Performance monitoring of ai-based CSI with rank uncertainty

By grouping data samples by transmission rank and using differential reporting, the method addresses rank uncertainty in AI-based CSI monitoring, ensuring accurate and reliable performance assessment.

WO2026235611A1PCT designated stage Publication Date: 2026-11-12TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/SE2026/050325
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-09
Filing Date
2026-05-08
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

Existing methods for performance monitoring of AI-based CSI with rank uncertainty are challenging due to varying ranks across data samples, leading to inaccuracies in calculating statistics for monitoring metrics like SGCS, which affects the reliability of model performance assessment.

Method used

The proposed solution involves grouping data samples based on transmission rank to calculate statistics of performance monitoring metrics, such as SGCS, using methods like mean or x% CDF of SGCS, and employing differential reporting to reduce overhead.

Benefits of technology

This approach removes rank uncertainty, ensuring accurate and reliable performance monitoring by calculating statistics that account for varying ranks, thereby improving the reliability of AI-based CSI prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure SE2026050325_12112026_PF_FP_ABST
    Figure SE2026050325_12112026_PF_FP_ABST
Patent Text Reader

Abstract

A method performed by a wireless communications device for performance monitoring related to CSI is provided The wireless communications device selects (902) data samples to be used based on a transmission rank of the data samples. The wireless communications device calculates (903) a performance monitoring metric based on the selected data samples. The wireless communications device transmits (904), to a network node, a performance monitoring report comprising the performance monitoring metric.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] PERFORMANCE MONITORING OF AI-BASED CSI WITH RANK UNCERTAINTY

[0002] TECHNICAL FIELD

[0003] The present disclosure relates generally to a wireless communication device, a network node, and a method for performance monitoring related to Channel State Information (CSI). The present disclosure may further relate to a computer program product and a computer-readable storage medium.

[0004] BACKGROUND

[0005] Artificial intelligence (Al) and machine learning (ML) have been investigated, both in academia and industry, as promising tools to optimize the design of the air interface in wireless communication networks. Example use cases include using autoencoders for CSI compression to reduce the feedback overhead and improve channel prediction accuracy; using deep neural networks for classifying line-of-sight (LOS) and non-LOS (NLOS) conditions to enhance positioning accuracy; and using reinforcement learning for beam selection at the network side and / or the user equipment (UE) side to reduce the signalling overhead and beam alignment latency; and using deep reinforcement learning to learn an optimal precoding policy for complex multiple input multiple output (MIMO) precoding problems.

[0006] The Third Generation Partnership Project (3GPP) New Radio (NR) standardization work for release 18 (Rel-18) included a study item (SI) on AI / ML for the NR air interface and this work will continue in release 19 (Rel-19). The works will explore 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 and specifying a few selected use cases CSI feedback, beam management, and positioning, the works aim to design the mechanisms to accommodate AI / ML into the 3GPP standard, laying the foundation for future air interface use cases leveraging AI / ML techniques.

[0007] An important part of Al development and operation is the lifecycle management (LCM) of the AI / ML model (e.g., model training, model deployment, model inference, model monitoring, model updating) and AI / ML functionality.

[0008] In NR Release 18 AI / ML for NR air interface study item, the LCM procedure is studied for the case that an AI / ML model has a model ID with associated information and / or for the case that a given functionality is provided by some AI / ML operations.

[0009] Two types of LCM operations were studied in NR Rel-18, functionality-based LCM, and model-l D-based LCM.

[0010] Functionality refers to an AI / ML-enabled feature / Feature Group (FG) enabled by configuration(s), where configuration(s) is(are) supported based on conditions indicated by UEcapability. For example, in the UE-side prediction case, a UE may be capable of predicting up to 10 future CSI prediction instances. In the implementation, the UE may have two models where the first model is a more specific model to predict 5 future CSI instances (and consumes lower power) and the second model is capable of predicting 10 future CSI instances (and consumes more power). A configuration / indication from the Network (NW), such as the NW configures the UE to report 8 future CSI instances, may serve as an indication for the UE to use the second model instead of the first one.

[0011] Correspondingly, functionality-based LCM operates based on, at least, one configuration of an AI / ML-enabled feature / FG or specific configurations of an AI / ML-enabled feature / FG. In functionality-based LCM, the network indicates activation / deactivation / fallback / switching of AI / ML functionality via 3GPP signalling (e.g., Radio Resource Control (RRC), medium access control (MAC) control element (CE), downlink control information (DCI). Models may not be identified at the network, and the UE may perform model-level LCM. This means that that the model currently used by the UE does not necessarily need be reported to the UE. Related to the example above, the UE does not necessarily inform the network that the UE switches from the first to the second model. For functionality identification, there may be either one or more than one functionalities defined within an AI / ML-enabled feature, whereby AI / ML-enabled feature refers to a feature where AI / ML may be used.

[0012] In model-l D-based LCM, models are identified at the network, and the network / UE may activate / deactivate / select / switch individual AI / ML models via model ID. A model may be associated with specific configurations / conditions associated with the UE capability of an AI / ML-enabled feature / FG and additional conditions (e.g., scenarios, sites, and datasets) as determined / identified between the UE side and network side. An AI / ML model identified by a model ID may be logical, and how it maps to physical AI / ML model(s) may be up to implementation.

[0013] Figure 1 is a block diagram illustrating a functional framework for AI / ML for NR air interface. The illustrated example shows a functional framework that may be used for studying model LCM aspects for different Al for physical layer (PHY) use cases. The general framework consists of the following.

[0014] Data Collection is a function that provides input data to the Model Training, Management, and Inference functions.

[0015] Training Data: Data needed as input for the AI / ML Model Training function.

[0016] Monitoring Data: Data needed as input for the Management of AI / ML models or AI / ML functionalities.

[0017] Inference Data: Data needed as input for the AI / ML Inference function.Model Training is a function that performs AI / ML model training, validation, and testing which may generate model performance metrics that may be used as part of the model testing procedure. The Model Training function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on Training Data delivered by a Data Collection function if required.

[0018] Trained / Updated Model: In case of having a Model Storage function, this is used to deliver trained, validated, and tested AI / ML models to the Model Storage function, or to deliver an updated version of a model to the Model Storage function.

[0019] Management is a function that oversees the operation (e.g., selection, (de)activation, switching, fallback) and monitoring (e.g., monitoring performance) of AI / ML models or AI / ML functionalities. This function is also responsible for making decisions to ensure the proper inference operation based on data received from the Data Collection function and the Inference function.

[0020] Management Instruction: Information needed as input to manage the Inference function. The needed information may refer to selection / (de)activation / switching of AI / ML models or AI / ML-based functionalities, fallback to non-AI / ML operation (i.e., not relying on inference process), etc.

[0021] Model Transfer / Delivery Request: Used to request model(s) to the Model Storage function.

[0022] Performance Feedback / Retraining Request: Information needed as input for the Model Training function, e.g., for model (re)training or updating purposes.

[0023] Inference is a function that provides outputs from the process of applying AI / ML models or AI / ML functionalities, using the data that is provided by the Data Collection function (i.e., Inference Data) as an input. The Inference function is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on Inference Data delivered by a Data Collection function, if required.

[0024] Inference Output: Data used by the Management function to monitor the performance of AI / ML models or AI / ML functionalities.

[0025] Model Storage is a function responsible for storing trained / updated models that may be used to perform the Inference function.

[0026] The Model Storage function in Figure 1 is only intended as a reference point (if any) when applicable for protocol terminations, model transfer / delivery, and related processes. Itshould be stressed that its purpose does not encompass restricting the actual storage locations of models.

[0027] Model Transfer / Delivery: Used to deliver an AI / ML model to the Inference function.

[0028] Time domain CSI prediction at UE

[0029] 3GPP NR Rel. 18 also includes time domain Type II CSI prediction at the UE. 3GPP NR Rel-18 introduces channel measurement resource (CMR) enhancement for Type II CSI prediction at UE (also referred to as Rel-18 Type II CSI). To enable CSI prediction, channel measurements for a sufficient number of time instances are required for extracting the time domain channel property, based on which a future CSI may be predicted. To obtain such measurements, gNodeB (gNB) may either configure a legacy periodic (P) or semi-persistent (SP) CSI-RS resource, or an aperiodic (AP) CSI-RS burst according to Rel-18. To be more specific, for AP CSI-RS burst based CSI prediction at a UE, a single burst of K e {4, 8, 12} CSI-RS resources may be configured to the UE within a single CSI-RS resource set, which may be aperiodically triggered using a single downlink control information (DCI). The CSI-RS resources are uniformly spaced in time, separated by m e {1,2} slots, within the resource set.

