Selecting user equipment to provide measurements for network training of ai / ML models

Abstract

Embodiments include methods performed by a management node configured for use in a communication network. Such methods include determining a first set of conditions related to selection of user equipment (UEs) for minimization of drive testing (MDT) measurements to be used for training artificial intelligence / machine learning (AI / ML) models, and sending the first set of conditions to a radio access network (RAN) node that serves at least one UE. In some embodiments, such methods also include receiving one or more of the following MDT measurements, for one or more served UEs selected by the RAN node in accordance with the first set of conditions: MDT measurements performed by the RAN node on the selected UEs; MDT measurements performed by the selected UEs; and predicted MDT measurements. Other embodiments include complementary methods for RAN nodes and UEs, as well as management nodes, RAN nodes, and UEs configured to perform such methods.

Description

[0001] SELECTING USER EQUIPMENT TO PROVIDE MEASUREMENTS FOR NETWORK TRAINING OF AI / ML MODELS

[0002] TECHNICAL FIELD

[0003] The present disclosure relates generally to communication networks, and more specifically to techniques for collecting training data for artificial intelligence / machine learning (AI / ML) models used to improve communication between user equipment (UEs) and a network.

[0004] BACKGROUND

[0005] Currently the fifth generation (5G) of cellular systems, also referred to as New Radio (NR), is being standardized within the Third-Generation Partnership Project (3GPP). 5G / NR is developed for maximum flexibility to support multiple and substantially different use cases. These include enhanced mobile broadband (eMBB), machine type communications (MTC), ultra-reliable low latency communications (URLLC), side-link device-to-device (D2D), and several other use cases. NR was initially specified in Rel-15 and continues to evolve through subsequent releases.

[0006] Figure 1 shows a high-level view of an exemplary 5G network architecture, including a next-generation RAN (NG-RAN, 199) and a 5G core network (5GC, 198). As shown in the figure, the NG-RAN can include gNBs (e.g., 110a, b) and ng-eNBs (e.g, 110a, b) that are interconnected with each other via respective Xn interfaces. The gNBs and ng-eNBs are also connected via the NG interfaces to the 5GC, more specifically to access and mobility management functions (AMFs, e.g, 130a, b) via respective NG-C interfaces and to user plane functions (UPFs, e.g, 140a, b) via respective NG-U interfaces. Moreover, AMFs can communicate with one or more policy control functions (PCFs, e.g., 150a, b) and network exposure functions (NEFs, e.g., 160a, b).

[0007] Each of the gNBs can support the NR radio interface including frequency division duplexing (FDD), time division duplexing (TDD), or a combination thereof. Each of ng-eNBs can support the fourth generation (4G) Long-Term Evolution (LTE) radio interface but unlike conventional LTE eNBs, ng-eNBs connect to the 5GC via the NG interface. Each of the gNBs and ng-eNBs can serve a geographic coverage area including one or more cells (e.g., 11 la-b and 121a-b shown in Figure 1). Depending on the cell in which it is located, a UE (e.g., 105 in Figure 1) can communicate with the gNB or ng-eNB serving that cell via the NR or LTE radio interface, respectively. Although Figure 1 shows gNBs and ng-eNBs separately, it is also possible that a single NG-RAN node provides both types of functionality.

[0008] Although not shown explicitly, each gNB in Figure 1 may include a Central Unit (CU or gNB-CU) and one or more Distributed Units (DUs or gNB-DUs). CUs are logical nodes that host higher-layer protocols and perform various gNB functions such as controlling operation of DUs. In contrast, DUs are decentralized logical nodes that host lower layer protocols and can include, depending on the functional split option, various subsets of the gNB functions. Each CU and DU can include various circuitry needed to perform their respective functions, including processing circuitry, communication interface circuitry (e.g., transceivers), and power supply circuitry.

[0009] UEs and RAN nodes (e.g., gNBs) can be configured to perform and report measurements to support minimization of drive testing (MDT), which is intended to reduce and / or minimize the requirements for manual testing of network performance by driving around the geographic coverage of the network. The MDT feature was first studied in Long-Term Evolution (LTE) Rel- 9 (e.g., 3GPP TR 36.805 v9.0.0), first standardized for LTE in Rel-10, and is also supported for 5G / NR. MDT can address various network performance improvements such as coverage optimization, capacity optimization, mobility optimization, quality-of-service (QoS) verification, and parameterization for common channels (e.g., PDSCH).

[0010] In general, MDT measurements can be management-based or signaling-based. In management-based MDT, data is collected from UEs in a specified area defined as a list of cells or as a list of tracking / routing / location areas. RAN nodes (e.g., gNBs) selects UEs for which MDT measurements are configured, collected, and reported to the trace collection entity (TCE). In signaling-based MDT, data is collected from a specific UE as specified by an IMEI(SV) or an IMSI. A management system (e.g., 0AM) selects the particular UE to collect and report MDT measurements.

[0011] Machine learning (ML) is a type of artificial intelligence (Al) that focuses on the use of data and algorithms to imitate the way that humans leam, gradually improving its accuracy. ML algorithms build models based on sample (or “training”) data, with the models being used subsequently to make predictions or decisions. ML algorithms can be used in a wide variety of applications (e.g., medicine, email filtering, speech recognition, etc.) in which it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.

[0012] AI / ML can be used to enhance the performance of a RAN, such as NG-RAN. One example use case is autoencoders for compressing channel state information (CSI) feedback to reduce overhead and improve channel prediction accuracy. Another example use case is using deep neural networks (DNNs) for detecting or classifying line-of-sight (LOS) and non-NLOS conditions to improve accuracy of RAN-based positioning of UEs. Another example use case is using reinforcement learning (RL) for beam selection by UE or RAN, thereby reducing signaling overhead and beam alignment latency. Another example use case is using deep RL to leam or determine an optimal policy for complex multiple-input multiple-output (MIMO) precoding. 3GPP document RP-213599 describes a Rel-18 study item that explored these and related use cases for AI / ML augmentation of radio interface features. AI / ML models used to enhance RAN performance are often trained based on actual data collected from the RAN and / or from UEs being served by the RAN. Training of AI / ML models may be performed by the network (e.g., by a RAN node or by a specific node in the core network), by the UE, or by a combination thereof.

[0013] SUMMARY

[0014] Even so, there are some problems, issues, and / or difficulties when management-based MDT is used to collect data used for network-side training of AI / ML models. For example, while the management system may identify an area scope for MDT collection, the RAN is responsible for selecting UEs to collect the MDT measurements. However, the state and / or condition of individual UEs being configured for MDT measurement collection may affect the measurements collected and consequently the training of the AI / ML models on such measurements. This may result in unpredictable and / or undesirable model behavior when used for inference or prediction.

[0015] An object of embodiments of the present disclosure is to address the problems, issues, and / or difficulties summarized above and described in more detail below. Embodiments may address these problems, issues, and / or difficulties by techniques for a management node to determine a set of conditions and / or criteria for RAN nodes to selecting served UEs to configure MDT measurement collection, as described in more detail below.

[0016] Embodiments include methods e.g., procedures) performed by a management node configured for use in a communication network.

[0017] These exemplary methods include determining a first set of conditions related to selection of UEs for MDT measurements to be used for training AI / ML models. These exemplary methods also include sending the first set of conditions to a RAN node that serves at least one UE. In some embodiments, these exemplary methods also include receiving one or more of the following MDT measurements, for one or more served UEs selected by the RAN node in accordance with the first set of conditions:

[0018] • MDT measurements performed by the RAN node on the selected UEs;

[0019] • MDT measurements performed by the selected UEs; and

[0020] • predicted MDT measurements.

[0021] In some embodiments, these exemplary methods also include receiving from the RAN node an indication that one or more conditions of the first set have been fulfilled and, based on the indication, sending to the RAN node an MDT measurement configuration that specifies MDT measurements to be collected. The received MDT measurements are based on the MDT measurement configuration. In some embodiments, these exemplary methods also include training one or more AI / ML models based on the received MDT measurements.

[0022] Other embodiments include methods (e.g., procedures) performed by a RAN node configured for use in a communication network. In general, these exemplary methods are complementary to the exemplary methods performed by an management node, summarized above.

[0023] These exemplary methods include receiving from a management node a first set of conditions related to selection of UEs for MDT measurements to be used for training AI / ML models. These exemplary methods also include selecting one or more UEs, served by the RAN node, for MDT measurements in accordance with the first set of conditions. These exemplary methods also include initiating one or more MDT measurements with respect to the selected UEs.

[0024] In some embodiments, the one or more MDT measurements initiated with respect to the selected UEs include one or more of the following:

[0025] • MDT measurements by the RAN node on the selected UEs,

[0026] • MDT measurements by the selected UEs, and

[0027] • predicted MDT measurements.

[0028] In some embodiments, these exemplary methods also include determining one or more of the following based on the received first set of conditions: a UE monitoring configuration, and a RAN monitoring configuration. In some of these embodiments, these exemplary methods also include sending the UE monitoring configuration to a plurality of UEs served by the RAN node and receiving one of the following from the one or more UEs, in accordance with the UE monitoring configuration: an indication that at least one condition of the first set has been fulfilled, and UE monitoring measurements. In such embodiments, selecting the one or more UEs is based on the received indication or the received UE monitoring measurements.

[0029] In other of these embodiments, these exemplary methods also include initiating RAN monitoring measurements for the plurality of UEs based on the RAN monitoring configuration and determining, based on the RAN monitoring measurements, that the one or more UEs have fulfilled at least one condition of the first set. In such embodiments, selecting the one or more UEs is based on the determination.

[0030] In some embodiments, selecting the one or more UEs is further based on a second set of conditions associated with the RAN node, including conditions on one or more of the following:

[0031] • RAN node capability of handling multiple MDT measurement sessions,

[0032] • UE capability or configurations need to perform the MDT measurements, and

[0033] • radio interface capacity available to handle UE reporting of MDT measurements. In some embodiments, these exemplary methods also include sending to the management node an indication that one or more conditions of the first set have been fulfilled and, in response to the indication, receiving from the management node an MDT measurement configuration that specifies MDT measurements to be collected. In such embodiments, the MDT measurements are initiated based on the MDT measurement configuration.

[0034] Other embodiments include methods (e g., procedures) performed by a UE configured for use in a communication network. In general, these exemplary methods are complementary to the exemplary methods performed by a management node and a RAN node, summarized above.

[0035] These exemplary methods include, based on a determination that the UE fulfills at least one condition of a first set of conditions related to selection of UEs for MDT measurements to be used for training AI / ML models, receiving an MDT configuration from a RAN node serving the UE. The MDT configuration includes an MDT measurement configuration and an MDT reporting configuration. These exemplary methods also include performing or predicting MDT measurements in accordance with the MDT measurement configuration. These exemplary methods also include sending the MDT measurements to a management node, in accordance with the MDT reporting configuration

[0036] In some embodiments, the exemplary method also includes the following operations:

[0037] • receiving from the RAN node a UE monitoring configuration, wherein the UE monitoring configuration includes a measurement configuration and a reporting configuration; and

[0038] • performing or predicting monitoring measurements in accordance with the UE monitoring configuration.

[0039] In some of these embodiments, these exemplary methods also include sending the monitoring measurements to the RAN node in accordance with the reporting configuration. The MDT configuration is received from the RAN node in response to the RAN node determining, based on the reported monitoring measurements, that the UE fulfills at least one condition of the first set.

[0040] In other of these embodiments, the UE monitoring configuration includes one or more conditions of the first set and these exemplary methods also include the following operations:

[0041] • determining, from the monitoring measurements, that the UE fulfills at least one condition included in the UE monitoring configuration; and

[0042] • sending, to the RAN node, an indication that the UE fulfills the at least one condition of the first set.

[0043] In such embodiments, the MDT configuration is received from the RAN node in response to the indication. In any of the embodiments summarized above, the first set of conditions can include various content and / or have various characteristics, which are described in more detail herein.

[0044] Other embodiments of the exemplary methods summarized above are described herein. Other embodiments include management nodes (e.g., OAM systems, SMOs, etc.), RAN nodes (e.g., base stations, eNBs, gNBs, etc.), and UEs (e.g., wireless devices) configured to perform operations of exemplary methods described herein. Other embodiments include non-transitory, computer-readable media storing program instructions that, when executed by processing circuitry, configure such management nodes, RAN nodes, and UEs to perform operations of the exemplary methods described herein.

[0045] These and other embodiments described herein may provide various benefits and / or advantages. For example, embodiments may facilitate a management node to observe UE performance and obtain UE measurements in different conditions, such as different levels or quality of radio coverage. Such measurements may then be used by the management node to train AI / ML models specific to each of the different conditions. At a high level, embodiments may improve the training of AI / ML models used to enhance performance of the radio interface between UEs and RAN nodes. As such, embodiments may improve various performance criteria of this radio interface, such as latency, reliability, bandwidth, etc.

[0046] These and other objects, features, and advantages of embodiments of the present disclosure will become apparent upon reading the following Detailed Description in view of the Drawings briefly described below.

[0047] BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 shows a high-level view of an exemplary 5G / NR network architecture.

[0049] Figure 2 is a block diagram of an exemplary framework for AI / ML model use in a RAN.

[0050] Figure 3 shows exemplary AI / ML model training and inference pipelines, along with their interactions during a model LCM procedure.

[0051] Figure 4 illustrates an exemplary channel state information (CSI) autoencoder based on a two-sided AI / ML model.

[0052] Figure 5 shows an exemplary procedure for management-based MDT activation in NG- RAN for the case of non-split RAN node architecture.

[0053] Figure 6 is a flow diagram of an exemplary method (e.g., procedure) for a management node, according to some embodiments of the present disclosure.

[0054] Figure 7 is a flow diagram of an exemplary method (e.g., procedure) for a RAN node, according to some embodiments of the present disclosure. Figure 8 is a flow diagram of an exemplary method (e.g., procedure) for a UE, according to some embodiments of the present disclosure.

[0055] Figure 9 shows a communication system according to some embodiments of the present disclosure.

[0056] Figure 10 shows a UE according to some embodiments of the present disclosure.

[0057] Figure 11 shows a network node according to some embodiments of the present disclosure.

[0058] Figure 12 is a block diagram of a virtualization environment in which functions implemented by some embodiments of the present disclosure may be virtualized.

[0059] DETAILED DESCRIPTION

[0060] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided as examples to convey the scope of the subject matter to those skilled in the art.

[0061] In general, all terms used herein are to be interpreted according to their ordinary meaning to a person of ordinary skill in the relevant technical field, unless a different meaning is expressly defined and / or implied from the context of use. All references to a / an / the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise or clearly implied from the context of use. The operations of any methods and / or procedures disclosed herein do not have to be performed in the exact order disclosed, unless an operation is explicitly described as following or preceding another operation and / or where it is implicit that an operation must follow or precede another operation. Any feature of any embodiment disclosed herein can apply to any other disclosed embodiment, as appropriate. Likewise, any advantage of any embodiment described herein can apply to any other disclosed embodiment, as appropriate.

[0062] Furthermore, the following terms are used throughout the description given below:

[0063] • Radio Access Node: As used herein, a “radio access node” (or equivalently “radio network node,” “radio access network node,” or “RAN node”) can be any node in a radio access network (RAN) that operates to wirelessly transmit and / or receive signals. Some examples of a radio access node include, but are not limited to, a base station (e.g., gNB in a 3GPP 5G / NR network or an enhanced or eNB in a 3 GPP LTE network), base station distributed components (e.g, CU and DU), a high-power or macro base station, a low-power base station (e.g., micro, pico, femto, or home base station, or the like), an integrated access backhaul (IAB) node, a transmission point (TP), a transmission reception point (TRP), a remote radio unit (RRU or RRH), and a relay node.

