First unit, second unit, method performed by first unit, and method performed by second unit of a distributed base station

Abstract

A method performed by a first unit of a distributed base station is disclosed. The method includes determining which Artificial Intelligence, AI, / Machine Learning, ML, models to be activated / deactivated / switched to other AI / ML models for AI / ML model management, based on user equipment, UE, capability for AI / ML model management.

Description

FIRST UNIT, SECOND UNIT, METHOD PERFORMED BY FIRST UNIT, AND METHOD PERFORMED BY SECOND UNIT OF A DISTRIBUTED BASE STATION

[0001] The present disclosure relates to a communication system. The disclosure has particular but not exclusive relevance to wireless communication systems and devices thereof operating according to the 3rd Generation Partnership Project (3GPP) standards or equivalents or derivatives thereof (including LTE-Advanced, Next Generation or 5G networks, future generations, and beyond). The disclosure has particular, although not necessarily exclusive, relevance to providing improved signalling for leveraging artificial intelligence and machine learning (AI / ML) models in 'New Radio' systems (also referred to as 'Next Generation' systems), and similar systems.

[0002] Earlier developments of the 3GPP standards were referred to as the Long-Term Evolution (LTE) of Evolved Packet Core (EPC) network and Evolved UMTS Terrestrial Radio Access Network (E-UTRAN), also commonly referred as '4G'. More recently, the term '5G' and 'new radio' (NR) has started to be used to refer to an evolving communication technology that is expected to support a variety of applications and services. Various details of 5G networks are described in, for example, the 'NGMN 5G White Paper' V1.0 (NPL 2) by the Next Generation Mobile Networks (NGMN) Alliance, which document is available from https: / / www.ngmn.org / 5g-white-paper.html. 3GPP intends to support 5G by way of the so-called 3GPP Next Generation (NextGen) radio access network (RAN) and the 3GPP NextGen core network.

[0003] Under the 3GPP standards, a NodeB (or an eNB in LTE, and gNB in 5G) is the radio access network (RAN) node (or simply 'access node', 'access network node' or 'base station') via which communication devices (user equipments or 'UEs') connect to a core network and communicate with other communication devices or remote servers. For simplicity, the present application will use the term access network node, RAN node or base station to refer to any such access nodes.

[0004] Also for simplicity, the present application will use the term mobile device, user device, or UE to refer to any communication device that is able to connect to the core network via one or more base stations. Although the present application may refer to mobile devices in the description, it will be appreciated that the technology described can be implemented on any communication devices (mobile and / or generally stationary) that can connect to a communications network for sending / receiving data, regardless of whether such communication devices are controlled by human input or software instructions stored in memory.

[0005] In the current 5G architecture, the gNB structure may be split into two or more parts. In some RAN implementations there are two parts, known as the Central Unit (CU or gNB-CU) - sometimes referred to as a 'control unit' - and the Distributed Unit (DU or gNB-DU), connected by an F1 interface. This enables the use of a 'split' architecture in which the typically 'higher' CU layers (for example, but not necessarily or exclusively, Packet Data Convergence Protocol (PDCP) and Radio Resource Control (RRC) layers) and the, 'lower' DU layers (for example, but not necessarily or exclusively, Radio Link Control (RLC), Media (sometimes referred to as 'Medium') Access Control (MAC), and Physical (PHY) layers) are separated between a particular CU, and one or more DUs that are connected to and controlled by that CU via the F1 interface. Thus, for example, the higher layer CU functionality for a number of gNBs may be implemented centrally (for example, by a single processing unit, or in a cloud-based or virtualised system), whilst retaining the lower layer DU functionality locally separately for each gNB.

[0006] In more recently proposed RAN distributed architectures, in addition to the CU and DU, the concept of a Radio Unit (RU) - sometimes referred to as a 'remote unit' - has been introduced. In this architecture the RU is responsible for handling the digital front end (DFE), digital beamforming functionality and, typically, the functionality of the lower parts of the PHY layer, whilst the DU typically handles the higher parts of the PHY layer and the RLC and MAC layers. The CU in this architecture continues to be responsible for controlling one or more DUs (each DU corresponding to a different respective gNB) and to handle higher layer signalling (typically RRC and PDCP layers).

[0007] The actual functional split between the CU and DUs (and potentially RUs where applicable) of these distributed architectures is flexible allowing the functionality to be optimised for different use cases. Effectively, the split architecture enables a 5G network to use a different distribution of protocol stacks between CU and DUs (and potentially RUs) depending on, for example, midhaul availability and network design.

[0008] The choice of how to split functions in the architecture depends on, among other things, factors related to radio network deployment scenarios, constraints and intended supported use cases. Key considerations include: the need to support a specific quality of service for each service offered and for real / non-real time applications; support of specific user density and load demand in a given geographical area; and available transport networks with different performance levels.

[0009] Some of the additional developments in 3GPP relate to the use of artificial intelligence (AI) and machine learning (ML), often abbreviated to AI / ML. Some AI / ML use cases are given below (though it will be appreciated that many use cases may be defined): 　　channel state information (CSI) feedback enhancement: e.g., overhead reduction, improved accuracy, prediction; 　　Beam management: e.g., beam prediction in time, and / or spatial domain for overhead and latency reduction, beam selection accuracy improvement; 　　Positioning accuracy enhancements for different scenarios including, e.g., those with heavy non-line of sight (NLOS) conditions.

[0010] Specifically, predictions or inferences generated using an AI / ML model can be used as part of various methods for improving the reliability or efficiency of communications in the network. For example, AI / ML models can be used to predict the path of a UE based on previous mobility of the UE, used for beam management (as mentioned above), or used in methods of encoding and transmitting information. An AI / ML model may be hosted at a base station (or any other suitable network node), and the base station may perform control of communication resources for UEs it serves, and / or perform control related to the status of a UE (e.g. control of UE mobility, or control of a radio resource control, RRC, state of the UE) based on an inference (e.g. determination or prediction) generated using the AI / ML model. The base station may also transmit an inference generated using the model to another node in the network, for use at the other node. Alternatively, an AI / ML model may be hosted at two nodes of the network, for example at a base station and at a UE. In this case, the base station and the UE may both make determinations and / or predictions using the model. For example, the UE may use the model as part of an encoding process for encoding (and / or compressing) CSI for transmission to the base station as mentioned above, and the base station may use the same model as part of a corresponding decoding (and / or decompression) process for decoding the CSI received from the UE.

[0011] The 3rdGeneration Partnership Project (3GPP) is studying how AI / ML functionality can be leveraged in the context of communications networks. For instance, what level of collaboration between the network and user equipment served by the network is needed when deploying AI / ML features. In this regard, three 'network-UE collaboration levels' have been proposed so far: 　　Level x: No collaboration between the network and the UE. Specifically, level x is an implementation-based AI / ML operation without any dedicated AI / ML-specific enhancement (or enhancements). 　　Level y: Signalling-based collaboration without model transfer. For example, this level is applicable when model training is performed offline, and models are registered to a base station and the UE is offline. Here, the base station and the UE are aware of available models (before operation), and the base station is only required to activate / deactivate UE residing models. 　　Level z: Signalling-based collaboration with model transfer.

[0012] Two AI / ML model types are currently proposed: 　　Single-sided model: A single-sided AI / ML model is deployed (hosted) only at the UE side or at the network side. One example this type of model is beam prediction in time, which can be deployed at the UE side. However, even when the model is a single-sided model, it will be appreciated that the model need not necessarily be trained at e.g. UE 3 or a base station 5. For example, the model could be trained at the base station 5 or at another node in the network (e.g. core network node / function), and then transmitted to the UE 3 for use at the UE 3. In other words, the AI / ML model may be trained at another network node, and then transferred / deployed to the UE 3. 　　Two-sided model: Alternatively, the AI / ML model may be a 'two-sided' model, in which an AI / ML model is hosted at the UE 3, and a corresponding AI / ML model is hosted at the base station 5 (however, the models need not necessarily be hosted at a UE 3 and a base station 5 - any other suitable two network nodes could alternatively be used). Such a model may be referred to as a 'paired' AI / ML model, over which joint inference is performed (the AI / ML model hosted at the UE 3 and the AI / ML model hosted at the base station 5 may be the same AI / ML model, but need not necessarily be the same model). The joint inference comprises an AI / ML inference whose inference is performed jointly across the UE 3 and the network. The first part of the inference may be performed by UE 3, and then the remaining part may be performed by the base station 5 (or at another network-side node). These roles may be reversed, such that the first part of the inference is performed at the network side and the second part at the UE side. One example of this type of model could be channel state information (CSI) compression, where the UE performs CSI compression and network performs CSI decompression. As with the single-sided model case, the two-sided model (or models) may be trained at any suitable network node, and then transmitted to the UE 3 and the base station 5 (or another respective node or nodes).

[0013] As part of 3GPP studies, it is proposed to study the impact on current specifications in supporting multiple AI models for the same functionality, for instance, aspects relating to the procedural and assistance signalling for model switching and / or selection.

[0014] Further aspects to be studied include the definition of components (if necessary) and necessity thereof, in AI / ML life cycle management (LCM), such as: 　　Model training; 　　Model deployment: This includes the process of compiling a trained AI / ML model and packaging it into an executable format and delivering to a target device. 　　Model inference operation; 　　Model selection, activation, deactivation, switching, and fallback operation: 　　　　Model selection refers to the selection of an AI / ML model among models for the same functionality. 　　　　Model switching, i.e., switching among a group of models where each model is for a particular scenario / configuration / site; 　　　　Fallback: Switching off AI / ML operation to operate with legacy RAN procedure (i.e., non-AI / ML based procedure); 　　Model monitoring; 　　　　Study AI / ML model monitoring for at least the following purposes: model activation, deactivation, selection, switching, fallback, and update (including re-training). 　　Model update: This includes model fine-tuning, retraining, and re-development via online / offline training. 　　　　Model update, i.e., using one model whose parameters are flexibly updated as the scenario / configuration / site that the device experiences changes over time. Fine-tuning is one example. 　　Model transfer; 　　UE capability.

[0015] It has been proposed to study the LCM procedure on the basis that an AI / ML model has a model ID with associated information and / or model functionality for at least some AI / ML operations.

[0016] It has been further proposed to monitor AI / ML models as they are deployed in communications networks. Specifically, the following metrics / methods are proposed for study with respect to AI / ML model monitoring in lifecycle management: 　　Monitoring based on inference accuracy, including metrics related to intermediate key performance indicators (KPIs); and 　　Monitoring based on system performance, including metrics related to system performance KPIs.

[0017] Additional monitoring under study relates to monitoring based on data distribution, which may be input-based, e.g., monitoring: the validity of the AI / ML input, out-of-distribution detection, drift detection of input data, or checking SNR, delay spread, etc., or output-based: e.g., drift detection of output data. Monitoring may also be based on applicable conditions in the communication system (e.g. related to load, path loss, etc). The above noted model monitoring, and any associated calculations, may be performed on the network-side or at the UE-side.

[0018] However, improved methods for coordinating the management of AI / ML features / functionalities / models are needed within communications networks, particularly so in the case where the communications networks uses a distributed base station (such as a gNB) comprising a central unit (CU) and one or more distributed units (DUs).

[0019] NPL 1: 3GPP TS 38.331 NPL 2: NGMN 5G White Paper' V1.0 NPL 3: 3GPP specification TS 38.473

[0020] The disclosure aims to provide apparatus and methods that at least partially address the above needs and / or issues.

[0021] In one aspect there is provided a method performed by a first unit of a distributed base station, the method comprising: 　　determining which Artificial Intelligence, AI, / Machine Learning, ML, models to be activated / deactivated / switched to other AI / ML models for AI / ML model management, based on user equipment, UE, capability for AI / ML model management.