[0030] For the Rel-18 Type II precoding matrix indicator (PMI) enhancement, a UE may be configured by gNB to report predicted PMIs for N4G {1, 2, 4, 8} time slots. Figure 2 illustrates the Rel-18 Type II PMI part. In Figure 2, CSI RS resource is referred to as 201, UL slot for CSI reporting is referred to as 202, and predicted PMI for one time instance is referred to as 203. 1, 2, 3 and K in Figure 2 refers to the CSI-RS measurements in an observation window, which contains K channel measurements. The prediction herein is relative to the CSI-RS reference resource. The predicted N4 PMIs are supposed to reflect the channels with d e {1, m} slots separation, starting from 8 e {-nCSI f, 0, 1, 2} slots into the future relative to the CSI-RS reference resource. For AP CSI-RS burst, m e {1, 2}, while for P / SP CSI-RS, m is the CSI-RS periodicity. The spacing d between the / V4PMIs and offset 8 relative to the CSI-RS reference resource may be configured by the gNB via RRC signalling. The / V4PMIs are compressed in a beam-frequency-Doppler domain, and the compressed PMI is reported to the gNB in a single CSI report.

[0031] 3GPP NR Rel-18 time-domain CSI prediction using UE-side AI / ML model

[0032] In Rel-18, Al-based UE-side CSI prediction was introduced as an Al for PHY layer use cases and being studied in the study item on AI / ML for the NR air interface. One or more AI / ML models may be trained and deployed at a UE for the Al-based CSI-prediction feature. During model inference, a UE is configured by the gNB to measure a set of historical CSI-RSsand then report a predicted CSI for one or multiple future time instances using its AI / ML model(s).

[0033] Model performance monitoring

[0034] An example of performance monitoring of a UE-sided Al model can be found in Figure 3, where the model input, denoted by X is input to an Al model deployed at the UE and generates an output given by Y. Then, a pair of model output and ground truth label, i.e.,

[0035]

[0036] may be used for performance monitoring. Note that this is just an illustrative example, the actual performance monitoring may be different. For example, it may be based on multiple samples of [Y, / }, etc. A performance monitoring decision may be made based on the performance monitoring result.

[0037] There are several methods for model performance monitoring. Monitoring based on intermediate KPIs (e.g., inference accuracy) requires collecting new ground truth data similar / identical to the training data, which is very accurate but has a high cost due to the potentially large measurement / reporting overhead. Monitoring based on data distribution of input / output data does not require any additional signalling overhead but is less accurate than monitoring based on inference accuracy since the ground truth is not retrieved. In this disclosure, ground truth refers to CSI obtained by actually measuring the received reference signal (e.g., CSI-RS). For example, the UE may be configured to report the performance of the model by predicting 5 future CSI instances by measuring 6 past CSI instances. Here, the network may send 11 CSI-RS, where the 5 CSI-RS of those corresponds to the 5 future CSI instances that the UE should predict. The measurement result (not the prediction result) of those 5 CSI-RS is referred to as the ground truth.

[0038] Similarly, monitoring based on system performance does not require any additional signalling overhead. However, it may be challenging to identify whether the root-cause for bad system performance is due to an inaccurate model or due to some other malfunctioning procedure or hardware. Monitoring based on data distribution may in contrast identify a potential problem in the model by detecting that the dataset observed during inference is not the same as during training. However, it is not trivial to define conditions and measurable data-distribution based KPIs for sounding a model failure alarm with a good trade-off between model failure detection reliability and accuracy (e.g., low false alarm rate, low missed detection rate and low latency).

[0039] To ensure reliable / accurate model performance monitoring results, sufficient monitoring data samples may be collected and used to derive the performance monitoring results.

[0040] Examples of model-output / inference accuracy-based performance monitoring results include intermediate KPI per monitoring data sample, intermediate KPI statistics associated to amonitoring data set, the percentage of monitoring data samples within a monitoring dataset for which the intermediate KPI fulfils a certain condition, a flag indicating whether the model is functioning ok or not. Examples of data drift-based performance monitoring results include monitoring data statistics, the difference between the monitoring data statistics and the data statistics obtained in the model training stage, and a flag indicating whether a data drift is detected or not.

[0041] When implementing model monitoring, the monitoring method may be selected based on UE service requirements. For example, a UEwith Enhanced Mobile Broadband (eMBB) may start with a low-cost solution (e.g. system performance-based). If problems are observed / predicted, then the UE may activate an inference accuracy-based monitoring method associated with higher complexity. High-complexity and signalling overhead monitoring may be required for certain UE service requirements, such as for emergency localization use cases or UEs with URLLC connections.

[0042] For CSI prediction using UE side AI / ML model use case studied in Rel-18 AI / ML for NR air interface study item, at least the following aspects have been proposed for performance monitoring for functionality-based LCM:

[0043] Type 1:

[0044] - UE calculates performance metric(s)

[0045] - UE reports performance monitoring output that facilitates functionality fallback decisions at the network. Performance monitoring output details may be further defined.

[0046] The performance monitoring metric is a metric that may be used to quantitatively measure the performance of a model. For example, a model may have in a certain performance monitoring occasion a squared generalized cosine similarity (SGCS) value of 0.8250 (e.g., by comparing the output of the model and the ground truth). The SGCS is here the metric used to evaluate the accuracy of the model. The performance monitoring output, on the other hand, is the output of a categorization of the performance monitoring metric, most likely with one or more thresholds to determine such an output. For example, a threshold may be defined (e.g., via a standard text, NW configuration, or UE implementation), where an SGCS value above 0.8000 corresponds to a performance deemed as acceptable and an SGCS value below 0.8000 corresponds to a performance deemed as unacceptable.

[0047] Considering the performance monitoring metric of 0.8250 as in the above example, the performance monitoring output in this case will be “acceptable”.

[0048] Network may configure threshold criteria to facilitate UE-side performance monitoring (if needed). As mentioned above, the threshold criteria may be something that directly relates tothe performance monitoring metric. For example, if the metric is an SGCS value, than the threshold may be one or more SGCS values that may categorize the SGCS value calculated by the UE into two or more performance monitoring outputs.

[0049] Network makes the decision(s) of functionality fallback operation (fallback mechanism to legacy CSI reporting). Functionality fallback decisions at the network corresponds to the fallback operation that may be taken by considering the performance monitoring output from the UE. For example, if the UE reports: “performance of the model is unacceptable”, the NW may then configure the UE with, e-g., non-AI based CSI prediction or disable the CSI prediction. In this particular example, the non-AI based CSI prediction or disabling the CSI prediction is the fallback.

[0050] Type 2:

[0051] - UE reports predicted CSI and / or the corresponding ground truth.

[0052] - Network calculates the performance metrics.

[0053] - Network makes a decision(s) of functionality fallback operation (a fallback mechanism to legacy CSI reporting).

[0054] Type 3:

[0055] - UE calculates the performance metric(s)

[0056] - UE reports performance metric(s) to the network

[0057] - Network makes a decision(s) of functionality fallback operation (a fallback mechanism to legacy CSI reporting).

[0058] The study includes functionality selection / activation / deactivation / switching as defined for other UE side use cases may be reused, if applicable.

[0059] The study further includes configuration and procedure for performance monitoring, such as CSI-RS configuration for performance monitoring.

[0060] The study may include performance metric including at least intermediate KPI (e.g., NMSE or SGCS) and UE report, including periodic / semi-persistent / aperiodic reporting, and event-driven report.

[0061] It is worth noting that UE may make decision within the same functionality on model selection, activation, deactivation, switching operation transparent to the NW.

[0062] Below are some agreements from 3GPP RAN1#120-bis meeting in Wuhan.

[0063] For the definition of SGCS,For a given layer I e {1,..., v}, subband n3e {1,..., N3, and prediction instance n4e {1,..., ZV4}, SGCS is defined as

[0064]

[0065] where is the predicted precoder represented by PMI used for inference for Z-th layer, n3-th subband and n4-th prediction instance, and w^tis the precoder represented by PMI used for ground-truth CSI for Z-th layer, n3-th subband and n4-th prediction instance.

[0066] Note: How to handle layer mapping mismatch, if any, is up to UE implementation

[0067] Agreement

[0068] For CSI prediction using UE-side model, for reporting contents of UE assisted performance monitoring, down-select one alternative by RAN1#121.

[0069] Alt 1: one SGCS is calculated based on predicted CSI for one inference reporting, ground-truth CSI.

[0070] Alt 2: one SGCS is calculated based on predicted CSI for one inference reporting, and ground-truth CSI, another SGCS is based on ground-truth CSI and CSI (non-predicted) corresponding to the latest CSI-RS transmission occasion not later than CSI reference resource of the inference reporting instance.