[0064] • Core Network Node: As used herein, a “core network node” is any type of node in a core network. Some examples of a core network node include, e.g., a Mobility Management Entity (MME), a serving gateway (SGW), a PDN Gateway (P-GW), a Policy and Charging Rules Function (PCRF), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a Charging Function (CHF), a Policy Control Function (PCF), an Authentication Server Function (AUSF), a location management function (LMF), or the like.

[0065] • Wireless Device: As used herein, a “wireless device” (or “WD” for short) is any type of device that is capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other wireless devices. Communicating wirelessly can involve transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information through air. Unless otherwise noted, the term “wireless device” is used interchangeably herein with the term “user equipment” (or “UE” for short), with both of these terms having a different meaning than the term “network node”.

[0066] • Radio Node: As used herein, a “radio node” can be either a “radio access node” (or equivalent term) or a “wireless device.”

[0067] • Network Node: As used herein, a “network node” is any node that is either part of the radio access network (e.g., a radio access node or equivalent term) or of the core network (e.g., a core network node discussed above) of a cellular communications network. Functionally, a network node is equipment capable, configured, arranged, and / or operable to communicate directly or indirectly with a wireless device and / or with other network nodes or equipment in the cellular communications network, to enable and / or provide wireless access to the wireless device, and / or to perform other functions (e.g, administration) in the cellular communications network.

[0068] • Node: As used herein, the term “node” (without prefix) can be any type of node that can in or with a wireless network (including RAN and / or core network), including a radio access node (or equivalent term), core network node, or wireless device. However, the term “node” may be limited to a particular type (e.g., radio access node, IAB node) based on its specific characteristics in any given context.

[0069] The above definitions are not meant to be exclusive. In other words, various ones of the above terms may be explained and / or described elsewhere in the present disclosure using the same or similar terminology. Nevertheless, to the extent that such other explanations and / or descriptions conflict with the above definitions, the above definitions should control.

[0070] Note that the description given herein focuses on a 3GPP cellular communications system and, as such, 3GPP terminology or terminology similar to 3GPP terminology is oftentimes used. However, the concepts disclosed herein are not limited to a 3GPP system and can be applied to any communication system that may benefit from them.

[0071] 5G / NR technology shares many similarities with LTE. For example, NR uses CP-OFDM (Cyclic Prefix Orthogonal Frequency Division Multiplexing) in the DL and both CP-OFDM and DFT-spread OFDM (DFT-S-OFDM) in the UL. As another example, in the time domain, NR DL and UL physical resources are organized into equal-sized 1-ms subframes. A subframe is further divided into multiple slots of equal duration, with each slot including multiple OFDM-based symbols. However, time-frequency resources can be configured much more flexibly for an NR cell than for an LTE cell. For example, rather than a fixed 15-kHz OFDM sub-carrier spacing (SCS) as in LTE, NR SCS can range from 15 to 240 kHz, with even greater SCS considered for future NR releases.

[0072] In addition to providing coverage via cells as in LTE, NR networks also provide coverage via “beams.” In general, a downlink (DL, i.e., network to UE) “beam” is a coverage area of a network-transmitted reference signal (RS) that may be measured or monitored by a UE. In NR, DL RS can include any of the following: synchronization signal / PBCH block (SSB), channel state information RS (CSI-RS), tertiary reference signals (or any other sync signal), positioning RS (PRS), demodulation RS (DMRS), phase-tracking reference signals (PTRS), etc. In general, SSB is available to all UEs regardless of the state of their connection with the network, while other RS (e.g., CSI-RS, DM-RS, PTRS) are associated with specific UEs that have a network connection.

[0073] The radio resource control (RRC) protocol controls communications between UE and gNB at the radio interface as well as mobility of a UE between cells in the NG-RAN. RRC also broadcasts system information (SI) and performs establishment, configuration, maintenance, and release of data radio bearers (DRBs) and signaling radio bearers (SRBs) and used by UEs. Additionally, RRC controls addition, modification, and release of carrier aggregation (CA) and dual-connectivity (DC) configurations for UEs. RRC also performs various security functions such as key management.

[0074] After a UE is powered ON it will be in the RRC IDLE state until an RRC connection is established with the network, at which time the UE will transition to RRC CONNECTED state (e.g., where data transfer can occur). The UE returns to RRC IDLE after the connection with the network is released. In RRC IDLE state, the UE’s radio is active on a discontinuous reception (DRX) schedule configured by upper layers. During DRX active periods (also referred to as “DRX On durations”), an RRC IDLE UE receives SI broadcast in the cell where the UE is camping, performs measurements of neighbor cells to support cell reselection, and monitors a paging channel on PDCCH for pages from 5GC via gNB. An NR UE in RRC IDLE state is not known to the gNB serving the cell where the UE is camping. However, NR RRC includes an RRC_INACTIVE state in which a UE is known (e.g., via UE context) by the serving gNB. RRC INACTIVE has some properties similar to a “suspended” condition in LTE.

[0075] 3GPP Technical Report (TR) 38.843 (vl8.0.0) describes a study on AI / ML for NR air interface between gNBs and UEs, including life cycle management (LCM) of AI / ML models. This LCM may include the following aspects or operations:

[0076] • Data collection;

[0077] • Model training;

[0078] • Functionality / model identification;

[0079] • Model delivery / transfer;

[0080] • Model inference operation;

[0081] • Functionality / model selection, activation, deactivation, switching, and fallback operation, which may involve decision by the network (e.g., network initiated or UE- requested) or decision by the UE (e.g., event-triggered as configured by the network, reported to the network, or UE-autonomous optionally with report to the network);

[0082] • Functionality / model monitoring;

[0083] • Model update; and

[0084] • UE capability.

[0085] 3GPP TR 38.843 (vl8.0.0) also includes Figure 2, which is a block diagram of an exemplary framework for AI / ML models used for NR air interface. The various blocks of Figure 2 are described below.

[0086] The Data Collection block provides raw or processed input data to other blocks in the framework. In particular, Data Collection provides training data to the Model Training block, inference data to the Model Inference block, and monitor data to the Model Management block (all described below). However, AI / ML algorithm-specific data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) is not performed by the Data Collection block. Examples of input data provided by Data Collection include measurements from UEs or different network entities, feedback from other blocks, and outputs from an AI / ML model.

[0087] The Model Training block in Figure 2 performs training, validation, and testing of AI / ML models. The testing may generate model performance metrics. The Model Training function is also responsible for data preparation (e.g., data pre-processing and cleaning, formating, and transformation) based on Training Data provided by the Data Collection function, if required. The Model Training block provides trained, validated, and tested AI / ML models to the Model Storage function, as well as to AI / ML model updates as available.

[0088] The Model Management block in Figure 2 oversees operation (e.g., deployment, selection, activation, deactivation, switching, fallback, etc.) and performance monitoring of AI / ML models. This block is also responsible for ensuring proper Model Inference operation based on data received from the Data Collection function and the Inference function. For example, the Model Management block sends to the Model Inference block a Management Instruction containing information needed to manage the Model Inference block, such as selection / activation / deactivation / switching of AI / ML models, fallback to non-AI / ML operation (i.e., non-inference), etc.

[0089] The Model Management block may also send a Model Transfer / Delivery Request to the Model Storage block in order to retrieve stored AI / ML models. The Model Management block may also send a Performance Feedback / Retraining Request to the Model Training block, with inputs needed for model (re)training or updating.

[0090] As noted above, the Model Management block should support performance monitoring of AI / ML models, which may be used to assist and control Model Inference. Based on the Inference Output received from the Model Inference block, the Model Management may decide to fall back to a conventional, non-AI / ML algorithm or change / update the AI / ML model being used. Model Management may be hosted by a network management function (e.g., OAM), a gNB-CU, or other network entity(ies) depending on the use case.

[0091] The Model Inference block in Figure 2 applies data provided by the Data Collection block (i.e., Inference Data) as inputs to the AI / ML models, which produce outputs such as predictions or decisions (i.e., Inference Output). The Model Inference block is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on the Inference Data provided by the Data Collection block, if required. The Model Inference block may also provide the Inference Output to the Model Management block to facilitate monitoring of AI / ML model performance.

[0092] The Model Storage block in Figure 2 is responsible for storing trained / updated AI / ML models that can be used by the Model Inference and / or Model Management blocks. In general, the Model Storage block is not a required part of the framework in Figure 2, but may function as a reference point for protocol terminations, model transfer / delivery, and related processes. However, this block should not restrict actual storage locations of AI / ML models. Figure 3 shows exemplary AI / ML model training and inference pipelines, along with their interactions during a model LCM procedure. The training (or retraining) pipeline includes the following stages or operations:

[0093] • Data Ingestion, which gathers raw training data from data storage, possibly followed by checking the validity of the gathered data;

[0094] • Data Pre-Processing, during which some feature engineering is applied to the gathered data, such as data normalization and / or transformation needed for input to the AI / ML model;

[0095] • Model Training, such as discussed above in relation to Figure 2;

[0096] • Model Evaluation, such as benchmarking AI / ML mode performance to some baseline; and

[0097] • Model Registration, including any corresponding metadata that provides information on how the AI / ML model was developed, and possibly AI / ML model evaluation results.

[0098] The operations of model training and model evaluation may continue iteratively until an acceptable level of performance is achieved, after which the AI / ML model is registered. Subsequently, a deployment stage is used to make the trained (or re-trained) AI / ML model part of the inference pipeline, which includes the following stages or operations:

[0099] • Data Ingestion, which gathers raw inference data from data storage;

[0100] • Data Pre-Processing, in a similar manner as in the training pipeline;

[0101] • Model operation, during which the trained and deployed model is used in an operational mode;

[0102] • Data and Model Monitoring, such as validating that the inference data is from a distribution that aligns well with the training data, monitoring model outputs for detecting any performance or operational drifts.

[0103] The pipeline shown in Figure 3 also includes a drift detection stage that informs about any drifts in the model operations.

[0104] The AI / ML models being discussed in the 3 GPP Rel-18 study item can be categorized into one-sided and two-sided. One-sided AI / ML models perform inference entirely in one side of the radio interface. For example, UE-sided AI / ML models perform inference entirely at the UE and network-sided AI / ML models perform inference entirely in the network (e.g., RAN node). In contrast, a two-sided AI / ML model includes “paired” AI / ML models that perform joint inference in the UE and in the network. For example, a first part of the inference is performed by UE and then a second part of the inference is performed by a RAN node (or vice versa).

[0105] Figure 4 illustrates an exemplary channel state information (CSI) autoencoder based on a two-sided AI / ML model. The UE measures the channel in the downlink using CSI-RS. The UE estimates that channel for each OFDM subcarrier (SC) from each RAN node transmit (TX) antenna and at each UE receive (RX) antenna. The estimate may be represented as a three- dimensional (3D) channel matrix or tensor. This 3D channel matrix representing estimates of the MIMO channel over several subcarriers is input to the encoder side of the AI / ML model.

[0106] For compression of UL CSI reports for the DL channel, the UE implements the encoder and the network (e.g., RAN node) implements the decoder. It is also possible to reverse the CSI reporting operation, such that the RAN node measures the UL channel using UE transmitted SRS and reports uplink CSI to the UE using the encoder side of the AI / ML model. The UL channel can be reconstructed by the UE using the decoder side of the AI / ML model.

[0107] For UE-side models and UE parts of two-sided models, 3GPP Rel-18 includes functionality-based LCM and model-ID based LCM. In functionality-based LCM, the network indicates activation, deactivation, fallback, and / or switching of AI / ML functionality via 3 GPP signaling (e.g., RRC, MAC-CE, DCI). Specific models may not be identified at the network, and UE may perform model-level LCM. Whether and how much awareness the network should have about model-level LCM is up for further study. Moreover, there may be one or more functionalities defined within an AI / ML-enabled feature (i.e., a feature in which AI / ML may be used). A UE may have one or more AI / ML models for a given functionality.

[0108] For functionality identification and functionality-based LCM of UE-side models and / or UE parts of two-sided models, “functionality” refers to an AI / ML-enabled Feature / FG enabled by network configuration that is facilitate by UE capability indication (i.e., for support of the functionality). A UE may also report updates of configured functionality.

[0109] In model-ID-based LCM, models are identified at the network, which may activate, deactivate, select, or switch individual AI / ML models via model ID. For AI / ML model identification and model-ID-based LCM of UE-side models and / or UE parts of two-sided models, model-ID-based LCM operates based on identified models associated with specific configurations / conditions that are supported by UE capabilities. A UE may also report updates of configured AI / ML models.

[0110] In general, a model ID may identify a “logical” AI / ML model, which may have an implementation-specific mapping to physical AI / ML model(s) in UE or network. The term “logical AI / ML model” may refer to an AI / ML model that is identified and assigned a model ID, while “physical AI / ML model” may refer to an actual implementation of such model. A model ID may or may not be globally unique, and different types of model IDs may be created for a single model for various LCM purposes.

[0111] For UE-side or UE parts of two-sided AI / ML models, model identification may be categorized according to the following types: • Type A: Model is identified to network (if applicable) and UE (if applicable) without over- the-air signaling. The model may be assigned a model ID during the model identification, which may be referred / used in over-the-air signaling after model identification.

[0112] • Type Bl : Model is identified via over-the-air signaling initiated by the UE, and NW assists the remaining steps (if any) of model identification. The model may be assigned a model ID during model identification.

[0113] • Type B2: Model is identified via over-the-air signaling initiated by the NW, and UE responds (if applicable) for the remaining steps (if any) of the model identification. The model may be assigned a model ID during model identification.

[0114] Once models are identified, UE can indicate supported AI / ML model IDs for a given AI / ML-enabled feature (or feature group, FG) in a UE capability report as an initial starting point. Model identification using UE capability report is not precluded for types Bl and B2. For functionality / model-ID based LCM, once the functionalities or models are identified, similar procedures may be used for their activation, deactivation, switching, fallback, and monitoring.

[0115] There are several techniques for UE-side model monitoring. In one technique, the UE performs both the training of the AI / ML model and the inference based on the trained AI / ML model. However, this may be too complex and / or infeasible in practice due to limited computational resources of the UE, since training often involves significant computational complexity. Also, if a model is location-dependent, a model trained by the UE would be limited to the areas the UE moves arounds, and may be invalid (e.g., needing to be retrained) when the UE enters an area for the first time.

[0116] A second technique for training UE-side models is a network node (e.g., RAN node, CN node, etc.) collects data from a UE and trains an AI / ML model that is later transferred to that UE and / or to other UEs that may benefit from it. For example, an over-the-top (OTT) application server, outside of a 3GPP network, may be in charge of the training. For example, this server could be a UE-vendor specific server. This variant may be beneficial to achieve optimal performance by matching the training data set to the intended inference operation at the UE, which may depend on UE-vendor specific hardware / software implementations.

[0117] Irrespective of where the UE-side model training is performed, a certain amount of training data needs to be collected by the UE to facilitate this training. For many AI / ML use cases such as CSI compression, CSI prediction, beam management, positioning, mobility / traffic prediction, etc., the training must be based one inputs from the UE. One example protocol is that a UE collects training data from some prescribed duration and then transfers the collected data to a training node in the network. 3GPP document R2-2308286 includes the following table showing agreed mapping between functionalities and entities for UE-side training, where “FFS” is an abbreviation for “for further study”:

[0118] 3GPP discussions so far assume the serving RAN node and / or an operations / admini strati on / maintenance (OAM) function will be responsible for network-side model training. If the RAN node is responsible, it is assumed that the RAN node may configure the UE with a set of resources (e.g., CSI-RS and / or SSB) for which the UE collects measurements for a prescribed duration. Subsequently, the UE reports the collected measurements to the RAN node, e.g., via RRC signaling. The training can then be performed by the RAN node itself, or by another node external to the 3 GPP network but controlled by the RAN node vendor (e.g., OTT server). A similar approach may be used when OAM performs network-side training. The OAM may request the RAN node to provide the UE a measurement configuration, based on which the UE collects measurements. Once the measurement collection is completed, the UE sends the collected data to OAM, e.g., using immediate MDT or logged MDT techniques.

