Using an ai / ML model for handover and cell reselection

Abstract

A communications device operates to communicate via a wireless communications network, by receiving radio resource control (RRC) configuration parameters including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with measurements, and receiving signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network. The communications device operates by measuring one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, generating predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning (AI / ML) model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the measurement actions. The communications device is receiving the signals to generate the measurement samples when in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

Description

[0001] USING AN AI / ML MODEL FOR HANDOVER AND CELL RESELECTION

[0002] BACKGROUND

[0003] Field of the Disclosure

[0004] The present disclosure relates to communications devices operating to communicate via a wireless communications network, in which the communications devices perform measurements of signals received from one or more of a plurality of cells to assist measurements. The present invention also relates to infrastructure equipment and methods of operating communications devices and infrastructure equipment as defined in the appended claims.

[0005] The present disclosure claims the Paris convention priority from European patent application number EP24168594.0 filed on 4 April 2024, the contents of which are incorporated by reference in their entirety.

[0006] Description of the Related Art

[0007] The “background” description provided is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in the background section, as well as aspects of the description which may not otherwise qualify as prior art at the time of filing, are neither expressly or impliedly admitted as prior art against the present disclosure.

[0008] Mobile telecommunication systems, such as those based on the 3GPP defined UMTS and Long Term Evolution (LTE) architecture, are able to support a wider range of services than simple voice and messaging services offered by previous generations of mobile telecommunication systems. For example, with the improved radio interface and enhanced data rates provided by LTE systems, a user is able to enjoy high data rate applications such as mobile video streaming and mobile video conferencing that would previously only have been available via a fixed line data connection. The demand to deploy such networks is therefore strong and the coverage area of these networks, i.e. geographic locations where access to the networks is possible, is expected to continue to increase rapidly.

[0009] Current and future wireless communications networks are expected to routinely and efficiently support communications with an ever-increasing range of devices associated with a wider range of data traffic profiles and types than existing systems are optimised to support. For example, such wireless communications networks will be expected to efficiently support communications with devices including reduced complexity devices, machine type communication (MTC) devices, high resolution video displays, virtual reality headsets, extended Reality (XR) and so on. Some of these different types of devices may be deployed in very large numbers, for example low complexity devices for supporting the “The Internet of Things”, and may typically be associated with the transmissions of relatively small amounts of data with relatively high latency tolerance. Other types of device, for example supporting high-definition video streaming, may be associated with transmissions of relatively large amounts of data with relatively low latency tolerance. Other types of device, for example used for autonomous vehicle communications and for other critical applications, may be characterised by data that should be transmitted through the network with low latency and high reliability. A single device type might also be associated with different traffic profiles / characteristics depending on the application(s) it is running. For example, different considerations may apply for efficiently supporting data exchange with a smartphone when it is running a video streaming application (high downlink data) as compared to when it is running an Internet browsing application (sporadic uplink and downlink data) or being used for voice communications by an emergency responder in an emergency scenario (data subject to stringent reliability and latency requirements).

[0010] In view of this there is expected to be a desire for current wireless communications networks, for example those which may be referred to as 5G or new radio (NR) systems / new radio access technology (RAT) systems, or indeed future 6G wireless communications, as well as future iterations / releases of existing systems, to efficiently support connectivity for a wide range of devices associated with different applications and different characteristic data traffic profiles and requirements.

[0011] 5G NR has continuously evolved and the current work plan includes 5 G-NR- Advanced in which some further enhancements are expected, especially to support new use-cases / scenarios with higher requirements. Indeed techniques may be adopted which can be used to make communication more efficient or conserve power.

[0012] SUMMARY

[0013] Embodiments of the present technique can provide a communications device and a method of operating a communications device to communicate via a wireless communications network, the method comprising receiving radio resource control, RRC, configuration parameters including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with measurements, and receiving signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network. The method further comprises measuring one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, generating predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the measurement actions. The communications device is receiving the signals to generate the measurement samples when in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

[0014] By adapting the predication of the samples using the AI / ML model based on whether the communications device was in connected or idle mode can reduce a likelihood of handover failure or radio like failure.

[0015] Various further aspects and features are defined in the appended claims and include an infrastructure equipment, a communications device acting as a sensing device and methods.

