input.

[0049] Some embodiments introduce a measure of radio signal power quality / reliability as part of measurement reports conveyed between nodes for the purpose of training data collection, and / or model training, and / or model monitoring. The following methods and / or features are provided:

[0050] • A power quality indicator metric is defined. The metric may be either in unit of power (linear or dB) or dimensionless;

[0051] • A power quality indicator request is defined;

[0052] • A table for power quality reporting is defined;

[0053] • When the UE or gNB / TRP is tasked to report measurements to the LMF for model input (for example, in cases 2b and 3b as defined above), if power is reported, a power quality indicator is attached to the measurement report; and

[0054] • When the UE or gNB is tasked to provide measurements to the LMF for the purpose of model monitoring, if power measurements are included, a power quality indicator may be attached: o The power quality indicator may be forwarded further by the LMF when one node (UE / TRP / gNB) is assisting another node with model monitoring.

[0055] A radio signal power may correspond to the model input of an AI / ML model, and the quality or reliability indication may convey information on the accuracy of the measurement data for model input. Further, the radio signal power estimation may correspond to the model output of an AI / ML model, and the quality or reliability indication may provide information on the accuracy of the model output as generated by the model.

[0056] Some embodiments provide valuable information to an Al ML model on the quality / reliability of the measured power in AI / ML measurement reports.

[0057] According to one aspect, a method in a radio node configured to communicate with a first network node is described. The first network node is configured to determine a user equipment (UE) position, and the method includes receiving a request for a measurement report, where the measurement report is associated with the position of the UE and based on an artificial intelligence (Al) model. The method also includes determining the measurement report that includes a measurement of a wireless channel and a power quality metric associated with the measurement of the wireless channel. Further, the method includes transmitting a response. The response includes the measurement report including the measurement of the wireless channel and the power quality metric associated with the measurement of the wireless channel. The measurement report triggers the first network node to determine the UE position.

[0058] In some embodiments, the method further includes training the Al model based at least in part on a training dataset associated at least in part with the power quality metric. In some other embodiments, the method further includes determining the training dataset based at least in part on the power quality metric and transmitting the Al model to the first network node.

[0059] In some embodiments, the determination of the UE position is based on an output of the Al model.

[0060] In some other embodiments, the method further includes monitoring model performance of the Al model based on the measurement of the wireless channel and the power quality metric.

[0061] In some embodiments, the measurement of the wireless channel and the power quality metric includes a power value.

[0062] In some other embodiments, the measurement of the wireless channel and the power quality metric corresponds to one or more of a downlink radio signal received power, an uplink radio signal received power, a downlink radio signal received power, and a sidelink radio signal received power.

[0063] In some embodiments, the power quality metric is based on a level of confidence in the measurement.

[0064] In some other embodiments, the power quality metric indicates a degree of precision of the measurement.

[0065] In some embodiments, the request includes a power quality indicator request that the power quality metric to be included in the measurement report.

[0066] In some other embodiments, the request is based on a UE capability for reporting the power quality metric.

[0067] In some embodiments, the radio node is one a UE and a second network node configured to communicate with the UE.

[0068] In some other embodiments, the first network node includes a location management function (LFM).

[0069] According to another aspect, a radio node configured to communicate with a first network node is described. The first network node is configured to determine a user equipment (UE) position, and the radio node is configured to perform one or more steps corresponding to one or more of the method embodiments implemented in the radio node and / or is associated with one or more features that are similar or the same as the features described in one or more of the method embodiments implemented in the radio node.

[0070] According to one aspect, a method in a first network node configured to communicate with a radio node and determine a user equipment (UE) position is described. The method includes transmitting a request for a measurement report, where the measurement report is associated with the position of the UE and based on an artificial intelligence (Al) model. The method also includes receiving a response that includes the measurement report including a measurement of a wireless channel and a power quality metric associated with the measurement of the wireless channel and determining the UE position based on the measurement report.

[0071] In some embodiments, the method further includes training the Al model based at least in part on a training dataset associated at least in part with the power quality metric.

[0072] In some other embodiments, the method further includes determining the training dataset based at least in part on the power quality metric.

[0073] In some embodiments, the method further includes receiving the Al model that is trained by the radio node based at least in part on the power quality metric.

[0074] In some other embodiments, the determination of the UE position is further based on an output of the Al model.

[0075] In some embodiments, the method further includes monitoring model performance of the Al model based on the measurement of the wireless channel and the power quality metric.

[0076] In some other embodiments, the measurement of the wireless channel and the power quality metric includes a power value.

[0077] In some embodiments, the measurement of the wireless channel and the power quality metric corresponds to one or more of: a downlink radio signal received power, an uplink radio signal received power, a downlink radio signal received power, and a sidelink radio signal received power.

[0078] In some other embodiments, the power quality metric is based on a level of confidence in the measurement.

[0079] In some embodiments, the power quality metric indicates a degree of precision of the measurement.

[0080] In some other embodiments, the request includes a power quality indicator request which requests the power quality metric to be included in the measurement report.

[0081] In some embodiments, the request is based on a UE capability for reporting the power quality metric.

[0082] In some other embodiments, the radio node is one a UE and a second network node configured to communicate with the UE. In some embodiments, the first network node comprises a location management function (LFM).

[0083] According to another aspect, a first network node configured to communicate with a radio node and determine a user equipment (UE) position is described. The first network node is configured to perform one or more steps corresponding to one or more of the method embodiments implemented in the first network node and / or is associated with one or more features that are similar or the same as the features described in one or more of method embodiments implemented in the first network node.

[0084] BRIEF DESCRIPTION OF THE DRAWINGS

[0085] A more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:

[0086] FIG. l is a block diagram of AI / ML training and inference;

[0087] FIG. 2 is a schematic diagram of an example network architecture illustrating a communication system according to principles disclosed herein;

[0088] FIG. 3 is a block diagram of a network node in communication with a user equipment over a wireless connection according to some embodiments of the present disclosure;

[0089] FIG. 4 is a flowchart of an example process in a network node for determining the quality of artificial intelligence / machine learning (AI / ML) model input according to some embodiments of the present disclosure; and

[0090] FIG. 5 is a flowchart of an example process in a user equipment for determining the quality of artificial intelligence / machine learning (AI / ML) model input according to some embodiments of the present disclosure;

[0091] FIG. 6 is a flowchart of an example process in a radio node according to some embodiments of the present disclosure;

[0092] FIG. 7 is a flowchart of an example process in a network node according to some embodiments of the present disclosure; and

[0093] FIG. 8 shows an example network node configured to determine a UE position and to communicate with at least one radio node according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0094] Before describing in detail example embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to methods for determining the quality of artificial intelligence / machine learning (AI / ML) model input. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0095] As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0096] In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate electrical or data communication, which may be accomplished by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling or optical signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate, and modifications and variations are possible of achieving the electrical and data communication.

[0097] In some embodiments described herein, the term “coupled,” “connected,” and the like, may be used herein to indicate a connection, although not necessarily directly, and may include wired and / or wireless connections.