[0119] 3GPP document R2-2308286 includes the following table showing agreed mapping between functionalities and entities for network-side training;

[0120] As briefly mentioned above, UEs and RAN nodes (e.g., gNBs) can be configured to perform and report measurements to support minimization of drive testing (MDT), which is intended to reduce and / or minimize the requirements for manual testing of network performance by driving around the geographic coverage of the network. The MDT feature was first studied in Long-Term Evolution (LTE) Rel-9 (e.g., 3GPP TR 36.805 v9.0.0), first standardized for LTE in Rel-10, and is also supported for 5G / NR. In general, there are two types of MDT measurements: logged MDT measurements for UEs in RRC IDLE / RRC INACTIVE states and immediate MDT measurements for UEs in RRC_CONNECTED state.

[0121] Also, MDT measurements can be management-based or signaling-based. In management-based MDT, data is collected from UEs in a specified area defined as a list of cells or as a list of tracking / routing / location areas. RAN nodes (e.g., gNBs) selects UEs for which MDT measurements are configured, collected, and reported to the trace collection entity (TCE). In signaling-based MDT, data is collected from a specific UE as specified by an IMEI(SV) or an IMSI. A management system (e.g., 0AM) selects the particular UE to collect and report MDT measurements.

[0122] For management-based MDT activation, a RAN node starts a trace recording session in a given cell for either immediate or logged MDT measurements for each selected UE that satisfies the MDT UE selection criteria or capability condition (e.g., logged MDT capable UE), provided that the management system previously activated a relevant cell trace session for that cell. The NG-RAN node configures each of the selected UEs with corresponding MDT RRC measurements. When the NG-RAN supports several PLMNs, the NG-RAN node only selects UEs that provide a selectedPLMN-Identity (e.g., in an RRCConnectionSetup message) that matches a pLMNTarget.

[0123] Figure 5 shows an exemplary procedure for management-based MDT activation in NG- RAN for the case of non-split RAN node architecture. For management-based MDT data collection with no IMSI / IMEI(SV) / SUPI criteria for non-split architecture, UE selection can be done in the RAN node (530, e.g., gNB) based on input information received from management system and the user consent information stored in the RAN node. This mechanism works for Area Information 0AM input parameter. A description of this procedure is given in 3GPP TS 32.422 (v!7.7.1) section 4.1. 1.9.2, with the most relevant parts repeated below.

[0124] Whenever the RAN node receives the Management based MDT PLMM List in an Initial Context Setup Request or in a Handover Request message, it stores it for possible later usage. This is shown as operation 0, occurring at two possible places in the flow.

[0125] In operation 1, the management system (510) sends a Trace Session activation request to the RAN node. This request includes one or more of the following parameters for configuring UE measurements (as described further in 3GPP TS 32.422 (v!7.7.1) section 5):

[0126] • Job Type. • Area Scope where the UE measurements should be collected, e.g., list of NG-RAN cells. Tracking Area should be converted to NG-RAN cell.

[0127] • List of Measurements.

[0128] • Reporting Trigger.

[0129] • Report Interval.

[0130] • Report Amount.

[0131] • Event Threshold.

[0132] • Logging Interval.

[0133] • Logging Duration.

[0134] • Trace Reference.

[0135] • TCE IP Address.

[0136] • Anonymization of MDT Data.

[0137] • Collection Period for NR RRM Measurements (present only if any M4 or M5 measurements are requested).

[0138] • Collection Period M6 in NR (present only if any M6 UL / DL measurements are requested).

[0139] • Collection Period M7 in NR (present only if any M7 UL / DL measurements are requested).

[0140] • MDT PLMN List.

[0141] • Report Type for Logged MDT (periodical logged or event-triggered measurement).

[0142] • Events List for Event-Triggered Measurement (logged MDT only), e.g., Event Threshold, Hysteresis, Time to Trigger (present only if LI event is configured for logged MDT).

[0143] • Area Configuration for Neighbor Cells (logged MDT only).

[0144] • Sensor Information.

[0145] In operation 2, when the RAN node receives the Trace Session activation request from its management system, it starts a Trace Session and saves the parameters associated with the Trace Session. In operation 3, the RAN node selects suitable UEs for MDT data collection. The selection is based on the area received from the management system, the areas where UEs are located, and user consent information received from the 5GC in the Management based MDT PLMN List. If a user is not in the specified area or if the Management based MDT PLMN List IE is not present in the UE context, the RAN node does not select the UE for MDT data collection. During UE selection, the RAN node also considers UE MDT capability when it selects UE for logged MDT configuration and does not select a UE that does not support logged MDT. If M4 or M5 measurements are requested in the MDT configuration, the RAN node starts measurement according to the received configuration. In operation 4, the RAN node activates the MDT functionality to the selected UEs. When the RAN node selects a UE, it considers availability of Management based MDT PLMN List in the associated user context and the area scope parameter received in MDT configuration (Trace Session activation). Detailed description about user consent handling and how it is provided to the RAN node is described in 3GPP TS 32.422 (vl7.7.1) section 4.9.2. If there is no Management based MDT PLMN List in the user context or the user is outside the area scope defined in the MDT configuration, the RAN node does not select the UE for MDT data collection. The RAN node assigns a Trace Recording Session Reference (TRSR) to each selected UE.

[0146] For logged MDT, the RAN node sends at least the following configuration information to the UE (540):

[0147] • Trace Reference (TR);

[0148] • TRSR;

[0149] • TCE Id (e.g., value signaled as IP address of TCE from the EM is mapped to a TCE Id, using a configured mapping in the RAN);

[0150] • Logging Interval;

[0151] • Logging Duration;

[0152] • Absolute time reference;

[0153] • Area Scope where the UE measurements should be collected (e.g., cell list or tracking area); and

[0154] • MDT PLMN List.

[0155] Note that the RAN node cannot send the logged MDT configuration to UEs currently camping in the cell in RRC IDLE / RRC INACTIVE. These UEs may be configured when they next initiate some activity (e.g., Service Request or Tracking Area Update) that causes them to transition to RRC CONNECTED.

[0156] For immediate MDT, the RAN node sends one or more of the following parameters to the UE: List of Measurements, Reporting Trigger, Report Interval, Report Amount, and Event Threshold.

[0157] The RAN node performs necessary actions specified in 3GPP TS 38.305 according to the value of Positioning Method (e.g., activating GNSS module of the UE) received in the Trace configuration. The RAN node captures location information and / or positioning measurements in the MDT trace record. If the Reporting Trigger parameter indicates that all configured RRM measurement triggers should be reported in MDT, the RAN node requests the UE to provide "best effort" location information together with the measurement reporting by setting the includeLocationlnfo IE in all RRC measurement reporting configurations. When UE receives the MDT activation, it starts MDT functionality based on the received configuration parameters. In operation 5, the RAN node can retrieve the MDT report from the UE, via RRC message. However, the RAN node shall not retrieve MDT report from the UE if UE’s registered PLMN (rPLMN) does not match the PLMN where the TCE (550) used to collect MDT data resides (e.g., RAN node’s primary PLMN).

[0158] For immediate MDT, when the RAN node receives the MDT report from the UE in the RRC message the RAN node stores the UE’s serving cell CGI together with the MDT report from the UE in the trace record. A UE configured to perform logged MDT measurements in RRC IDLE or RRC INACTIVE indicates the availability of MDT measurements by means of a one-bit indicator, in RRCConnectionSetupComplete message during connection establishment as specified in 3GPP TS 32.422 (v!7.7.1). The RAN node can decide to retrieve the logged measurements based on this indication by sending the UEInformationRequest message to the UE. The UE can answer with the collected MDT logs in UEInformationRespon.se message.

[0159] When the RAN node receives the MDT report from UE, the RAN node obtains TRSR, TR, and TCE Id from the report and compare the Trace PLMN (i.e., PLMN portion of TR) with the PLMN where TCE used to collect MDT data resides (e.g., its primary PLMN). The RAN node discards the MDT report in case of a mismatch but otherwise saves the UE measurements from the report to MDT records in operation 6.

[0160] In operation 7, the RAN node checks whether MDT anonymization requires the IMEI- TAC in the MDT record. If so, in operation 8 the RAN node sends TRSR, TR, serving cell CGI, and TCE IP Address in the CELL TRAFFIC TRACE message to the AMF (520) via the NG connection. When the AMF receives this NG signaling message from the RAN node, it checks the Privacy Indicator (set to Logged MDT or Immediate MDT depending on configured Job Type). For logged MDT, the AMF sends the IMEI-TAC together with TRSR and TR to TCE as shown in Figure 5.

[0161] For immediate MDT, the AMF looks up the subscriber identities (IMEI(SV)) of the given call from its database and includes that information in the message sent in operation 9. Note that for management-based immediate MDT, TRSR may be duplicated among different RAN nodes when multiple cells are selected as the area scope for the same MDT job. In this case, the combination of TRSR and the UE’s serving cell CGI in the MDT report can uniquely identify one trace recording session.

[0162] In operation 10, the RAN node forwards the trace records to the TCE. In case of logged MDT, the TCE Id indicated in the MDT report is translated to the actual IP address of the TCE by the RAN node before it forwards the measurement records, using configured mapping in the RAN node. In case of immediate MDT, the IP address of the TCE is indicated for the RAN node in the trace configuration.

[0163] An Immediate MDT measurement configuration is deleted in the UE together with the RRC context when entering idle or inactive mode. A Logged MDT trace session is preserved in the UE until the duration time of the trace session expires, including also multiple idle or inactive periods interrupted by various state transitions between RRC IDLE and RRC CONNECTED.

[0164] In operation 11, the TCE combines the MDT record received in operation 10 with TAC received in operation 9 (for logged MDT) based on TR and TRSR included in both. The Management system validates that mobile country code (MCC) and mobile network code (MNC) specified TR is the same as the PLMN supported by all the cells specified in the area scope. If the RAN node receives a request with a PLMN in TR that does not match any PLMN in its list, it shall ignore the request.

[0165] Even so, there are some problems, issues, and / or difficulties when management-based MDT is used to collect data used for network-side training of AI / ML models. For example, while a management node (e.g., 0AM) may identify an area scope for MDT collection, the RAN is responsible for selecting UEs within the area scope to collect the MDT measurements.

[0166] When the management node performs the network-side model training, the existing solution to select the UEs for MDT measurement collection is not efficient. For example, the management node may need to build different AI / ML models for different conditions experienced by UEs; such conditions are not considered for selection of UEs to collect MDT measurements to be used for model training. In other words, the states of and conditions experienced by individual UEs may affect the measurements collected and, consequently, the training of the AI / ML models on such measurements. This may result in unpredictable and / or undesirable model behavior when used for inference or prediction.

[0167] Accordingly, embodiments of the present disclosure provide flexible and efficient techniques for a management node (e.g., 0AM) to determine a first set of conditions for activation of MDT measurement collection by one or more UEs served by a RAN node (e.g., gNB). After receiving the first set from the management node, the RAN node applies the first to select UEs for MDT measurement collection, possibly in conjunction with a configured area scope for the measurements. In some embodiments, the RAN node may also determine and apply a second set of conditions when selecting UEs for MDT measurement collection.

[0168] Embodiments may provide various benefits and / or advantages. For example, embodiments facilitate a management node to observe UE performance and obtain UE measurements in different conditions, such as different levels or quality of radio coverage. Such measurements may then be used by the management node to train AI / ML models specific to each of the different conditions, e.g., for radio coverage. At a high level, embodiments improve the training of AI / ML models used to enhance performance of the radio interface between UEs and RAN nodes. As such, embodiments may improve various performance criteria of this radio interface, such as latency, reliability, bandwidth, etc.

[0169] In the following description of embodiments, the following groups of terms and / or abbreviations have the same or substantially similar meanings and, as such, are used interchangeably and / or synonymously unless specifically noted or unless a different meaning is clear from a specific context of use:

[0170] • “training”, “optimizing”, “optimization”, and “updating” of models;

[0171] • “changing” and “modifying” of models, which are used to indicate that a type, structure, parameters, connectivity, etc. of a model is different than it was before the change or modification;

[0172] • “model”, “policy”, “algorithm”, “AI / ML model”, “AI / ML policy”, “AI / ML algorithm”.

[0173] In general, embodiments disclosed herein are applicable to any type of ML used in a RAN. Non-limiting examples include supervised learning, deep learning, reinforcement learning, contextual multi-armed bandit algorithms, autoregression algorithms, etc. or combinations thereof. Such algorithms may exploit functional approximation models, also referred to as AI / ML models, including feedforward neural networks, deep neural networks, recurrent neural networks, convolutional neural networks, etc.

[0174] Specific examples of reinforcement learning algorithms include deep reinforcement learning algorithms such as deep Q-network (DQN), proximal policy optimization (PPO), double Q-leaming, policy gradient algorithms, off-policy learning algorithms, actor-critic algorithms, and advantage actor-critic algorithms (e.g., A2C, A3C, actor-critic with experience replay, etc.).

[0175] Some embodiments include methods for a management node (e.g., OAM), which may initiate MDT procedures for UEs to collect data for training (e.g., network-side training) of AI / ML models pertaining to specific conditions on a radio interface between the UE and a RAN node. The management node determines a first set of conditions for selection of one or more UEs by the RAN node.

[0176] In some embodiments, the first set of conditions may include conditions on radio-related measurements available at the RAN node. For example, the first set of conditions may include one or more of the following:

[0177] • ranges of interest for reference signal received power (RSRP), reference signal received quality (RSRQ), received signal strength (RSSI), and / or signal to interference and noise ratio (SINR) measured by the UE based on DL RS, or measured by the RAN node based on UL RS;

[0178] • one or more thresholds for RSRP, RSRQ, RS SI, and / or SINR measured by the UE or by the RAN node;

[0179] • one or more thresholds for a difference between consecutive samples of RSRP, RSRQ, RSSI, and / or SINR measured by the UE or by the RAN node.

[0180] For example, an RSRP threshold condition in the first set may indicate that RSRP measurements above (below) the RSRP threshold are of interest for AI / ML model training. Likewise, an RSRQ range condition in the first set may indicate that RSRQ measurements within the RSRQ range are of interest for AI / ML model training. Similarly, an RSRP difference threshold condition in the first set may indicate that consecutive RSRP measurements that change by more than the RSRP difference threshold of interest for AI / ML model training

[0181] In some embodiments, the first set of conditions may include conditions on UE mobility state available at the RAN node. For example, these type of conditions may be defined by ranges of UE speed (e.g., km / h) or coarse categories of UE mobility (e.g., high / medium / low), the latter of which may be derived by existing specified techniques. As a more specific example, a mobility condition may indicate that measurements by UEs in low mobility state are of interest for AI / ML model training.

[0182] In some embodiments, the first set of conditions may include conditions on UE location, such as specific geographic areas, coverage areas, locations, or types of coverage at which a UE is located. For example, one or more location conditions may indicate that measurements by UEs in specific locations (e.g., cell border) or in specific types of coverage (e.g., indoor, outdoor) are of interest for AI / ML model training.

[0183] In some embodiments, the first set of conditions may include conditions on UE traffic type. For example, one or more of these conditions may indicate that measurements by UEs carrying or handling certain types of traffic (e.g., radio bearer, network slice, service type, QoS, etc.) are of interest for AI / ML model training. As some specific examples, the management node may want to train a model tailored for URLLC traffic or for a data radio bearer (DRB) associated with a particular QoS class.

[0184] In some embodiments, the first set of conditions may include conditions on status of an AI / ML model in the UE (e.g., for UE-side or UE part), in the network (e.g., for network-side or network part), or for both.

[0185] In various embodiments, any of the above-described conditions of the first set may also be associated with (or specific to) one or more RAN characteristics or resources, such as beams, cells, frequencies, RAN nodes, tracking areas (e.g., TAC, TAI), PLMNs, or other geographical area defined by RAN characteristics.