[0016] BRIEF DESCRIPTION OF THE DRAWINGS Non-limiting embodiments and advantages of the present disclosure are explained with reference to the following detailed description taken in conjunction with the accompanying drawings, in which like reference numerals designate identical or corresponding parts throughout the drawings, wherein:

[0017] Figure 1 schematically shows an example wireless communications network according to a general architecture, which may operate according to an LTE technology;

[0018] Figure 2 schematically shows an example wireless communications network configured according to a 5G or New Radio architecture;

[0019] Figure 3 is a schematic block diagram illustrating parts of the wireless communications network, including a communications device (UE) and an infrastructure equipment (gNB) shown in Figure 2 in more detail;

[0020] Figure 4 is an illustrative representation of a communications device (UE) moving through a geographical area served by cells formed by infrastructure equipment (gNB) of the wireless communications network of Figure 2;

[0021] Figure 5A is a part message part flow diagram illustrating an operation of a wireless communications system in which a communications device hands over from one cell to another in a connected mode;

[0022] Figure 5B is a part message part flow diagram illustrating an operation of a wireless communications system in which a communications device performs a cell re-selection in an Idle / Inactive mode;

[0023] Figure 6 is a schematic bock diagram representing a measurement model performed by a communications device (UE) to evaluate a cell or beams of a cell;

[0024] Figure 7 is an illustrative representation showing measurements and mobility actions performed by a communications device (UE) as the communications device moves along a path in a geographical area served by cell formed by infrastructure equipment (gNB) of a wireless communications network;

[0025] Figure 8 is a part flow diagram, part block diagram illustrating operations of a communications device (UE) performing handover using an adapted prediction technique according to example embodiments;

[0026] Figure 9 is a part flow diagram, part block diagram illustrating operations of a communications device (UE) to perform cell re-selection using an adapted prediction technique according to example embodiments; and

[0027] Figure 10A is a message sequence diagram illustrating an example of adapting a prediction model to use only measurement samples taken during a connected mode;

[0028] Figure 10B is a message sequence diagram illustrating an example of adapting a prediction model to use measurement samples taken during a connected mode or connected and idle modes, which are indicated to the network on request; and

[0029] Figure IOC is a message sequence diagram illustrating an example of adapting a prediction model to use always measurement samples taken during a connected mode.

[0030] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] Long Term Evolution Advanced Radio Access Technology (4G)

[0032] Figure 1 provides a schematic diagram illustrating some basic functionality of a mobile telecommunications network / system 6 operating generally in accordance with LTE principles, but which may also support other radio access technologies, and which may be adapted to implement embodiments of the disclosure as described herein. Various elements of Figure 1 and certain aspects of their respective modes of operation are well-known and defined in the relevant standards administered by the 3GPP (RTM) body, and also described in many books on the subject, for example, Holma H. and Toskala A [1], It will be appreciated that operational aspects of the telecommunications networks discussed herein which are not specifically described (for example in relation to specific communication protocols and physical channels for communicating between different elements) may be implemented in accordance with any known techniques, for example according to the relevant standards and known proposed modifications and additions to the relevant standards.

[0033] The network 6 includes a plurality of base stations 1 connected to a core network (CN) 2. Each base station provides a coverage area 3 (i.e. a cell) within which data can be communicated to and from communications devices 4. Although each base station 1 is shown in Figure 1 as a single entity, the skilled person will appreciate that some of the functions of the base station may be carried out by disparate, inter-connected elements, such as antennas (or antennae), remote radio heads, amplifiers, etc. Collectively, one or more base stations may form a radio access network.

[0034] Data is transmitted from base stations 1 to communications devices 4 within their respective coverage areas 3 via a radio downlink (DL). Data is transmitted from communications devices 4 to the base stations 1 via a radio uplink (UL). The core network 2 routes data to and from the communications devices 4 via the respective base stations 1 and provides functions such as authentication, mobility management, charging and so on. Communications devices may also be referred to as mobile stations, user equipment (UEs), user terminals, mobile radios, mobile terminals, terminal devices, wireless transmit and receive units (WTRUs), and so forth. Services provided by the core network 2 may include connectivity to the internet or to external telephony services. The core network 2 may further track the location of the communications devices 4 so that it can efficiently contact (i.e. page) the communications devices 4 for transmitting downlink data towards the communications devices 4.

[0035] Base stations, which are an example of network infrastructure equipment, may also be referred to as transceiver stations, nodeBs, e-nodeBs, eNB, g-nodeBs, gNBs and so forth. In this regard different terminology is often associated with different generations of wireless telecommunications systems for elements providing broadly comparable functionality. However, certain embodiments of the disclosure may be equally implemented in different generations of wireless telecommunications systems, and for simplicity certain terminology may be used regardless of the underlying network architecture. That is to say, the use of a specific term in relation to certain example implementations is not intended to indicate these implementations are limited to a certain generation of network that may be most associated with that particular terminology.