[0022] In one aspect there is provided a method performed by a first unit of a distributed base station, the method comprising: 　　transmitting, to a second unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

[0023] In one aspect there is provided a method performed by a second unit of a distributed base station, the method comprising: 　　receiving, to a first unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

[0024] In one aspect there is provided a first unit of a distributed base station comprising: 　　means for determining which Artificial Intelligence, AI, / Machine Learning, ML, models to be activated / deactivated / switched to other AI / ML models for AI / ML model management, based on user equipment, UE, capability for AI / ML model management.

[0025] In one aspect there is provided a first unit of a distributed base station comprising: 　　means for transmitting, to a second unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

[0026] In one aspect there is provided a second unit of a distributed base station comprising: 　　means for receiving, from a first unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

[0027] According to the present disclosure, it is possible to provide a method performed by a first unit, a method performed by a second unit, a first unit, and a second unit.

[0028] Detailed examples embodiments of the disclosure will now be described, by way of example, with reference to the accompanying drawings in which:

[0029] Fig. 1 schematically illustrates a mobile ('cellular' or 'wireless') communication system 1;Fig 2 illustrates a typical frame structure that may be used in the communication system 1 of Fig. 1;Fig. 3 illustrates a framework in respect of an AI / ML model;Fig. 4 shows an illustration of a method of training an AI / ML model, and of monitoring the performance of the AI / ML model;Fig. 5 illustrates the relationship between AI / ML features, functionalities and models;Fig. 6 illustrates the exchange of information between a DU 5b and a CU 5c for the activation of network operated AI / ML models;Fig. 7 illustrates the exchange of information between a UE 3, DU 5b and a CU 5c for the CU 5c to take a model management decision;Fig. 8 illustrates the exchange of information between a UE 3, DU 5b and a CU 5c for the DU 5b to take a model management decision;Fig. 9 illustrates the exchange of information between a UE 3, DU 5b and a CU 5c for the CU 5c and DU 5b to take a combined model management decision;Fig. 10 is a schematic block diagram illustrating the main components of a UE 3 for the communication system 1 of Fig. 1;Fig. 11 is a schematic block diagram illustrating the main components of a base station 5 of a distributed type for the communication system 1 of Fig. 1; andFig. 12 is a schematic block diagram illustrating the main components of a core network node or function for the communication system 1 of Fig. 1.

[0030] < Overview > 　　An exemplary communication system will now be described in general terms, by way of example only, with reference to Figs. 1 to 5.

[0031] Fig. 1 schematically illustrates a mobile ('cellular' or 'wireless') communication system 1 to which examples of the present disclosure are applicable.

[0032] In the communication system 1, user equipment (UEs) 3-1, 3-2, 3-3 (e.g. mobile telephones and / or other mobile devices) can communicate with each other via a radio access network (RAN) node 5 that operates according to one or more compatible radio access technologies (RATs). In the illustrated example, the RAN node 5 comprises a distributed base station 5 or 'gNB' operating one or more associated cells 9. Communication via the RAN node 5 is typically routed through an associated core network 7 (e.g. a 5G / 6G or later generation core network or evolved packet core network (EPC)).

[0033] As those skilled in the art will appreciate, whilst three UEs 3 and one base station 5 are shown in Fig. 1 for illustration purposes, the system, when implemented, will typically include other base stations 5 and UEs 3.

[0034] Each base station 5 controls one or more associated cells 9 either directly, or indirectly via one or more other nodes (such as home base stations, relays, remote radio heads, distributed units, and / or the like). It will be appreciated that the base stations 5 may be configured to support 4G, 5G, 6G, and / or later generation and / or any other 3GPP or non-3GPP communication protocols.

[0035] In this example the illustrated RAN node 5 comprises a distributed base station comprising at least one distributed unit (DU) 5b (e.g., a gNB-DU or the like), and a central unit (CU) 5c (e.g., a gNB-CU or the like). The CU 5c employs a separated control plane and user plane and so is, itself, split between a control plane function (CU-CP) and a user plane function (CU-UP) which respectively communicate, with the DU 5b via an appropriate interface (e.g. an F1-C interface) and an appropriate interface (e.g. F1-U interface) (together forming an F1 interface (or 'reference point')), and with one another via an appropriate interface (e.g. an E1 interface). It will be appreciated that while, in this example, the DU 5b includes the physical and virtual elements required to provide the functionality of the lower parts of the PHY layer and hence communicate with the UEs 3 over the air interface, the RAN node 5 may alternatively (or additionally) include one or more separate radio units (RUs) (e.g., providing this functionality of the lower parts of the PHY layer). It will, nevertheless, be appreciated that whilst distributed RAN node 5 is shown and described, the RAN node 5 may be provided in a non-distributed form, for example as an integrated gNB or eNB.

[0036] The UEs 3 and their serving base station 5 are connected via an appropriate air interface (for example the so-called 'Uu' interface and / or the like). Neighbouring base stations 5 may be connected to each other via an appropriate base station to base station interface (such as the so-called 'X2' interface, 'Xn' interface and / or the like).

[0037] The core network 7 includes a number of logical nodes (or 'functions') for supporting communication in the communication system 1. In this example, the core network 7 comprises control plane functions (CPFs) 10 and one or more network node entities for the communication of user data (e.g. user plane functions (UPFs) 11). The CPFs 10 include one or more network node entities for the communication of control signalling (e.g. Access and Mobility Management Functions (AMFs) 10-1), one or more network node entities for session management (e.g. Session Management Functions (SMFs) 10-2) and a number of other functions 10-n (such as, for example, an Authentication Server Function (AUSF) which facilitates security processes, a Unified Data Management (UDM) entity for managing user specific data (e.g., for access authorization, user registration, and data network profiles), a Policy Control Function (PCF), an Application Function (AF), and / or the like). It will be appreciated that the nodes or functions may have different names in different systems.

[0038] The RAN node 5 is connected to the core network nodes via appropriate interfaces (or 'reference points') such as an N2 reference point between the CU 5c (CU-CP) of the RAN and the AMF 10-1 for the communication of control signalling, and an N3 reference point between the CU 5c (CU-UP) of the RAN and each UPF 11 for the communication of user data. The UEs 3 are each connected to the AMF 10-1 via a non-access stratum (NAS) connection over an appropriate interface (e.g. an N1 reference point (analogous to the S1 reference point in LTE)). It will be appreciated, that N1 communications are routed transparently via the RAN.

[0039] One or more UPFs 11 are connected to an external data network (e.g., an IP network such as the Internet) via an appropriate interface (e.g. an N6 reference point) for communication of the user data.

[0040] The AMF 10-1 performs mobility management related functions, maintains the NAS signalling connection with each UE 3 and manages UE registration. The AMF 10-1 is also responsible for managing paging. The SMF 10-2 provides session management functionality (that formed part of MME functionality in LTE) and additionally combines some control plane functions (provided by the serving gateway and packet data network gateway in LTE). The SMF 10-2 also allocates IP addresses to each UE 3.

[0041] The base station 5 of the communication system 1 may be configured to operate at least one cell 9 on an associated time-division duplex (TDD) carrier that operates in unpaired spectrum. It will be appreciated that the base station 5 may also operate at least one cell 9 on an associated frequency-division duplex (FDD) carrier that operates in paired spectrum.

[0042] The base station 5 is also configured for transmission of, and the UEs 3 are configured for the reception of, control information and user data via a number of downlink (DL) physical channels and for transmission of a number of physical signals. The DL physical channels correspond to resource elements (REs) carrying information originating from a higher layer, and the DL physical signals are used in the physical layer and correspond to REs which do not carry information originating from a higher layer.

[0043] The physical channels may include, for example, a physical downlink shared channel (PDSCH), a physical broadcast channel (PBCH), and a physical downlink control channel (PDCCH). The PDSCH carries data sharing the PDSCH's capacity on a time and frequency basis. The PDSCH can carry a variety of items of data including, for example, user data, UE-specific higher layer control messages mapped down from higher channels, system information blocks (SIBs), and paging. The PDCCH carries downlink control information (DCI) for supporting a number of functions including, for example, scheduling the downlink transmissions on the PDSCH and also the uplink data transmissions on a physical uplink shared channel (PUSCH). The PBCH provides UEs 3 with the Master Information Block (MIB). It also, in conjunction with the PDCCH, supports the synchronisation of time and frequency, which aids cell acquisition, selection and re-selection. The UE 3 may receive a Synchronization Signal Block (SSB), and the UE 3 may assume that reception occasions of a PBCH, primary synchronization signal (PSS) and secondary synchronization signal (SSS) are in consecutive symbols and form a SS / PBCH block. The base station 5 may transmit a number of synchronization signal (SS) blocks corresponding to different DL beams. The total number of SS blocks may be confined, for example, within a 5 ms duration as an SS burst. The periodicity of the SSB transmissions may be indicated to the UE 3 using any suitable signalling (e.g. per serving cell using ssb-periodicityServingCell). The periodicity value for the SSB may be, for example, greater than or equal to 20 ms. For initial cell selection, the UE 3 may be configured to assume that an SS burst occurs with a periodicity of 2 frames. The UE 3 may also be provided with an indication of which SSBs within a 5 ms duration are transmitted (e.g. using ssb-PositionsInBurst).

[0044] The DL physical signals may include, for example, reference signals (RSs) and synchronization signals (SSs). A reference signal (sometimes known as a pilot signal) is a signal with a predefined special waveform known to both the UE 3 and the base station 5. The reference signals may include, for example, cell specific reference signals, UE-specific reference signal (UE-RS), downlink demodulation signals (DMRS), and channel state information reference signal (CSI-RS).

[0045] Similarly, the UEs 3 are configured for transmission of, and the base station 5 is configured for the reception of, control information and user data via a number of uplink (UL) physical channels corresponding to REs carrying information originating from a higher layer, and UL physical signals which are used in the physical layer and correspond to REs which do not carry information originating from a higher layer. The physical channels may include, for example, the PUSCH, a physical uplink control channel (PUCCH), and / or a physical random-access channel (PRACH). The UL physical signals may include, for example, demodulation reference signals (DMRS) for a UL control / data signal, and / or sounding reference signals (SRS) used for UL channel measurement.

[0046] When the UE 3 initially establishes a radio resource control (RRC) connection with a base station 5 via a cell 9 it registers with an appropriate core network node (e.g., AMF 10-1, MME). The UE 3 is in the so-called RRC connected state and an associated UE context is maintained by the network. When the UE 3 is in the so-called RRC idle state, or is in the RRC inactive state, it selects an appropriate cell for camping so that the network is aware of the approximate location of the UE 3 (although not necessarily on a cell level).

[0047] As mentioned above, the base station 5 in this example is a 'distributed' base station 5 that is split between one or more distributed units (DUs) 5b and a central unit (CU) 5c, with a CU 5c typically performing higher level functions and communication with the next generation core, and with the DU 5b performing lower level functions and communication over an air interface with UEs 3 in the vicinity (i.e. in a cell 9 operated by the base station 5). A distributed base station 5 may, for example, include the following functional units hosting the following functions: 　　Central Unit (CU) 5c: a logical node hosting Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP) and Packet Data Convergence Protocol (PDCP) layers of the base station 5 that controls the operation of one or more DUs 5b. The CU 5c terminates an appropriate interface (e.g. the so-called F1 interface) connected with the DU 5b.

[0048] Distributed Unit (DU) 5b: a logical node hosting Radio Link Control (RLC), Medium Access Control (MAC) and Physical (PHY) layers of the base station 5, and its operation is partly controlled by the CU 5c. One DU 5b supports one or multiple cells 9. One cell 9 is supported by only one DU 5b. The DU 5b terminates an appropriate interface (e.g. the F1 interface) connected with the CU 5c.

[0049] CU-Control Plane (CU-CP): a logical node hosting the RRC and the control plane part of the PDCP protocol of the CU 5c for the base station 5. The CU-CP terminates an appropriate interface (e.g. the so-called E1 interface) connected with the CU-UP and an appropriated interface (e.g. the F1-C (F1 control plane) interface) connected with the DU 5b.