[0186] For example, the management node may provide different first sets of conditions for different cells, beams, or frequencies. As a more specific example, the management node may be interested in collecting measurements when the UE is located where its serving cell provides poor coverage but a neighbor cells provides good radio coverage. To this end, the management node may provide a threshold for an offset between serving cell RSRP and neighbor cell RSRP. If the offset between UE reported measurements for these quantities is larger than the threshold, then the RAN node should initiate MDT measurement collection.

[0187] In other embodiments, a single first set of conditions may apply to all RAN characteristics or resources, such as all cells, beams, and / or frequencies. For example, if the RSRP level is below a certain threshold for all indicated cells or beams, then the RAN node should consider the conditions as triggered and initiate MDT measurement collection.

[0188] As mentioned above, the first set of conditions may include conditions on status of an AI / ML model in the UE (e.g., for UE-side or UE part), in the network (e.g., for network-side or network part), or for both. For example the management node may want to collect measurements for scenarios in which AI / ML models (or model functionalities) are active / operational at the network (and / or UE) side, or for scenarios in which AI / ML models (or model functionalities) are inactive / non-operational at the network (and / or UE) side. This may desired for comparative analysis of UE and network performance using AI / ML, or for collecting model training data under different operative conditions at the RAN node and / or UE.

[0189] In some of these embodiments, conditions on status of an AI / ML model may include an identified AI / ML model (or model functionality) being activated or operational at the UE (e.g., for a UE-side model), at the RAN node (e.g., for a network-side model), or at both UE and RAN node (e.g., for two-sided model). In such case, the entity (e.g., RAN node) monitoring this condition initiates MDT measurements when the identified model / functionality is activated by this entity. For example, the RAN node initiates an MDT measurement session when it activates an identified AI / ML model (or model functionality), and stops the MDT measurement session when it deactivates the identified AI / ML model (or model functionality). Likewise, for a UE- sided model, the RAN node the RAN node initiates an MDT measurement session when it activates / configures the identified AI / ML model (or model functionality) in the UE, or when the UE indicates to the RAN node that it has activated the identified AI / ML model (or model functionality).

[0190] In some of these embodiments, conditions on status of an AI / ML model may include an identified AI / ML model (or model functionality) being applicable at the UE (e.g., for a UE-side model), at the RAN node (e.g., for a network-side model), or at both UE and RAN node (e.g., for two-sided model). In such case, the entity (e.g., RAN node) monitoring this condition initiates MDT measurements when the conditions to activate an AI / ML model / functionality becomes applicable. For UE-side models, the RAN node may initiate a new MDT measurement session whenever the UE indicates to the RAN node that a UE-side AI / ML model (or model functionality) has become applicable.

[0191] In some of these embodiments, conditions on status of an AI / ML model may include conditions on outputs (e.g., predictions) of an AI / ML model (or model functionality). For example, the conditions may include a threshold for predicted measurements (e.g., RSRP, RSRQ) of physical layer resources (e.g., beams, frequencies, cells), and the management node initiates MDT measurements when predicted measurements are above (or below) the threshold. As another example, the conditions may include a threshold for prediction accuracy, and the management node initiates MDT measurements when estimated accuracy of predicted measurements are above (or below) the accuracy threshold. Such conditions may facilitate measurement collection fortraining of AI / ML models (or model functionalities) that work under different accuracy conditions.

[0192] In some of these embodiments, conditions on status of an AI / ML model may include mobility-related conditions. For example, the conditions may include a predicted radio link failure (RLF) or handover failure (HOF), and the management node initiates MDT measurements when the AI / ML model (or model functionality) predicts that a UE will detect an RLF or an HOF in the near future.

[0193] In a variant of any of the embodiments discussed above, rather than initiating a new MDT measurement session, the RAN node includes in an already ongoing MDT measurement session the measurements that are collected after the relevant condition is fulfilled. For example, the RAN node may add an indicator (or flag) to the measurements collected in this manner.

[0194] In some embodiments, the management node may obtain a first set of measurements for one or more UEs that are determined to have met one or more of the first set of conditions. In other words, the first set of measurements are associated with the first set of conditions, such that the RAN node that detects that condition(s) of the first set are fulfilled will cause the one or more UEs to collect and report the first set of measurements. Alternately, the RAN node may collect one or more of the first set of measurements.

[0195] For example, the first set of measurements may be MDT measurements, based on which the management node may train one or more AI / ML models (or model functionalities). In various embodiments, the first set of measurements may include one or more of the following: • UL / DL radio-related measurements (e.g., RSRP, RSRQ, SINR, RSSI), including layer-

[0196] 3 filtered measurements and layer- 1 unfiltered measurements;

[0197] • UL / DL traffic-related (e.g., Layer-2) measurements such as packet delays, packet loss rate, packet throughput, packet jitter, etc.

[0198] • UE positioning measurements (e.g., location, trajectory);

[0199] • Any immediate MDT measurements specified in 3GPP TS 38.314 (vl7.4.0)

[0200] • Any logged MDT measurements specified in 3GPP TS 38.331 (vl8.0.0).

[0201] In some embodiments, the first set of measurements may include outputs (e.g., predictions) of an AI / ML model (or model functionality) operating at the UE, the RAN node, or both, according to the type of AI / ML model. In various embodiments, the first set of measurements may include predictions of one or more of the following:

[0202] • UL / DL radio-related measurements (e.g., RSRP, RSRQ, SINR, RSSI), including layer-

[0203] 3 filtered measurements and layer- 1 unfiltered measurements;

[0204] • UL / DL traffic-related (e.g., Layer-2) measurements such as packet delays, packet loss rate, packet throughput, packet jitter, etc.

[0205] • Quality of service (QoS) per data radio bearer (DRB), protocol data unit (PDU) session, or QoS flow, such as predicted throughput, delay, packet loss rate, etc.

[0206] • UE positioning measurements (e.g., location, trajectory);

[0207] • Events, such as mobility-related events (e.g., A1-A5 or B1-B2) or failure-related events (e.g., RLF, HOF, BFD).

[0208] In some of these embodiments, the first set of measurements may also include inputs to the AI / ML model (or model functionality) operating at the UE, the RAN node, or both, that caused the outputs (e.g., predictions). For example, such inputs may be measurements (e.g., on cells, beams, frequencies, etc.) that the UE or RAN node used to derive the predictions. The input measurements may be any of the measurements mentioned above.

[0209] In various embodiments, the first set of measurements may be common to all conditions in the first set, or different ones of the first set of measurements may be specific to individual conditions in the first set. For example, the management node may request MDT measurements for multiple cells / frequencies / beams, so that the RAN node will provide measurements of the first set separately for each requested cell / frequency / beam. This example may be particularly applicable to radio-related measurements.

[0210] Both the first set of conditions and the required first set of MDT measurements are indicated by the management node to the RAN node. In some embodiments, the management node may initially indicate the first set of conditions and once the RAN node indicates that one or more of the first set have been fulfilled, the management node indicates the required first set of measurements. Alternatively, both the first set of conditions and the required first set of MDT measurements can be indicated prior to fulfillment of any conditions in the first (e.g., concurrently). In such case, the RAN node can directly initiate an MDT session for one or more UEs that fulfill condition(s) in the first set, to obtain the required first set of measurements.

[0211] In some embodiments, the RAN node may perform one or more measurements of the first set. For example, L2 measurements can be performed by the RAN node. Other measurements of the first set may be performed by UE(s), as configured by the RAN node.

[0212] In various embodiments, the RAN node initiates MDT measurements (e.g., of the first set) for one or more UEs that fulfill one or more of the first set of conditions. In different variants, the RAN node may initiate MDT measurements for some or all of the UEs that fulfill one or more of the first set of conditions. In different variants, the RAN node may initiate a single MDT session for all UEs that fulfill conditions of the first set, or an individual MDT session for each UE (or some subset of UEs) that fulfills conditions of the first set.

[0213] In different variants, the RAN node may initiate a single MDT session to collect measurements pertaining to all fulfilled conditions of the first set, or an individual MDT session for each fulfilled condition of the first set. In the latter variant, the measurement report for each MDT session may include MDT measurements for a plurality of UEs, such all UEs that fulfilled the associated condition.

[0214] In various embodiments, a measurement report for an MDT session may include one or more of the following:

[0215] • a list of MDT measurements initiated for each of one or more UEs whose associated conditions in the first set of conditions are fulfilled

[0216] • a list of MDT measurements initiated for each condition of the first set, that was fulfilled (or a single list if the MDT session is condition-specific, as mentioned above);

[0217] • a trace ID, trace reference, and / or trace recording session reference;

[0218] • C-RNTIs of UEs whose MDT measurements are included in the list of initiated MDT measurements for the MDT session;

[0219] • an indication of the one or more conditions in the first set of conditions that are fulfilled

[0220] • a timestamp indicating when the MDT session started

[0221] • a timestamp of each MDT measurement included in the list of MDT measurements, indicating when the measurement was performed.

[0222] Upon receiving the conditions in the first set of conditions, the RAN node determines which of the conditions require measurements by the RAN node (“RAN monitoring measurements”) and which of the conditions require measurements by the UE (“UE monitoring measurements”). In the first case, the RAN node may start performing the RAN monitoring measurements for one or more of the UEs served by the RAN node, or for a cell or beam provided by the RAN node and indicated by the management node. For example, the RAN node may start performing L2 measurements (e.g., as packet delay, packet loss rate, etc.) and UL radio measurements (e.g., based on UL SRS) for various UEs, and evaluate DL radio measurements reported by such UEs (e.g., based on DL CSI-RS or SSB).

[0223] In some embodiments, the RAN node may initiate performing or evaluating such measurements only for UEs handling a certain type of traffic, such as a particular DRB, network slice, or service (e.g., URLLC). In some variants, different conditions in the first set of conditions may be monitored by different entities or units of a RAN node, e.g., DU, CU control plane (CP), CU user plane (UP), etc.. For example, UL / DL radio measurements may be performed / evaluated by the DU while some L2 measurements (e.g., PDCP packet delay or loss rate) may be performed by the CU-UP.

[0224] In some embodiments, the RAN node may provide a monitoring configuration for the UE monitoring measurements to those UEs that are to perform such measurements. These UEs then perform and report the UE monitoring measurements in accordance with the monitoring configuration. The monitoring configuration may include a measurement configuration that facilitates the UE to perform measurements that enable the RAN node to determine if any of the conditions indicated by the management node are met. As such, the measurement configuration may be specific to, or depend on, the first set of conditions provided to the RAN node by the management node.

[0225] As an example, if the management node is interested in training AI / ML models (or model functionalities) pertaining to UE operation under poor radio coverage, the measurement configuration may define measurements than enable the RAN node to determine when the UE is in poor radio coverage, such as:

[0226] • resources (e.g., SSB, CSI-RS) and / or resource sets to be measured;

[0227] • cells to be measured, such as UE’s serving and non-serving / neighbor cells;.

[0228] • carrier frequencies or bandwidth parts (BWPs) to be measured; and

[0229] • quantities to be measured (e.g. RSRP, SINR, RSRQ, SINR).

[0230] As another example, if the management node is interested in training AI / ML models (or model functionalities) pertaining to specific UE location (e.g., indoor or outdoor), the measurement configuration may include a geographic location or area to be measured.

[0231] The monitoring configuration may also include a reporting configuration that indicates how and / or when the UE should report the performed UE monitoring measurements. For example, the reporting can be periodic, upon RAN node request, or upon fulfilling one or more conditions in the first set. As an example, if the management node is interested in training AI / ML models (or model functionalities) pertaining to UE operation under poor radio coverage, the reporting configuration may indicate that UE monitoring measurements should be reported when measured RSRP (or another quantity) is below a threshold.

[0232] As another example, if the management node is interested in training AI / ML models (or model functionalities) pertaining to specific UE location (e.g., indoor or outdoor), the reporting configuration may indicate that that UE monitoring measurements should be reported when the UE enters or exits the area of interest. As another example, if the management node is interested in training AI / ML models (or model functionalities) pertaining to specific UE mobility state, the reporting configuration may indicate that that UE mobility state (e.g., low, medium, or high) should be reported periodically, upon a state change, or when UE speed crosses a threshold (e.g., 50 km / h).

[0233] In some embodiments, rather than reporting UE monitoring measurements to the RAN node, the UE may evaluate the performed UE monitoring measurements to determine whether any conditions of the first set are fulfilled. When any such conditions are fulfilled, the UE may send the RAN node an indication that one or more of the first set of conditions has been fulfilled. In some variants, the UE includes the UE monitoring measurements that fulfilled such conditions. The UE’s evaluation of the UE monitoring measurements may be configured by the measurement configuration, while the UE’s reporting of the indication and / or fulfilling UE monitoring measurements may be configured by the reporting configuration.

[0234] For example, the RAN node may configure the UE to report an indication of when RSRP is below a certain threshold, particularly when the management node is interested in training AI / ML models (or model functionalities) pertaining to UE operation under poor radio coverage. In a similar manner, the RAN node may configured the UE to report an indication of when the UE exits / enters an area of interest, when the UE changes mobility state, or when UE speed reaches a certain threshold.

[0235] Based on the RAN monitoring measurements, reported UE monitoring measurements, and / or UE- reported indication of condition fulfillment, the RAN node can determine which served UEs have fulfilled which conditions of the first set. For example, if the management node wants to collect data when UEs are in poor radio coverage and when packet delay is high, then the RAN node should collect RAN monitoring measurements (from which it can determine packet delay) and UE monitoring measurement or indication (from which it can determine if UEs are in poor radio coverage), in order to determine if both conditions are fulfilled.

[0236] In some embodiments, in addition to the first set of conditions provided by the management node, the RAN node may consider a second set of conditions when determining which UE to select for performing MDT measurements. For example, the second set of conditions may be used by the RAN node to determine how many UEs should be selected for monitoring related to the first set of conditions. This can depend on how many MDT sessions the RAN node has already initiated, or on how many UEs needed for AI / ML model (or model functionality) training, as indicated by the management node. More generally, the second set of conditions may be related to RAN node capability of handling multiple MDT measurement sessions, to UE capability or configurations need to performing the MDT measurements, or radio interface capacity available to handle UE reporting of MDT measurements.

[0237] Upon determining that one or more UEs have fulfilled one or more conditions of the first set (and optionally conditions of the second set), the RAN node may initiate MDT measurements for the determined one or more UEs. In different embodiments, some of the first set of measurements indicated by the management node may be performed by the RAN node (“RAN MDT measurements”) while other of the first set of measurements may be performed by the UE (“UE MDT measurements”) and sent to the RAN node. For UE MDT measurements, initiating the MDT measurements may involve the RAN node sending the selected UEs with an MDT configuration that specifies how to perform and report the required measurements.

[0238] In some embodiments, the RAN MDT measurements may be performed by different RAN node entities (e.g., DU, CU-CP, CU-UP, etc.) in a similar manner as the RAN monitoring measurements discussed above. The entity that detects fulfillment of conditions by RAN monitoring measurements should inform the entity responsible for configuring the UE to perform UE MDT measurements and (if different) the entity responsible for performing the RAN MDT measurements. For example, if the management node requests the RAN node to evaluate radio-related conditions related to an AI / ML model (or model functionality), the DU may monitor for fulfillment of the relevant conditions and indicate the fulfillment to CU-CP, which will configure the UE to perform and report the required UE MDT measurements of the first set of measurements.

[0239] As another example, if the first set of conditions include radio-related conditions that should be evaluated by the DU (e.g., based on RAN and / or UE monitoring measurements), the DU may monitor for fulfillment of such conditions and indicate fulfillment to CU-UP, which then initiates RAN MDT measurements for PDCP packet delay.