[0098] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0099] The term “network node” used herein may be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, base transceiver station (BTS), base station controller (BSC), radio network controller (RNC), g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multistandard radio (MSR) radio node such as MSR BS, multi-cell / multicast coordination entity (MCE), relay node, donor node controlling relay, radio access point (AP), transmission points, transmission nodes, Remote Radio Unit (RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), self-organizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), LMF, etc. The network node may also comprise test equipment. The term “radio node” used herein may be used to also denote a user equipment (UE) such as a wireless device (WD), a network node such as a radio network node, or any other type of network node or device.

[0100] In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The UE herein may be any type of user equipment capable of communicating with a network node or another UE over radio signals, such as a wireless device (WD). The UE may also be a radio communication device, target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine communication (M2M), low-cost and / or low-complexity UE, a sensor equipped with UE, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device etc.

[0101] Also, in some embodiments the generic term “radio network node” is used. It may be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, Multi-cell / multicast Coordination Entity (MCE), relay node, access point, radio access point, Remote Radio Unit (RRU) Remote Radio Head (RRH). Note that although terminology from one particular wireless system, such as, for example, 3GPP LTE and / or New Radio (NR), may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.

[0102] Note further, that functions described herein as being performed by a user equipment or a network node may be distributed over a plurality of user equipments and / or network nodes. In other words, it is contemplated that the functions of the network node and user equipment described herein are not limited to performance by a single physical device and, in fact, may be distributed among several physical devices.

[0103] In some embodiments, the term Al may include machine learning. In some embodiments, AI / ML may be referred to as Al. For example an AI / ML model may be referred to as an Al model.

[0104] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0105] Some embodiments are directed to methods for determining the quality of artificial intelligence / machine learning (AI / ML) model input.

[0106] Returning to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 2 a schematic diagram of a communication system 10, according to an embodiment, such as a 3 GPP -type cellular network that may support standards such as LTE and / or NR (5G), which comprises an access network 12, such as a radio access network, and a core network 14. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). Each network node 16a, 16b, 16c is connectable to the core network 14 over a wired or wireless connection 20. A first user equipment (UE) 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second UE 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of UEs 22a, 22b (collectively referred to as user equipments 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding network node 16. Note that although only two UEs 22 and three network nodes 16 are shown for convenience, the communication system may include many more UEs 22 and network nodes 16.

[0107] Also, it is contemplated that a UE 22 may be in simultaneous communication and / or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a UE 22 may have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, UE 22 may be in communication with an eNB for LTE / E-UTRAN and a gNB for NR / NG-RAN.

[0108] A network node 16 (eNB or gNB) is configured to include a node management unit 24 which may be configured to perform one or more network node functions described herein. A user equipment 22 is configured to include a UE management unit 26 which may be configured to perform one or more UE functions described herein.

[0109] Example implementations, in accordance with an embodiment, of the UE 22 and network node 16 discussed in the preceding paragraphs will now be described with reference to FIG. 3.

[0110] The communication system 10 includes a network node 16 provided in a communication system 10 and including hardware 28 enabling it to communicate with the UE 22. The hardware 28 may include communication interface 29 which may include a radio interface 30 for setting up and maintaining at least a wireless connection 32 with a UE 22 located in a coverage area 18 served by the network node 16. The radio interface 30 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 30 includes an array of antennas 34 to radiate and receive signal(s) carrying electromagnetic waves. Further, communication interface 29 may be configured for setting up and maintaining at least a wireless (and / or wired) connection 60 with a at least one other network node 16.

[0111] In the embodiment shown, the hardware 28 of the network node 16 further includes processing circuitry 36. The processing circuitry 36 may include a processor 38 and a memory 40. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 36 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 38 may be configured to access (e.g., write to and / or read from) the memory 40, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0112] Thus, the network node 16 further has software 42 stored internally in, for example, memory 40, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the network node 16 via an external connection. The software 42 may be executable by the processing circuitry 36. The processing circuitry 36 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by network node 16. Processor 38 corresponds to one or more processors 38 for performing network node 16 functions described herein. The memory 40 is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 42 may include instructions that, when executed by the processor 38 and / or processing circuitry 36, causes the processor 38 and / or processing circuitry 36 to perform the processes described herein with respect to network node 16. For example, processing circuitry 36 of the network node 16 may include a node management unit 24 which may be configured to perform one or more network nodes functions described herein.

[0113] The communication system 10 further includes the UE 22 already referred to. The UE 22 may have hardware 44 that may include a radio interface 46 configured to set up and maintain a wireless connection 32 with a network node 16 serving a coverage area 18 in which the UE 22 is currently located. The radio interface 46 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 46 includes an array of antennas 48 to radiate and receive signal(s) carrying electromagnetic waves.

[0114] The hardware 44 of the UE 22 further includes processing circuitry 50. The processing circuitry 50 may include a processor 52 and memory 54. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 50 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 52 may be configured to access (e.g., write to and / or read from) memory 54, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0115] Thus, the UE 22 may further comprise software 56, which is stored in, for example, memory 54 at the UE 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the UE 22. The software 56 may be executable by the processing circuitry 50. The software 56 may include a client application 58. The client application 58 may be operable to provide a service to a human or non-human user via the UE 22.

[0116] The processing circuitry 50 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by UE 22. The processor 52 corresponds to one or more processors 52 for performing UE 22 functions described herein. The UE 22 includes memory 54 that is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 56 and / or the client application 58 may include instructions that, when executed by the processor 52 and / or processing circuitry 50, causes the processor 52 and / or processing circuitry 50 to perform the processes described herein with respect to UE 22. For example, the processing circuitry 50 of the user equipment 22 may include a UE management unit 26 which may be configured to perform one or more UE functions described herein.

[0117] In some embodiments, the inner workings of the network node 16 and UE 22 may be as shown in FIG. 3 and independently, the surrounding network topology may be that of FIG. 2.

[0118] The wireless connection 32 between the UE 22 and the network node 16 is in accordance with the teachings of the embodiments described throughout this disclosure. More precisely, the teachings of some of these embodiments may improve the data rate, latency, and / or power consumption and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime, etc. In some embodiments, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve.

[0119] Although FIGS. 2 and 3 show various “units” such as node management unit 24 and UE management unit 26 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry.

[0120] FIG. 4 is a flowchart of an example process in a network node 16 for determining the quality of artificial intelligence / machine learning (AI / ML) model input. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 36 (including the node management unit 24), processor 38, and / or radio interface 30. Network node 16 such as via processing circuitry 36 and / or processor 38 and / or radio interface 30 is configured to receive from the UE 22 at least one measurement report that includes a power quality metric (Block SI 00). The process includes determining a training dataset based at least in part on the power quality metric (Block SI 02). The process also includes training an artificial intelligence / machine learning, AI / ML, based at least in part on the training dataset (Block SI 04).

[0121] In some embodiments, the power quality metric is received in response to a request, the request including a minimum quality threshold to be surpassed as a condition of transmitting the at least one measurement report by the UE 22. In some embodiments, the power quality metric includes at least one of a reference signal received power (RSRP) and a reference signal received path power (RSRPP). In some embodiments, a number of received measurement reports depends on a value of a power quality metric. In some embodiments, a power quality metric includes a relative time difference of arrival (TOA).