[0050] CU-User Plane (CU-UP): a logical node hosting the user plane part of the PDCP protocol and the SDAP protocol of the CU 5c for the base station 5. The CU-UP terminates an appropriate interface (e.g. the E1 interface) connected with the CU-CP and an appropriate interface (e.g. the F1-U (F1 user plane) interface) connected with the DU 5b.

[0051] < Frame Structure > 　　Referring to Fig. 2, which illustrates a typical frame structure that may be used in the communication system 1, the base station 5 and UEs 3 of the communication system 1 communicate with one another using resources that are organised, in the time domain, into frames of length 10 ms. Each frame comprises ten equally sized subframes of 1 ms length. Each subframe is divided into one or more slots comprising 14 orthogonal frequency-division multiplexing (OFDM) symbols of equal length.

[0052] As seen in Fig. 2, the communication system 1 supports multiple different numerologies (subcarrier spacing (SCS), slot lengths and hence OFDM symbol lengths). Specifically, each numerology is identified by a parameter, μ, where μ=0 represents 15 kHz (corresponding to the LTE SCS). Currently, the SCS for other values of μ can, in effect, be derived from μ = 0 by scaling up in powers of 2 (i.e. SCS = 15 x 2μkHz). The relationship between the parameter, μ, and SCS (Δf) is as shown in Table 1:

[0053] Table 1 - 5G Numerology

[0054] < CU-DU Information Exchange > 　　In the communication system 1, various messages may be exchanged between the CU 5c and the DU 5b, for instance during a setup procedure for configuring communication between the DU 5b and CU 5c (e.g., an 'F1 setup procedure'). The purpose of the setup procedure is to exchange application level data needed for the DU 5b and the CU 5c to interoperate correctly (e.g., on the F1 interface). This procedure is the initial procedure triggered for control plane communication (e.g., over the F1-C interface) after a transport network layer (TNL) association has become operational. Typically, this procedure will use non-UE associated signalling.

[0055] During such a procedure, the DU 5b may transmit a setup request message (e.g., an F1 Setup Request) to the CU 5c. Where the setup request message is an F1 Setup Request it may, for example, include the following information: 　　　　DU Served Cells List IE: Information about the cells supported by the DU and associated features (e.g., NR-U); 　　　　DU System Information IE.

[0056] It will be appreciated that differently named information elements, having a similar purpose, may be used.

[0057] In response, the CU 5c typically transmits an F1 Setup Response message to the DU 5b. The following information may be included in the F1 Setup Response message: 　　　　Cells to be Activated List IE: a list of cells that the CU 5c requests the DU 5b to activate.

[0058] Further to the above messages, other messages (with associated information elements) may be used to update the configuration between the CU 5c and the DU 5b. For example, Public Land Mobile Network (PLMN) list, served cell information, GNB-DU Configuration Update or GNB-CU Configuration Update messages may be used to exchange information between the CU 5c and the DU 5b.

[0059] Additional messaging may be used between the CU 5c and the DU 5b, for instance when establishing a UE's context during a UE Context Setup procedure. The purpose of the UE Context Setup procedure is to establish the UE Context including, signalling radio bearer (SRB), and data radio bearer (DRB). This procedure uses UE associated signalling.

[0060] During such a procedure, the CU 5c may transmit a UE Context Setup Request message to the DU 5b (this message may comprise an RRC container used to carry additional information, e.g. in an RRC information IE). The following information may be included in the UE Context Setup Request message: 　　　　UE-CapabilityRAT-ContainerList: the DU 5b may take this information into account for UE specific configurations; 　　　　DRX Cycle IE: the DU 5b may use the provided value from the CU 5c; 　　　　RRC Information IE; in the case where the CU 5c receives a UEAssistanceInformation IE from the UE 3, the UEAssistanceInformation IE may be included in the RRC Information IE. The DU 5b may, if supported, take the UE's assistance information into account when configuring resources for the UE 3.

[0061] SRB To Be Setup List; 　　　　DRB To Be Setup List.

[0062] In response, the DU 5b transmits a UE Context Setup Response message to the CU 5c. The following information may be included in the UE Context Setup Response message: 　　　　A list of DRBs (and SRBs) which are successfully established and DRBs (and SRBs) which failed to establish; 　　　　When the DU 5b reports the unsuccessful establishment of a DRB or SRB, an associated cause value should be precise enough to enable the CU 5c to know the reason for the unsuccessful establishment. This may include the reason that a given feature is not supported by the DU 5b; 　　　　CellGroupConfig: As an Octet string which is included by CU 5c transparently within an RRC reconfiguration message sent to UE 3; 　　　　DRX Config: As an Octet string which is included by CU 5c transparently within the RRC reconfiguration message sent to UE 3.

[0063] Instead of the above messages, alternative messages (with associated information elements) may be used to update the UE's configuration between the CU 5c and the DU 5b.

[0064] For example, to further update the UE 3 configuration between CU 5c and DU 5b (e.g., DRB / SRB), UE Context Modification Request message (from CU 5c to DU 5b) or UE Context Modification Required (from DU 5b to CU 5c) messages may be used for information exchange between the CU 5c and the DU 5b.

[0065] < System information and SIB > 　　It will be appreciated that transmissions in a cell 9 of a base station 5 may include one or more broadcast transmissions, one or more unicast transmissions for reception by a UE 3, and / or one or more multicast transmissions for reception by a group of UEs 3. System information (SI) transmitted in a cell may include 'minimum SI' (MSI) and 'other SI' (OSI). The OSI may be broadcast on-demand, for example using a downlink shared channel (DL-SCH). The OSI may be broadcast upon request from a UE 3 that is in a radio resource control (RRC) idle or RRC inactive state. The OSI may also be requested by a UE 3 that is in the RRC connected state, for example via one or more dedicated RRC transmissions.

[0066] The SI may include information for enabling (e.g. configuring) the UE 3 to complete a cell selection, may include information for enabling the UE 3 to complete a cell reselection procedure, or for enabling the UE 3 to receive one or more paging messages transmitted in a cell. SI may be broadcast using a Master Information Block (MIB) and one or more System Information Blocks (SIB).

[0067] The MSI comprises the MIB and system information block 1 (SIB1). The MIB includes information for use by the UE 3 to receive SIB1, for example a subcarrier spacing for SIB1. The MIB provides information corresponding to a Control Resource Set (CORESET) and Search Space. SIB1 may be referred to as 'remaining MSI' (RMSI). SIB1 may be transmitted in a dedicated RRC message, and other SIB (e.g. SIB2 to SIB9) may be transmitting using one or more other suitable RRC transmissions (e.g. another dedicated RRC message). The MIB and SIB1 may provide the UE 3 with an indication of scheduling information for receiving and decoding the other SIB, such as SIB2 to SIB9, and may provide information for use by the UE 3 to receive one or more paging messages. The OSI may comprise, for example, SIB2 to SIB9 transmitted using a downlink shared channel (DL-SCH) in SI messages. A mapping of SIB2 to SIB9 to corresponding SI messages may be provided to the UE 3 by the base station 5. MIB and SIB1 to SIB9 are described in more detail, for example, in 3GPP TS 38.331 (NPL 1). SIB2 provides information for intra-frequency, inter-frequency and inter-system cell reselection. SIB3 provides cell-specific information for intra-frequency cell reselection. SIB4 provides information for inter-frequency cell reselection. SIB5 provides information regarding inter-system cell reselection towards 4G (LTE). SIB6 and SIB7 provide information for an earthquake and tsunami warning system (ETWS). SIB8 provides information for a commercial mobile alert service (CMAS) notification, for example to provide warning text messages to the UE 3. SIB9 includes information regarding coordinated universal time (UTC), global positioning system (GPS) time (e.g. for GPS initialisation) and local time.

[0068] SIB may be broadcast periodically (e.g. according to a predetermined periodic pattern), or alternatively may be provided 'on-demand', for example in response to a request from a UE 3. For example, MIB may be transmitted with a periodicity of 80 ms and repetitions made within 80 ms, and SIB1 may be transmitted with a periodicity of 15c ms and a variable transmission repetition periodicity within 15c ms (e.g. 20 ms). SIB1 can be used to indicate to a UE 3 which SIB are transmitted periodically and which SIB are available on-demand in response to a request from the UE 3. A UE 3 may be configured to request on-demand SIB using message 1 (MSG1), which may be referred to as a MSG1-based on-demand SI request, or message 3 (MSG3), which may be referred to as a MSG3-based on-demand SI request.

[0069] A physical broadcast channel (PBCH) can be used to broadcast the MIB. The base station 5 may transmit the PBCH with synchronisation signals (SS) (e.g. primary synchronisation signal (PSS) and secondary synchronisation signal (SSS)) in a SS / PBCH Block. The SS / PBCH block comprises four orthogonal frequency-division multiplexed (OFDM) symbols that are mapped to PSS, SSS and PBCH associated with a demodulation reference signal (DM-RS). In the frequency domain, an SS / PBCH block comprises 240 contiguous subcarriers. When the UE 3 is in an RRC connected state, the base station 5 may provide the UE 3 with an indication of resources used for the SS / PBCH, for example using dedicated signalling. SIB1 may be transmitted using a physical downlink shared channel (PDSCH). The OSI may be similarly transmitted, for example, using a PDSCH. When one or more beamformed transmissions are transmitted in a cell provided by the base station 5, some of the SI (e.g. some of the SIB) may only be transmitted using particular beams, or using a particular transmission / reception point (TRP).

[0070] < Artificial Intelligence (AI) / Machine Learning (ML) > 　　The base station 5 and UE 3 are each configured to take advantage of AI / ML for the purposes of enhancing their respective interfaces with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead. Enhanced performance could be, for example, improved throughput, robustness, accuracy or reliability, etc.

[0071] A general discussion of how AI / ML may be implemented in the communication system 1 will now be provided, by way of example only, with reference to Figs 3 to 5.

[0072] Fig. 3 illustrates a functional framework for AI / ML models, and how various entities of the framework may interact with one another, that may be implemented in the communication system 1.

[0073] The entities include a data collection function 41, a model training function 43, a model inference function 45, an actor 47, a management function 49, and a model storage entity 51.

[0074] The model storage entity 51 may be a reference point for protocol terminations for model transfer and delivery. The AI / ML models could be stored at any suitable node in the network.

[0075] The data collection function 41 provides training data to the model training function 43, inference data to the model inference function 45, and monitoring data to the management function 49. The collected data may be, for example, data regarding mobility (e.g. handover of a UE 3, or a location of the UE 3). The data may be obtained, for example, by a UE 3 or a base station 5 (e.g. by receiving a measurement report from a UE 3, or by receiving data from another base station 5 or a core network node / function) and transmitted to another base station 5 or core network node that generates the AI / ML model inference output (or alternatively, the same base station 5 that obtains the data may generate the AI / ML model output).

[0076] The model training function 43 performs the ML model training, validation, and testing, and may generate model performance metrics as part of a model testing procedure. The model training function 43 may output a trained AI / ML model to the model storage entity 51 (though it will be appreciated that the output model may be stored at locations other than model storage entity 51).

[0077] The model inference function 45 provides AI / ML model inference output (e.g., predictions or decisions), and the actor 47 is a function or node that receives the output from the model inference function 45 and triggers or performs corresponding actions (e.g. a base station 5 that increases / reduces its transmit power, or initiates a handover procedure for a UE 3). The AI / ML model inference output may be, for example, a prediction of mobility (e.g. expected path, route or trajectory, inter-cell or inter-beam mobility, or expected handover) of the UE 3, or one or more parameters for use in encoding or decoding transmissions between the base station 5 and the UE 3. The model inference function 45 may receive an AI / ML model from the model storage entity 51, and inference data from the data collection function 41 for use with the AI / ML model. The model inference function 45 may also output monitoring data for use at the management function 49, and receive information indicating an AI / ML to activate or deactivate from the management function 49.

[0078] The management function 49 receives monitoring data from the data collection function 41, and may also receive monitoring data from the model inference function 45. The management function 49 may transmit, to the model storage entity 51, an indication of an AI / ML model to be transmitted for use at the model inference function 45. The management function 49 may also transmit, to the model training function 43, performance feedback or a retraining request for the AI / ML model.