[0240] In such embodiments, the first set of conditions (i.e., for UE selection) should be distributed to other RAN node entities by the CU-CP, such that the other entities can indicate to the CU-CP (or CU-UP, as the case may be) the UEs selected by the other entities based on fulfillment of conditions of the first set of conditions. In some embodiments, the UE MDT measurements and / or the RAN MDT measurements may depend on the first set of measurements indicated by the management node. For example, the RAN MDT measurements may include L2 measurements and / or UL channel estimation, while UE MDT measurements may include DL radio measurements, UE location information, UE mobility state, etc.

[0241] In some embodiments, the MDT configuration may include an MDT measurement configuration and an MDT reporting configuration. The MDT measurement configuration may indicate, for example, radio resources (e.g. SSB resource sets, CSI-RS resources, cells / frequencies / BWPs) on which to perform the UE MDT measurements. The MDT reporting configuration may indicate when to report the UE MDT measurements, e.g., periodically or event-based.

[0242] In some embodiments, the MDT configuration may include one or more monitoring conditions, which may be part of the first set of conditions pertaining to monitoring. Upon receiving the MDT configuration, the UE performs monitoring measurements and determines whether such monitoring measurements fulfill the monitoring condition(s). Once one or more of the monitoring conditions are fulfilled, the UE starts performing the UE MDT measurements in accordance with the MDT measurement configuration.

[0243] In other words, the MDT measurement configuration may include a portion that is applied when the monitoring conditions are fulfilled. The RAN node can determine that the monitoring conditions are fulfilled based on an indication received from the UE, based on which the RAN node initiates the RAN MDT measurements.

[0244] As mentioned above, the UE may receive from the RAN node a monitoring configuration, based on which the UE performs and report UE monitoring measurements, which may enable the RAN node to determine if any of the conditions indicated by the management node are met. The monitoring configuration may include a measurement configuration that facilitates the UE to perform the required measurements, such as in the various embodiments and examples discussed above.

[0245] As also discussed above, the monitoring configuration may include a reporting configuration that indicates how and / or when the UE should report the UE monitoring measurements. For example, the reporting can be periodic, upon RAN node request, or upon fulfilling one or more conditions in the first set. Various examples were discussed above.

[0246] In some embodiments, rather than reporting UE monitoring measurements to the RAN node, the UE may evaluate the performed UE monitoring measurements to determine whether any conditions of the first set are fulfilled. When any such conditions are fulfilled, the UE may send the RAN node an indication that one or more of the first set of conditions has been fulfilled. In some variants, the UE includes the UE monitoring measurements that fulfilled such conditions. The UE’s evaluation of the UE monitoring measurements may be configured by the measurement configuration, while the UE’s reporting of the indication and / or fulfilling UE monitoring measurements may be configured by the reporting configuration.

[0247] Upon the UE indicating to the RAN node (or the RAN node determining) that one or more conditions of the first set are fulfilled, the UE receives from the RAN node an MDT configuration. As discussed above, the MDT configuration may include an MDT measurement configuration and an MDT reporting configuration. The MDT measurement configuration may indicate, for example, radio resources (e.g. SSB resource sets, CSI-RS resources, cells / frequencies / BWPs) on which to perform the UE MDT measurements. The MDT reporting configuration may indicate when to report the UE MDT measurements, e.g., periodically or event-based. The UE performs and reports UE MDT measurements in accordance with the MDT configuration.

[0248] As also mentioned above, the MDT configuration may include one or more monitoring conditions, which may be part of the first set of conditions pertaining to monitoring. Upon receiving the MDT configuration, the UE performs monitoring measurements and determines whether such monitoring measurements fulfill the monitoring condition(s). Once one or more of the monitoring conditions are fulfilled, the UE starts performing the UE MDT measurements in accordance with the MDT measurement configuration.

[0249] In various embodiments, the UE may stop performing the UE MDT measurements based on an indication or command from the RAN node. For example, the RAN node may send such an indication or command in response to determining that the one or more conditions for initiating the MDT measurements are no longer fulfilled, from one or more of the following:

[0250] • monitoring or MDT measurements received from the UE;

[0251] • the RAN MDT measurements; and

[0252] • an indication from the UE.

[0253] Alternately, the UE stops the third set of UE measurements autonomously upon determining that the one or more conditions for initiating the MDT measurements are no longer fulfilled.

[0254] Various features of the embodiments described above correspond to various operations illustrated in Figures 6-8, which show exemplary methods (e.g., procedures) for a management node, a RAN node, and a UE, respectively. In other words, various features of the operations described below correspond to various embodiments described above. Furthermore, the exemplary methods shown in Figures 6-8 can be used cooperatively to provide various benefits, advantages, and / or solutions to problems described herein. Although Figures 6-8 show specific blocks in particular orders, the operations of the exemplary methods can be performed in different orders than shown and can be combined and / or divided into blocks having different functionality than shown. Optional blocks or operations are indicated by dashed lines.

[0255] In particular, Figure 6 shows an exemplary method (e.g., procedure) for a management node configured for use in a communication network, according to various embodiments of the present disclosure. The exemplary method can be performed by any appropriate management node (e.g., OAM, SMO, etc.) such as described elsewhere herein.

[0256] The exemplary method includes the operations of block 610, where the management node determines a first set of conditions related to selection of UEs for MDT measurements to be used for training AI / ML models. The exemplary method also includes the operations of block 620, where the management node sends the first set of conditions to a RAN node that serves at least one UE. In some embodiments, the exemplary method also includes the operations of block 650, where the management node receives one or more of the following MDT measurements, for one or more served UEs selected by the RAN node in accordance with the first set of conditions:

[0257] • MDT measurements performed by the RAN node on the selected UEs;

[0258] • MDT measurements performed by the selected UEs; and

[0259] • predicted MDT measurements.

[0260] In some embodiments, the first set of conditions includes conditions on one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, UE traffic type, and status for one or more AI / ML models or model functionalities.

[0261] In some of these embodiments, the conditions on radio-related measurements and the conditions on traffic-related measurements include one or more of the following: a measurement range of interest, a measurement threshold, and a measurement difference threshold. In some of these embodiments, the radio-related measurements include one or more of the following: RSRP, RSRQ, RS SI, and SINR. Also, the traffic-related measurements include one or more of the following: packet loss rate, packet throughput, packet delay, and packet delay jitter.

[0262] In some of these embodiments, the conditions on UE traffic type include conditions on one or more of the following: data radio bearer (DRB), network slice, service, and quality-of-service (QoS). In some of these embodiments, the first set of conditions is sent to the RAN node with an identifier of an AI / ML model or model functionality, and the conditions on status for the identified AI / ML model or model functionality include one or more of the following:

[0263] • the identified AI / ML model or model functionality being activated or operational in a UE and / or in the RAN node;

[0264] • the identified AI / ML model or model functionality being supported by a UE and / or by the RAN node; • the identified AI / ML model or model functionality being applicable to a UE and / or to the RAN node; and

[0265] • one or more conditions on outputs of the identified AI / ML mode or model functionality. In some variants of these embodiments, the one or more conditions on outputs of the identified AI / ML model or model functionality include one or more of the following: one or more thresholds for predicted measurements, and one or more types of predicted events.

[0266] In some embodiments, the first set of conditions includes conditions on AI / ML model predictions of one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, a UE mobility-related event, and a UE failure- related event.

[0267] In some embodiments, the received MDT measurements performed by the RAN node include one or more of the following: uplink (UL) radio-related measurements, UL traffic-related measurements, positioning measurements on the selected UEs. In some embodiments, the received MDT measurements performed by the selected UEs include one or more of the following: downlink (DL) radio-related measurements, DL traffic-related measurements, UE positioning measurements, indication of a UE mobility-related event, and indication of a UE failure-related event.

[0268] In some embodiments, the first set of conditions includes a plurality of subsets, with each subset being specific to one or more of the following: respective cells served by the RAN node or another RAN node, respective beams provided by the RAN node or another RAN, or respective carrier frequencies served by the RAN node or another RAN node.

[0269] In some embodiments, the received MDT measurements are common to all conditions of the first set. In other embodiments, respective subsets of the received MDT measurements are specific to respective conditions in the first set.

[0270] In some embodiments, the exemplary method also includes the following operations, labelled with corresponding block numbers:

[0271] • (630) receiving from the RAN node an indication that one or more conditions of the first set have been fulfilled; and

[0272] • (640) based on the indication, sending to the RAN node an MDT measurement configuration that specifies MDT measurements to be collected.

[0273] The received MDT measurements are based on the MDT measurement configuration.

[0274] In some embodiments, the exemplary method also includes the operations of block 660, where the management node trains one or more AI / ML models based on the received MDT measurements.

[0275] In addition, Figure 7 shows an exemplary method (e.g., procedure) for a RAN node configured for use in a communication network, according to various embodiments of the present disclosure. The exemplary method can be performed by any appropriate RAN node (e.g., base station, eNB, gNB, CU, etc.) such as described elsewhere herein.

[0276] The exemplary method includes the operations of block 710, where the RAN node receives from a management node a first set of conditions related to selection of UEs for MDT measurements to be used for training AI / ML models. The exemplary method also includes the operations of block 750, where the RAN node selects one or more UEs, served by the RAN node, for MDT measurements in accordance with the first set of conditions. The exemplary method also includes the operations of block 780, where the RAN node initiates one or more MDT measurements with respect to the selected UEs.

[0277] In some embodiments, the exemplary method also includes the operations of block 720, where the RAN node determines one or more of the following based on the received first set of conditions: a UE monitoring configuration, and a RAN monitoring configuration.

[0278] In some of these embodiments, the exemplary method also includes the following operations, labelled with corresponding block numbers:

[0279] • (725) sending the UE monitoring configuration to a plurality of UEs served by the RAN node; and

[0280] • (730) receiving one of the following from the one or more UEs, in accordance with the UE monitoring configuration: an indication that at least one condition of the first set has been fulfilled, and UE monitoring measurements.

[0281] In such embodiments, selecting the one or more UEs in block 750 is based on the received indication or the received UE monitoring measurements. In some variants of these embodiments, the UE monitoring configuration includes a measurement configuration and a reporting configuration.

[0282] In other of these embodiments, the exemplary method also includes the following operations, labelled with corresponding block numbers:

[0283] • (740) initiating RAN monitoring measurements for the plurality of UEs based on the RAN monitoring configuration; and

[0284] • (745) determining based on the RAN monitoring measurements that the one or more UEs have fulfilled at least one condition of the first set.

[0285] In such embodiments, selecting the one or more UEs in block 750 is based on the determination in block 745. In some variants of these embodiments, a first entity or function of the RAN node (e.g., DU) performs the RAN monitoring measurements and a second entity or function of the RAN node (e.g., CU-UP) performs the MDT measurements on the selected UEs. In some of these embodiments, selecting the one or more UEs in block 750 is further based on a second set of conditions associated with the RAN node, including conditions on one or more of the following:

[0286] • RAN node capability of handling multiple MDT measurement sessions,

[0287] • UE capability or configurations need to perform the MDT measurements, and

[0288] • radio interface capacity available to handle UE reporting of MDT measurements.

[0289] In some embodiments, the exemplary method also includes the following operations, labelled with corresponding block numbers:

[0290] • (760) sending to the management node an indication that one or more conditions of the first set have been fulfilled; and

[0291] • (770) in response to the indication, receiving from the management node an MDT measurement configuration that specifies MDT measurements to be collected.

[0292] In such embodiments, the MDT measurements are initiated based on the MDT measurement configuration.

[0293] In some of these embodiments, the one or more MDT measurements initiated with respect to the selected UEs include one or more of the following:

[0294] • MDT measurements by the RAN node on the selected UEs,

[0295] • MDT measurements by the selected UEs, and

[0296] • predicted MDT measurements.

[0297] In some of these embodiments, initiating the MDT measurements in block 780 includes the following operations, labelled with corresponding block numbers:

[0298] • (781) determining an MDT configuration for the selected UEs based on the received MDT measurement configuration, wherein the MDT configuration includes an MDT measurement configuration and an MDT reporting configuration; and

[0299] • (782) sending the MDT configuration to the selected UEs.

[0300] In such embodiments, the MDT measurements may be reported (e.g., to the management node) by the selected UEs in accordance with the MDT reporting configuration.

[0301] In other of these embodiments, initiating the MDT measurements in block 780 includes the following operations, labelled with corresponding block numbers:

[0302] • (783) determining an MDT configuration for the RAN node based on the received MDT measurement configuration; and

[0303] • (784) performing the RAN MDT measurements on the selected UEs based on the MDT configuration. In some variants of these embodiments, the exemplary method also includes the operations of block 790, where the RAN node sends the RAN MDT measurements to the management node.

[0304] In some embodiments, for the MDT measurements performed by the RAN node on the selected UEs, a first entity or function of the RAN node (e.g., DU) performs a first subset and a second entity or function of the RAN node (e.g., CU-UP) performs a second subset.

[0305] In various embodiments, the first set of conditions can include any of the same content and / or have any of the same characteristics as the first set of conditions described above in relation to management node embodiments.

[0306] In some embodiments, the initiated MDT measurements by the RAN node on the selected UEs include one or more of the following: uplink (UL) radio-related measurements, UL traffic- related measurements, and positioning measurements. In some embodiments, the initiated MDT measurements by the selected UEs include one or more of the following: downlink (DL) radiorelated measurements, DL traffic-related measurements, positioning measurements, detection of a UE mobility -related event, and detection of a UE failure-related event.

[0307] In some embodiments, the MDT measurements are common to all conditions of the first set. In other embodiments, respective subsets of the MDT measurements are specific to respective conditions in the first set.

[0308] In addition, Figure 8 shows an exemplary method (e.g., procedure) for a UE configured for use in a communication network, according to various embodiments of the present disclosure. The exemplary method can be performed by any appropriate UE (e.g., wireless device, etc.) such as described elsewhere herein.

[0309] The exemplary method includes the operations of block 860, where based on a determination that the UE fulfills at least one condition of a first set of conditions related to selection of UEs for MDT measurements to be used for training AI / ML models, the UE receives an MDT configuration from a RAN node serving the UE. The MDT configuration includes an MDT measurement configuration and an MDT reporting configuration. The exemplary method also includes the operations of block 870, where the UE performs or predicts MDT measurements in accordance with the MDT measurement configuration. The exemplary method also includes the operations of block 880, where the UE sends the MDT measurements to a management node, in accordance with the MDT reporting configuration

[0310] In some embodiments, the exemplary method also includes the following operations, labelled with corresponding block numbers:

[0311] • (810) receiving from the RAN node a UE monitoring configuration, wherein the UE monitoring configuration includes a measurement configuration and a reporting configuration; and • (820) performing or predicting monitoring measurements in accordance with the UE monitoring configuration.

[0312] In some of these embodiments, the exemplary method also includes the operations of block 830, where the UE sends the monitoring measurements to the RAN node in accordance with the reporting configuration. The MDT configuration is received from the RAN node in block 860 in response to the RAN node determining, based on the reported monitoring measurements, that the UE fulfills at least one condition of the first set.

[0313] In other of these embodiments, the UE monitoring configuration includes one or more conditions of the first set and the exemplary method also includes the following operations, labelled with corresponding block numbers:

[0314] • (840) determining, from the monitoring measurements, that the UE fulfills at least one condition included in the UE monitoring configuration; and

[0315] • (850) sending, to the RAN node, an indication that the UE fulfills the at least one condition of the first set.

[0316] In such embodiments, the MDT configuration is received from the RAN node in block 860 in response to the indication.

[0317] In various embodiments, the first set of conditions can include any of the same content and / or have any of the same characteristics as the first set of conditions described above in relation to management node embodiments.