[0122] FIG. 5 is a flowchart of an example process in a user equipment 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of user equipment 22 such as by one or more of processing circuitry 50 (including the UE management unit 26), processor 52, and / or radio interface 46. User equipment 22 such as via processing circuitry 50 and / or processor 52 and / or radio interface 46 is configured to determine a power quality metric for each of a plurality of transmission paths (Block SI 06). The process also includes transmitting the power quality metrics in at least one measurement report (Block SI 08).

[0123] In some embodiments, the power quality metric is measured in response to a request, the request including a minimum quality threshold to be surpassed as a condition of transmitting the at least one measurement report by the method. In some embodiments, the power quality metric includes at least one of an RSRP and an RSRPP. In some embodiments, a number of transmitted measurement reports depends on a value of a power quality metric. In some embodiments, a power quality metric includes a relative TOA.

[0124] FIG. 6 is a flowchart of an example process in a radio node 62 (e.g., a UE 22 or a network node 16 such as a gNB). The radio node 62 is configured to communicate with a first network node 16 that is configured to determine a UE position. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 36 (including the node management unit 24), processor 38, and / or radio interface 30 or one or more elements of user equipment 22 such as by one or more of processing circuitry 50 (including the UE management unit 26), processor 52, and / or radio interface 46. Radio node 62 such as via processing circuitry 36 and / or processor 38 and / or radio interface 30 is configured to receive (Block SI 10) a request for a measurement report, where the measurement report is associated with the position of the UE 22 and based on an artificial intelligence (Al) model. Radio node 62 is also configured to determine (Block SI 12) the measurement report that includes a measurement of a wireless channel and a power quality metric associated with the measurement of the wireless channel. Further, radio node 62 is configured to transmit (Block SI 14) a response. The response includes the measurement report including the measurement of the wireless channel and the power quality metric associated with the measurement of the wireless channel. The measurement report triggers the first network node 16 to determine the UE position.

[0125] In some embodiments, the method further includes training the Al model based at least in part on a training dataset associated at least in part with the power quality metric.

[0126] In some other embodiments, the method further includes determining the training dataset based at least in part on the power quality metric and transmitting the Al model to the first network node 16.

[0127] In some embodiments, the determination of the UE position is based on an output of the Al model.

[0128] In some other embodiments, the method further includes monitoring model performance of the Al model based on the measurement of the wireless channel and the power quality metric.

[0129] In some embodiments, the measurement of the wireless channel and the power quality metric includes a power value.

[0130] In some other embodiments, the measurement of the wireless channel and the power quality metric corresponds to one or more of a downlink radio signal received power, an uplink radio signal received power, a downlink radio signal received power, and a sidelink radio signal received power.

[0131] In some embodiments, the power quality metric is based on a level of confidence in the measurement.

[0132] In some other embodiments, the power quality metric indicates a degree of precision of the measurement.

[0133] In some embodiments, the request includes a power quality indicator request that the power quality metric to be included in the measurement report.

[0134] In some other embodiments, the request is based on a UE capability for reporting the power quality metric.

[0135] In some embodiments, the radio node 62 is one a UE 22 and a second network node 16 configured to communicate with the UE 22.

[0136] In some other embodiments, the first network node 16 includes a location management function (LFM).

[0137] FIG. 7 is a flowchart of an example process in a network node 16. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 36 (including the node management unit 24), processor 38, and / or radio interface 30. Network node 16 such as via processing circuitry 36 and / or processor 38 and / or radio interface 30 is configured to transmit (Block SI 16) a request for a measurement report, where the measurement report is associated with the position of the UE 22 and based on an artificial intelligence (Al) model. Network node 16 is also configured to receive (Block SI 18) a response that includes the measurement report including a measurement of a wireless channel and a power quality metric associated with the measurement of the wireless channel and determine (Block S120) the UE position based on the measurement report.

[0138] In some embodiments, the method further includes training the Al model based at least in part on a training dataset associated at least in part with the power quality metric.

[0139] In some other embodiments, the method further includes determining the training dataset based at least in part on the power quality metric.

[0140] In some embodiments, the method further includes receiving the Al model that is trained by the radio node 62 based at least in part on the power quality metric.

[0141] In some other embodiments, the determination of the UE position is further based on an output of the Al model. In some embodiments, the method further includes monitoring model performance of the Al model based on the measurement of the wireless channel and the power quality metric.

[0142] In some other embodiments, the measurement of the wireless channel and the power quality metric includes a power value.

[0143] In some embodiments, the measurement of the wireless channel and the power quality metric corresponds to one or more of: a downlink radio signal received power, an uplink radio signal received power, a downlink radio signal received power, and a sidelink radio signal received power.

[0144] In some other embodiments, the power quality metric is based on a level of confidence in the measurement.

[0145] In some embodiments, the power quality metric indicates a degree of precision of the measurement.

[0146] In some other embodiments, the request includes a power quality indicator request which requests the power quality metric to be included in the measurement report.

[0147] In some embodiments, the request is based on a UE capability for reporting the power quality metric.

[0148] In some other embodiments, the radio node 62 is one a UE 22 and a second network node 16 configured to communicate with the UE 22.

[0149] In some embodiments, the first network node 16 comprises a location management function (LFM).

[0150] Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for methods for determining the quality of artificial intelligence / machine learning (AI / ML) model input.

[0151] In some embodiments the non-limiting terms UE or a wireless device are used interchangeably. The UE 22 herein may be any type of wireless device capable of communicating with a network node 16 or another UE 22 over radio signals. The UE 22 may also be a radio node, a radio communication device, target device, device to device (D2D) UE 22, machine type UE 22 or UE 22 capable of machine to machine communication (M2M), low-cost and / or low-complexity UE 22, a sensor equipped with UE 22, tablet, mobile terminals, smart phone, laptop embedded equipment (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device, etc.

[0152] In some embodiments the generic term “anchor node” is used, which are used as reference points for determining the location of a target UE 22. In general, the anchor nodes for positioning may be a variety of nodes in the wireless network. For positioning using the radio link between the target UE 22 and a radio network node, the anchor node may be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, Node B, evolved Node B (eNB), Next-Generation Node B (gNodeB or gNB), NG-RAN node, Transmission Point (TP), Transmission- Reception Point (TRP), Multi-cell / multicast Coordination Entity (MCE), relay node, access point (AP), Antenna Reference Point (ARP), radio access point, Remote Radio Unit (RRU), Remote Radio Head (RRH). For positioning using sidelink between two UEs 22, the anchor node is a UE 22 or a wireless device.

[0153] For ease of discussion, the methods are described using the radio links between a UE 22 and an anchor node. A TRP is used as a representative example of the anchor node, where the TRP is connected to a gNB (hereafter referred to as a network node 16). It is understood by those skilled in the art that the same methodology may easily be applied to many other wireless communication scenarios, e.g., sidelink-based positioning.

[0154] One or more methods are provided to support AI / ML models, and the methods are described using the positioning use case as a representative example. It is understood that the same methodology applies to other AI / ML models for other physical layer functionalities in the wireless communication system.