[0071] Alt 3: statistic of reporting contents (e.g., mean, x% Cumulative distribution function (CDF) of SGCS values) of inference reporting instances within configured monitoring window.

[0072] Monitoring window may be configured by NW.

[0073] FFS on signalling details.

[0074] FFS on whether to report per prediction instance, selected prediction instance(s), averaged over prediction instances.

[0075] FFS on report frequency granularity (e.g., per wideband or per subband or averaged over subband or selected subband).

[0076] FFS on whether to report per layer, the first layer, averaged over layer.

[0077] FFS on how to quantize and report mechanism.

[0078] Angles in complex vector spaces and principal angles between subspaces

[0079] Cosine similarity is based on the angles between vectors. This is well defined in the real-valued case, which is most common in AI / ML literature. For complex-valued vector spaces, there are several different angles that may be measured. A summary of those is available in document K. Scharnhorst, “Angles in Complex Vector Spaces”, arXiv: 9904077, 1999. The agreed SGCS is the square of the GCS (Generalize Cosine Similarity), which in turn is basedon an Hermitian angle. One may also consider the Euclidean angle and define a corresponding ECS (Euclidean Cosine Similarity) and its squared counterpart SECS (Squared Euclidean Cosine Similarity). In the language of the above agreement on SGCS, the following is defined

[0080]

[0081] It is also possible to do a further generalization, where the inner product is a weighted inner product, using a Hermitian and positive (semi-)definite matrix A. This defines what may be called “weighted angles”. Thus, in the language of the above agreement on SGCS, we define the SWGCS (Squared Weighted Generalized Cosine Similarity) and SWECS (Squared Weighted Euclidean Cosine Similarity)

[0082]

[0083] Using the weighted / generalized vector norm HplM = pHA p. The non-squared versions WGCS and WECS are straightforwardly defined.

[0084] Examples of matrices A that may be used are the channel transmit correlation HHH. Moreover, based on this concept of angles in vector spaces, one may define principal angles between subspaces. This is treated in document A. Galantai, Cs. J. Hegedus, “Jordan’s principal angles in complex vector spaces”, Numerical Linear Algebra with Applications, 2006. Specifically, definition 4 in this document may be useful. These angles may be computed using an SVD of an appropriately defined matrix, see Theorem 13 in the aforementioned document. The discussion following the theorem also outlines that this may be applied also to “weighted angles” as defined using the weighted inner product above.

[0085] In 3GPP RAN1#120-bis, it has been agreed to use SGCS as a performance monitoring metric for monitoring Al models for CSI prediction use case, which is calculated per layer.

[0086] In addition, statistics of the SGCS values over multiple monitoring data samples (Alt 3) might be used, for the network to make reliable functionality-based LCM operation decisions. However, when multiple monitoring data samples are needed for the UE to calculate the statistics of the SGCS values, where each data sample corresponds to a pair of {predicted CSI, ground-truth CSI}, the rank may change across different data samples. For example, insome data samples, the rank of the associated predicted CSI reports may be 1, while in some other data samples, the associated rank is 2.

[0087] SUMMARY

[0088] An object of embodiments herein may be to obviate at least some of the above-mentioned problems.

[0089] Embodiments disclosed herein are directed to methods and apparatuses for defining statistics of performance monitoring metrics when there is rank uncertainty / variation across performance monitoring data samples, e.g. directed to how to define SGCS statistics for performance monitoring when data samples have different ranks.

[0090] Embodiments disclosed herein comprise, for example, grouping data samples for monitoring by layer, by transmission rank, etc. The layer may be a transmission layer, such as a MIMO transmission layer. A transmission layer may be a data stream that may be transmitted simultaneously with other data streams / transmission layers over the air and over the same time-frequency resources using different antenna constellations (which also may be referred to as different spatial signatures or precoding vectors). The layers may be mapped to the physical antennas through a process called precoding.

[0091] Precoding is a mathematical transformation applied to the data streams before transmission. It maps each data stream (layer) to the antenna elements using a precoding matrix. This matrix may be designed based on the CSI to optimize signal separation at the receiver.

[0092] In addition, embodiments disclosed herein also comprise methods for reporting performance metrics using differential reporting to reduce overhead.

[0093] According to an aspect of embodiments herein, the object is achieved by a method performed by a wireless communications device. The method is for performance monitoring related to CSI. The wireless communications device selects data samples to be used based on a transmission rank of the data samples. The wireless communications device calculates a performance monitoring metric based on the selected data samples. The wireless communications device transmits, to a network node, a performance monitoring report comprising the performance monitoring metric.

[0094] According to a further aspect, the object is achieved by a method performed by a network node. The method is for performance monitoring. The network node receives, from a wireless communications device, a performance monitoring metric. The performance monitoring metric is based on data samples which are selected based on a transmission rank of the data samples.According to a further aspect, the object is achieved by a wireless communications device. The wireless communications device is configured to perform performance monitoring related to CSI. The wireless communications device is further configured to:

[0095] - Select data samples to be used based on a transmission rank of the data samples. - Calculate a performance monitoring metric based on the selected data samples, and. - Transmit, to a network node, a performance monitoring report comprising the performance monitoring metric.

[0096] According to a further aspect, the object is achieved by a network node. The network node is configured to perform performance monitoring related to CSI. The network node is further configured to:

[0097] - Receive, from a wireless communications device, a performance monitoring metric. The performance monitoring metric is based on data samples which are selected based on a transmission rank of the data samples.

[0098] According to a further aspect, the object is achieved by a computer program comprising instructions, which when executed by a processor, causes the processor to perform actions according to any of the aspects above.

[0099] According to a further aspect, the object is achieved by a carrier comprising the computer program of the aspect above, wherein the carrier is one of an electronic signal, an optical signal, an electromagnetic signal, a magnetic signal, an electric signal, a radio signal, a microwave signal, or a computer-readable storage medium.

[0100] An advantage of embodiments of embodiments herein, e.g. for calculating statistics of performance monitoring metrics, is that they remove rank uncertainty, when different data samples for monitoring are associated with different ranks.

[0101] BRIEF DESCRIPTION OF THE DRAWINGS

[0102] Examples of embodiments herein are described in more detail with reference to attached drawings in which:

[0103] Figure 1 is a schematic block diagram illustrating Prior Art.

[0104] Figure 2 is a schematic block diagram illustrating Prior Art.

[0105] Figure 3 is a schematic block diagram illustrating Prior Art.

[0106] Figure 4 is a schematic block diagram illustrating embodiments performance monitoring based on statistics of SGCS.

[0107] Figure 5a is a flowchart depicting a method performed by a wireless communications device in some embodiments.

[0108] Figure 5b is a flowchart depicting a method performed by a wireless communications device in some embodiments.Figure 6 is a flowchart depicting a method performed by a network node in some embodiments.

[0109] Figure 7 is a generalized block diagram of embodiments of a wireless device.

[0110] Figure 8 is a generalized block diagram of embodiments of a network node.

[0111] Figure 9 schematically illustrates embodiments of a communication system.

[0112] Figure 10 schematically illustrates embodiments of a communication system.

[0113] Figure 11 is a generalized block diagram of embodiments of a wireless device.

[0114] Figure 12 is a generalized block diagram of embodiments of a network node.

[0115] Figure 13 is a generalized block diagram of embodiments of a virtualization environment.

[0116] DETAILED DESCRIPTION

[0117] Note that although embodiments disclosed herein use SGCS as a performance monitoring metric, the same embodiments may also be applied to any performance monitoring metric that is defined per layer, e.g., GCS, NMSE, ECS, SECS, SWGCS, SWECS, log(GCS), log(SGCS). See more examples and generalizations in the last embodiments.

[0118] Note that although embodiments herein focus on the CSI prediction use case with UE-sided AI / ML model, the same or a similar method may also be applied to performance monitoring of UE-sided model in other use cases. Some example use cases are the UE-sided model of the two-sided CSI compression use case and UE-sided models for CSI-RS overhead reduction use case.