[0318] In some embodiments, the UE monitoring configuration includes an identifier of an AI / ML model or model functionality, and the conditions (of the first set) on status for the identified AI / ML model or model functionality include one or more of the following:

[0319] • the identified AI / ML model or model functionality being activated or operational in the UE;

[0320] • the identified AI / ML model or model functionality being supported by the UE;

[0321] • the identified AI / ML model or model functionality being applicable to the UE; and

[0322] • one or more conditions on outputs of the identified AI / ML mode or model functionality.

[0323] In some of these embodiments, the one or more conditions on outputs of the identified AI / ML model or model functionality include one or more of the following: one or more thresholds for predicted measurements, and one or more types of predicted events. In some of these embodiments, the predicted MDT measurements are predicted using the identified AI / ML model or model functionality for inference.

[0324] In some embodiments, the performed or predicted MDT measurements are common to all conditions of the first set. In other embodiments, respective subsets of the performed or predicted MDT measurements are specific to respective conditions in the first set. Although various embodiments are described above in terms of methods, techniques, and / or procedures, the person of ordinary skill will readily comprehend that such methods, techniques, and / or procedures can be embodied by various combinations of hardware and software in various systems, communication devices, computing devices, control devices, apparatuses, non-transitory computer-readable media, computer program products, etc.

[0325] Figure 9 shows an example of a communication system 900 in accordance with some embodiments. In this example, the communication system 900 includes a telecommunication network 902 that includes an access network 904, such as a radio access network (RAN), and a core network 906, which includes one or more core network nodes 908. In some embodiments, telecommunication network 902 can also include one or more Network Management (NM) nodes 920, which can be part of an operation support system (OSS), a business support system (BSS), and / or an 0AM system. The NM nodes can monitor and / or control operations of other nodes in access network 904 and core network 906. Although not shown in Figure 9, NM node 920 can be configured to communicate with other nodes in access network 904 and core network 906 for these purposes.

[0326] Access network 904 includes one or more access network nodes, such as network nodes 910a-b (one or more of which may be generally referred to as network nodes 910), or any other similar 3GPP access node or non-3GPP access point. Network nodes 910 facilitate direct or indirect connection of UEs, such as by connecting UEs 912a-d (one or more of which may be generally referred to as UEs 912) to the core network 906 over one or more wireless connections. In some embodiments, access network 904 can include a service management and orchestration (SMO) system or node 918, which can monitor and / or control operations of the access network node 910. This arrangement can be used, for example, when access network 904 utilizes an Open RAN (O-RAN) architecture. SMO system 918 can be configured to communicate with core network 906 and / or host 916, as shown in Figure 9.

[0327] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals 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, communication system 900 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. Communication system 900 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system. UEs 912 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with network nodes 910 and other communication devices. Similarly, network nodes 910 are arranged, capable, configured, and / or operable to communicate directly or indirectly with UEs 912 and / or with other network nodes or equipment in telecommunication network 902 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in telecommunication network 902.

[0328] In the depicted example, core network 906 connects network nodes 910 to one or more hosts, such as host 916. 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. Core network 906 includes one or more core network nodes (e.g., 908) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 908. Example core network nodes include 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).

[0329] Host 916 may be under the ownership or control of a service provider other than an operator or provider of access network 904 and / or telecommunication network 902, and may be operated by the service provider or on behalf of the service provider. Host 916 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 center, or any other such function performed by a server.

[0330] As a whole, communication system 900 of Figure 9 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system 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); 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) 902.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0331] In some examples, telecommunication network 902 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 902 may support network slicing to provide different logical networks to different devices that are connected to telecommunication network 902. For example, the telecommunications network 902 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.

[0332] In some examples, UEs 912 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to access network 904 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from access network 904. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard 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).

[0333] In the example, hub 914 communicates with access network 904 to facilitate indirect communication between one or more UEs (e.g., 912c and / or 912d) and network nodes (e.g., 910b). In some examples, hub 914 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, hub 914 may be a broadband router enabling access to core network 906 for the UEs. As another example, hub 914 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 910, or by executable code, script, process, or other instructions in hub 914. As another example, hub 914 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, hub 914 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, hub 914 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which hub 914 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, hub 914 acts as a proxy server or orchestrator for the UEs, in particular in if one or more of the UEs are low energy loT devices. Hub 914 may have a constant / persistent or intermittent connection to the network node 910b. Hub 914 may also allow for a different communication scheme and / or schedule between hub 914 and UEs (e.g., 912c and / or 912d), and between hub 914 and core network 906. In other examples, hub 914 is connected to core network 906 and / or one or more UEs via a wired connection. Moreover, hub 914 may be configured to connect to an M2M service provider over access network 904 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with network nodes 910 while still connected via hub 914 via a wired or wireless connection. In some embodiments, hub 914 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 910b. In other embodiments, hub 914 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 910b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0334] In some embodiments, any of UEs 912 may be configured to perform operations attributed to a UE in various embodiments described above, including the exemplary method shown in Figure 8. Likewise, any of network nodes 910 may be configured to perform operations attributed to a RAN node in various embodiments described above, including the exemplary method shown in Figure 7. Similarly, NM node 920, SMO node 918, host 916, and / or core network node 908 may be configured to perform operations attributed to a management node in various embodiments described above, including the exemplary method shown in Figure 6.

[0335] Figure 10 shows a UE 1000 in accordance with some embodiments. Examples of a UE 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-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by 3GPP, including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0336] A UE 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, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE 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, a UE 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).

[0337] UE 1000 includes processing circuitry 1002 that is operatively coupled via a bus 1004 to an input / output interface 1006, a power source 1008, a memory 1010, a communication interface 1012, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 10. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0338] Processing circuitry 1002 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 memory 1010. Processing circuitry 1002 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, processing circuitry 1002 may include multiple central processing units (CPUs).

[0339] In the example, input / output interface 1006 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 any combination thereof. An input device may allow a user to capture information into UE 1000. 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.

[0340] In some embodiments, power source 1008 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. Power source 1008 may further include power circuitry for delivering power from power source 1008 itself, and / or an external power source, to the various parts of UE 1000 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of power source 1008. Power circuitry may perform any formatting, converting, or other modification to the power from power source 1008 to make the power suitable for the respective components of UE 1000 to which power is supplied.

[0341] Memory 1010 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, memory 1010 includes one or more application programs 1014, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1016. Memory 1010 may store, for use by UE 1000, any of a variety of various operating systems or combinations of operating systems.

[0342] Memory 1010 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 / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ Memory 1010 may allow UE 1000 to access instructions, application 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 memory 1010, which may be or comprise a device-readable storage medium.

[0343] Processing circuitry 1002 may be configured to communicate with an access network or other network using communication interface 1012. Communication interface 1012 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1022. Communication interface 1012 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 UE or a network node in an access network). Each transceiver may include a transmitter 1012 and / or a receiver 1020 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, transmitter 1012 and receiver 1020 may be coupled to one or more antennas (e.g., antenna 1022) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0344] In the illustrated embodiment, communication functions of communication interface 1012 may include cellular communication, Wi-Fi communication, 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 in 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 / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0345] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 1012, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 10 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., an alert is sent when moisture is detected), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0346] As another example, a UE 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, the UE 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.

[0347] A UE, 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, city 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 head-mounted display for Augmented Reality (AR) or Virtual Reality (VR), 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. A UE in the form of an loT device 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 UE 1000 shown in Figure 10.

[0348] As yet another specific example, in an loT scenario, a UE 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 UE and / or a network node. The UE 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, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE 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.

[0349] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE 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 UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0350] In some embodiments, UE 1000 may be configured to perform various operations attributed to a UE in various embodiments described above, including the exemplary method shown in Figure 8.

[0351] Figure 11 shows a network node 1100 in accordance with some embodiments. Examples of network nodes include, but are not limited to, access points (e.g., radio access points) and base stations (e.g., radio base stations, Node Bs, eNBs, gNBs, etc.).

[0352] Base stations 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. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units 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).

[0353] Other examples of network nodes 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 (OAM) nodes, Operations Support System (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).

[0354] Network node 1100 includes processing circuitry 1102, memory 1104, communication interface 1106, and power source 1108. Network node 1100 may be composed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which network node 1100 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components 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, network node 1100 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1104 for different RATs) and some components may be reused (e.g., a same antenna 1110 may be shared by different RATs). Network node 1100 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1100, for example GSM, WCDMA, LTE, NR, WiFi, 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 1100.

[0355] Processing circuitry 1102 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 network node 1100 components, such as memory 1104, to provide network node 1100 functionality.

[0356] In some embodiments, processing circuitry 1102 includes a system on a chip (SOC). In some embodiments, processing circuitry 1102 includes one or more of radio frequency (RF) transceiver circuitry 1112 and baseband processing circuitry 1114. In some embodiments, RF transceiver circuitry 1112 and baseband processing circuitry 1114 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 1112 and baseband processing circuitry 1114 may be on the same chip or set of chips, boards, or units.

[0357] Memory 1104 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 processing circuitry 1102. Memory 1104 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 (collectively denoted computer program product 1104a) capable of being executed by processing circuitry 1102 and utilized by network node 1100. Memory 1104 may be used to store any calculations made by processing circuitry 1102 and / or any data received via communication interface 1106. In some embodiments, processing circuitry 1102 and memory 1104 is integrated.

[0358] Communication interface 1106 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, communication interface 1106 comprises port(s) / terminal(s) 1110 to send and receive data, for example to and from a network over a wired connection. Communication interface 1106 also includes radio frontend circuitry 1112 that may be coupled to, or in certain embodiments a part of, antenna 1110. Radio front-end circuitry 1112 comprises filters 1120 and amplifiers 1122. Radio front-end circuitry 1112 may be connected to antenna 1110 and processing circuitry 1102. The radio frontend circuitry may be configured to condition signals communicated between antenna 1110 and processing circuitry 1102. Radio front-end circuitry 1112 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. Radio front-end circuitry 1112 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1120 and / or amplifiers 1122. The radio signal may then be transmitted via antenna 1110. Similarly, when receiving data, antenna 1110 may collect radio signals which are then converted into digital data by radio front-end circuitry 1112. The digital data may be passed to processing circuitry 1102. In other embodiments, the communication interface may comprise different components and / or different combinations of components. In certain alternative embodiments, network node 1100 does not include separate radio front-end circuitry 1112; instead, processing circuitry 1102 includes radio front-end circuitry and is connected to antenna 1110. Similarly, in some embodiments, all or some of RF transceiver circuitry 1112 is part of communication interface 1106. In other embodiments, communication interface 1106 includes one or more ports or terminals 1116, radio front-end circuitry 1112, and RF transceiver circuitry 1112, as part of a radio unit (not shown), and communication interface 1106 communicates with the baseband processing circuitry 1114, which is part of a digital unit (not shown).

[0359] Antenna 1110 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. Antenna 1110 may be coupled to radio front-end circuitry 1112 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, antenna 1110 is separate from network node 1100 and connectable to network node 1100 through an interface or port.

[0360] Antenna 1110, communication interface 1106, and / or processing circuitry 1102 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, antenna 1110, communication interface 1106, and / or processing circuitry 1102 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0361] Power source 1108 provides power to the various components of network node 1100 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). Power source 1108 may further comprise, or be coupled to, power management circuitry to supply the components of network node 1100 with power for performing the functionality described herein. For example, network node 1100 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 power source 1108. As a further example, power source 1108 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0362] Embodiments of network node 1100 may include additional components beyond those shown in Figure 11 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, network node 1100 may include user interface equipment to allow input of information into network node 1100 and to allow output of information from network node 1100. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for network node 1100.

[0363] In some embodiments, network node 1100 may be configured to perform various operations attributed to a RAN node in various embodiments described above, including the exemplary method shown in Figure 7. In other embodiments, network node 1100 may be configured to perform various operations attributed to a management node in various embodiments described above, including the exemplary method shown in Figure 6.

[0364] Figure 12 is a block diagram illustrating a virtualization environment 1200 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 1200 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized.

[0365] Applications 1202 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 1200 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein. For example, one or more virtual nodes 1202 may be configured to perform operations attributed to a RAN node in various embodiments described above, including the exemplary method shown in Figure 7. As another example, one or more virtual nodes 1202 may be configured to perform operations attributed to a management node in various embodiments described above, including the exemplary method shown in Figure 6.

[0366] Hardware 1204 includes processing circuitry, memory that stores software and / or instructions (collectively denoted computer program product 1204a) 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 1206 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 1208a-b (one or more of which may be generally referred to as VMs 1208), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. Virtualization layer 1206 may present a virtual operating platform that appears like networking hardware to VMs 1208.

[0367] VMs 1208 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 1206. Different embodiments of the instance of a virtual appliance 1202 may be implemented on one or more of VMs 1208, 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.

[0368] In the context of NFV, each VM 1208 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each VM 1208, and that part of hardware 1204 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 VMs 1208 on top of hardware 1204 and corresponds to application 1202.

[0369] Hardware 1204 may be implemented in a standalone network node with generic or specific components. Hardware 1204 may implement some functions via virtualization. Alternatively, hardware 1204 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 1210, which, among others, oversees lifecycle management of applications 1202. In some embodiments, hardware 1204 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 1212 which may alternatively be used for communication between hardware nodes and radio units.

[0370] The foregoing merely illustrates the principles of the disclosure. Various modifications and alterations to the described embodiments will be apparent to those skilled in the art in view of the teachings herein. It will thus be appreciated that those skilled in the art will be able to devise numerous systems, arrangements, and procedures that, although not explicitly shown or described herein, embody the principles of the disclosure and can be thus within the spirit and scope of the disclosure. Various embodiments can be used together with one another, as well as interchangeably therewith, as should be understood by those having ordinary skill in the art.

[0371] The term unit, as used herein, can have conventional meaning in the field of electronics, electrical devices and / or electronic devices and can include, for example, electrical and / or electronic circuitry, devices, modules, processors, memories, logic solid state and / or discrete devices, computer programs or instructions for carrying out respective tasks, procedures, computations, outputs, and / or displaying functions, and so on, as such as those that are described herein.

[0372] Any appropriate steps, methods, features, functions, or benefits disclosed herein may be performed through one or more functional units or modules of one or more virtual apparatuses. Each virtual apparatus may comprise a number of these functional units. These functional units may be implemented via processing circuitry, which may include one or more microprocessor or microcontrollers, as well as other digital hardware, which may include Digital Signal Processor (DSPs), special-purpose digital logic, and the like. The processing circuitry may be configured to execute program code stored in memory, which may include one or several types of memory such as Read Only Memory (ROM), Random Access Memory (RAM), cache memory, flash memory devices, optical storage devices, etc. Program code stored in memory includes program instructions for executing one or more telecommunications and / or data communications protocols as well as instructions for carrying out one or more of the techniques described herein. In some implementations, the processing circuitry may be used to cause the respective functional unit to perform corresponding functions according one or more embodiments of the present disclosure.

[0373] As described herein, device and / or apparatus can be represented by a semiconductor chip, a chipset, or a (hardware) module comprising such chip or chipset; this, however, does not exclude the possibility that a functionality of a device or apparatus, instead of being hardware implemented, be implemented as a software module such as a computer program or a computer program product comprising executable software code portions for execution or being run on a processor. Furthermore, functionality of a device or apparatus can be implemented by any combination of hardware and software. A device or apparatus can also be regarded as an assembly of multiple devices and / or apparatuses, whether functionally in cooperation with or independently of each other. Moreover, devices and apparatuses can be implemented in a distributed fashion throughout a system, so long as the functionality of the device or apparatus is preserved. Such and similar principles are considered as known to a skilled person.

[0374] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0375] In addition, certain terms used in the present disclosure, including the specification and drawings, can be used synonymously in certain instances (e.g., “data” and “information”). It should be understood that although such terms may be used synonymously herein, there also may be instances when such terms are not intended to be used synonymously.