[0155] In some embodiments, a power quality metric is defined. In one example, this metric is attached to any reported power quantity, such as:

[0156] • For downlink radio signal received power: o Path Power of the downlink (DL) Positioning Reference Signal (PRS), e.g. DL PRS reference signal received path power (DL-RSRP); o Power of the DL PRS, e.g. DL PRS reference signal received power (DL- PRS RSRP); o Power of the DL Synchronization Signal Block (SSB), e.g. synchronization signal (SS) reference signal received power (SS-RSRP); o Power per branch, e.g., SS reference signal received power per branch (SS- reference signal received power per branch (RSRPB)); o Power of the DL CSLRS, e.g. CSI reference signal received power (CSI- RSRP);

[0157] • For uplink radio signal received power: o Path Power of the uplink (UL) Sounding Reference Signal (SRS), e.g. UL SRS reference signal received path power (UL-SRS reference signal received path power (RSRPP)); o Power of the UL SRS, e.g. UL SRS reference signal received power (UL- SRS RSRP);

[0158] • For sidelink radio signal received power: o Power of physical sidelink broadcast channel (PSBCH), e.g., PSBCH reference signal received power (PSBCH-RSRP); o Power of physical sidelink shared channel (PSSCH), e.g., PSSCH reference signal received power (PSSCH-RSRP); o Power of physical sidelink control channel (PSCCH), e.g., PSCCH reference signal received power (PSCCH-RSRP); o Power of sidelink PRS reference signal, e.g., Sidelink PRS reference signal received power (SL PRS-RSRP); and / or o Path power of sidelink PRS reference signal, e.g., Sidelink PRS reference signal received path power (SL PRS-RSRPP)

[0159] The downlink radio signal received power may be generated by the UE 22 after measuring the radio signal sent by the network node (e.g., gNB). The uplink radio signal received power may be generated by the network node (e.g., gNB) after measuring the radio signal sent by UE 22. The sidelink radio signal received power may be generated by one UE 22 after measuring the radio signal sent by another UE 22. For the sidelink scenario, the AI / ML model may be (a) located in the target UE 22 or (b) located in the location server to support SL positioning methods: (a) SL-Target UE-based or (b) SL- Target UE-assisted, server-based.

[0160] In some embodiments, the methods are described using downlink or uplink radio signal power as an illustrative example, with the understanding that similar measurements, reports, methodologies and procedures can be easily applied to the sidelink scenario.

[0161] In a related embodiment, the metric of the measured power quality is defined by the level of confidence in a measurement precision in unit of power, e.g. in linear watts W or log-scale decibel, dB or dBm. In some embodiments, the quality value indicates the degree of precision of the measured quantity and to which level of confidence the precision is reported. For example, the quality value may be defined with a pair of values which may include quality precision and quality confidence, e.g.: (Qprecision,Qconfidence), where the Qprecision value is reported in unit of power and Qconfidence is reported without dimensions. Qconfidence is a scale of the confidence the UE 22 has on the reported precision, where for example a value 0 translates to no confidence and a value 100 translates to high confidence.

[0162] In some embodiments, the quality metric may be defined to be dimensionless, e.g. only consisting of Qconfidence, so that the device reporting the measurements only provides a grading of the measurement quality, without providing an associated accuracy. In some other embodiments, the quality metric may be defined to be only including the precision indicator, e.g. only including Qprecision, so that the device reporting the measurements only provides the quality of the measurement in terms of precision, without providing an associated confidence index.

[0163] Some embodiments provide a power quality indicator request for measurement for model input at model inference. Quality indication reports may be supported by NR, mandatory, and attached to the measurement report in LTE positioning protocol (LPP). In some embodiments, a measurement quality is an optional element in network nodelocation management function (LMF) measurement reports in NR positioning protocol A (NRPPa). However, the LMF may be capable to explicitly request the measurement quality to be reported, and also optionally place conditions on reporting based on quality. For example, a power measurement quality may be attached to a measurement report by the UE 22 or network node 16 upon request by the node requesting the measurement, e.g. the LMF. Several options are listed below.

[0164] In some embodiments, a specific field is added to the measurement request to request the UE 22 to include a measurement quality for power measurement. In some embodiments, the measurement quality indicator request may also include a minimum quality threshold under which the UE 22 or network node 16 may not transmit the report.

[0165] In some embodiments, a generic quality indicators request field is added to the measurement request to signal that the requesting node, e.g., the LMF is interested in receiving quality indicators for all measurement types, e.g., timing quality, power quality, angle quality. In some embodiments, the quality indicator request field may signal which quality indicators the requesting node wants to be reported. For example, the request field may be a bit string where each bit codes for a different quality indicator.

[0166] The request for quality reporting may also be based on acquiring the UE capability for reporting the quality of its measurement. For example, different resolutions for quality reporting may be supported.

[0167] Some embodiments provide a power quality indicator for training data collection and model training. More specifically, for training data collection, when a power value is collected, its associated power quality indicator is also collected together with it. Here, the power value may correspond to model input or model output, depending on the intended usage of the AI / ML model. The power value may be a measurement of received radio signal and correspond to model input. Further, the power value may correspond to a model output.

[0168] In some embodiments, for training data collection, the measurement entity (e.g., UE 22 or network node 16) detects the radio signal of a given radio channel, performs measurement using the detected radio signal, generates one or more measurement reports, and sends the one or more measurement reports to the training data collection entity. Each of the measurement report include one or more pairs of {power value, quality of power value}. For example, if the power value is DL-PRS RSRP, then a measurement report include one power value (i.e., DL-PRS RSRP), and one quality indication of the power value. If the power value is a per-path power value like DL-PRS RSRPP, and N paths are detected, measured and reported, then a measurement report includes N pairs of {DL-PRS RSRPP value, quality indication of DL-PRS RSRPP value}, with one pair for one detected path of the given radio channel.

[0169] The training data collection entity records and stores a multitude of measurement reports for the targeted use case. From the stored measurement reports, a training dataset may be built by either the training data collection entity or the model training entity. After that, the model training entity may train and produce an AI / ML model using the training dataset.

[0170] The measurement quality indication (e.g., timing quality, phase quality, power quality) may be used by the training data collection entity and / or the model training entity to build a desirable training dataset before model training. A training dataset meeting predetermined conditions may be built since this directly affects the outcome of the training process, i.e., the trained model.

[0171] In some embodiments, measurement reports of quality poorer than a threshold is excluded from the training dataset. This ensures that the training data samples in the training dataset have adequate quality for model training.

[0172] In some embodiments, the proportion of measurement reports to include in a training dataset takes into account the measurement quality. For example, 10% of the samples in the training dataset are in a high quality range, 70% are in the medium quality range, and 20% are in the poor quality range. This ensures that the training dataset have representative measurement reports with a wide range of qualities, and the proper proportion is provided. Further, the training dataset being dominated by data of extremely bad quality, or data of extremely good quality may be avoided.

[0173] Power quality indicator request for measurement for model monitoring

[0174] In a node (i.e., a network node 16 or UE 22), model monitoring may be done with assistance from additional measurements provided by another node (i.e. another network node 16 or UE 22). For example, the UE 22 may receive downlink signals and run inference on these signals. At the same time, the UE 22 may also receive feedback on transmitted uplink signals for the purpose of model monitoring. Therefore, measurements that may be conveyed to the UE 22 for the purpose of monitoring are also complemented with quality measurement.