[0119] A non-limiting example is shown in Figure 4 for performance monitoring based on statistics of SGCS that are calculated based on multiple data samples, wherein the data samples may be associated with different ranks. Each data sample may contain one predicted CSI and one ground-truth CSI. The predicted CSI is in the format of PM I used for inference, e.g., Rel-18 Type II Doppler format, i.e., “typell-Doppler-r18” codebook, as defined in clause 5.2.2.2.10 of 3GPP TS 38.214 V18.6.0, while the ground-truth CSI is in the same format as the PMI for inference, including the transmission rank. A ground truth for performance monitoring may be obtained using measured one or multiple CSI-RS(s) for the corresponding one or multiple prediction time instances (e.g., the measured CSI-RS(s) on the N4time slots in the prediction window as shown in Figure 2), assuming that the network has scheduled suitable CSI-RS resources in that prediction window. Based on each data sample, an SGCS value is calculated for each layer, each subband and each prediction instance. For simplicity of disclosing embodiments without loss of generality, a subband index and a prediction instance index are dropped in embodiments herein. This e.g. means that SGCS”^, as defined above, is defined fora layer / e {1,...,v}, a subband n3∈ {1,...,N3}, and a prediction instance n4e{1,...,N4}, but the notation / indexing with n3and n4is not explicitly written out in the coming disclosing embodiments. Denote the SGCS for sample s and layer I as SGCS, for s = 1,..., S and I = 1,..., vs, wherein vsis the rank associated with data sample s. SGCS may be calculated for each subband and / or prediction instance, or it may be averaged over subbands and / or prediction instances. The value of vsmay change for different samples as the channel may change over time. When the value of vschanges across the data samples for performance monitoring, there is uncertainty on how statistics of SGCS values for performance monitoring should be calculated by the UE.

[0120] In light of the above, embodiments herein disclose methods and apparatuses for calculating statistic of SGCS, such as a mean of SGCS, or x% CDF of SGCS, for performance monitoring. In embodiments below SGCS is used as an example, but for a person skilled in the art the sample-selection methodologies are directly applicable also to, e.g., x percentile of CDFs and other statistical measures.

[0121] In the following description and embodiments,

[0122] S = {Data sample #1, Data sample #2, Data sample #3,..., Data sample #S},

[0123] is the set of data samples for performance monitoring, as illustrated in Figure 4.

[0124] Based on layer grouping

[0125] In some embodiments, the statistic of SGCS for layer I is calculated based on data samples which are associated with a transmission rank larger than or equal to I.

[0126] The set of data samples that are associated with the rank larger than or equal to l is denoted as S'_l = {s ∈ S|vs≥ l}. The statistics of SGCS for layer I are then calculated only based on data samples from set S'_l. For example, if mean of SGCS is used as performance monitoring metric, then the mean SGCS of layer l, denoted as SGCSl, is given by

[0127]

[0128] In essence, this approach groups the data samples according to the layer index l. As long as a data sample contains CSI for layer l, then it is used for calculating the statistics of SGCS for layer l.

[0129] Based on rank groupingIn some other embodiments, if the performance monitoring report is for rank v, then the statistics of SGCS for layer I are calculated based on data samples which are associated with a rank that is larger than or equal to v.

[0130] This approach picks a subset of data samples that are at least with rank v for calculating statistics of SGCS for performance monitoring report of rank v. The set of data samples that are associated with at least rank v is denoted as S''_v = {s ∈ S|vs≥ v}. Then the statistics of SGCS for layer l are calculated based on data samples from set S''_v. For example, if mean of SGCS is used as performance monitoring metric, then the mean SGCS of layer l ≤ v and rank v, denoted as SGCSl,v, is given by

[0131]

[0132] where |S''_v| is the cardinality of sets.

[0133] In another embodiment, if performance monitoring report is for rank v, then the statistics of SGCS for layer I for the case of rank v are calculated based on data samples which are associated with a rank equal to v.

[0134] This approach groups data samples based on the associated rank value v for calculating statistics of SGCS for performance monitoring, and the statistics of SGCS are calculated per layer per rank. The set of data samples that are associated with rank v is denoted as S'''_v = {s ∈ S|vs= v}. The statistics of SGCS for layer l ≤ v and rank v are then calculated based on data samples from set S'''_v. For example, if mean of SGCS is used as performance monitoring metric, then the mean SGCS of layer l for the case of rank v, denoted as SGCSl,v, is given by

[0135]

[0136] where [S ' | is the cardinality of sets,',".

[0137] In some embodiments of the two embodiments related to rank-grouping, the one or more rank value(s) v to consider for monitoring is configured by the network. In some other embodiments, the rank value v is taken to be all the ranks (1, 2,...) that the UE is capable of receiving, as given by the UE capability. In some other embodiments, the selection of one or more rank value(s) v is up to UE implementation. The UE informs the network of the chosenrank value(s). In some other embodiments, the one or more rank value(s) to consider may be predefined as part of 3GPP specifications.

[0138] In some embodiments of the two embodiments related to rank-grouping, the UE computes SGCSt vfor all rank values v that have a non-empty set S'''_v (i.e., SGCSl,vcomputed if at least one data sample is associated with rank value v). The UE skips computation of SGCSl,v

[0139] for rank values v that have an empty set S" (i.e., SGCStiVcomputation is skipped if none of the data samples are associated with rank value v). In one embodiment, the UE reports to the network the computed statistics SGCStiVonly for rank values v that have a non-empty set S '. In an alternative embodiment, the UE reports the statistics SGCStiVfor all rank values v. In this alternative embodiment, a default value (e.g., ‘invalid’) is reported for SGCStiVfor rank values v that have an empty set S '.

[0140] Based on the maximum rank

[0141] In another embodiment, the maximum transmission rank over all data samples is used for calculation of statistics of SGCS.

[0142] For example, the maximum transmission rank may be denoted as vmax= max{v1,...,S}. In a related embodiment, when a data sample is associated with a rank that is lower than the maximum rank, the SGCS value(s) for said data sample that corresponds to the layers higher than the reported rank is replaced with a fixed value. Said fixed value may be predefined in 3GPP specifications, or it may be configured in the UE by the network.

[0143] For example, in Figure 4, data sample #2 is associated with rank v2= 1, and the maximum rank across all S data samples is vmax= max{v1,...,S} = 3. Then the value of SGCS for layer 2 and layer 3 for data sample #2, i.e., SGCS22and SGCS23respectively, is given by a fixed value, e.g., 0, i.e., SGCS22= SGCS23= 0. The mean SGCS for the S data samples for layer I may then be calculated as

[0144]

[0145] for l = 1,..., vmax.

[0146] In some further embodiments, the UE may inform the network about vmaxthrough standardized signalling. In some yet further embodiments, vmaxmay be implicitly inferred by the network based on the number of reported SGCStvalues. In yet another dependent embodiment, the UE has reported the predicted CSI to the network before or together with the monitoring results and vmaxis calculated by the network. In some further embodiments, vmaxmay be predefined as part of 3GPP specifications.

[0147] Based on minimum rankIn another embodiment, the minimum transmission rank over all data samples is used for calculation of statistics of SGCS. A UE is not expected to report SGCS corresponding to layer higher than the minimum rank.

[0148] For example, the minimum transmission rank may be denoted as vmin= min{v1,...,S}. In the example of Figure 4, the minimum rank is given by vmin= min{v1,...,S} = v2= 1, then the value of SGCS for the S data samples for layer I, for I = 1,...,vmin, may be calculated as

[0149]

[0150] for l = 1,...,vmin. A UE is not expected to report SGCS for layer larger than vmin.

[0151] In some further embodiments, the UE may inform the network about vminthrough standardized signalling. In some further embodiments, vminmay be implicitly inferred by the >

[0152] network based on the number of reported SGCStvalues. In yet some other embodiments, the UE reports the predicted CSI to the network before or together with the monitoring results and vminis calculated by the network. In some further embodiments, vminmay be predefined as part of 3GPP specifications.

[0153] Based on the rank restriction configuration from the NW

[0154] In some further embodiments, within the performance monitoring report configuration, the network indicates a rank value v such that the UE shall always generate the predicted CSI with rank v for all the configured monitoring data samples when calculating the statistics of SGCS. If such indication is not configured in the performance monitoring report configuration, then the UE shall derive and report the statistics of SGCS based on the minimum rank approach, or the UE shall only report the statistics of SGCS for the first layer.

[0155] Reporting of performance metric

[0156] Once the statistic of performance monitoring metric is calculated, e.g., mean of SGCS, or x% CDF value of SGCS, it may be quantized and reported to the network in a performance monitoring report.

[0157] Note that although the embodiments below are proposed for statistics-based performance monitoring metric, the same methods may also be used for per data samplebased performance monitoring.

[0158] In one embodiment, differential reporting of the performance monitoring metric over a layer is used, wherein the performance monitoring metric for at least one layer is reported relative to a reference value.In one example, the performance monitoring metric for layer l (l ≥ 2), is reported according to the performance monitoring metric for layer 1 plus an offset. In this case, the performance monitoring metric for layer 1 is said reference value.

[0159] In another example, the performance monitoring metric for layer l (l ≥ 1), is reported according to an average performance monitoring metric across all layers, plus an offset. In this case, the average performance monitoring metric is said reference value.

[0160] In some embodiments, differential reporting of performance monitoring metric over prediction instance (i.e., time) is used, wherein the performance monitoring metric for at least one time instance is reported relative to a reference value.