[0079] The functions illustrated in Fig. 3 may be co-located at a single node of the communications network (e.g. at a base station 5 or core network node / function), or may be distributed amongst a plurality of network nodes (e.g. a plurality of base stations 5).

[0080] Terms referred to by 3GPP in the context of this framework include: 　　AI / ML model training: A process to train an AI / ML Model [by learning the input / output relationship] in a data driven manner and obtain the trained AI / ML Model for inference. Model training can be performed offline or online or combination of both.

[0081] AI / ML model validation: A subprocess of training, to evaluate the quality of an AI / ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.

[0082] AI / ML model testing: A subprocess of training, to evaluate the performance of a final AI / ML model using a dataset different from one used for model training and validation. Differently from AI / ML model validation, testing does not assume subsequent tuning of the model.

[0083] AI / ML model Inference: A process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0084] Data collection: A process of collecting data by the network nodes, management entity, or UE 3 for the purpose of AI / ML model training, data analytics and inference.

[0085] Model monitoring: A procedure that monitors the inference performance of the AI / ML model.

[0086] Model activation: Enable an AI / ML model for a specific function.

[0087] Model deactivation: Disable an AI / ML model for a specific function.

[0088] Model switching: Deactivating a currently active AI / ML model and activating a different AI / ML model for a specific function.

[0089] Supervised learning: A process of training a model from input and its corresponding labels.

[0090] Unsupervised leaning: A process of training a model without labelled data.

[0091] Semi-supervised learning: A process of training a model with a mix of labelled data and unlabelled data.

[0092] Reinforcement Learning (RL): A process of training an AI / ML model from input (also referred to as 'state') and a feedback signal (also referred to as 'reward') resulting from the model's output (also referred to as 'action') in an environment the model is interacting with.

[0093] The data collection 41 may be performed at various nodes of the communication system 1 (e.g., at one or more base stations 5 or UEs 3). Particularly advantageous methods of obtaining, at a UE 3, data for an AI / ML model, and transmitting the AI / ML data from the UE 3 to a base station 5, will be described in more detail later.

[0094] Fig. 4 schematically illustrates of a method of training an AI / ML model, and of monitoring the performance of the AI / ML model. As illustrated in Fig. 4, stored data / features may first be extracted in a data extraction step. In the data validation step, a determination of whether to proceed with training or retaining the AI / ML model is made (e.g., based on the extracted data). In the data preparation stage, the data is prepared for use in training the AI / ML model. For example, the data may be cleaned (e.g., filtered), subject to a transformation, or modified in any other suitable manner. The data may also be divided in training data, validation data and test data sets in the data preparation stage.

[0095] In the model training step, the AI / ML model is trained (or retrained) using training data prepared in the data preparation step. It will be appreciated that any suitable training method can be used to train the AI / ML model (e.g. a method that comprises supervised learning or unsupervised learning). In the model evaluation step, the AI / ML model is evaluated (e.g. a prediction accuracy of the AI / ML model is evaluated) using a test data set (which may be generated in the data preparation step). In the model validation step, a determination of whether the AI / ML model is suitable for deployment in the communication system 1 is made (e.g. based on the results of the model evaluation step).

[0096] In the model serving step, the AI / ML model is deployed for use in the communication system 1. AI / ML model deployment may comprise compiling a trained AI / ML model, packaging the model into an executable format, and delivering the AI / ML model to a target device. For example, the AI / ML model may be transmitted to the base station 5 and / or the UE 3, for use at the base station 5 and / or the UE 3 to generate predictions or determinations using the AI / ML model as part of a prediction service step, as illustrated in the Fig. In the performance monitoring step, the performance of the deployed AI / ML model is monitored. The predictive performance of the AI / ML model may be monitored by comparing predictions generated using the model with one or more measurements. For example, when the AI / ML model is used to predict a location of a UE 3, the prediction accuracy of the AI / ML model may be assessed using a measurement of an actual location of the UE 3. Alternatively, if the AI / ML model is used for determining parameters for use in encoding and decoding data transmitted between a base station 5 and a UE 3, the model may be assessed based on the performance of the encoding and / or decoding processes. In the retraining trigger step, retraining of the AI / ML model is triggered (e.g. because the prediction accuracy of the AI / ML model has fallen below an acceptable threshold accuracy, or because a performance of a method that uses inferences from the AI / ML model has fallen below an acceptable threshold performance), and the method returns to the data extraction step.

[0097] As described above with reference to Fig. 3, each step of the method of Fig. 4 may be executed at a single node of the communication system 1, or alternatively steps of the method may be distributed between a plurality of different nodes (or indeed one or more of these steps may be performed online or offline).

[0098] As discussed above with reference to Figs. 3 and 4, information collected by nodes / functions in the communication system 1 (e.g. at a UE 3) can be used as training data for an AI / ML model, and used as inference data for use in generating one or more model inferences using the AI / ML model. The information used as training data, monitoring data, and / or to generate the one or more model inferences may be referred to as 'AI / ML information' or 'AI / ML data'.

[0099] Reference is now made to Fig. 5, which illustrates the relationship between AI / ML features, functionalities and models which may be used in the communication system 1.

[0100] Typically, an AI / ML feature - such as 'Feature 1' and 'Feature 2' shown in Fig. 5 - is generally considered as an AI / ML use case (e.g., CSI compression-decompression, spatial beam prediction, etc.).

[0101] Within one AI / ML feature, multiple (different) functionalities may exist (as illustrated, 'Feature 1' has two 'Functionalities'), where each functionality may refer to one configuration of an associated AI / ML feature. For example, for spatial beam prediction (an AI / ML feature), different functionalities can be defined in terms of the number of beams predicted by the AI / ML model. Hence, a functionality is defined by configuration of input, output and other applicable conditions (e.g., UE vendor, deployment scenarios) associated with a given AI / ML feature.

[0102] AI / ML model (or models) can provide even finer granularity than AI / ML functionality, but any such AI / ML model may also be defined without any reference to functionality (i.e., each AI / ML feature can have multiple AI / ML models without any functionality definition). An AI / ML model is associated with a configuration related to an AI / ML feature (similar to the above-described definition of AI / ML functionality) and may further include additional detailed aspects such as the version of the model. Hence, if one or more AI / ML functionalities are defined, then each functionality can be associated to multiple AI / ML models. As shown in Fig. 5, a given functionality may be discretely associated with a functionality specific model. A given functionality may, alternatively or additionally, be associated, together with one or more other functionalities, with a shared model.

[0103] Beneficially, as will be described in more detail below the communication system implements a general model management framework that advantageously provides for effective coordination between network nodes, such as a CU 5c and a DU 5b, to achieve the AI / ML LCM operations. This is beneficial because, given that AI / ML applications are physical layer based, in the context of a base station 5 of the distributed type, active involvement of the DU 5b may be required. Similarly, CU 5c involvement may be required, for example in the context of handling radio resource control protocols. The framework beneficially allows for variations of AI / ML model management including the use of the above-described single-sided and two-sided models, as well as alternative reporting mechanisms (e.g., RRC based, L1 / L2 based, etc.).

[0104] In more detail, in in the context of the General Model Management Framework, a number of beneficial procedures may be implemented. In one such procedure, for example, an indication of a DU's AI / ML capability is exchanged between the DU 5b and CU 5c. The procedure for providing the DU capability indication of AI / ML includes capability sharing from the DU 5b to the CU 5c, along with information for system information message construction. This procedure is also applicable for the activation / deactivation of network-based AI / ML models.

[0105] In another example, a procedure for CU-DU context setup and initial model activation is provided. The CU-DU context setup and initial model activation procedure includes exchange of a UE capability indication from the CU 5c to the DU 5b and subsequent methodology for model activation. The model activation methodology is equally applicable to any other model management decision (deactivation / switch / fallback) framework by the network side.

[0106] In these examples, it will be appreciated that, the set of information exchanged between the CU 5c and the DU 5b can be provided either via an existing CU-DU message (e.g., a UE Context Setup Request and / or F1 Setup Request) or can be provided using a newly defined message.

[0107] It will also be appreciated that whilst the procedures can be implemented together in the same system any of the procedures may be implemented independently to provide a commensurate benefit.

[0108] These procedures will now be discussed in greater detail below.

[0109] < General Model Management Framework > 　　Procedure for DU Capability Indication of AI / ML 　　Fig. 6 shows an example of a procedure for providing an indication of DU AI / ML capability. As the DU 5b is responsible for AI / ML operations for different AI / ML features / functionality / models, the DU 5b can indicate, to the CU 5c, its AI / ML capability (in addition to other information, if needed).

[0110] In this regard, in Step S601, the DU 5b transmits a message to the CU 5c which contains the DU's AI / ML capability information, metadata, system information (e.g., information relating to the SI that the DU 5b broadcasts in one or more of its cells 9) and / or additional AI / ML system parameters.

[0111] The DU AI / ML capability information indicates which AI / ML features / functionalities / models are supported by the DU 5b. Such information may be provided per serving cell of the DU 5b. More detailed information e.g., a list of AI / ML functionality IDs / AI / ML model IDs supported by the DU 5b, etc., may also be included in the DU AI / ML capability information.

[0112] The metadata can include information for scenarios (e.g., cells / conditions) where AI / ML features / functionalities / models are applicable for the DU 5b.

[0113] The transmission of the above information in S601 may be initiated by the DU 5b during a setup procedure for configuring communication between the DU 5b and CU 5c (e.g., using an F1 SETUP REQUEST message to transmit the information to the CU 5c), or may instead by transmitted in response to a request from the CU 5c (e.g., where DU 5b uses a GNB-CU CONFIGURATION UPDATE MESSAGE to respond to a request from CU 5c). In the case when the DU 5b responds to the request from the CU 5c, the CU 5c can include a field in its request message which indicates the CU's intent to use AI / ML.

[0114] Examples of the information elements (IEs) that may be included by the DU 5b within the message transmitted at S601 include (but are not limited to): 　　Supported AI / ML features: a list of AI / ML features supported by DU 5b. For each entry, the following IEs can be included: 　　　　AI / ML Feature ID / AI / ML Feature name; 　　　　Supported AI / ML functionalities: a list of AI / ML functionalities, which may include; 　　　　　　Functionality ID; 　　　　　　Applicable Conditions: a list of conditions (specific to each AI / ML functionality) where an AI / ML model can be operated; 　　　　　　Applicable Cells: a list of cells 9 for which given functionality is applicable. Each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　　　Supported AI / ML models: a list of AI / ML models (can be sub-IE of Supported AI / ML functionalities), which may include; 　　　　　　Model ID; 　　　　　　Applicable Conditions: a list of conditions (specific to each AI / ML functionality) where the AI / ML model can be operated; 　　　　　　Applicable Cells: a list of cells 9 for which this functionality is applicable, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; and / or 　　DU System Information: System information provided by DU 5b to CU 5c. When the system information is provided per AI / ML application, then this IE is included as sub-field of Supported AI / ML features or Supported AI / ML functionalities or Supported AI / ML models.

[0115] It should be noted that if a feature / functionality / model is applicable for all cells of the DU 5b, then the above IEs need not necessarily include cell information for that feature / functionality / model, or the IEs can be provided outside the cell specific parameters. Also, the Applicable Cells IE may be omitted from the IEs sent in step S601 if Supported AI / ML features are included inside an IE associated with a serving cell of DU 5b, e.g., a modified Served Cell Information IE (defined in 3GPP TS 38.473 (NPL 3)).

[0116] The CU 5c can use the received AI / ML capability information in step S601 in a manner consistent with the DU's indicated capabilities. For instance, CU 5c may only forward a message, in S602, having UE AI / ML capabilities associated with the features / models which were indicated as being supported by the DU 5b in step S601. CU 5c may also perform further procedures / message exchanges with the DU 5b to activate / enable one or more AI / ML features / models supported by the DU 5b in step S602 (as described in more detail below).