[0175] In one embodiment, network node 16 (e.g., the LMF) may request a node (UE 22 or network node 16) to provide a quality metric associated with a measurement reported for monitoring purposes. The request may take a form similar to the one used for measurement reports.

[0176] The model monitoring decision may need to take into account the power quality of the observed measurements. This is because the model output accuracy may be affected by the quality of model input. For example, a model may exhibit larger model output inaccuracy if the measurement error is larger in model input, even if the model is operating normally.

[0177] According to one aspect, examples of power quality reporting implementation in measurement reports and requests are described and LPP embodiments examples are provided.

[0178] In the following, the power quality request and measurement report are provided below for model inference (i.e., model deployment). It is understood that similar requests and reports may be defined for other life cycle stages of the AI / ML model, including training data collection and model monitoring.

[0179] In some embodiments, the reporting of timing or phase quality is not required. Therefore, it may be entirely up to the reporting node to decide what quality it wants to report. A table for quality reporting mapping to quality values may be defined.

[0180] With respect to a reporting request, the Information Element (IE) NR-DL-TDOA- RequestLocationlnformation may be used as an example for a location request by the location server to request location measurements from a target device with quality indication added. Fields are added to support requesting quality metric(s) to be reported, and to set a quality threshold before a measurement is reported. In the example below, the threshold is provided in dB, so that if the power quality is not in a resolution higher than the threshold, the measurement may be discarded and not reported.

[0181] - ASN1 START

[0182] NR-DL-TDOA-RequestLocationInformation-rl6 ::= SEQUENCE { nr-DL-PRS-RstdMeasurementInfoRequest-rl6 ENUMERATED { true }

[0183] OPTIONAL,- Need ON nr-RequestedMeasurements-r 16 BIT STRING { prsrsrpReq (0), firstPathRsrpReq-rl7 (1), j ointMeasurementsReq- rl8 (2) nr-AssistanceAvailability-rl6 BOOLEAN, nr-DL-TDO A-ReportConfig-r 16 NR-DL-TDOA-ReportConfig rl6 OPTIONAL, - Need ON additionalPaths-rl6 ENUMERATED { requested } OPTIONAL, - Need ON

[0184] [[ nr-UE-RxTEG-Request-r 17 ENUMERATED { requested }

[0185] OPTIONAL, - Need ON nr-los-nlos-IndicatorRequest-rl7 SEQUENCE { type-rl7 LOS-NLOS-

[0186] IndicatorType 1 -r 17, granularity-r!7 LOS-NLOS-

[0187] IndicatorGranularity 1 -r 17,

[0188] }

[0189] OPTIONAL, - Need ON additionalPathsExt-r 17 ENUMERATED { requested }

[0190] OPTIONAL, - Need ON additionalPathsDL-PRS-RSRP -Request-rl7 ENUMERATED { requested

[0191] } OPTIONAL, - Need ON multiMeasInSameReport-r 17 ENUMERATED { requested }

[0192] OPTIONAL - Need ON

[0193] ]],

[0194] [[ nr-DL-PRS-JointMeasurementRequested-rl8 SEQUENCE (SIZE (2..3)) OF

[0195] INTEGER (0..nrMaxFreqLayers- 1 -rl 6) OPTIONAL, - Need ON nr-DL-PRS-RxHoppingRequest-rl8 ENUMERATED { requested

[0196] } OPTIONAL, - Need ON nr-DL-PRS-RxHoppingTotalBandwidth-rl8 CHOICE { frl ENUMERATED {mhz40, mhz50, mhz80, mhzlOO}, fr2 ENUMERATED {mhzlOO, mhz200, mhz400}

[0197] }

[0198] OPTIONAL, - Need ON nr-DL-PRS-RSCPD-Request-r 18 ENUMERATED { requested

[0199] } OPTIONAL - Need ON

[0200] ]],

[0201] [[

[0202] } (SIZE(1..8)), nr-RequestedQualityMetrics-r 19 BIT STRING { powerQuality(0),timingQuality(l),angleQuality(2) } (SIZE(1..8))

[0203] Alternatively nr-RequestedQualityPower-r 19 ENUMERATED { requested }

[0204] OPTIONAL - Need ON nr-RequestedQualitythreshold-rl9 ENUMERATED {dotonedB, onedB, fivedB } OPTIONAL, - Need ON

[0205] ]]

[0206] }

[0207] - ASN1STOP

[0208] In some embodiments, the quality indicator may be added to a measurement report as follows. The measurement element for downlink (DL) time difference of arrival (TDOA) is used here as an example, but other measurement types may also be used. In the following: (a) power quality indication is reported for nr-DL-PRS-RSRP-Result; and (b) power quality indication is reported for per-path power values nr-DL-PRS-RSRPP.

[0209] - ASN1 START

[0210] NR-DL-TD0A-MeasElement-rl6 ::= SEQUENCE { dl-PRS-ID-rl6 INTEGER (0..255), nr-PhysCellID-rl6 NR-PhysCellID-rl6 OPTIONAL, nr-CellGlobalID-rl6 NCGI-rl5

[0211] OPTIONAL, nr-ARFCN-rl6 ARFCN-ValueNR-rl5

[0212] OPTIONAL, nr-DL-PRS-ResourcelD-r 16 NR-DL-PRS-ResourcelD-r 16 OPTIONAL, nr-DL-PRS -Re source S etID-r 16 NR-DL-PRS-ResourceSetID-r 16 OPTIONAL, nr-TimeStamp-r 16 NR-TimeStamp-rl6, nr-RSTD-rl6 CHOICE { k0-rl6 INTEGER (0..1970049), kl-rl6 INTEGER (0..985025), k2-rl6 INTEGER (0..492513), k3-rl6 INTEGER (0..246257), k4-rl6 INTEGER (0..123129), k5-r!6 INTEGER (0 .61565), kMinusl-rl8 INTEGER (0..3940097) kMinus2-rl8 INTEGER (0..7880193)

[0213] }, nr- AdditionalPathList-r 16 NR- AdditionalPathList-r 16

[0214] OPTIONAL, nr-TimingQuality-rl6 NR-TimingQuality-rl6, nr-DL-PRS-RSRP-Result-r 16 INTEGER (0 .126)

[0215] OPTIONAL, nr-DL-TDOA-AdditionalMeasurements-r!6

[0216] NR-DL-TDOA-AdditionalMeasurements-rl6 OPTIONAL,

[0217] [[ nr-UE-Rx-TEG-ZD-rl7 INTEGER (0..maxNumOfRxTEGs-l-rl7)

[0218] OPTIONAL, nr-DL-PRS-FirstPathRSRP-Result-r!7 INTEGER (0..126)

[0219] OPTIONAL, nr-los-nlos-Indicator-r 17 CHOICE { perTRP-rl7 LO S-NLO S-Indicator-r 17, perResource-rl7 LOS-NLOS-Indicator-rl7 }