[0161] In one example, the performance monitoring metric for the prediction instance n4(n4> 2), is reported according to the performance monitoring metric for the first prediction instance plus an offset. In this case, the performance monitoring metric for the first prediction instance is said reference value.

[0162] In another example, the performance monitoring metric for prediction instance n4(n4> 1), is reported according to an average performance monitoring metric across all prediction instances, plus an offset. In this case, the average performance monitoring metric is said reference value.

[0163] In some embodiments, differential reporting of the performance monitoring metric over both prediction instance and layer is used.

[0164] For all the above embodiments, the offset value is quantized.

[0165] Generalization of the above embodiments

[0166] In any of the above embodiments, the number of data samples, |S| = #S, may be explicitly configured by the network.

[0167] In any of the above embodiments, the number of data samples, |S| = #S, may be indicated via the number of inference reports linked to the performance monitoring report based on the performance monitoring report configuration.

[0168] In any of the above embodiments, the number of data samples, |S| = #S, may be indicated via the CSI-RS resource set(s) configured for the performance monitoring report.

[0169] In any of the above embodiments, the number of data samples, |S| = #S, may be inferred from a time window, which may either be configured by the network or specified in 3GPP specifications.

[0170] In any of the above embodiments, the SGCS for layer I is per subband and / or per prediction instance.In any of the above embodiments, the SGCS for layer I is averaged over subbands and / or prediction instances.

[0171] For all of the above embodiments, the SGCS may be replaced with another performance monitoring metric that is calculated per layer, such as a Ml MO transmission layer, and / or per time instance.

[0172] For example, any real-valued function f(ppred,l, pground,l) such that ppred,lis a predicted precoder for layer l and pground,lis the corresponding ground-truth precoder for layer l, in suitable formats. Examples of such functions are, but not limited to, SGCS, GCS, and NMSE.

[0173] For example, any real-valued function f(ppred,l, pground) such that ppred,lis a predicted precoder for layer l and pground,lis the corresponding ground-truth precoder for all layers, in suitable formats. Example of such functions are, but not limited to, the principal angle between ppred,land the subspace spanned by the precoders in pground, for every subband.

[0174] In both the above examples, if the “weighted angles” are used, then there is a dependence on the corresponding matrix A. The matrix A may be taken to be dependent on the measured channel corresponding to the ground truth, e.g., the transmit correlation matrix HHH, and in such case the performance metric depends not only on the ground-truth PM I but also the corresponding ground-truth channel.

[0175] Any monotonously increasing or decreasing function, g, will have a one-to-one mapping to a corresponding single-sample performance monitoring metric value. However, when computing statistics over multiple samples, the results will be different if the function is nonlinear. Hence, for all of the above embodiments, and exemplified performance monitoring metrics, the per-sample performance monitoring metrics may be replaced by

[0176] g(performance monitoring metric), for any monotone function g. Examples of such functions, g, illustrated by application to SGCS, are log(SGCS), log(1 + SGCS), eSGCS, (SGCS)2, and in general (SGCS)afor any a ∈ ℝ.

[0177] Figure 5a illustrates a flow chart with the actions performed by a wireless communications device, such as a UE, for performance monitoring of Al-based CSI, such as e.g. performance monitoring related to CSI, according to some embodiments disclosed herein.

[0178] Action 501. The wireless communications device may receive from a network node, such as a base station, a performance monitoring configuration, e.g. comprising rank information, according to embodiments disclosed herein. The performance monitoring configuration may be for performance monitoring of Al-based CSI.In some embodiments (e.g. of the two embodiments related to rank-grouping), the one or more rank value(s) v to consider for monitoring is configured by the network node with the performance monitoring configuration.

[0179] The wireless communications device may select which data samples to use for the calculation of the performance monitoring metric based on a transmission rank of the data samples. The selection may be further based on a layer, such as a transmission layer, such as a MIMO transmission layer, and a transmission rank of the CSI prediction.

[0180] Action 502. The wireless communications device transmits, to a network node, a performance monitoring report comprising a performance monitoring metric, also referred to as a measure representing CSI. The measure representing channel state information is based on data samples which are selected based on a transmission rank of the data samples. The performance monitoring report may be for performance monitoring of Al-based CSI.

[0181] Figure 5b is a flow chart illustrating example embodiments of the method, with example actions performed by the wireless communications device, such as a UE. The method is for performance monitoring of Al-based CSI, such as e.g. performance monitoring related to CSI, according to some embodiments disclosed herein.

[0182] Action 901 The wireless communications device may receive from a network node, such as a base station, a performance monitoring configuration, e.g. comprising rank information, according to embodiments disclosed herein. Action 901 is performed similarly to action 501 as illustrated in Figure 5a.

[0183] Action 902 The wireless device selects data samples to be used based on a transmission rank of the data samples.

[0184] Action 903 The wireless device calculates a performance monitoring metric based on the selected data samples.

[0185] Action 904 The wireless device transmits, to a network node, a performance monitoring report comprising the performance monitoring metric. For example, the performance monitoring report may comprise the performance monitoring metric for CSI prediction that may be defined per layer. The performance monitoring metric may be for monitoring Al models for CSI prediction. Action 904 is performed similarly to action 502 as illustrated in Fig. 5a.

[0186] Figure 6 illustrates a flow chart with the actions performed by a network node, such as a base station, for performance monitoring of Al-based CSI, such as e.g. performance monitoring related to CSI, according to some embodiments disclosed herein.

[0187] Action 601. The network node may transmit to the wireless communications device, a performance monitoring configuration, e.g. comprising rank information, according to embodiments disclosed herein.Action 602. The network node receives the performance monitoring report comprising the measure representing channel state information. The measure representing channel state information is based on data samples which are selected based on a transmission rank of the data samples.

[0188] Figure 7 and Figure 8 illustrate further optional details of a wireless communications device 700 and a network node 800, such as a base station. The wireless communications device 700 is configured to perform some of the actions above, e.g. the method actions of Figure 5a and Figure 5b above. The network node 800 is configured to perform some of the actions described above, for example in relation to Figure 6.

[0189] The wireless communications device 700 is configured to perform performance monitoring related to CSI. The wireless communications device 700 is further configured to receive a performance monitoring configuration from the network node 800. The wireless communications device 700 is configured to select data samples to be used based on a transmission rank of the data samples. The wireless communications device 700 is further configured to calculate a performance monitoring metric based on the selected data samples. The wireless communications device 700 is further configured to transmit to a network node 800, a performance monitoring report comprising the performance monitoring metric.

[0190] The network node 800 is configured to perform performance monitoring related to CSI. The network node 800 is further configured to receive from a wireless communications device 700, a performance monitoring metric. The performance monitoring metric is based on data samples which are selected based on a transmission rank of the data samples.

[0191] The embodiments herein may be implemented through a processor or one or more processors, such as the processor 804, 704, of a processing circuitry in the network node 800 and the wireless communications device 700, together with computer program code for performing the functions and actions of the embodiments herein. The program code mentioned above may also be provided as a computer program product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the network node 800, and the wireless communications device 700. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the network node 800, and the wireless communications device 700.

[0192] The network node 800, and the wireless communications device 700 may further comprise a memory 802, 702, comprising one or more memory units. The memory comprisesinstructions executable by the processor in the network node 800, and the wireless communications device 700.

[0193] The respective memory 802, 902, is arranged to be used to store e.g. information, data, configurations, and applications to perform the methods herein when being executed in the network node 800, and the wireless communications device 700.

[0194] In some embodiments, a computer program 803, 703 comprises instructions, which when executed by the at least one processor, cause the at least one processor of the network node 800, and the wireless communications device 700 to perform the actions above.

[0195] In some embodiments, a carrier 805, 705 comprises the computer program, wherein the carrier is one of an electronic signal, an optical signal, an electromagnetic signal, a magnetic signal, an electric signal, a radio signal, a microwave signal, or a computer-readable storage medium.

[0196] The network node 800, and the wireless communications device 700 may further comprise an Input and Output interface (I / O) 806, 706, configured to communicate with other devices. The input and output interface 806, 706, may comprise a wireless transceiver.

[0197] Those skilled in the art will also appreciate that the units described above may refer to a combination of analog and digital circuits, and / or one or more processors configured with software and / or firmware, e.g. stored in the network node 800, and the wireless communications device 700, that when executed by the respective one or more processors such as the processors described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application-Specific Integrated Circuitry (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a system-on-a-chip (SoC).

[0198] When using the word "comprise" or “comprising” it shall be interpreted as non- limiting, i.e. meaning "consist at least of".

[0199] The embodiments herein are not limited to the above-described preferred embodiments. Various alternatives, modifications and equivalents may be used.