[0117] In certain scenarios, CU 5c may be responsible for activation of one or more AI / ML features / functionalities / models at DU 5b. Some examples of such AI / ML applications include AI / ML features / functionalities / models whose inference operation is performed only at the DU 5b (i.e., network side AI / ML models). In these instances, the CU 5c may indicate to the DU 5b in step S602 selected AI / ML features / functionalities / models which are to be activated at DU 5b. Similarly, if one or more AI / ML features / functionalities / models are already running at DU 5b, then CU 5c can also indicate as part of the message sent at step S602 the AI / ML features / functionalities / models which should be deactivated by the DU 5b.

[0118] It will be appreciated that the message sent by the CU 5c in S602 may take the form of a F1 SETUP RESPONSE message, a GNB-DU CONFIGURATION UPDATE ACKNOWLEDGE message, a GNB CONFIGURATION UPDATE message, or another suitable message.

[0119] Information elements (IEs) included by CU 5c within the message transmitted at step S602 may be different depending on given scenarios. For instance, according to one example, separate lists may be provided by the CU 5c to the DU 5b in step S602, in which case the IEs in the message may include: 　　Activated AI / ML features: a list of AI / ML features activated. For each entry following IEs can be included: 　　　　AI / ML Feature ID / AI / ML Feature name; 　　　　Activated AI / ML functionality ID: a list of AI / ML functionalities, which may include; 　　　　　　Applicable Cells: a list of cells 9 for which given functionality is activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　　　Activated AI / ML model ID (this may or may not be sub-IE of the Activated AI / ML functionality): a list of AI / ML models, which may include; 　　　　　　Applicable Cells: a list of cells 9 for which a given model is activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　Deactivated AI / ML features: a list of AI / ML features deactivated. For each entry following IEs can be included: 　　　　AI / ML Feature ID / AI / ML Feature name; 　　Deactivated AI / ML functionality ID: a list of deactivated AI / ML functionalities, which may include; 　　　　　　Applicable Cells: a list of cells 9 for which given functionality is deactivated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; and / or 　　Deactivated AI / ML model ID (this may or may not be sub-IE of the Deactivated AI / ML functionality): a list of deactivated AI / ML models, which may include; 　　　　　　Applicable Cells: a list of cells 9 for which a given model is deactivated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b;

[0120] According to another example, a single list of AI / ML functionality / model is provided by the CU 5c to the DU 5b in step S602, within which an IE may be included for activation or deactivation as follows: 　　Selected AI / ML features: a list of AI / ML features. For each entry the following IEs can be included: 　　　　AI / ML Feature ID / AI / ML Feature name; 　　　　Selected AI / ML functionality ID: a list of AI / ML functionalities, which may include; 　　　　　　Action: Activate or deactivate; 　　　　　　Applicable Cells: a list of cells 9 for which given functionality is activated / deactivated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; and / or 　　　　Selected AI / ML model ID (this may or may not be a sub-IE of the selected AI / ML functionality) a list of AI / ML models which may include: 　　　　　　Action: Activate or deactivate; 　　　　　　Applicable Cells: a list of cells 9 for which a given model is activated / deactivated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b.

[0121] Note that if a feature / functionality / model is applicable for all cells 9 of the DU 5b then the above IEs of the single list need not necessarily include cell information for that feature / functionality / model, or the IEs shall be provided outside a cell specific set of parameters. Also, the Applicable Cells IE may not be required if the enclosing IE set (e.g., Selected AI / ML feature name) is included inside an IE associated with a serving cell 9 of DU 5b, e.g., a modified version of the Served Cell Information IE (defined in 3GPP TS 38.473).

[0122] Then, in step S603, DU 5b may transmit a DU Success / Failure response message to CU 5c in respect of any AI / ML features / functionalities / models which failed to activate (which may include an associated cause for the failure). This message may also include a field comprising AI / ML system information parameters (e.g., some or all of those discussed above, or other relevant system information parameters). Specifically, in the case where the message sent in step S603 indicates a success, this field may be used to indicate, to the CU 5c, the AI / ML system information. Also, when the CU 5c indicates a functionality / model which needs to be activated at the DU 5b, then it may result in a change in the system information applicable for the DU 5b. Hence, the DU 5b can regenerate a system information block and include it in the field sent to the CU 5c in the success message so that the CU 5c can generate the full system information message for UEs 3.

[0123] As noted above, the DU 5b may also include, in the message transmitted in step S601 (and / or step S603), in the case where system information (SI) of a cell 9 operated by DU 5b contains parameters related to AI / ML operation, information which enables CU 5c to construct system information containing the AI / ML configuration. In one option, the DU 5b provides a system information container including the AI / ML configuration to the CU 5c. The CU 5c may then use the container transparently to construct the system information for broadcasting in the cell, and provide an associated cell specific configuration (e.g. comprising SI and / or AI / ML information) to the DU 5b in step S604. According to another option, the DU 5b may provide one or more system information IEs associated to each of the AI / ML features / functionalities / models included within the message transmitted at step S601 (and / or step S603). The CU 5c may then use the information to construct the system information message for broadcasting in the cell, and provide an associated cell specific configuration (e.g. comprising SI and / or AI / ML information) to the DU 5b in step S604.

[0124] < Initial Model Activation > 　　Initial model activation relates to the enabling of an AI / ML model for a specific function. As a UE's capability is provided to the CU 5c via RRC signalling, according to a first option it is possible for the CU 5c to take a model management decision as to which AI / ML feature / functionality / model is to be activated at the UE 3. In an alternative second option, the DU 5b may take the model management decision, taking into account assistance information received from CU 5c with respect to a UE's capabilities. Finally, according to a third option, the model management decision may be taken by the CU 5c and the DU 5b.

[0125] Each of these three options will now be described in more detail below. 　　< Option-1: Model management decision is taken by CU 5c > 　　Reference is now made to Fig. 7, which illustrates the procedure for CU 5c to take a model management decision in terms of which AI / ML features / functionalities / model is / are to be activated at UE 3.

[0126] First, in step S701, UE 3 may transmit a message to CU 5c comprising its UE AI / ML capability / Assistance information for AI / ML. This message may for example be an RRC message, or another appropriate message. It should, however, be appreciated that the CU 5c does not necessarily need this information from the UE 3 to make a model management decision. For example, when an AI / ML model is cell specific and no capability information is provided by UE 3, CU 5c may select AI / ML features / functionalities / model IDs for the UE 3 based on its own implementation.

[0127] Steps S702 and S703 are illustrated as being part of an overall optional 'DU Assistance' step, though it will be appreciated that CU 5c may take the decision for model activation without the assistance of DU 5b (and hence steps S702 and S703 may be omitted from the procedure).

[0128] In the case where DU assistance would be beneficial for the CU 5c in taking its model management decision, in step S702 CU 5c forwards a message comprising the received UE capability / assistance information for AI / ML to DU 5b, or CU 5c indicates to DU 5b AI / ML features / functionalities / models which are supported by UE 3. This message may, for example, may be a UE Context Setup Request message (or another suitable message).

[0129] The CU 5c may include in the message transmitted in step S702 information about UE capabilities for the AI / ML models which are operated by DU 5b. The CU 5c may also forward, in the message transmitted in step S702, any assistance information it has received from UE 3 in relation to AI / ML operation (e.g., UE power level information or temporary restriction of AI / ML operation, etc.).

[0130] Then, in step S703, DU 5b provides one or more AI / ML features / functionalities / models which can be activated for the UE 3. The DU 5b may provide this information in a UE Context Setup Response message, or in another suitable message.

[0131] For instance, according to one example of the DU assistance procedure, CU 5c indicates (in step S702) to DU 5b the list of AI / ML features / functionalities supported by UE 3, and DU 5b returns the AI / ML features / functionalities which can be activated at the UE 3 based on DU capability in step S703. This information can be provided per cell configured for UE 3. Based on this, CU 5c decides which AI / ML model ought to be activated at UE 3 (described below at step S704). Alternatively, according to a second example of the DU assistance procedure, CU 5c indicates to DU 5b (in step S702) the list of AI / ML functionality IDs / model IDs supported by UE 3 and DU 5b returns (in step S703) a subset of the AI / ML functionality IDs / model IDs which can be activated at the UE 3. Among this subset, CU 5c decides on the exact AI / ML functionality / model which ought to be activated by UE 3 (described below at step S704).

[0132] Examples of the information elements (IEs) that may be provided in step S703 by the DU 5b to the CU 5c include: 　　AI / ML Feature id / AI / ML Feature name; 　　Applicable Cells: A list of cells 9 for which a given feature can be activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　Shortlisted AI / ML functionalities: a list of AI / ML functionalities which can be used. For each entry the following IEs can be included: 　　　　AI / ML Functionality ID; 　　　　Applicable Cells: A list of cells 9 for which given functionality can be activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　Shortlisted AI / ML models a list of AI / ML models (can be sub-IE of Supported AI / ML functionalities), which may include: 　　　　AI / ML Model ID; 　　　　Applicable Cells: A list of cells 9 for which a given model can be activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　In step S704 (which may occur after step S701, or steps S702 and S703 if DU Assistance is relied on), CU 5c transmits to DU 5b a message comprising its AI / ML Model Management Decision (activation / deactivation / switch). This message may, for instance, be a UE Context Modification Request message, or any other suitable message.

[0133] According to a first example, the message transmitted by CU 5c to DU 5b in step S704 may include separate lists for Activation and Deactivation of AI / ML features / functionalities, and may carry the following information elements: 　　Activated AI / ML features: a list of AI / ML features activated. For each entry the following IEs can be included: 　　　　AI / ML Feature ID / AI / ML Feature name; 　　　　Activated AI / ML functionality ID; 　　　　　　Applicable Cells: A list of cells 9 for which given functionality shall be activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　　　Activated AI / ML model ID (this may or may not be sub-IE of Activated AI / ML functionality) 　　　　　　Applicable Cells: A list of cells 9 for which a given model shall be activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　Deactivated AI / ML features: a list of AI / ML features deactivated. For each entry the following IEs can be included: 　　　　AI / ML Feature ID / AI / ML Feature name; 　　　　Deactivated AI / ML functionality ID; 　　　　　　Applicable Cells: A list of cells 9 for which given functionality shall be deactivated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　　　Deactivated AI / ML model ID (this may or may not be sub-IE of Deactivated AI / ML functionality) 　　　　　　Applicable Cells: A list of cells 9 for which a given model shall be deactivated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b;

[0134] According to a second example, the message transmitted by CU 5c to DU 5b in step S704 may include a single list of AI / ML functionality / model (or models), within which a respective IE is included for Activation and Deactivation thereof. These IEs may include: 　　Selected AI / ML features: a list of AI / ML features. For each entry following IEs can be included: 　　　　AI / ML Feature ID / AI / ML Feature name; 　　　　Action: Activate or Deactivate or Switch or Fallback (this IE provides an indication that for a given feature what action needs to be taken, while the actual AI / ML functionality / model to be activated / deactivated / switch is provided in subsequent IEs); 　　　　Selected AI / ML functionality ID; 　　　　　　Action: Activate or Deactivate; 　　　　　　Applicable Cells: A list of cells 9 for which given functionality shall be activated / deactivated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　　　Selected AI / ML model ID; 　　　　　　Action: Activate or Deactivate; 　　　　　　Applicable Cells: A list of cells 9 for which a given model (or models) shall be activated / deactivated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　It should be appreciated that if a feature / functionality / model is applicable for all cells 9 of the DU 5b, then the above IEs shall not include cell information for that feature / functionality / model, or the IEs shall be provided outside the cell specific parameters. Also, the Applicable Cells IE may not be required if the enclosing IE set (e.g., Selected AI / ML features) is included inside an IE associated with a serving cell of DU 5b, e.g., the Served Cell Information IE (defined in 3GPP TS 38.473).