[0220] OPTIONAL, nr-AdditionalPathListExt-r 17 NR-AdditionalPathListExt-r 17

[0221] OPTIONAL, nr-DL-TDOA-AdditionalMeasurementsExt-r!7

[0222] NR-DL-TDOA-AdditionalMeasurementsExt- rl7 OPTIONAL

[0223] ]],

[0224] [[ nr-RSTD-BasedOnAggregatedResources-rl8 ENUMERATED {true} OPTIONAL, nr-AggregatedDL-PRS-ResourceSetID-List-r 18 SEQUENCE (SIZE (2. 3))

[0225] OF

[0226] NR- AggregatedDL-PRS -Re source S etID-El ement-r 18

[0227] OPTIONAL, nr-RSCPD-rl8 INTEGER (0 .61565)

[0228] OPTIONAL, nr-PhaseQuality-r 18 NR-PhaseQuality-rl 8

[0229] OPTIONAL, nr-RSCPD-AddSampleMeasurements-rl8 SEQUENCE (SIZE

[0230] (L.nrNumOfSamples-l-rl8 )) OF

[0231] NR-RS CPD - Additi onalMeasurementEl ement-r 18

[0232] OPTIONAL, nr-ReportDL-PRS-MeasBasedOnSingleOrMultiHopRx-r!8 ENUMERATED { singleHop, multipleHop }

[0233] OPTIONAL

[0234] ]], [[ nr-PowerQuality-r 19 NR-PowerQuality-r 19

[0235] OPTIONAL, ]] } NR-DL-TDOA-AdditionalMeasurements-rl6 ::= SEQUENCE (SIZE (1..3)) OF

[0236] NR-DL-TDOA-

[0237] AdditionalMeasurementElement-rl6

[0238] - ASN1STOP

[0239] - NR-AdditionalPathList

[0240] The IE NR-AdditionalPathList may be used by the target device to provide information about additional paths in association to the time of arrival (TOA) measurements associated to NR positioning in the form of a relative time difference and a quality value. The additional path nr-RelativeTimeDifference is the detected path timing relative to the detected path timing used for the TOA value, and each additional path may be associated with a quality value nr-PathQuality.

[0241] - ASN1 START

[0242] NR-AdditionalPathList-rl6 ::= SEQUENCE (SIZE(1..2)) OF NR-AdditionalPath- rl6

[0243] NR-AdditionalPathListExt-rl7 ::= SEQUENCE (SIZE(1..8)) OF NR- AdditionalPath-r 16

[0244] NR-AdditionalPath-rl6 ::= SEQUENCE { nr-RelativeTimeDifference-rl6 CHOICE { k0-rl6 INTEGER(0..16351), kl-rl6 INTEGER(0..8176), k2-rl6 INTEGER(O..4O88), k3-rl6 INTEGER(O..2O44), k4-rl6 INTEGER(O..1O22), k5-r!6 INTEGER(0..511), kMinusl-rl8 INTEGER(O..327O1), kMinus2-rl8 INTEGER(O..65401)

[0245] }, nr-PathQuality-r 16 NR-TimingQuality-r 16

[0246] OPTIONAL, [[ nr-DL-PRS-RSRPP-rl7 INTEGER (0 .126)

[0247] OPTIONAL nr-DL-PRS-RSRPP-Quality-r 19 NR-PowerQuality-r 19

[0248] OPTIONAL, ]] } - ASN1STOP As an example, the IE NR-PowerQuality may be defined as follows. It is understood that other values and value ranges may be used instead of those shown in the illustrative example, without deviating from the principle of the method.

[0249] NR-PowerQuality-rl9 ::= SEQUENCE { powerQualityValue-rl9 INTEGER (0..9), OPTIONAL powerQualityResolution-rl9 ENUMERATED {dBdotl, dBl,... }, confidence-r 19 INTEGER(0..100) OPTIONAL

[0250] }

[0251] Table 4. NR-PowerQuality field descriptions

[0252] In some embodiments, the uncertainty may also be encoded in terms of mean and standard deviation of the error estimation of the power. The UE 22 or network node 16 while performing measurement keeps on averaging the error and deduces mean error and standard deviation of the power measurement error and that is reported as quality metrics to the network node 16 such as LMF.

[0253] NR-PowerQuality-rl9 ::= SEQUENCE { meanPowerError-r 19 INTEGER (0..126), standardDeviationPowerError-rl9 INTEGER (0..126), confidence-r!9 INTEGER(0..100) OPTIONAL

[0254] }

[0255] In some embodiments, the NG-RAN receives an indication to report the power quality for the requested positioning measurement UL SRS-RSRP and UL SRS-RSRPP. In some embodiments, such an indication may be a new bit in the Measurement Characteristics Request Indicator IE, signaled in the NRPPa MEASUREMENT REQUEST message:

[0256]

[0257] Table 4. Measurement characteristics information

[0258] In some embodiments, the LMF receives from the NG-RAN a power quality associated with the measurement as new choice in the TRP Measurement Result IE

[0259] Table 5. Measurement quality

[0260] In some embodiments, the network node-DU receives from the network node-CU an indication to report the power quality for the requested positioning measurement UL SRS-RSRP and UL SRS-RSRPP. In some embodiments, such an indication may be a new bit in the Measurement Characteristics Request Indicator IE, signaled in the Fl Application Protocol (F1AP) POSITIONING MEASUREMENT REQUEST message.

[0261] In some embodiments, the network node-CU receives from the network node-DU a power quality associated to the measurement as new choice in the TRP Positioning Measurement Result IE.

[0262] Some embodiments provide a power measurement capability. For example, in addition to, or as an alternative to power quality indicator reporting, different levels of measurement capabilities may be defined, which correspond to different levels of sophistication in wireless signal measurement implementation. Thus, the power measurement capability may depend on the measurement equipment implementation, and may be reported by the equipment to give a static quality indication. This may be in contrast to the power quality metric, which is dynamic in nature, and a different quality metric may be reported for a different measurement instance, even if the measurement is performed by the same equipment.

[0263] For measurements at the UE 22, the power measurement capability is a type of UE 22 capability or UE feature. The UE 22 may report the power measurement capability to the network as a part of capability report. For the positioning use case, the UE 22 sends its capability reports to the LMF before the positioning session starts.

[0264] The power measurement capability may be defined by the different levels of power measurement accuracy achievable by the equipment. As an illustrative example, 3 levels of power measurement capability may be defined as:

[0265] • Low capability: the power measurement accuracy in the given channel condition is ±6.5 dB;

[0266] • Medium capability: the power measurement accuracy in the given channel condition is ±4 dB;

[0267] • High capability: the power measurement accuracy in the given channel condition is ±2 dB;

[0268] In general :

[0269] - NPlevels of power measurement capabilities may be defined, NP>=2;

[0270] - Lower capability corresponds to less accurate power measurement (corresponding to larger error margin, e.g., ±6.5 dB), and higher capability corresponds to more accurate power measurement (corresponding to smaller error margin, e.g., ±2 dB);

[0271] - Different power measurement capabilities may be defined for different channel conditions. In some embodiments, one set of capabilities is defined in Additive White Gauss Noise (AWGN) channel, another set of capabilities in fading channel. In another example, one set of capabilities is defined in high Signal to Interference Noise Ratio (SINR) channel and another set of capabilities in defined in low SINR channel;

[0272] - Different power measurement capabilities may be defined for different operating conditions. In some embodiments, one set of capabilities for operating in normal condition may be defined and another set of capabilities in extreme condition may be defined with respect to temperature and voltage condition; and / or

[0273] - Different power measurement capabilities may be defined for different wireless signal configurations. The configurations include one or more of: the band, band combination, bandwidth, frequency layer.