[0200] Figure 9, also referred to as Figure QQ1 shows an example of a communication system QQ100 in accordance with some embodiments.

[0201] In the example, the communication system QQ100 includes a telecommunications network QQ102 that includes an access network QQ104, such as a radio access network (RAN), and a core network QQ106, which includes one or more core network nodes QQ108. The access network QQ104 includes one or more access network nodes or base stations ofvarious types, access network nodes QQ110A and QQ110B are depicted (which may be collectively referred to as network nodes QQ110), or any other similar 3rd Generation Partnership Project (3GPP) access nodes or non-3GPP access points (APs). Some embodiments of the access network QQ104 may include more than one access network technology. The network nodes QQ110 of access network QQ104 facilitate direct or indirect connection of wireless devices, also referred to as user equipments (UEs), such as by connecting UEs QQ112A, QQ112B, QQ112C, and QQ112D (one or more of which may be generally referred to as UEs QQ112) to the core network QQ106 over one or more wireless connections.

[0202] Moreover, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunications network QQ102 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a network node in the telecommunications network QQ102 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other network nodes to implement one or more functionalities of any network node in the telecommunications network QQ102, including one or more access network nodes QQ110 and / or core network nodes QQ108.

[0203] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). An ORAN network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1, F1, W1, E1, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN network node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies.

[0204] The network nodes QQ110 facilitate direct or indirect connection of one or more UEs QQ112 to the core network QQ106 over one or more wireless connections. Example wireless communications over a wireless connection include transmitting and / or receiving wirelesssignals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system QQ100 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system QQ100 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0205] The UEs QQ112 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes QQ110 and other communication devices. Similarly, the network nodes QQ108, QQ110 are arranged, capable, configured, and / or operable to communicate directly or indirectly (e.g., via other devices of telecommunications network QQ102) with the UEs QQ112 and / or with other network nodes or equipment in the telecommunications network QQ102 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunications network QQ102. More specifically, UEs QQ112 may send messages, data, and / or other signals to network nodes QQ108, QQ110 or other elements of the telecommunications network QQ102 by transmitting such signals to the relevant device directly without the signals passing through any intervening devices or by transmitting such signals to the relevant device indirectly through an intervening device (or multiple intervening devices) that then transmit the signal to the relevant device. Similarly, network nodes QQ108, QQ110 may send messages, data, and other signals to UEs QQ1122, other network nodes QQ108, QQ110, and other devices in telecommunications network QQ102 directly or indirectly. As one specific example, a core network node 108 may transmit a particular message to a UE QQ112 by transmitting the message to an access network node QQ110 that will then transmit the message to the intended UE QQ112. Similarly, a core network node 108 may receive a particular message from a UE QQ112 by receiving the message from an access network node QQ110 that itself received the message from the UE QQ112.

[0206] In the depicted example, the core network QQ106 connects elements of the access network QQ104 (e.g., one or more of the network nodes QQ110) to one or more host computing systems, such as host QQ116. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network QQ106 includes one or more core network nodes (e.g., core network node QQ108) of various types, one or more of which may be generally referred to as network nodes QQ108. Network nodes QQ108 are structured with hardware andsoftware components. Features of these components may be substantially similar to those described with respect to the UEs, access network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node QQ108. Example core network nodes provide functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0207] The host QQ116 may be under the ownership or control of a service provider other than an operator or provider of the access network QQ104 and / or the telecommunications network QQ102. The host QQ116 may be operated by the service provider or on behalf of the service provider. The host QQ116 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance centre, or any other such function performed by a server.

[0208] As a whole, the communication system QQ100 of Figure 9 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system QQ100 may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM);

[0209] Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (Wi-Fi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (Wi-Max), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, Li-Fi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox. Moreover, the communication system QQ100 may be configured to support multiple different standards, protocols, or other rule sets, with individual components supporting all of the relevant rule sets or with different components or sub-systems within the communication system QQ100 supporting different standards, protocols, or rule sets.

[0210] As one example, in certain embodiments, access network QQ104 may contain some access network nodes QQ110 that support 3GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes QQ110 support (or the same access networknodes QQ110 additionally support) non-3GPP RATs, such as Wi-Fi or a proprietary RAT. As another example, telecommunications network QQ102 may support multiple generations of related communication standards (e.g., 4G and 5G 3GPP communication standards) and, as a result, may include an access network 104 and / or a core network 106 that supports multiple different standard generations or may include multiple access networks 104 and / or multiple core networks 106 with individual networks 104, 106 supporting different standard generations.

[0211] Telecommunications network QQ102 may support network slicing to provide different logical networks to different devices that are connected to the telecommunications network QQ102. For example, the telecommunications network QQ102 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0212] In some examples, one or more of the UEs QQ112 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network QQ104 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network QQ104. Additionally, a UE may be configured for operating in single- or multi-RAT or multistandard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0213] In the example, the hub QQ114 communicates with the access network QQ104 to facilitate indirect communication between one or more UEs (e.g., UE QQ112C and / or QQ112D) and network nodes (e.g., network node QQ110B). In some examples, the hub QQ114 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub QQ114 may be a broadband router enabling access to the core network QQ106 for the UEs. As another example, the hub QQ114 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes QQ110, or by executable code, script, process, or other instructions in the hub QQ114.

[0214] As another example, the hub QQ114 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub QQ114 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub QQ114 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub QQ114 then provides to the UE either directly, after performinglocal processing, and / or after adding additional local content. In still another example, the hub QQ114 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0215] The hub QQ114 may have a constant / persistent or intermittent connection to the network node QQ110B. The hub QQ114 may also allow for a different communication scheme and / or schedule between the hub QQ114 and UEs (e.g., UE QQ112C and / or QQ112D), and between the hub QQ114 and the core network QQ106. In other examples, the hub QQ114 is connected to the core network QQ106 and / or one or more UEs via a wired connection. Moreover, the hub QQ114 may be configured to connect to an M2M service provider over the access network QQ104 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes QQ110 while still connected via the hub QQ114 via a wired or wireless connection. In some embodiments, the hub QQ114 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node QQ110B. In other embodiments, the hub QQ114 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node QQ110B, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0216] Figure 10, also referred to as Figure QQ2 is another example of a communication system QQ200 according to some embodiments. As used herein, the communication system QQ200 includes multiple access points (APs) QQ210 (with four exemplary APs QQ210A, QQ210B, QQ210C, and QQ210D being depicted) and multiple wireless devices, referred to in the context of communication system QQ200 as stations (STAs) QQ212 (referred to individually as STA QQ212A, STA QQ212B, STA QQ212C, STA QQ212D, and STA QQ212E). STA QQ212A is served by AP QQ210A in a first basic service set (BSS) QQ220A. STA QQ210B and STA QQ210C are served by AP QQ210B in a second BSS, BSS QQ220B. STA QQ212D is served by AP QQ210C in a third BSS, BSS QQ220C. STA QQ212E is served by AP QQ210D in a fourth BSS, BSS QQ220D. Stations QQ212 may be non-AP STAs and correspond to various kinds of wireless devices, for example, user terminals, such as mobile or stationary computing devices like smartphones, laptop computers, desktop computers, tablet computers, gaming devices, head-mounted displays (HMDs) for Augmented Reality (AR) or Virtual Reality (VR), or the like. Further, stations QQ212 could, for example, correspond to other kinds of equipment like smart home devices, printers, multimedia devices, data storage devices, or the like.

[0217] Each of STAs QQ212 may connect through a radio link to one of APs QQ210. For example, depending on location or channel conditions experienced by a given STA QQ212, the STA may select an appropriate AP and BSS for establishing the radio link. The radio linkmay be based on one or more orthogonal frequency-division multiplexing (OFDM) carriers from a frequency spectrum that is shared on the basis of a contention-based mechanism, e.g., an unlicensed or license exempt band like 2.4 GHz Industrial, Scientific, and Medical (ISM) band, the 5 GHz band, the 6 GHz band, or the 60 GHz band.

[0218] Each AP QQ210 may provide data connectivity to STAs QQ212 connected to a particular AP QQ210. As illustrated, APs QQ210 may be connected to a data network QQ230. In this way, APs QQ210 may also provide data connectivity between STAs QQ212 and other entities, e.g., to one or more servers, service providers, data sources, data sinks, user terminals, or the like. Accordingly, the radio link established between a given STA QQ212 and its serving AP QQ210 may be used for providing various kinds of services to STA QQ212, e.g., a voice service, a multimedia service, or other data service. Such services may be based on applications that are executed on STA QQ212 and / or on a device linked to STA QQ212. By way of example, Figure 10 illustrates an application service platform QQ232 provided in data network QQ230. The application(s) executed on STA QQ212 and / or on one or more other devices linked to STA QQ212 may use the radio link for data communication with one or more other STA QQ212 and / or the application service platform QQ232, thereby enabling utilization of the corresponding service(s) at STA QQ212.