[0376] Embodiments of the techniques and apparatus described herein also include, but are not limited to, the following enumerated examples:

[0377] Al. A method performed by a management node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the method comprising: determining a first set of conditions related to selection of user equipment (UEs) for minimization of drive testing (MDT) measurements to be used for training AI / ML models; sending the first set of conditions to a radio access network (RAN) node that serves at least one UE; and receiving one or more of the following MDT measurements, for one or more served UEs selected by the RAN node in accordance with the first set of conditions: MDT measurements performed by the RAN node on the selected UEs;

[0378] MDT measurements performed by the selected UEs; and predicted MDT measurements.

[0379] A2. The method of embodiment Al, wherein the first set of conditions includes conditions on one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, UE traffic type, and status for one or more AI / ML models or model functionalities.

[0380] A3. The method of embodiment A2, wherein the conditions on radio-related measurements and the conditions on traffic-related measurements include one or more of the following: a measurement range of interest, a measurement threshold, and a measurement difference threshold.

[0381] A4. The method of any of embodiments A2-A3, wherein: the radio-related measurements include one or more of the following: RSRP, RSRQ,

[0382] RS SI, and SINR; and the traffic-related measurements include one or more of the following: packet loss rate, packet throughput, packet delay, and packet delay jitter.

[0383] A5. The method of any of embodiments A2-A4, wherein the conditions on UE traffic type include conditions on one or more of the following: data radio bearer (DRB), network slice, service, and quality-of-service (QoS).

[0384] A6. The method of any of embodiments A2-A5, wherein the first set of conditions is sent to the RAN node with an identifier of an AI / ML model or model functionality, and the conditions on status for the identified AI / ML model or model functionality include one or more of the following: the identified AI / ML model or model functionality being activated or operational in a UE and / or in the RAN node; the identified AI / ML model or model functionality being supported by a UE and / or by the RAN node; the identified AI / ML model or model functionality being applicable to a UE and / or to the RAN node; and one or more conditions on outputs of the identified AI / ML mode or model functionality.

[0385] A6a. The method of embodiment A6, wherein the one or more conditions on outputs of the identified AI / ML model or model functionality include one or more of the following: one or more thresholds for predicted measurements, and one or more types of predicted events.

[0386] A7. The method of any of embodiments Al-A6a, wherein the first set of conditions includes conditions on AI / ML model predictions of one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, a UE mobility- related event, and a UE failure-related event.

[0387] A8. The method of any of embodiments A1-A7, wherein the received MDT measurements performed by the RAN node include one or more of the following: uplink (UL) radio-related measurements, UL traffic-related measurements, positioning measurements on the selected UEs. A9. The method of any of embodiments A1-A8, wherein the received MDT measurements performed by the selected UEs include one or more of the following: downlink (DL) radiorelated measurements, DL traffic-related measurements, UE positioning measurements, indication of a UE mobility-related event, and indication of a UE failure-related event.

[0388] A10. The method of any of embodiments A1-A9, wherein the first set of conditions includes a plurality of subsets, with each subset being specific to one or more of the following: respective cells served by the RAN node or another RAN node, respective beams provided by the RAN node or another RAN, or respective carrier frequencies served by the RAN node or another RAN node.

[0389] Al 1. The method of embodiment A1-A10, wherein one of the following applies: the received MDT measurements are common to all conditions of the first set, or respective subsets of the received MDT measurements are specific to respective conditions in the first set.

[0390] A12. The method of any of embodiments Al-All, further comprising: receiving from the RAN node an indication that one or more conditions of the first set have been fulfilled; and based on the indication, sending to the RAN node an MDT measurement configuration that specifies MDT measurements to be collected, wherein the received MDT measurements are based on the MDT measurement configuration.

[0391] A13. The method of any of embodiments A1-A12, further comprising training one or more AI / ML models based on the received MDT measurements.

[0392] Bl . A method performed by a radio access network (RAN) node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the method comprising: receiving, from a management node, a first set of conditions related to selection of user equipment (UEs) for minimization of drive testing (MDT) measurements to be used for training AI / ML models; selecting one or more UEs, served by the RAN node, for MDT measurements in accordance with the first set of conditions; and initiating one or more of the following MDT measurements:

[0393] MDT measurements by the RAN node on the selected UEs, MDT measurements by the selected UEs, and predicted MDT measurements.

[0394] B2. The method of embodiment Bl, further comprising determining one or more of the following based on the received first set of conditions: a UE monitoring configuration, and a RAN monitoring configuration.

[0395] B2a. The method of embodiment B2, further comprising: sending the UE monitoring configuration to a plurality of UEs served by the RAN node; and receiving one of the following from the one or more UEs, in accordance with the UE monitoring configuration: an indication that at least one condition of the first set has been fulfilled, and UE monitoring measurements, wherein selecting the one or more UEs is based on the received indication or the received UE monitoring measurements.

[0396] B2b. The method of embodiment B2a, wherein the UE monitoring configuration includes a measurement configuration and a reporting configuration.

[0397] B3. The method of embodiment B2, further comprising: initiating RAN monitoring measurements for the plurality of UEs based on the RAN monitoring configuration; and determining based on the RAN monitoring measurements that the one or more UEs have fulfilled at least one condition of the first set, wherein selecting the one or more UEs is based on the determination.

[0398] B3a. The method of embodiment B3, wherein a first entity or function of the RAN node performs the RAN monitoring measurements, and a second entity or function of the RAN node performs the MDT measurements on the selected UEs. B4. The method of any of embodiments B2-B3a, wherein selecting the one or more UEs is further based on a second set of conditions associated with the RAN node, including conditions on one or more of the following:

[0399] RAN node capability of handling multiple MDT measurement sessions, UE capability or configurations need to perform the MDT measurements, and radio interface capacity available to handle UE reporting of MDT measurements.

[0400] B5. The method of any of embodiments B1-B4, further comprising: sending to the management node an indication that one or more conditions of the first set have been fulfilled; and in response to the indication, receiving from the management node an MDT measurement configuration that specifies MDT measurements to be collected, wherein the MDT measurements are initiated based on the MDT measurement configuration.

[0401] B5a. The method of embodiment B5, wherein initiating the MDT measurements comprises: determining an MDT configuration for the selected UEs based on the received MDT measurement configuration, wherein the MDT configuration includes an MDT measurement configuration and an MDT reporting configuration; and sending the MDT configuration to the selected UEs, wherein the MDT measurements are received from the selected UEs in accordance with the MDT reporting configuration.

[0402] B5b. The method of embodiment B5, wherein initiating the MDT measurements comprises: determining an MDT configuration for the RAN node based on the received MDT measurement configuration; and performing the RAN MDT measurements on the selected UEs based on the MDT configuration.

[0403] B5c. The method of embodiment B5b, further comprising sending the RAN MDT measurements to the management node.

[0404] B6. The method of any of embodiments Bl-B5b, wherein for the MDT measurements performed by the RAN node on the selected UEs, a first entity or function of the RAN node performs a first subset and a second entity or function of the RAN node performs a second subset.

[0405] B7. The method of any of embodiments B1-B6, wherein the first set of conditions includes conditions on one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, UE traffic type, and status for one or more AI / ML models or model functionalities.

[0406] B7a. The method of embodiment B7, wherein the conditions on radio-related measurements and the conditions on traffic-related measurements include one or more of the following: a measurement range of interest, a measurement threshold, and a measurement difference threshold.

[0407] B7b. The method of any of embodiments B7-B7a, wherein: the radio-related measurements include one or more of the following: RSRP, RSRQ, RS SI, and SINR; and the traffic-related measurements include one or more of the following: packet loss rate, packet throughput, packet delay, and packet delay jitter.

[0408] B8. The method of any of embodiments B7-B7b, wherein the conditions on UE traffic type include conditions on one or more of the following: data radio bearer (DRB), network slice, service, and quality-of-service (QoS).

[0409] B9. The method of any of embodiments B7-B8, wherein the first set of conditions is received from the management node with an identifier of an AI / ML model or model functionality, and the conditions on status for the identified AI / ML model or model functionality include one or more of the following: the identified AI / ML model or model functionality being activated or operational in a UE and / or in the RAN node; the identified AI / ML model or model functionality being supported by a UE and / or by the RAN node; the identified AI / ML model or model functionality being applicable to a UE and / or to the RAN node; and one or more conditions on outputs of the identified AI / ML mode or model functionality. B9a. The method of embodiment B9, wherein the one or more conditions on outputs of the identified AI / ML model or model functionality include one or more of the following: one or more thresholds for predicted measurements, and one or more types of predicted events.

[0410] BIO. The method of any of embodiments Bl-B9a, wherein the first set of conditions includes conditions on AI / ML model predictions of one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, a UE mobility- related event, and a UE failure-related event.

[0411] Bl 1. The method of any of embodiments Bl -BIO, wherein the MDT measurements performed by the RAN node on the selected UEs include one or more of the following: uplink (UL) radiorelated measurements, UL traffic-related measurements, and positioning measurements.

[0412] Bl 2. The method of any of embodiments A1-A8, wherein the MDT measurements performed by the selected UEs include one or more of the following: downlink (DL) radio-related measurements, DL traffic-related measurements, positioning measurements, detection of a UE mobility-related event, and detection of a UE failure-related event.

[0413] B13. The method of any of embodiments B1-B12, wherein the first set of conditions includes a plurality of subsets, with each subset being specific to one or more of the following: respective cells served by the RAN node or another RAN node, respective beams provided by the RAN node or another RAN, or respective carrier frequencies served by the RAN node or another RAN node.

[0414] Bl 4. The method of embodiment Bl -Bl 3, wherein one of the following applies: the MDT measurements are common to all conditions of the first set, or respective subsets of the MDT measurements are specific to respective conditions in the first set.

[0415] CL A method performed by a user equipment (UE) configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the method comprising: based on a determination that the UE fulfills at least one condition of a first set of conditions related to selection of UEs for minimization of drive testing (MDT) measurements to be used for training AI / ML models, receiving an MDT configuration from a radio access network (RAN) node serving the UE, wherein the MDT configuration includes an MDT measurement configuration and an MDT reporting configuration; performing or predicting MDT measurements in accordance with the MDT measurement configuration; and sending the MDT measurements to a management node, in accordance with the MDT reporting configuration.

[0416] C2. The method of embodiment Cl, further comprising: receiving from the RAN node a UE monitoring configuration, wherein the UE monitoring configuration includes a measurement configuration and a reporting configuration; and performing or predicting monitoring measurements in accordance with the UE monitoring configuration.

[0417] C2a. The method of embodiment C2, further comprising sending the monitoring measurements to the RAN node in accordance with the reporting configuration, wherein the MDT configuration is received from the RAN node in response to the RAN node determining, based on the reported monitoring measurements, that the UE fulfills at least one condition of the first set.

[0418] C2b. The method of embodiment C2, wherein the UE monitoring configuration includes one or more conditions of the first set, and the method further comprises: determining, from the monitoring measurements, that the UE fulfills at least one condition included in the UE monitoring configuration; and sending, to the RAN node, an indication that the UE fulfills the at least one condition of the first set, wherein the MDT configuration is received from the RAN node in response to the indication.

[0419] C3. The method of embodiment C2b, wherein the first set of conditions includes conditions on one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, UE traffic type, and status for one or more AI / ML models or model functionalities. C3a. The method of embodiment C3, wherein the conditions on radio-related measurements and the conditions on traffic-related measurements include one or more of the following: a measurement range of interest, a measurement threshold, and a measurement difference threshold.

[0420] C3b. The method of any of embodiments C3-C3a, wherein: the radio-related measurements include one or more of the following: RSRP, RSRQ, RS SI, and SINR; and the traffic-related measurements include one or more of the following: packet loss rate, packet throughput, packet delay, and packet delay jitter.

[0421] C4. The method of any of embodiments C3-C3b, wherein the conditions on UE traffic type include conditions on one or more of the following: data radio bearer (DRB), network slice, service, and quality-of-service (QoS).

[0422] C5. The method of any of embodiments C3-C4, wherein the UE monitoring configuration includes an identifier of an AI / ML model or model functionality, and the conditions on status for the identified AI / ML model or model functionality include one or more of the following: the identified AI / ML model or model functionality being activated or operational in the UE; the identified AI / ML model or model functionality being supported by the UE; the identified AI / ML model or model functionality being applicable to the UE; and one or more conditions on outputs of the identified AI / ML mode or model functionality.

[0423] C5a. The method of embodiment C5, wherein the one or more conditions on outputs of the identified AI / ML model or model functionality include one or more of the following: one or more thresholds for predicted measurements, and one or more types of predicted events.

[0424] C5b. The method of embodiments C5-C5a, wherein the predicted MDT measurements are predicted using the identified AI / ML model or model functionality for inference.

[0425] C6. The method of any of embodiments C2b-C5b, wherein the first set of conditions includes conditions on AI / ML model predictions of one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, a UE mobility- related event, and a UE failure-related event. C7. The method of any of embodiments C1-C6, wherein the MDT measurements performed or predicted by the UE include one or more of the following: downlink (DL) radio-related measurements, DL traffic-related measurements, positioning measurements, a detected or predicted UE mobility -related event, and a detected or predicted UE failure-related event.

[0426] C8. The method of any of embodiments C1-C7, wherein the first set of conditions includes a plurality of subsets, with each subset being specific to one or more of the following: respective cells served by the RAN node or another RAN node, respective beams provided by the RAN node or another RAN, or respective carrier frequencies served by the RAN node or another RAN node.

[0427] C9. The method of embodiment C1-C8, wherein one of the following applies: the performed or predicted MDT measurements are common to all conditions of the first set, or respective subsets of the performed or predicted MDT measurements are specific to respective conditions in the first set.

[0428] DI . A management node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the management node comprising: communication interface circuitry configured to communicate with radio access network (RAN) nodes of the communication network; and processing circuitry operatively coupled to the communication interface circuitry, wherein the processing circuitry and the communication interface circuitry are configured to perform operations corresponding to any of the methods of embodiments Al -Al 3.

[0429] D2. A management node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the management node being further configured to perform operations corresponding to any of the methods of embodiments A1-A13.

[0430] D3. A non-transitory, computer-readable medium storing computer-executable instructions that, when executed by processing circuitry of a management node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the management node, configure the management node to perform operations corresponding to any of the methods of embodiments Al -Al 3.

[0431] D4. A computer program product comprising computer-executable instructions that, when executed by processing circuitry of a management node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the management node, configure the management node to perform operations corresponding to any of the methods of embodiments Al -Al 3.

[0432] El. A radio access network (RAN) node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the RAN node comprising: communication interface circuitry configured to communicate with a management node and with user equipment (UEs); and processing circuitry operatively coupled to the communication interface circuitry, whereby the processing circuitry and the communication interface circuitry are configured to perform operations corresponding to any of the methods of embodiments Bl -Bl 4.

[0433] E2. A radio access network (RAN) node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the RAN node being further configured to perform operations corresponding to any of the methods of embodiments Bl -Bl 4.

[0434] E3. A non-transitory, computer-readable medium storing computer-executable instructions that, when executed by processing circuitry of a radio access network (RAN) node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, configure the RAN node to perform operations corresponding to any of the methods of embodiments Bl -Bl 4.

[0435] E4. A computer program product comprising computer-executable instructions that, when executed by processing circuitry of a radio access network (RAN) node configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, configure the RAN node to perform operations corresponding to any of the methods of embodiments Bl -Bl 4.

[0436] Fl . A user equipment (UE) configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the UE comprising: communication interface circuitry configured to communicate with a radio access network (RAN) node; and processing circuitry operatively coupled to the communication interface circuitry, whereby the processing circuitry and the communication interface circuitry are configured to perform operations corresponding to any of the methods of embodiments C1-C9.

[0437] F2. A user equipment (UE) configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, the UE being further configured to perform operations corresponding to any of the methods of embodiments C1-C9.

[0438] F3. A non-transitory, computer-readable medium storing computer-executable instructions that, when executed by processing circuitry of a user equipment (UE) configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, configure the UE to perform operations corresponding to any of the methods of embodiments C1-C9.