[0274] For the various life-cycle management stages of an AI / ML model, the power measurement capability may be taken into account, if the power information is used as a part of model input:

[0275] • For training data collection, the power measurement capability of the measurement entity needs to be stored together with the training data samples. For example, it may be attached to each training data sample individually, or stored as a part of metadata of the training dataset;

[0276] • For training data collection, a network node 16 or an external entity may set a threshold criterion that if the power quality is within certain range and resolution then only the UE 22 may store the data for data collection, else the data may be discarded;

[0277] • For model inference, the power measurement capability of the measurement equipment may be reported by the measurement entity to the inference entity, if measurement generation and model inference are carried out by different entities. In some embodiments, for the case where the UE 22 generates the measurement report and sends it to an LMF for an AI / ML model hosted by LMF, the UE 22 may send its power measurement capability to the LMF as a part of establishment procedure;

[0278] • For model monitoring, the parameter setting for model monitoring decisions may be set as a function of the power measurement capability. The parameter setting may include one or more of: threshold for declaring model drift, the time duration (or the number of model inference instances) to monitor before a model monitoring decision may be made.

[0279] Also, in addition to, or as an alternative to the power measurement capability, the power measurement requirement may be defined differently for different cases of AI / ML based positioning. Compared to power measurement capability (can vary from equipment to equipment based on its implementation complexity), the power measurement requirement is common to all equipment implementations of a given type or a given category. For example, a common requirement may be for all normal UEs regardless of UE implementation details, or common requirements to all Reduced Capability (RedCap) UEs, or common requirements for gNB type 1-C in Frequency Range 1 (FR1) regardless of network node 16 implementation details. For the UE 22, the power measurement requirement may be understood as the minimum accuracy that a UE 22 needs to satisfy in order to pass the performance test. To support AI / ML based positioning, requirements on the power measurements (e.g., DL PRS RSRP, DL PRS RSRPP) may be defined to support different positioning variants.

[0280] FIG. 8 shows an example network node 16a (e.g., an LMF) configured to determine a UE position and to communicate with a radio node 62a and / or a radio node 62b. The radio node 62a may comprise a network node 16b (e.g., gNB), and the radio node 62b may comprise a UE 22. Radio node 62a, 62b (collectively referred to as radio node 16) may include any of the components of the corresponding network node 16 and / or UE 22 and be configured to perform one or more network node functions and / or UE functions.

[0281] Network node 16a may be configured to transmit, at step S200, a request for a measurement report to radio node 62a and / or radio node 62b. The measurement report may be determined by radio node 62a and / or radio node 62, at step 202 (or determined by network node 16a). At step S204, network node 16a may receive a response from radio node 62a and / or radio node 62b including the measurement report. The measurement report may include a measurement of a wireless channel (e.g., a wireless channel associated with the communication between radio node 62a and radio node 62b or with the communication of radio node 62a and radio node 62b with any other node. The measurement report may also include a power quality metric associated with the measurement of the wireless channel. At step S206, network node 16a may determine the UE position based on the measurement report.

[0282] The Al model may be trained by network node 16a, radio node 62a, and / or radio node 62b based at least in part on a training dataset associated at least in part with the power quality metric. The training dataset may be determined by network node 16a, radio node 62a, and / or radio node 62b based at least in part on the power quality metric. The Al model may be trained and transmitted by any one of network node 16a, radio node 62a, and / or radio node 62b to any other component of system 10. Further, the UE position may be based on or be an output of the Al model.

[0283] Any one of network node 16a, radio node 62a, and radio node 62b may monitor model performance of the Al model based on the measurement of the wireless channel and the power quality metric. Any one of network node 16a, radio node 62a, and radio node 62b may determine and transmit signaling (e.g., beams) having one or more characteristics (e.g., power values, phase, timing, frequency) based on the determination of the UE position (e.g., using the Al model, measurement report, etc.). For example, network node 16a (e.g., LMF) may determine the UE position based on the Al model and / or measurement report and determine signaling having one or more beam characteristics such as beam angle or path to reach the UE at the UE position. Any one of network node 16a, radio node 62a, and radio node 62b may determine not to transmit the signaling (e.g., beams) having one or more characteristics (e.g., power values, phase, timing, frequency) based on the determination of the UE position (e.g., using the Al model, measurement report, etc.). That is, although the measurement value may be below a predetermined threshold (e.g., low power signal), the quality / reliability of the measurement (e.g., indicated by the power quality metric) may be used for selection of a dataset and / or training and / or monitoring of an Al model usable for determining UE position.

[0284] The following is a nonlimiting list of example embodiments. Embodiment Al . A network node configured to communicate with a user equipment (UE), the network node configured to, and / or comprising a radio interface and / or comprising processing circuitry configured to: receive from the UE at least one measurement report that includes a power quality metric; determine a training dataset based at least in part on the power quality metric; and train an artificial intelligence / machine learning, AI / ML, based at least in part on the training dataset.

[0285] Embodiment A2. The network node of Embodiment Al, wherein the power quality metric is received in response to a request, the request including a minimum quality threshold to be surpassed as a condition of transmitting the at least one measurement report by the UE.

[0286] Embodiment A3. The network node of any of Embodiments Al and A2, wherein the power quality metric includes at least one of a reference signal received power, RSRP, and a reference signal received path power, RSRPP.

[0287] Embodiment A4. The network node of any of Embodiments, A1-A3, wherein a number of received measurement reports depends on a value of a power quality metric.

[0288] Embodiment A5. The network node of any of Embodiments, A1-A4, wherein a power quality metric includes a relative time difference of arrival, TOA.

[0289] Embodiment Bl. A method implemented in a network node that is configured to communicate with a user equipment, the method comprising: receiving from the UE at least one measurement report that includes a power quality metric; determining a training dataset based at least in part on the power quality metric; and training an artificial intelligence / machine learning, AI / ML, based at least in part on the training dataset.

[0290] Embodiment B2. The method of Embodiment Bl, wherein the power quality metric is received in response to a request, the request including a minimum quality threshold to be surpassed as a condition of transmitting the at least one measurement report by the UE.

[0291] Embodiment B3. The method of any of Embodiments Bl and B2, wherein the power quality metric includes at least one of a reference signal received power, RSRP, and a reference signal received path power, RSRPP. Embodiment B4. The method of any of Embodiments, B1-B3, wherein a number of received measurement reports depends on a value of a power quality metric.

[0292] Embodiment B5. The method of any of Embodiments, B1-B4, wherein a power quality metric includes a relative time difference of arrival, TOA.

[0293] Embodiment Cl . A user equipment (UE) configured to communicate with a network node, the UE configured to, and / or comprising a radio interface and / or processing circuitry configured to: determine a power quality metric for each of a plurality of transmission paths; and transmit the power quality metrics in at least one measurement report.