[0219] Figure 11, also referred to as Figure QQ3 shows a wireless device QQ300, which may be configured to operate in communication system QQ100 of Figure 9 or in communication system QQ200 of Figure 10. The wireless device QQ300 may be alternatively referred to as a UE QQ300, like a UE QQ112 within the context of communication system QQ100, or as a station (STA) QQ300 or as a non-access-point station (non-AP STA) QQ300, like a STA QQ212 within the context of the communication system QQ200, in accordance with respective embodiments. As used herein, a wireless device refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other wireless devices. Examples of a wireless device include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, and wireless terminal. Other examples include any type of UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.A wireless device QQ300 may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, wireless device QQ300 may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, wireless device QQ300 may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, wireless device QQ300 may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0220] In particular embodiments, wireless device QQ300 includes processing circuitry QQ302 that is operatively coupled via a bus QQ304 to an input / output interface QQ306, a power source QQ308, a memory QQ310, a communication interface QQ312, and / or any other component, or any combination thereof. Certain embodiments of wireless device QQ300 may include all or a subset of the components shown in Figure 11. The level of integration between the components may vary from one embodiment of wireless device QQ300 to another. In general, in a particular embodiment of wireless device QQ300, processing circuitry QQ302, input / output interface QQ306, power source QQ308, memory QQ310, and communication interface QQ312 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of wireless device QQ300. Further, certain embodiments of wireless devices QQ300 may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0221] The processing circuitry QQ302 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory QQ310. The processing circuitry QQ302 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry QQ302 may include multiple central processing units (CPUs).

[0222] In the example, the input / output interface QQ306 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or anycombination thereof. An input device may allow a user to capture information into wireless device QQ300. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0223] In some embodiments, the power source QQ308 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used to supply power to circuitry or to charge an associated battery. The power source QQ308 may further include power circuitry for delivering power from the power source QQ308 itself, and / or an external power source, to the various parts of wireless device QQ300 via input circuitry or an interface such as an electrical power cable. Power source QQ308 may perform any formatting, converting, or other modification to make accessible power suitable for the respective components of the wireless device QQ300 to which power is supplied.

[0224] The memory QQ310 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory QQ310 includes one or more programs QQ314, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data QQ316. The memory QQ310 may store, for use by wireless device QQ300, any of a variety of various operating systems or combinations of operating systems.

[0225] The memory QQ310 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / orISIM, other memory, or any combination thereof. The IIICC may for example be an embedded IIICC (elllCC), integrated IIICC (illlCC) or a removable IIICC commonly known as ‘SIM card.’ The memory QQ310 may allow wireless device QQ300 to access instructions, programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory QQ310, which may be or comprise a device-readable storage medium.

[0226] The processing circuitry QQ302 may be configured to communicate with an access network or other network via or using the communication interface QQ312. The communication interface QQ312 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna QQ322. The communication interface QQ312 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another wireless device or a network node in an access network). Each transceiver may include a transmitter QQ318 and / or a receiver QQ320 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter QQ318 and receiver QQ320 may be coupled to one or more antennas (e.g., antenna QQ322) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0227] In the illustrated embodiment, communication functions of the communication interface QQ312 may include cellular communication, Wi-Fi communication (e.g., according to an IEEE 802.11 family standard), LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0228] In particular embodiments, wireless device QQ300 may provide an output of data captured via a sensor, through its communication interface QQ312, via a wireless connection to a network node, and / or in any appropriate manner. Data captured by sensors of a wireless device QQ300 can be communicated through a wireless connection to a network node via another wireless device QQ300. In particular embodiments, such output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the loadfrom reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0229] As another example, wireless device QQ300 comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, wireless device QQ300 may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0230] Wireless device QQ300, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. In particular embodiments, wireless device QQ300 represents an loT device that comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the example embodiment of wireless device QQ300 shown in Figure 11.

[0231] As yet another specific example, in an loT scenario, wireless device QQ300 may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another wireless device and / or a network node. Wireless device QQ300 may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, wireless device QQ300 may implement the 3GPP NB-loT standard. In other scenarios, wireless device QQ300 may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.In practice, any number of wireless devices QQ300 may be used together with respect to a single use case. For example, a first wireless device QQ300 might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second wireless device QQ300 that is a remote controller operating the drone. When a user makes changes from the remote controller, the first wireless device QQ300 may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second wireless device QQ300 can also include more than one of the functionalities described above. For example, wireless device QQ300 might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0232] Figure 12, also referred to as Figure QQ4 shows a network node QQ400 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunications network. In accordance with respective embodiments, network node QQ400 may be configured to operate in communication system QQ100 of Figure 9, like network nodes QQ108 or QQ110, or in communication system QQ200 of Figure 10, like an AP QQ210 or a station QQ212. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0233] Network nodes QQ400 may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. Network node QQ400 may be a relay node or a relay donor node controlling a relay. Network nodes QQ400 may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0234] Other examples of network nodes QQ400 include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O& M) nodes, Operations SupportSystem (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0235] In particular embodiments, network node QQ400 includes a processing circuitry QQ402, a memory QQ404, a communication interface QQ406, and a power source QQ408. In general, in a particular embodiment of network node QQ400, processing circuitry QQ402, memory QQ404, communication interface QQ406, and power source QQ408 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of network node QQ400.

[0236] The network node QQ400 may be composed of multiple distinct network entities (e.g., a NodeB entity and a RNC entity, or a BTS entity and a BSC entity, etc.), which may each have or utilize their own respective physical components. In certain scenarios in which the network node QQ400 comprises multiple such entities (e.g., BTS and BSC), one or more of the separate entities may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node QQ400 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memories QQ404 or portions of memory QQ404 for different RATs) and some components may be reused (e.g., a same antenna QQ410 may be shared by different RATs). The network node QQ400 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node QQ400, for example GSM, WCDMA, LTE, NR, Wi-Fi (e.g., according to an IEEE 802.11 family standard), Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node QQ400.

[0237] The processing circuitry QQ402 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other components, such as the memory QQ404, to provide network node QQ400 functionality.

[0238] In some embodiments, the processing circuitry QQ402 includes a system on a chip (SOC). In some embodiments, the processing circuitry QQ402 includes one or more of radio frequency (RF) transceiver circuitry QQ412 and baseband processing circuitry QQ414. In some embodiments, the RF transceiver circuitry QQ412 and the baseband processing circuitry QQ414 may be on separate chips (or sets of chips), boards, or units, such as radio units anddigital units. In alternative embodiments, part or all of RF transceiver circuitry QQ412 and baseband processing circuitry QQ414 may be on the same chip or set of chips, boards, or units.

[0239] The memory QQ404 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry QQ402. The memory QQ404 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry QQ402 and utilized by the network node QQ400. The memory QQ404 may be used to store any calculations made by the processing circuitry QQ402 and / or any data received via the communication interface QQ406. In some embodiments, the processing circuitry QQ402 and memory QQ404 is integrated.

[0240] The communication interface QQ406 is used in wired or wireless communication of signaling and / or data with UEs, other network nodes, and / or any other network equipment. In the illustrated embodiment, communication interface QQ406 comprises port(s) / terminal(s) QQ416 to send and receive data, for example to and from a network over a wired connection. In particular embodiments, network node QQ300 may be capable of wireless communication and communication interface QQ406 may also include radio front-end circuitry QQ418 that may be coupled to, or in certain embodiments a part of, an antenna QQ410. Particular embodiments of radio front-end circuitry QQ418 include filter(s) QQ420 and amplifier(s) QQ422. The radio front-end circuitry QQ418 may be connected to an antenna QQ410 and processing circuitry QQ402. The radio front-end circuitry may be configured to condition signals communicated between antenna QQ410 and processing circuitry QQ402. The radio front-end circuitry QQ418 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry QQ418 may convert the digital data into a radio signal(s) having the appropriate channel and bandwidth parameters using a combination of filters QQ420 and / or amplifiers QQ422. The radio signal(s) may then be transmitted via the antenna QQ410. Similarly, when receiving data, the antenna QQ410 may collect radio signals which are then converted into digital data by the radio front-end circuitry QQ418. The digital data may be passed to the processing circuitry QQ402. In otherembodiments, the communication interface may comprise different components and / or different combinations of components.