[0135] Then, in step S705, the DU 5b may send a message acknowledging the decision requested by CU 5c in step S704 (note that step S705 is not needed in the case where the DU assistance is used) and activate the AI / ML feature / functionality / model. This message may, for instance, be a UE Context Modification Response message, or another suitable message. In the case of acknowledgement, DU 5b may also pass the relevant RRC configuration which should be applicable for the chosen AI / ML feature / functionality / model to the CU 5c in step S705.

[0136] However, in some instances the DU 5b may fail to activate the AI / ML feature / functionality / model which was decided upon by the CU 5c and may therefore send a message to the CU 5c in step S705 indicating this failure (which is sometimes referred as 'reject' message instead of a 'failure' message).

[0137] For instance, if the decision taken by CU 5c cannot be complied with by DU 5b, e.g. because the DU 5b does not have the capability to support the chosen AI / ML feature / functionality / model, then DU 5b transmits a failure message, along with a cause value indicating the reason for the failure in step S705 which, in this example, may include an indication that the DU 5b does not have the capability to support the configuration chosen by CU 5c.

[0138] Provided step S705 yielded an acknowledgement message from DU 5b, in step S706 the CU 5c provides the AI / ML Model Management Decision and the associated RRC reconfiguration information to UE 3, such that the UE 3 can implement the decision to activate the AI / ML feature / functionality / model in step S707. For subsequent model management actions, e.g., deactivation / switch / fallback, the procedure may start at step S704.

[0139] < Option-2: Model management decision is taken by DU 5b > 　　Reference is now made to Fig. 8, which illustrates the procedure for DU 5b to take a model management decision in terms of which AI / ML features / functionalities / model is / are to be activated at UE 3.

[0140] Firstly, in step S801, UE 3 may transmit its UE AI / ML capability / Assistance information for AI / ML to CU 5c (e.g., via an RRC message, or via another appropriate message).

[0141] Step S802 is a step for performing UE capability exchange between CU 5c and DU 5b. To facilitate the exchange, CU 5c transmits a message comprising the UE AI / ML assistance information and / or supported AI / ML features / functionality / model. This message may, for example, be a UE Context Setup Request message (or another appropriate message). This message may include information corresponding to the information described above with reference to step S702 of Fig. 7 (which will not be repeated here).

[0142] The assistance information can then be used by the DU 5b to take a model management decision (as described below).

[0143] Once the exchange of information in step S802 is complete, two alternative procedures can be followed. The first alternative (ALT-1) is illustrated in Fig. 8 with reference to steps S803 and S804, and the second alternative (ALT-2) is illustrated with reference to steps S805 and S810. Both of these alternatives beneficially minimise the latency for indicating the model management decision. This is particularly advantageous when making management decisions in respect of AI / ML features which are time sensitive.

[0144] The first step of the first alternative is illustrated in step S803. In step S803, DU 5b transmits its AI / ML Model Management Decision and an associated RRC configuration for the UE 3 to the CU 5c, based on the support information provided in step S802. The UE RRC configuration message may comprise the information on AI / ML feature / functionality / model to be activated, or this information may instead be provided independently to CU 5c in a separate F1-AP IE field which can then be used by the CU 5c to build an AI / ML activation message for the UE (and / or may be used for AI / ML tracking purposes). Also, as a part of the message sent in step S803, the DU 5b DU may also indicate the AI / ML feature / functionality / model to be activated to CU 5c. This message may be a UE Context Modification Required message, or may be another suitable message. Finally, in step S804, the CU 5c transmits the AI / ML Model Management Decision and the RRC reconfiguration information to UE 3.

[0145] The first step of the second alternative is illustrated in step S805. In step S805, DU 5b transmits one or more RRC configurations (for one or more AI / ML features / functionalities / models) for the UE 3 to the CU 5c, based on the support information provided in step S802. Then, in step S806, the CU 5c forwards the information received in step S805 to the UE 3 using a message such as an RRC message (or another suitable message). The UE 3 then stores, in step S807, the received AI / ML configuration. Later, in step S808, the DU 5b takes a model management decision (to activate / deactivate / switch / fallback) and transmits its decision directly to UE 3 using L1 / L2 signalling (e.g. using a Medium Access Control Element (MAC CE), or a downlink control channel (DCI) indication, or another appropriately formatted message). This message may include information of the model management decision and information on the AI / ML feature / functionality / model ID associated with the decision. When the message sent in step S808 indicates the model management decision to the UE 3, the UE 3 selects, in step S810, the RRC configuration associated with the model management decision / AI / ML feature / functionality / model indicated by DU 5b.

[0146] In step S809, the DU 5b may send its model management decision (which the DU 5b previously indicated to the UE 3 in step S808) to the CU 5c. The message provided by the DU 5b in step S809 may then be used by the CU 5c, for example, for record management or other analytics. This message may be a UE Context Modification Required message, or may be another suitable message. DU 5b may use the IEs described with reference to step S704 of Fig. 7 as part of the message transmitted in step S809 of Fig. 8 (which, for the sake of brevity, will not be repeated here).

[0147] For subsequent AI / ML model management decisions (e.g., deactivation / switch / fallback), the steps described with respect to the first or second alternatives can be performed (i.e. the UE capability exchange between the CU 5c and DU 5b can be omitted from the procedure).

[0148] < Option-3: Combined model management decision taken by DU 5b and CU 5c > 　　Reference is now made to Fig. 9, which illustrates the procedure where DU 5b and CU 5c take a combined model management decision in terms of which AI / ML features / functionalities / model is / are to be activated at UE 3.

[0149] Step S901 of Fig. 9 is analogous to step S801 Fig. 8 and the associated description thereof above (and therefore for the sake of brevity will not be repeated here).

[0150] Then, in step S902, the CU 5c transmits to the DU 5b its decision with respect to which AI / ML features (or functionality) ought to be activated by UE 3 (for the DU 5b to then subsequently take the decision of AI / ML functionality (or model) which needs to be activated, as described below. As a part of this message, CU 5c also includes UE capability information for the UE 3 received in step S901.

[0151] The message transmitted in S902 may be a UE Context Setup Request message, or may be another suitable message.

[0152] Alternatively, the CU 5c may instead select a subset of AI / ML features / functionalities / models supported by the UE 3 (which may be considered as a 'shortlist'), and forwards the set to DU 5b for the DU 5b to take the final decision on the exact AI / ML feature / functionality / model to be activated (described in more detail below). In this case, the CU 5c may provide information in respect of the AI / ML features / functionalities / models in a separate IE to the DU 5b (rather than using the above-mentioned UE capability information).

[0153] The following information elements may be provided by the CU 5c in the message transmitted to the DU 5b in S902: 　　AI / ML Feature ID / AI / ML Feature name; 　　　　Applicable Cells: A list of cells 9 for which a given feature can be activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b; 　　　　Shortlisted AI / ML functionalities (if model ID within the functionality is selected by DU 5b): a list of AI / ML functionalities which can be used. For each entry following IEs can be included: 　　　　　　AI / ML Functionality ID; 　　　　　　Applicable Cells: A list of cells 9 for which given functionality can be activated, and each entry contains a cell ID value which maps to the cells 9 supported by the DU 5b.

[0154] The remaining steps S903 to S904 are analogous the first alternative of Fig. 8 (i.e., to steps S803 and S804) and the associated description thereof, whereas the remaining steps S905 to S910 are analogous the second alternative of Fig. 8 (i.e. to steps S805 to S810) and the associated description thereof, which will not be repeated here for the sake of brevity.

[0155] < User Equipment > 　　Fig. 10 is a schematic block diagram illustrating the main components of a UE 3 as shown in Fig. 1.

[0156] As shown, the UE 3 has a transceiver circuit 310 that is operable to transmit signals to and to receive signals from a base station 5 via one or more antenna 330 (e.g., comprising one or more antenna elements). The UE 3 has a controller 370 to control the operation of the UE 3. The controller 370 is associated with a memory 390 and is coupled to the transceiver circuit 310. Although not necessarily required for its operation, the UE 3 might, of course, have all the usual functionality of a conventional UE 3 (e.g. a user interface 350, such as a touch screen / keypad / microphone / speaker and / or the like for, allowing direct control by and interaction with a user) and this may be provided by any one or any combination of hardware, software, and firmware, as appropriate. Software may be pre-installed in the memory 390 and / or may be downloaded via the communication system 1 or from a removable data storage device (RMD), for example.

[0157] The controller 370 is configured to control overall operation of the UE 3 by, in this example, program instructions or software instructions stored within memory 390. As shown, these software instructions include, among other things, an operating system 410, a communications control module 430, and an AI / ML module 450.

[0158] The communications control module 430 is operable to control the communication between the UE 3 and its one or more serving base stations 5 (and other communication devices connected to the base station 5, such as further UEs 3 and / or core network nodes). The communications control module 430 is configured for the overall handling uplink communications via associated uplink channels (e.g. via a physical uplink control channel (PUCCH), random access channel (RACH), and / or a physical uplink shared channel (PUSCH)) including both dynamic and semi-static signalling (e.g., SRS). The communications control module 430 is also configured for the overall handling of receipt of downlink communications via associated downlink channels (e.g. via a physical downlink control channel (PDCCH) and / or a physical downlink shared channel (PDSCH)) including both dynamic and semi-static signalling (e.g., CSI-RS). The communications control module 430 is responsible, for example: for determining where to monitor for downlink control information (e.g., the location of CSSs / USSs, CORESETs, and associated PDCCH candidates to monitor); for determining the resources to be used by the UE 3 for transmission / reception of UL / DL communications (including interleaved resources and resources subject to frequency hopping); for managing frequency hopping at the UE 3 side; for determining how slots / symbols are configured (e.g., for UL, DL or SBFD communication, or the like); for determining which one or more bandwidth parts are configured for the UE 3; for determining how uplink transmissions should be encoded; for applying any SBFD specific communication configurations appropriately; and the like. The communications control module 430 may be configured to control communications in accordance with any of the methods described above (for example, to transmit a measurement report according to any of the methods described above).

[0159] The AI / ML module 450 is configured to perform any of the AI / ML related functions of the UE 3 of any of the methods described above.

[0160] < RAN (Distributed Type) > 　　Fig. 11 is a simplified block schematic illustrating the main components of a distributed RAN comprising a distributed type of base station 5 for implementation in the system of Fig. 1.

[0161] As shown, the RAN includes a central unit 5c and a distributed unit 5b (although it may include other DUs as described above). Each unit 5c, 5b includes respective transceiver circuitry 51c, 51b.

[0162] The distributed unit 5b transceiver circuitry 51b is operable to transmit signals to and to receive signals from UEs 3 via an air interface 53b and one or more antennas and is also operable to transmit signals to and to receive signals from the central unit 5c via an interface, for example the distributed unit side of an F1 interface (which may be provided over a satellite radio interface).

[0163] The central unit 5c transceiver circuitry 51c is operable to transmit signals to and to receive signals from functions of the core network 7 and / or other RANs via a network interface 55c. The network interface 55c typically includes an N1, N2 and / or N3 interfaces for communicating with the core network 7 and a base station to base station (e.g. Xn) interface for communicating with other RANs. The central unit 5c transceiver circuitry 51c is also operable to transmit signals to and to receive signals from one or more distributed units 5b, for example the central unit side of the F1 interface provided.

[0164] Each unit 5c, 5b includes a respective controller 57c, 57b which controls the operation of the corresponding transceiver circuitry 51c, 51b in accordance with software stored in the respective memories 59c and 59b of the distributed unit 5b and the central unit 5c. The software of each unit may be pre-installed in the memory 59c, 59b and / or may be downloaded via the communication system 1 or from a removable data storage device (RMD), for example. The software of each unit 5c, 5b includes, among other things, a respective operating system 61c, 61b, a respective communications control module 63c, 63b and an AI / ML module 65c, 65b.

[0165] Each communications control module 63c, 63b is operable to control the communication of its corresponding unit 5c, 5b including the communication from one unit to the other. The communications control module 63b of the distributed unit 5b controls communication between the distributed unit 5b and the UEs 3, and the communications control module 63c of the central unit 5c controls communication between the central unit 5c and other network entities that are connected to the distributed RAN.