[0294] Embodiment C2. The UE of Embodiment Cl, wherein the power quality metric is measured in response to a request, the request including a minimum quality threshold to be surpassed as a condition of transmitting the at least one measurement report by the UE.

[0295] Embodiment C3. The UE of any of Embodiments Cl and C2, wherein the power quality metric includes at least one of a reference signal received power, RSRP, and a reference signal received path power, RSRPP.

[0296] Embodiment C4. The UE of any of Embodiments, C1-C3, wherein a number of transmitted measurement reports depends on a value of a power quality metric.

[0297] Embodiment C5. The UE of any of Embodiments, C1-C4, wherein a power quality metric includes a relative time difference of arrival, TOA.

[0298] Embodiment DI . A method implemented in a user equipment (UE) that is configured to communicate with a network node, the method comprising: determining a power quality metric for each of a plurality of transmission paths; and transmitting the power quality metrics in at least one measurement report.

[0299] Embodiment D2. The method of Embodiment DI, wherein the power quality metric is measured in response to a request, the request including a minimum quality threshold to be surpassed as a condition of transmitting the at least one measurement report by the method.

[0300] Embodiment D3. The method of any of Embodiments DI and D2, wherein the power quality metric includes at least one of a reference signal received power, RSRP, and a reference signal received path power, RSRPP.

[0301] Embodiment D4. The method of any of Embodiments, D1-D3, wherein a number of transmitted measurement reports depends on a value of a power quality metric. Embodiment D5. The method of any of Embodiments, D1-D4, wherein a power quality metric includes a relative time difference of arrival, TOA.

[0302] As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and / or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step, action and / or functionality described herein may be performed by, and / or associated to, a corresponding module, which may be implemented in software and / or firmware and / or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that may be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD-ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.

[0303] Some embodiments are described herein with reference to flowchart illustrations and / or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a special purpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0304] These computer program instructions may also be stored in a computer readable memory or storage medium that may direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0305] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0306] It is to be understood that the functions / acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality / acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows.

[0307] Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, Java® or C++. However, the computer program code for carrying out operations of the disclosure may also be written in conventional procedural programming languages, such as the "C" programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0308] Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments may be combined in any way and / or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.

[0309] It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings and following claims.

Claims

What is claimed is:

1. A method in a radio node (62) configured to communicate with a first network node (16), the first network node (16) being configured to determine a user equipment, UE (22), position, the method comprising: receiving (SI 10) a request for a measurement report, the measurement report being associated with the position of the UE (22) and based on an artificial intelligence, Al, model; determining (SI 12) the measurement report, the measurement report including a measurement of a wireless channel and a power quality metric associated with the measurement of the wireless channel; and transmitting (SI 14) a response including the measurement report, the measurement report including the measurement of the wireless channel and the power quality metric associated with the measurement of the wireless channel, the measurement report triggering the first network node (16) to determine the UE (22) position.

2. The method of Claim 1, wherein the method further includes: training the Al model based at least in part on a training dataset associated at least in part with the power quality metric.

3. The method of Claim 2, wherein the method further includes: determining the training dataset based at least in part on the power quality metric; and transmitting the Al model to the first network node (16).

4. The method of any one of Claims 1-3, wherein the determination of the UE position is based on an output of the Al model.

5. The method of any one of Claims 1-4, wherein the method further includes: monitoring model performance of the Al model based on the measurement of the wireless channel and the power quality metric.

6. The method any one of Claims 1-5, wherein the measurement of the wireless channel and the power quality metric includes a power value.

7. The method any one of Claims 1-6, wherein the measurement of the wireless channel and the power quality metric corresponds to one or more of a downlink radio signal received power, an uplink radio signal received power, a downlink radio signal received power, and a sidelink radio signal received power.

8. The method of any one of Claims 1-7, wherein the power quality metric is based on a level of confidence in the measurement.

9. The method of any one of Claims 1-8, wherein the power quality metric indicates a degree of precision of the measurement.

10. The method of any one of Claims 1-9, wherein the request includes a power quality indicator request requesting the power quality metric to be included in the measurement report.

11. The method of any one of Claims 1-10, wherein the request is based on a UE capability for reporting the power quality metric.

12. The method of any one of Claims 1-11, wherein the radio node (62) is one a UE (22) and a second network node (16) configured to communicate with the UE (22).

13. The method of any one of Claims 1-12, wherein the first network node (16) comprises a location management function, LFM.

14. A radio node (62) configured to communicate with a first network node (16), the first network node (16) being configured to determine a user equipment, UE (22), position, the radio node (62) being configured to perform one or more steps corresponding to one or more of Claims 1-13 and / or being associated with one or more features that are similar or the same as the features described in one or more of Claims 1-13.

15. A method in a first network node (16) configured to communicate with a radio node (62) and determine a user equipment, UE (22), position, the method comprising:transmitting (SI 16) a request for a measurement report, the measurement report being associated with the position of the UE (22) and based on an artificial intelligence, Al, model; receiving (S 118) a response including the measurement report, the measurement report including a measurement of a wireless channel and a power quality metric associated with the measurement of the wireless channel; and determining (SI 20) the UE position based on the measurement report.

16. The method of Claim 15, wherein the method further includes: training the Al model based at least in part on a training dataset associated at least in part with the power quality metric.

17. The method of Claim 16, wherein the method further includes: determining the training dataset based at least in part on the power quality metric.

18. The method of Claim 15, wherein the method further includes: receiving the Al model, the received Al model being trained by the radio node (62) based at least in part on the power quality metric.

19. The method of any one of Claims 15-18, wherein the determination of the UE position is further based on an output of the Al model.

20. The method of any one of Claims 15-19, wherein the method further includes: monitoring model performance of the Al model based on the measurement of the wireless channel and the power quality metric.

21. The method of any one of Claims 15-20, wherein the measurement of the wireless channel and the power quality metric includes a power value.

22. The method of any one of Claims 15-21, wherein the measurement of the wireless channel and the power quality metric corresponds to one or more of: a downlink radio signal received power, an uplink radio signal received power, a downlink radio signal received power, and a sidelink radio signal received power.

23. The method of any one of Claims 15-22, wherein the power quality metric is based on a level of confidence in the measurement.

24. The method of any one of Claims 15-23, wherein the power quality metric indicates a degree of precision of the measurement.

25. The method of any one of Claims 15-24, wherein the request includes a power quality indicator request requesting the power quality metric to be included in the measurement report.

26. The method of any one of Claims 15-25, wherein the request is based on a UE capability for reporting the power quality metric.

27. The method of any one of Claims 15-26, wherein the radio node (62) is one a UE (22) and a second network node (16) configured to communicate with the UE (22).

28. The method of any one of Claims 15-27, wherein the first network node (16) comprises a location management function, LFM.

29. A first network node (16) configured to communicate with a radio node (62) and determine a user equipment, UE (22), position, the first network node (16) being configured to perform one or more steps corresponding to one or more of Claims 15-28 and / or being associated with one or more features that are similar or the same as the features described in one or more of Claims 15-28.

Images