[0241] In certain alternative embodiments, network node QQ400 may be capable of wireless communication but does not include separate radio front-end circuitry QQ418, instead, the processing circuitry QQ402 includes radio front-end circuitry and is connected to the antenna QQ410. Similarly, in some embodiments, all or some of the RF transceiver circuitry QQ412 is part of the communication interface QQ406. In still other embodiments, the communication interface QQ406 includes one or more ports or terminals QQ416, the radio front-end circuitry QQ418, and the RF transceiver circuitry QQ412, as part of a radio unit (not shown), and the communication interface QQ406 communicates with the baseband processing circuitry QQ414, which is part of a digital unit (not shown).

[0242] The antenna QQ410 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna QQ410 may be coupled to the radio front-end circuitry QQ418 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna QQ410 is separate from the network node QQ400 and connectable to the network node QQ400 through one or more interfaces or ports.

[0243] The antenna QQ410, communication interface QQ406, and / or the processing circuitry QQ402 may be configured to perform some or all of the receiving operations and / or obtaining operations described herein as being performed by the network node QQ400. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna QQ410, the communication interface QQ406, and / or the processing circuitry QQ402 may be configured to perform some or all of the transmitting or sending operations described herein as being performed by the network node QQ400. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0244] The power source QQ408 provides power to the various components of network node QQ400 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source QQ408 may further comprise, or be coupled to, power management circuitry to supply the components of the network node QQ400 with power for performing the functionality described herein. For example, the network node QQ400 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source QQ408. As a further example, the power source QQ408 may comprise a source of power in the form of abattery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0245] Embodiments of the network node QQ400 may include additional components beyond those shown in Figure 12 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node QQ400 may include user interface equipment to allow input of informationusus into the network node QQ400 and to allow output of information from the network node QQ400. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node QQ400.

[0246] Figure 13, also referred to as Figure QQ5 is a block diagram illustrating a virtualization environment QQ500 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments QQ500 hosted by one or more of hardware nodes, such as a hardware computing device that operates as an access network node, UE, core network node, or host. Further, in embodiments in which a virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment QQ500 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an 0-2 interface.

[0247] Applications QQ502 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0248] Hardware QQ504 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers QQ506 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VM QQ508A and VM QQ508B (which may be collectively referred to as VMs QQ508), and / or perform any of the functions, features and / or benefits described in relation with someembodiments described herein. The virtualization layer QQ506 may present a virtual operating platform that appears like networking hardware to one or more of the VMs QQ508.

[0249] The VMs QQ508 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by virtualization layer QQ506. Different embodiments of the instance of a virtual appliance QQ502 may be implemented on one or more of VMs QQ508, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0250] In the context of NFV, each of the VMs QQ508 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs QQ508, and that part of hardware QQ504 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more of the VMs QQ508 on top of the hardware QQ504 and corresponds to an application QQ502.

[0251] Hardware QQ504 may be implemented in a standalone network node with generic or specific components. Hardware QQ504 may implement some functions via virtualization. Alternatively, hardware QQ504 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration QQ510, which, among others, oversees lifecycle management of applications QQ502. In some embodiments, hardware QQ504 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system QQ512 which may alternatively be used for communication between hardware nodes and radio units.

[0252] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processingcircuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0253] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0254] Numbered embodiments:

[0255] Embodiment 1. A method, performed by a wireless communications device, for performance monitoring, e.g. performance monitoring related to CSI, such as of CSI prediction. The same or a similar method may also be applied to performance monitoring of UE-sided model of other use cases, for example, UE-sided model of the two-sided CSI compression use case and CSI-RS overhead reduction using UE-sided models. The CSI may be Al-based.

[0256] The method comprises transmitting, to a network node, a performance monitoring report comprising a performance monitoring metric, e.g. for CSI prediction, e.g. defined per layer. The performance monitoring metric may be for monitoring Al models for CSI prediction. The performance monitoring metric is based on data samples which are selected based on a transmission rank of the data samples.Embodiment 2. The method according to embodiment 1, wherein the performance monitoring metric is a statistical measure, such as SGCS.

[0257] Embodiment 3. The method according to embodiment 2, wherein the statistics of the statistical measure for a layer I is calculated based on data samples which are associated with a transmission rank larger than or equal to I.

[0258] Embodiment 4. The method according to embodiment 2 or 3, wherein the statistics of the statistical measure for layer I is calculated based on data samples which comprise a CSI for layer I.

[0259] Embodiment 5. The method according to any of the embodiments 2-4, wherein the statistical measure is for a first transmission rank v, and wherein the statistics of the statistical measure for layer I is calculated based on data samples which are associated with a second rank that is larger than or equal to the first transmission rank v.

[0260] Embodiment 6. The method according to any of the embodiments 2-5, wherein the statistical measure is based on a maximum transmission rank over all data samples.

[0261] Embodiment 7. The method according to embodiment 6, wherein a data sample is associated with a rank that is lower than the maximum rank, and wherein the performance monitoring metric for said data sample that corresponds to layers higher than the reported rank is replaced with a fixed value in the performance monitoring report.

[0262] Embodiment 8. The method according to any of the embodiments 2-7, wherein the statistical measure is based on a minimum transmission rank over all data samples.

[0263] Embodiment 9. The method according to embodiment 8, wherein the performance monitoring metric is based on layers lower or equal to the minimum transmission rank.

[0264] Embodiment 10. A method, performed by a network node, for performance monitoring, e.g. performance monitoring related to CSI, such as of CSI prediction. The same or a similar method may also be applied to performance monitoring of UE-sided model of other use cases, for example, UE-sided model of the two-sided CSI compression use case and CSI-RS overhead reduction using UE-sided models. The CSI may be Al-based. The method comprises receiving, from a wireless communications device, a performance monitoring metric, e.g. for CSI prediction, e.g. defined per layer. The performance monitoring metric may be for monitoring Al models for CSI prediction. The performance monitoring metric is based on data samples which are selected based on a transmission rank of the data samples.

[0265] Embodiment 11. A wireless communications device configured to perform the method according to any of embodiments 1-10.

[0266] Embodiment 12. A network node configured to perform the method according to embodiment 10.Embodiment 13. A computer program, comprising computer readable code units which when executed on a computer causes the computer to perform the method according to any of the embodiments 1-10.

[0267] Embodiment 14. A carrier comprising the computer program according to the preceding embodiment, wherein the carrier is one of an electronic signal, an optical signal, a radio signal and a computer readable medium.

Claims

CLAIMS1. A method, performed by a wireless communications device (700), for performance monitoring, related to Channel State Information, CSI, the method comprising:selecting (902) data samples to be used based on a transmission rank of the data samples,calculating (903) a performance monitoring metric based on the selected data samples,transmitting (502, 904) to a network node (800), a performance monitoring report comprising the performance monitoring metric.

2. The method according to claim 1, wherein the method comprises:receiving (501, 901), from the network node (800), a performance monitoring configuration.

3. The method according to claim 1, wherein the performance monitoring metric is a statistical measure, such as Squared Generalized Cosine Similarity, SGCS.

4. The method according to claim 2, wherein the statistics of the statistical measure for a layer I is calculated based on data samples which are associated with a transmission rank larger than or equal to I.

5. The method according to claim 2 or 3, wherein the statistics of the statistical measure for layer I is calculated based on data samples which comprise a CSI for layer I.

6. The method according to any of the claims 2-4, wherein the statistical measure is for a first transmission rank v, and wherein the statistics of the statistical measure for layer I is calculated based on data samples which are associated with a second rank that is larger than or equal to the first transmission rank v.

7. The method according to any of the claims 2-5, wherein the statistical measure is based on a maximum transmission rank over all data samples.

8. The method according to claim 6, wherein a data sample is associated with a rank that is lower than the maximum rank, and wherein the performance monitoring metric for saiddata sample that corresponds to layers higher than the reported rank is replaced with a fixed value in the performance monitoring report.

9. The method according to any of the claims 2-7, wherein the statistical measure is based on a minimum transmission rank over all data samples.

10. The method according to claim 8, wherein the performance monitoring metric is based on layers lower or equal to the minimum transmission rank.

11. A method, performed by a network node (800), for performance monitoring related to CSI, the method comprising:receiving (602), from a wireless communications device (700), a performance monitoring metric, wherein the performance monitoring metric is based on data samples which are selected based on a transmission rank of the data samples.

12. The method according to claim 11, wherein the method comprises:transmitting (601) a performance monitoring configuration to the wireless device.

13. A wireless communications device (700) configured to perform the method according to any of claims 1-10.

14. A network node (800) configured to perform the method according to any of the claims 11- 12.

15. A computer program (703, 803), comprising computer readable code units which when executed on a computer causes the computer to perform the method according to any of the claims 1-12.

16. A carrier (705, 805) comprising the computer program (703, 803) according to the preceding claim, wherein the carrier (705, 805) is one of an electronic signal, an optical signal, a radio signal and a computer readable medium.