[0166] The communications control modules 63c, 63b also respectively control the part played by the distributed unit 5b and central unit 5c in the flow of uplink and downlink user traffic and control data to be transmitted to the communications devices served by the RAN including, for example, control data for managing operation of the UEs 3. Each communication control module 63c, 63b is responsible, for example, for controlling the respective part played by the distributed unit 5b and central unit 5c in the reception and decoding of uplink communications, via associated uplink channels (e.g. via a physical uplink control channel (PUCCH), a random-access channel (RACH), and / or a physical uplink shared channel (PUSCH)) including both dynamic and semi-static signalling (e.g., SRS). Each communication control module 63c, 63b is responsible for controlling the respective part played by the distributed unit 5b and central unit 5c in the transmission of downlink communications via associated downlink channels (e.g. via a physical downlink control channel (PDCCH) and / or a physical downlink shared channel (PDSCH)) including both dynamic and semi-static signalling (e.g., CSI-RS, SSBs etc.).

[0167] It will be appreciated that the communications control modules 63c, 63b may also include a number of sub-modules (or 'layers') to support specific functionalities for the corresponding unit 5c, 5b. The modules included will depend on how the corresponding unit 5c, 5b is configured (e.g., the precise CU-DU split). For example, the communications control modules 63b of the distributed unit 5b may include a PHY sub-module, a MAC sub-module, and an RLC sub-module, whereas the communications control modules 63c of the central unit 5c may include a PDCP sub-module, an SDAP sub-module, an IP sub-module, an RRC sub-module, etc.

[0168] The AI / ML module 65c, 65b is configured to perform any of the AI / ML related functions described above.

[0169] < Core Network Node / Function > 　　Fig. 12 is a block diagram illustrating the main components of a core network node or function, such as the AMF 10-1, CPF 10, the UPF 11, the SMF 10-2 or OAM. As shown, the core network 7 function includes a transceiver circuit 710 which is operable to transmit signals to and to receive signals from other nodes (including the UE 3, the base station 5, and other core network nodes) via a network interface 720. A controller 730 controls the operation of the core network function in accordance with software stored in a memory 740. The software may be pre-installed in the memory 740 and / or may be downloaded via the communication system 1 or from a removable data storage device (RMD), for example. The software includes, among other things, an operating system 750, and a communications control module 760.

[0170] The communications control module 760 is responsible for handling (generating / sending / receiving) signalling between the core network 7 function and other nodes, such as the UE 3, the base station 5, and other core network nodes.

[0171] As shown in Fig. 12, the core network node / function may also include an AI / ML module 770. If present, the AI / ML module 770 is operable to perform any of the AI / ML related functions of the core network node / function according to any of the methods described above. The core network node / function may be configured for training or re-training the AI / ML model as described above (for example, in response to AI / ML data that is fed back to the core network node / function from another node in the network, such as the base station 5.

[0172] < Modifications and Alternatives > 　　As those skilled in the art will appreciate, a number of modifications and alternatives can be made to the above examples whilst still benefiting from the disclosures embodied therein.

[0173] Whilst the above examples have been described with reference to an AI / ML model, it will be appreciated that the above described methods are advantageous even when the model is not an AI / ML model. Any other suitable type of model or function may be used to generate inferences (e.g. determinations or predictions).

[0174] It will be appreciated, for example, that whilst cellular communication generation (2G, 3G, 4G, 5G, 6G etc.) specific terminology may be used, in the interests of clarity, to refer to specific communication entities, the technical features described for a given entity are not limited to devices of that specific communication generation. The technical features may be implemented in any functionally equivalent communication entity regardless of any differences in the terminology used to refer to them.

[0175] In the above description, the UEs and the base station are described for ease of understanding as having a number of discrete functional components or modules. Whilst these modules may be provided in this way for certain applications, for example where an existing system has been modified to implement the disclosure, in other applications, for example in systems designed with the inventive features in mind from the outset, these modules may be built into the overall operating system or code and so these modules may not be discernible as discrete entities.

[0176] In the above detailed examples, a number of software modules were described. As those skilled in the art will appreciate, the software modules may be provided in compiled or un-compiled form and may be supplied as a signal over a computer network, or on a recording medium. Further, the functionality performed by part, or all of this software may be performed using one or more dedicated hardware circuits. However, the use of software modules is preferred as it facilitates the updating of the base station or the UE in order to update their functionalities.

[0177] Each controller may comprise any suitable form of processing circuitry including (but not limited to), for example: one or more hardware implemented computer processors; microprocessors; central processing units (CPUs); arithmetic logic units (ALUs); input / output (IO) circuits; internal memories / caches (program and / or data); processing registers; communication buses (e.g. control, data and / or address buses); direct memory access (DMA) functions; hardware or software implemented counters, pointers and / or timers; and / or the like. Various other modifications will be apparent to those skilled in the art and will not be described in further detail here.

[0178] The User Equipment (or "UE", "mobile station", "mobile device" or "wireless device") in the present disclosure is an entity connected to a network via a wireless interface. It should be noted that the present disclosure is not limited to a dedicated communication device and can be applied to any device having a communication function as explained in the following paragraphs.

[0179] The terms "User Equipment" or "UE" (as the term is used by 3GPP), "mobile station", "mobile device", and "wireless device" are generally intended to be synonymous with one another, and include standalone mobile stations, such as terminals, cell phones, smart phones, tablets, cellular IoT devices, IoT devices, and machinery. It will be appreciated that the terms "mobile station" and "mobile device" also encompass devices that remain stationary for a long period of time.

[0180] A UE may, for example, be an item of equipment for production or manufacture and / or an item of energy related machinery (for example equipment or machinery such as: boilers; engines; turbines; solar panels; wind turbines; hydroelectric generators; thermal power generators; nuclear electricity generators; batteries; nuclear systems and / or associated equipment; heavy electrical machinery; pumps including vacuum pumps; compressors; fans; blowers; oil hydraulic equipment; pneumatic equipment; metal working machinery; manipulators; robots and / or their application systems; tools; molds or dies; rolls; conveying equipment; elevating equipment; materials handling equipment; textile machinery; sewing machines; printing and / or related machinery; paper converting machinery; chemical machinery; mining and / or construction machinery and / or related equipment; machinery and / or implements for agriculture, forestry and / or fisheries; safety and / or environment preservation equipment; tractors; precision bearings; chains; gears; power transmission equipment; lubricating equipment; valves; pipe fittings; and / or application systems for any of the previously mentioned equipment or machinery etc.).

[0181] A UE may, for example, be an item of transport equipment (for example transport equipment such as: rolling stocks; motor vehicles; motorcycles; bicycles; trains; buses; carts; rickshaws; ships and other watercraft; aircraft; rockets; satellites; drones; balloons etc.). A UE may, for example, be an item of information and communication equipment (for example information and communication equipment such as: electronic computer and related equipment; communication and related equipment; electronic components etc.).

[0182] A UE may, for example, be a refrigerating machine, a refrigerating machine applied product, an item of trade and / or service industry equipment, a vending machine, an automatic service machine, an office machine or equipment, a consumer electronic and electronic appliance (for example a consumer electronic appliance such as: audio equipment; video equipment; a loud speaker; a radio; a television; a microwave oven; a rice cooker; a coffee machine; a dishwasher; a washing machine; a dryer; an electronic fan or related appliance; a cleaner etc.).

[0183] A UE may, for example, be an electrical application system or equipment (for example an electrical application system or equipment such as: an x-ray system; a particle accelerator; radio isotope equipment; sonic equipment; electromagnetic application equipment; electronic power application equipment etc.).

[0184] A UE may, for example, be an electronic lamp, a luminaire, a measuring instrument, an analyser, a tester, or a surveying or sensing instrument (for example a surveying or sensing instrument such as: a smoke alarm; a human alarm sensor; a motion sensor; a wireless tag etc.), a watch or clock, a laboratory instrument, optical apparatus, medical equipment and / or system, a weapon, an item of cutlery, a hand tool, or the like.

[0185] A UE may, for example, be a wireless-equipped personal digital assistant or related equipment (such as a wireless card or module designed for attachment to or for insertion into another electronic device (for example a personal computer, electrical measuring machine)).

[0186] A UE may be a device or a part of a system that provides applications, services, and solutions described below, as to "internet of things (IoT)", using a variety of wired and / or wireless communication technologies.

[0187] Internet of Things devices (or "things") may be equipped with appropriate electronics, software, sensors, network connectivity, and / or the like, which enable these devices to collect and exchange data with each other and with other communication devices. IoT devices may comprise automated equipment that follow software instructions stored in an internal memory. IoT devices may operate without requiring human supervision or interaction. IoT devices might also remain stationary and / or inactive for a long period of time. IoT devices may be implemented as a part of a (generally) stationary apparatus. IoT devices may also be embedded in non-stationary apparatus (e.g. vehicles) or attached to animals or persons to be monitored / tracked.

[0188] It will be appreciated that IoT technology can be implemented on any communication devices that can connect to a communications network for sending / receiving data, regardless of whether such communication devices are controlled by human input or software instructions stored in memory.

[0189] It will be appreciated that IoT devices are sometimes also referred to as Machine-Type Communication (MTC) devices or Machine-to-Machine (M2M) communication devices. It will be appreciated that a UE may support one or more IoT or MTC applications. Some examples of MTC applications are listed in the following Table 2. This list is not exhaustive and is intended to be indicative of some examples of machine type communication applications.

[0190] Table 2

[0191] Applications, services, and solutions may be an MVNO (Mobile Virtual Network Operator) service, an emergency radio communication system, a PBX (Private Branch eXchange) system, a PHS / Digital Cordless Telecommunications system, a POS (Point of sale) system, an advertise calling system, an MBMS (Multimedia Broadcast and Multicast Service), a V2X (Vehicle to Everything) system, a train radio system, a location related service, a Disaster / Emergency Wireless Communication Service, a community service, a video streaming service, a femto cell application service, a VoLTE (Voice over LTE) service, a charging service, a radio on demand service, a roaming service, an activity monitoring service, a telecom carrier / communication NW selection service, a functional restriction service, a PoC (Proof of Concept) service, a personal information management service, an ad-hoc network / DTN (Delay Tolerant Networking) service, etc.

[0192] Further, the above-described UE categories are merely examples of applications of the technical ideas described in the present document. Needless to say, these technical ideas are not limited to the above-described UE and various modifications can be made thereto.

[0193] Various other modifications will be apparent to those skilled in the art and will not be described in further detail here.

[0194] Although the present disclosure has been described with reference to the example embodiments, the present disclosure is not limited to the above. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the disclosure.

[0195] This application is based upon and claims the benefit of priority from UK patent application No. 2311263.4, filed on July 21, 2023, the disclosure of which is incorporated herein in its entirety by reference.

[0196] The program can be stored and provided to the computer device using any type of non-transitory computer readable media. Non-transitory computer readable media include any type of tangible storage media. Examples of non-transitory computer readable media include magnetic storage media (such as floppy disks, magnetic tapes, hard disk drives, etc.), optical magnetic storage media (e.g. magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, and semiconductor memories (such as mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory), etc.). The program may be provided to the computer device using any type of transitory computer readable media. Examples of transitory computer readable media include electric signals, optical signals, and electromagnetic waves. Transitory computer readable media can provide the program to the computer device via a wired communication line, such as electric wires and optical fibers, or a wireless communication line.