[0439] F4. A computer program product comprising computer-executable instructions that, when executed by processing circuitry of a user equipment (UE) configured to facilitate training of artificial intelligence / machine learning (AI / ML) models for use in a communication network, configure the UE to perform operations corresponding to any of the methods of embodiments C1-C9.

Claims

CLAIMS1. A method performed by a management node configured for use in a communication network, the method comprising: determining (610) a first set of conditions related to selection of user equipment, UEs, for minimization of drive testing, MDT, measurements to be used for training artificial intelligence / machine learning, AI / ML, models; and sending (620) the first set of conditions to a radio access network, RAN, node that serves at least one UE.

2. The method of claim 1, wherein the first set of conditions includes conditions on one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, UE traffic type, and status for one or more AI / ML models or model functionalities.

3. The method of claim 2, wherein one or more of the following applies: the conditions on radio-related measurements and the conditions on traffic-related measurements include one or more of the following: a measurement range of interest, a measurement threshold, and a measurement difference threshold; the radio-related measurements include one or more of the following: reference signal received power, RSRP; reference signal received quality, RSRQ; received signal strength, RSSI; and signal-to-interference-and-noise ratio, SINR; and the traffic-related measurements include one or more of the following: packet loss rate, packet throughput, packet delay, and packet delay jitter.

4. The method of any of claims 2-3, wherein the conditions on UE traffic type include conditions on one or more of the following: data radio bearer, DRB; network slice; service; and quality-of-service, QoS.

5. The method of any of claims 2-4, wherein the first set of conditions is sent to the RAN node with an identifier of an AI / ML model or model functionality, and the conditions on status for the identified AI / ML model or model functionality include one or more of the following: the identified AI / ML model or model functionality being activated or operational in a UE and / or in the RAN node;the identified AI / ML model or model functionality being supported by a UE and / or by the RAN node; the identified AI / ML model or model functionality being applicable to a UE and / or to the RAN node; and one or more conditions on outputs of the identified AI / ML mode or model functionality.

6. The method of any of claims 1-5, wherein the first set of conditions includes conditions on AI / ML model predictions of one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, a UE mobility-related event, and a UE failure-related event.

7. The method of any of claims 1-6, wherein the first set of conditions includes a plurality of subsets, with each subset being specific to one or more of the following: respective cells served by the RAN node or another RAN node, respective beams provided by the RAN node or another RAN, or respective carrier frequencies served by the RAN node or another RAN node.

8. The method of any of claims 1-7, further comprising receiving (650) one or more of the following MDT measurements, for one or more served UEs selected by the RAN node in accordance with the first set of conditions:MDT measurements performed by the RAN node on the selected UEs;MDT measurements performed by the selected UEs; and predicted MDT measurements.

9. The method of claim 8, wherein one or more of the following applies: the received MDT measurements performed by the RAN node include one or more of the following: uplink, UL, radio-related measurements; UL traffic-related measurements; and positioning measurements on the selected UEs; and the received MDT measurements performed by the selected UEs include one or more of the following: downlink, DL, radio-related measurements, DL traffic-related measurements, UE positioning measurements, indication of a UE mobility- related event, and indication of a UE failure-related event.

10. The method of any of claims 8-9, further comprising:receiving (630) from the RAN node an indication that one or more conditions of the first set have been fulfilled; and based on the indication, sending (640) to the RAN node an MDT measurement configuration that specifies MDT measurements to be collected, wherein the received MDT measurements are based on the MDT measurement configuration.

11. The method of any of claims 1-10, further comprising training (660) one or more AI / ML models based on the received MDT measurements.

12. A method performed by a radio access network, RAN, node configured for use in a communication network, the method comprising: receiving (710), from a management node, a first set of conditions related to selection of user equipment, UEs, for minimization of drive testing, MDT, measurements to be used for training artificial intelligence / machine learning, AI / ML, models; selecting (750) one or more UEs, served by the RAN node, for MDT measurements in accordance with the first set of conditions; and initiating (780) one or more MDT measurements with respect to the selected UEs.

13. The method of claim 12, further comprising determining (720) one or more of the following based on the received first set of conditions: a UE monitoring configuration, and a RAN monitoring configuration.

14. The method of claim 13, further comprising: sending (725) the UE monitoring configuration to a plurality of UEs served by the RAN node; and receiving (730) one of the following from the one or more UEs, in accordance with the UE monitoring configuration: an indication that at least one condition of the first set has been fulfilled, and UE monitoring measurements, wherein selecting (750) the one or more UEs is based on the received indication or the received UE monitoring measurements.

15. The method of claim 14, further comprising:initiating (740) RAN monitoring measurements for the plurality of UEs based on the RAN monitoring configuration; and determining (745) based on the RAN monitoring measurements that the one or more UEs have fulfilled at least one condition of the first set, wherein selecting (750) the one or more UEs is based on the determination.

16. The method of claim 15, wherein a first entity or function of the RAN node performs the RAN monitoring measurements, and a second entity or function of the RAN node performs the MDT measurements on the selected UEs.

17. The method of any of claims 13-16, wherein selecting (750) the one or more UEs is further based on a second set of conditions associated with the RAN node, including conditions on one or more of the following:RAN node capability of handling multiple MDT measurement sessions, UE capability or configurations need to perform the MDT measurements, and radio interface capacity available to handle UE reporting of MDT measurements.

18. The method of any of claims 12-17, further comprising: sending (760) to the management node an indication that one or more conditions of the first set have been fulfilled; and in response to the indication, receiving (770) from the management node an MDT measurement configuration that specifies MDT measurements to be collected, wherein the MDT measurements are initiated based on the MDT measurement configuration.

19. The method of claim 18, wherein the one or more MDT measurements initiated with respect to the selected UEs include one or more of the following:MDT measurements by the RAN node on the selected UEs,MDT measurements by the selected UEs, and predicted MDT measurements.

20. The method of claim 19, wherein one or more of the following applies: the MDT measurements performed by the RAN node on the selected UEs include one or more of the following: uplink, UL, radio-related measurements; UL traffic- related measurements, and positioning measurements; andthe MDT measurements performed by the selected UEs include one or more of the following: downlink, DL, radio-related measurements; DL traffic-related measurements; positioning measurements; detection of a UE mobility-related event; and detection of a UE failure-related event.

21. The method of any of claims 19-20, wherein initiating (780) the MDT measurements comprises: determining (781) an MDT configuration for the selected UEs based on the received MDT measurement configuration, wherein the MDT configuration includes an MDT measurement configuration and an MDT reporting configuration; and sending (782) the MDT configuration to the selected UEs.

22. The method of any of claims 19-20, wherein initiating (780) the MDT measurements comprises: determining (783) an MDT configuration for the RAN node based on the received MDT measurement configuration; and performing (784) the MDT measurements on the selected UEs based on the MDT configuration, wherein the method further comprises sending (790) the MDT measurements performed on the selected UEs to the management node.

23. The method of any of claims 19-22, wherein for the MDT measurements performed by the RAN node on the selected UEs, a first entity or function of the RAN node performs a first subset and a second entity or function of the RAN node performs a second subset.

24. The method of any of claims 12-23, wherein the first set of conditions includes conditions on one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, UE traffic type, and status for one or more AI / ML models or model functionalities.

25. The method of claim 24, wherein one or more of the following applies: the conditions on radio-related measurements and the conditions on traffic-related measurements include one or more of the following: a measurement range of interest, a measurement threshold, and a measurement difference threshold;the radio-related measurements include one or more of the following: reference signal received power, RSRP; reference signal received quality, RSRQ; received signal strength, RSSI; and signal-to-interference-and-noise ratio, SINR; and the traffic-related measurements include one or more of the following: packet loss rate, packet throughput, packet delay, and packet delay jitter.

26. The method of any of claims 24-25, wherein the conditions on UE traffic type include conditions on one or more of the following: data radio bearer, DRB; network slice; service; and quality-of-service, QoS..

27. The method of any of claims 24-26, wherein the first set of conditions is received from the management node with an identifier of an AI / ML model or model functionality, and the conditions on status for the identified AI / ML model or model functionality include one or more of the following: the identified AI / ML model or model functionality being activated or operational in a UE and / or in the RAN node; the identified AI / ML model or model functionality being supported by a UE and / or by the RAN node; the identified AI / ML model or model functionality being applicable to a UE and / or to the RAN node; and one or more conditions on outputs of the identified AI / ML mode or model functionality.

28. The method of any of claims 12-27, wherein the first set of conditions includes conditions on AI / ML model predictions of one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, a UE mobility- related event, and a UE failure-related event.

29. The method of any of claims 12-28, wherein the first set of conditions includes a plurality of subsets, with each subset being specific to one or more of the following: respective cells served by the RAN node or another RAN node, respective beams provided by the RAN node or another RAN, or respective carrier frequencies served by the RAN node or another RAN node.

30. A method performed by a user equipment, UE, configured for use in a communication network, the method comprising:based on a determination that the UE fulfills at least one condition of a first set of conditions related to selection of UEs for minimization of drive testing, MDT, measurements to be used for training artificial intelligence / machine learning, AI / ML, models, receiving (860) an MDT configuration from a radio access network, RAN, node serving the UE, wherein the MDT configuration includes an MDT measurement configuration and an MDT reporting configuration; performing or predicting (870) MDT measurements in accordance with the MDT measurement configuration; and sending (880) the MDT measurements to a management node, in accordance with the MDT reporting configuration.

31. The method of claim 30, further comprising: receiving (810) from the RAN node a UE monitoring configuration that includes a measurement configuration and a reporting configuration; and performing or predicting (820) monitoring measurements in accordance with the UE monitoring configuration.

32. The method of claim 31, further comprising sending (830) the monitoring measurements to the RAN node in accordance with the reporting configuration, wherein the MDT configuration is received from the RAN node in response to the reported monitoring measurements fulfilling at least one condition of the first set.

33. The method of claim 31, wherein the UE monitoring configuration includes one or more conditions of the first set, and the method further comprises: determining (840), from the monitoring measurements, that the UE fulfills at least one condition included in the UE monitoring configuration; and sending (850), to the RAN node, an indication that the UE fulfills the at least one condition of the first set, wherein the MDT configuration is received from the RAN node in response to the indication.

34. The method of claim 33, wherein the first set of conditions includes conditions on one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, UE traffic type, and status for one or more AI / ML models or model functionalities.

35. The method of claim 34, wherein one or more of the following applies: the conditions on radio-related measurements and the conditions on traffic-related measurements include one or more of the following: a measurement range of interest, a measurement threshold, and a measurement difference threshold. the radio-related measurements include one or more of the following: reference signal received power, RSRP; reference signal received quality, RSRQ; received signal strength, RSSI; and signal-to-interference-and-noise ratio, SINR; and the traffic-related measurements include one or more of the following: packet loss rate, packet throughput, packet delay, and packet delay jitter.

36. The method of any of claims 34-35, wherein the conditions on UE traffic type include conditions on one or more of the following: data radio bearer, DRB; network slice; service; and quality-of-service, QoS.

37. The method of any of claims 34-36, wherein the UE monitoring configuration includes an identifier of an AI / ML model or model functionality, and the conditions on status for the identified AI / ML model or model functionality include one or more of the following: the identified AI / ML model or model functionality being activated or operational in the UE; the identified AI / ML model or model functionality being supported by the UE; the identified AI / ML model or model functionality being applicable to the UE; and one or more conditions on outputs of the identified AI / ML mode or model functionality.

38. The method of any of claims 33-37, wherein the first set of conditions includes conditions on AI / ML model predictions of one or more of the following: radio-related measurements, traffic-related measurements, UE mobility state, UE location, a UE mobility- related event, and a UE failure-related event.

39. The method of any of claims 30-38, wherein the MDT measurements performed or predicted by the UE include one or more of the following: downlink, DL, radio-related measurements; DL traffic-related measurements; positioning measurements, a detected or predicted UE mobility-related event; and a detected or predicted UE failure-related event.

40. The method of any of claims 30-39, wherein the first set of conditions includes a plurality of subsets, with each subset being specific to one or more of the following: respective cells served by the RAN node or another RAN node, respective beams provided by the RAN node or another RAN, or respective carrier frequencies served by the RAN node or another RAN node.

41. Management node (510, 908, 916, 918, 920, 1100, 1202) configured for use in a communication network (198, 199, 902), the management node comprising: communication interface circuitry (1106, 1204) configured to communicate with radio access network, RAN, nodes (110, 120, 530, 910, 1100, 1202) of the communication network; and processing circuitry (1102, 1204) operatively coupled to the communication interface circuitry, wherein the processing circuitry and the communication interface circuitry are configured to: determine a first set of conditions related to selection of user equipment, UEs (105, 540, 912, 1000) for minimization of drive testing, MDT, measurements to be used for training artificial intelligence / machine learning, AI / ML, models; and send the first set of conditions to a RAN node that serves at least one UE.

42. The management node of claim 41, wherein the processing circuitry and the communication interface circuitry are further configured to perform operations corresponding to any of the methods of claims 2-11.

43. Non-transitory, computer-readable medium (1104, 1204) storing computer-executable instructions that, when executed by processing circuitry (1102, 1204) of a management node (510, 908, 916, 918, 920, 1100, 1202) configured for use in a communication network (198, 199, 902), configure the management node to perform operations corresponding to any of the methods of claims 1-12.

44. Radio access network, RAN, node (110, 120, 530, 910, 1100, 1202) configured for use in a communication network (198, 199, 902), the RAN node comprising: communication interface circuitry (1106, 1204) configured to communicate with a management node (510, 908, 916, 918, 920, 1100, 1202) and with user equipment, UEs (105, 540, 912, 1000); andprocessing circuitry (1102, 1204) operatively coupled to the communication interface circuitry, wherein the processing circuitry and the communication interface circuitry are configured to: receive, from the management node, a first set of conditions related to selection of UEs for minimization of drive testing, MDT, measurements to be used for training artificial intelligence / machine learning, AI / ML, models; select one or more UEs, served by the RAN node, for MDT measurements in accordance with the first set of conditions; and initiate one or more MDT measurements with respect to the selected UEs.

45. The RAN node of claim 44, wherein the processing circuitry and the communication interface circuitry are further configured to perform operations corresponding to any of the methods of claims 13-29.

46. Non-transitory, computer-readable medium (1104, 1204) storing computer-executable instructions that, when executed by processing circuitry (1102, 1204) of a radio access network, RAN, node (110, 120, 530, 910, 1100, 1202) configured for use in a communication network (198, 199, 902), configure the RAN node to perform operations corresponding to any of the methods of claims 12-29.

47. User equipment, UE (105, 540, 912, 1000) configured for use in a communication network (198, 199, 902), the UE comprising: communication interface circuitry (1012) configured to communicate with a radio access network, RAN, node (110, 120, 530, 910, 1100, 1202) of the communication network; and processing circuitry (1002) operatively coupled to the communication interface circuitry, wherein the processing circuitry and the communication interface circuitry are configured to: based on a determination that the UE fulfills at least one condition of a first set of conditions related to selection of UEs for minimization of drive testing, MDT, measurements to be used for training artificial intelligence / machine learning, AI / ML, models, receive an MDT configuration from the RAN, node, wherein the MDT configuration includes an MDT measurement configuration and an MDT reporting configuration;perform or predict MDT measurements in accordance with the MDT measurement configuration; and send the MDT measurements to a management node (510, 908, 916, 918, 920, 1100, 1202), in accordance with the MDT reporting configuration.

48. The UE of claim 47, wherein the processing circuitry and the communication interface circuitry are further configured to perform operations corresponding to any of the methods of claims 31-40.

49. Non-transitory, computer-readable medium (1010) storing computer-executable instructions that, when executed by processing circuitry (1002) of user equipment, UE (105, 540, 912, 1000) configured for use in a communication network (198, 199, 902), configure the UE to perform operations corresponding to any of the methods of claims 30-40.

Images