[0197] For example, the whole or part of the example embodiments disclosed above can be described as, but not limited to, the following supplementary notes. (Supplementary note 1) 　　A method performed by a first unit of a distributed base station, the method comprising: 　　determining which Artificial Intelligence, AI, / Machine Learning, ML, models to be activated / deactivated / switched to other AI / ML models for AI / ML model management, based on user equipment, UE, capability for AI / ML model management. (Supplementary note 2) 　　The method according to Supplementary note 1, further comprising: 　　transmitting, to a second unit of the distributed base station, a request for activating / deactivating / switching to other AI / ML models, at least one AI / ML model for the AI / ML model management; and 　　receiving, from the second unit, a message for acknowledging the request, the message including Radio Resource Control, RRC, configuration which should be applicable for the at least one AI / ML model, or a message for rejecting the request, the message including a cause value indicating a reason for a failure. (Supplementary note 3) 　　The method according to Supplementary note 1 or 2, further comprising: 　　receiving, from a second unit of the distributed base station, selection information for the determining which AI / ML models to be activated / deactivated / switched to other AI / ML models for the AI / ML model management, and wherein 　　the determining is performed based on the selection information. (Supplementary note 4) 　　The method according to Supplementary note 3, further comprising: 　　transmitting, to the second unit, the UE capability for the AI / ML model management, and wherein 　　the receiving the selection information is performed in response to the transmitting the UE capability. (Supplementary note 5) 　　The method according to Supplementary note 1, further comprising: 　　receiving, from a second unit of the distributed base station, a request for activating / deactivating / switching to other AI / ML models, at least one AI / ML model for the AI / ML model management, wherein 　　the determining is performed based on the request. (Supplementary note 6) 　　The method according to Supplementary note 5, further comprising: 　　transmitting, to the second unit, a message for acknowledging the request, the message including Radio Resource Control, RRC, configuration which should be applicable for the at least one AI / ML model, or a message for rejecting the request, the message including a cause value indicating a reason for a failure. (Supplementary note 7) 　　The method according to Supplementary note 5 or 6, further comprising: 　　receiving, from a second unit of the distributed base station, selection information for the determining which AI / ML models to be activated / deactivated / switched to other AI / ML models for the AI / ML model management, and wherein 　　the determining is performed based on the selection information. (Supplementary note 8) 　　The method according to Supplementary note 7, further comprising: 　　transmitting, to the second unit, the UE capability for the AI / ML model management, and wherein 　　the receiving the selection information is performed in response to the transmitting the UE capability. (Supplementary note 9) 　　The method according to any one of Supplementary notes 5 to 8, further comprising: 　　transmitting, to a user equipment, UE, information indicating at least one AI / ML model to be activated / deactivated / switched to other AI / ML models. (Supplementary note 10) 　　The method according to any one of Supplementary notes 1 to 9, wherein 　　the second unit determines which AI / ML models to be activated / deactivated / switched to other AI / ML models for the AI / ML model management, and 　　the determining is performed based on determining of the second unit. (Supplementary note 11) 　　The method according to any one of Supplementary notes 1 to 10, wherein 　　the request includes at least one of: 　　　　information indicating at least one AI / ML feature, AI / ML functionality or AI / ML model to be activated, or 　　　　information indicating at least one AI / ML feature, AI / ML functionality or AI / ML model to be deactivated. (Supplementary note 12) 　　The method according to Supplementary note 3 or 7, wherein 　　the selection information includes first information indicating at least one AI / ML feature, each of the at least one AI / ML feature corresponding to at least one AI / ML model. (Supplementary note 13) 　　The method according to Supplementary note 12, wherein 　　the first information includes at least one of: 　　　　second information indicating at least one AI / ML functionality corresponding to one of the at least one AI / ML feature, 　　　　third information indicating at least one AI / ML model corresponding to one of the at least one AI / ML feature or at least one AI / ML functionality, or 　　　　cell information indicating at least one cell corresponding to one of the at least one AI / ML feature, at least one AI / ML functionality or at least one AI / ML model. (Supplementary note 14) 　　The method according to any one of Supplementary notes 3, 7, 12 and 13, wherein 　　the selection information is included in UE context setup response message. (Supplementary note 15) 　　A method performed by a first unit of a distributed base station, the method comprising: 　　transmitting, to a second unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports. (Supplementary note 16) 　　The method according to Supplementary note 15, wherein 　　the information is provided per serving cell of the first unit. (Supplementary note 17) 　　The method according to Supplementary note 15 or 16, wherein 　　the information includes information indicating scenarios where the AI / ML features, the AI / ML functionalities, or the AI / ML models are applicable. (Supplementary note 18) 　　The method according to Supplementary note 17, wherein 　　the scenarios indicate at least one of: 　　　　conditions where the AI / ML features, the AI / ML functionalities, or the AI / ML models are applicable, or 　　　　cells the AI / ML features, the AI / ML functionalities, or the AI / ML models are applicable. (Supplementary note 19) 　　The method according to any one of Supplementary notes 15 to 18, wherein 　　the information is included in a F1 Setup request message. (Supplementary note 20) 　　The method according to any one of Supplementary notes 15 to 18, further comprising: 　　receiving, from the second unit, a request, and wherein 　　the transmitting the information is performed in response to the request. (Supplementary note 21) 　　The method according to any one of Supplementary notes 15 to 20, wherein 　　the information includes system information. (Supplementary note 22) 　　A method performed by a second unit of a distributed base station, the method comprising: 　　receiving, to a first unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports. (Supplementary note 23) 　　The method according to any one of Supplementary notes 1 to 14, wherein 　　the first unit includes a central unit of the distributed base station, and 　　the second unit includes a distributed unit of the distributed base station. (Supplementary note 24) 　　The method according to any one of Supplementary notes 1 to 22, wherein 　　the first unit includes a distributed unit of the distributed base station, and 　　the second unit includes a central unit of the distributed base station. (Supplementary note 25) 　　A first unit of a distributed base station comprising: 　　means for determining which Artificial Intelligence, AI, / Machine Learning, ML, models to be activated / deactivated / switched to other AI / ML models for AI / ML model management, based on user equipment, UE, capability for AI / ML model management. (Supplementary note 26) 　　A first unit of a distributed base station comprising: 　　means for transmitting, to a second unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports. (Supplementary note 27) 　　A second unit of a distributed base station comprising: 　　means for receiving, from a first unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

[0198] 1　　communication system 3　　UEs 5　　radio access network (RAN) node, base station 5b　　distributed unit (DU) 5c　　central unit (CU) 7　　core network 9　　cells 10　　control plane functions (CPFs) 10-1　　Access and Mobility Management Functions (AMFs) 10-2　　Session Management Functions (SMFs) 11　　user plane functions (UPFs) 41　　data collection function 43　　model training function 45　　model inference function 47　　actor 49　　management function 51　　model storage entity 310, 51b, 51c, 710　　transceiver circuit 330　　antenna 53b　　air interface 350　　user interface 55c, 720　　　　network interface 370, 57b, 57c, 730　　controller 390, 59b, 59c, 740　　memory 410, 61b, 61c, 750　　operating system 430, 63b, 63c, 760　　communications control module 450, 65b, 65c, 770　　AI / ML module

Claims

1. A method performed by a first unit of a distributed base station, the method comprising: 　　determining which Artificial Intelligence, AI, / Machine Learning, ML, models to be activated / deactivated / switched to other AI / ML models for AI / ML model management, based on user equipment, UE, capability for AI / ML model management.

2. The method according to claim 1, further comprising: 　　transmitting, to a second unit of the distributed base station, a request for activating / deactivating / switching to other AI / ML models, at least one AI / ML model for the AI / ML model management; and 　　receiving, from the second unit, a message for acknowledging the request, the message including Radio Resource Control, RRC, configuration which should be applicable for the at least one AI / ML model, or a message for rejecting the request, the message including a cause value indicating a reason for a failure.

3. The method according to claim 1 or 2, further comprising: 　　receiving, from a second unit of the distributed base station, selection information for the determining which AI / ML models to be activated / deactivated / switched to other AI / ML models for the AI / ML model management, and wherein 　　the determining is performed based on the selection information.

4. The method according to claim 3, further comprising: 　　transmitting, to the second unit, the UE capability for the AI / ML model management, and wherein 　　the receiving the selection information is performed in response to the transmitting the UE capability.

5. The method according to claim 1, further comprising: 　　receiving, from a second unit of the distributed base station, a request for activating / deactivating / switching to other AI / ML models, at least one AI / ML model for the AI / ML model management, wherein 　　the determining is performed based on the request.

6. The method according to claim 5, further comprising: 　　transmitting, to the second unit, a message for acknowledging the request, the message including Radio Resource Control, RRC, configuration which should be applicable for the at least one AI / ML model, or a message for rejecting the request, the message including a cause value indicating a reason for a failure.

7. The method according to claim 5 or 6, further comprising: 　　receiving, from a second unit of the distributed base station, selection information for the determining which AI / ML models to be activated / deactivated / switched to other AI / ML models for the AI / ML model management, and wherein 　　the determining is performed based on the selection information.

8. The method according to claim 7, further comprising: 　　transmitting, to the second unit, the UE capability for the AI / ML model management, and wherein 　　the receiving the selection information is performed in response to the transmitting the UE capability.

9. The method according to any one of claims 5 to 8, further comprising: 　　transmitting, to a user equipment, UE, information indicating at least one AI / ML model to be activated / deactivated / switched to other AI / ML models.

10. The method according to any one of claims 1 to 9, wherein 　　the second unit determines which AI / ML models to be activated / deactivated / switched to other AI / ML models for the AI / ML model management, and 　　the determining is performed based on determining of the second unit.

11. The method according to any one of claims 1 to 10, wherein 　　the request includes at least one of: 　　　　information indicating at least one AI / ML feature, AI / ML functionality or AI / ML model to be activated, or 　　　　information indicating at least one AI / ML feature, AI / ML functionality or AI / ML model to be deactivated.

12. The method according to claim 3 or 7, wherein 　　the selection information includes first information indicating at least one AI / ML feature, each of the at least one AI / ML feature corresponding to at least one AI / ML model.

13. The method according to claim 12, wherein 　　the first information includes at least one of: 　　　　second information indicating at least one AI / ML functionality corresponding to one of the at least one AI / ML feature, 　　　　third information indicating at least one AI / ML model corresponding to one of the at least one AI / ML feature or at least one AI / ML functionality, or 　　　　cell information indicating at least one cell corresponding to one of the at least one AI / ML feature, at least one AI / ML functionality or at least one AI / ML model.

14. The method according to any one of claims 3, 7, 12 and 13, wherein 　　the selection information is included in UE context setup response message.

15. A method performed by a first unit of a distributed base station, the method comprising: 　　transmitting, to a second unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

16. The method according to claim 15, wherein 　　the information is provided per serving cell of the first unit.

17. The method according to claim 15 or 16, wherein 　　the information includes information indicating scenarios where the AI / ML features, the AI / ML functionalities, or the AI / ML models are applicable.

18. The method according to claim 17, wherein 　　the scenarios indicate at least one of: 　　　　conditions where the AI / ML features, the AI / ML functionalities, or the AI / ML models are applicable, or 　　　　cells the AI / ML features, the AI / ML functionalities, or the AI / ML models are applicable.

19. The method according to any one of claims 15 to 18, wherein 　　the information is included in a F1 Setup request message.

20. The method according to any one of claims 15 to 18, further comprising: 　　receiving, from the second unit, a request, and wherein 　　the transmitting the information is performed in response to the request.

21. The method according to any one of claims 15 to 20, wherein 　　the information includes system information.

22. A method performed by a second unit of a distributed base station, the method comprising: 　　receiving, to a first unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

23. The method according to any one of claims 1 to 14, wherein 　　the first unit includes a central unit of the distributed base station, and 　　the second unit includes a distributed unit of the distributed base station.

24. The method according to any one of claims 1 to 22, wherein 　　the first unit includes a distributed unit of the distributed base station, and 　　the second unit includes a central unit of the distributed base station.

25. A first unit of a distributed base station comprising: 　　means for determining which Artificial Intelligence, AI, / Machine Learning, ML, models to be activated / deactivated / switched to other AI / ML models for AI / ML model management, based on user equipment, UE, capability for AI / ML model management.

26. A first unit of a distributed base station comprising: 　　means for transmitting, to a second unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

27. A second unit of a distributed base station comprising: 　　means for receiving, from a first unit of the distributed base station, information indicating Artificial Intelligence, AI, / Machine Learning, ML, models, AI / ML functionalities or AI / ML features which the first unit supports.

Images