[0036] New Radio Access Technology (5G)

[0037] Systems incorporating NR technology are expected to support different services (or types of services), which may be characterised by different requirements for latency, data rate and / or reliability. For example, Enhanced Mobile Broadband (eMBB) services are characterised by high capacity with a requirement to support up to 20 Gb / s. The requirements for Ultra Reliable and Low Latency Communications (URLLC) services are for one transmission of a 32 byte packet to be transmitted from the radio protocol layer 2 / 3 SDU ingress point to the radio protocol layer 2 / 3 SDU egress point of the radio interface within 1 ms with a reliability of 1 - 10-5(99.999 %) or higher (99.9999%) [2].

[0038] Massive Machine Type Communications (mMTC) is another example of a service which may be supported by NR- based communications networks. In addition, systems may be expected to support further enhancements related to Industrial Internet of Things (IIoT) in order to support services with new requirements of high availability, high reliability, low latency, and in some cases, high-accuracy positioning. An example configuration of a wireless communications network which uses some of the terminology proposed for and used in NR and 5G is shown in Figure 2. In Figure 2 a plurality of transmission and reception points (TRPs) 10 are connected to distributed control units (DUs) 41, 42 by a connection interface represented as a line 16. Each of the TRPs 10 is arranged to transmit and receive signals via a wireless access interface within a radio frequency bandwidth available to the wireless communications network. Thus, within a range for performing radio communications via the wireless access interface, each of the TRPs 10, forms a cell of the wireless communications network as represented by a circle 12. As such, wireless communications devices 14 which are within a radio communications range provided by the cells 12 can transmit and receive signals to and from the TRPs 10 via the wireless access interface. Each of the distributed units 41, 42 are connected to a central unit (CU) 40 (which may be referred to as a controlling node) via an interface 46. The central unit 40 is then connected to the core network 20 which may contain all other functions required to transmit data for communicating to and from the wireless communications devices and the core network 20 may be connected to an application function (AF) 25.

[0039] The elements of the wireless access network shown in Figure 2 may operate in a similar way to corresponding elements of an LTE network as described with regard to the example of Figure 1. It will be appreciated that operational aspects of the telecommunications network represented in Figure 2, and of other networks discussed herein in accordance with embodiments of the disclosure, which are not specifically described (for example in relation to specific communication protocols and physical channels for communicating between different elements) may be implemented in accordance with any known techniques, for example according to currently used approaches for implementing such operational aspects of wireless telecommunications systems, e.g. in accordance with the relevant standards.

[0040] The TRPs 10 of Figure 2 may in part have a corresponding functionality to a base station or eNodeB of an LTE network. Similarly, the communications devices 14 may have a functionality corresponding to the UE devices 4 known for operation with an LTE network. It will be appreciated therefore that operational aspects of a new RAT network (for example in relation to specific communication protocols and physical channels for communicating between different elements) may be different to those known from LTE or other known mobile telecommunications standards. However, it will also be appreciated that each of the core network component, base stations and communications devices of a new RAT network will be functionally similar to, respectively, the core network component, base stations and communications devices of an LTE wireless communications network.

[0041] In terms of broad top-level functionality, the core network 20 connected to the new RAT telecommunications system represented in Figure 2 may be broadly considered to correspond with the core network 2 represented in Figure 1, and the respective central units 40 and their associated distributed units 41, 42 / TRPs 10 may be broadly considered to provide functionality corresponding to the base stations 1 of Figure 1. The term network infrastructure equipment / access node may be used to encompass these elements and more conventional base station type elements of wireless telecommunications systems. Depending on the application at hand the responsibility for scheduling transmissions which are scheduled on the radio interface between the respective distributed units and the communications devices may lie with the controlling node / central unit and / or the distributed units / TRPs. A communications device 14 is represented in Figure 2 within the coverage area of a communication cell 12. This communications device 14 may thus exchange signalling with the central unit 40 via one of the distributed units / TRPs 10 associated with the communication cell 12. It will further be appreciated that Figure 2 represents merely one example of a proposed architecture for a new RAT based telecommunications system in which approaches in accordance with the principles described herein may be adopted, and the functionality disclosed herein may also be applied in respect of wireless telecommunications systems having different architectures.

[0042] Thus, certain embodiments of the disclosure as discussed herein may be implemented in wireless telecommunication systems / networks according to various different architectures, such as the example architectures shown in Figs. 1 and 2. It will thus be appreciated the specific wireless telecommunications architecture in any given implementation is not of primary significance to the principles described herein. In this regard, certain embodiments of the disclosure may be described generally in the context of communications between network infrastructure equipment / access nodes and a communications device, wherein the specific nature of the network infrastructure equipment / access node and the communications device will depend on the network infrastructure for the implementation at hand. For example, in some scenarios the network infrastructure equipment / access node may comprise a base station, such as an LTE-type base station 1 as shown in Figure 1 which is adapted to provide functionality in accordance with the principles described herein, and in other examples the network infrastructure equipment may comprise a control unit / controlling node 40, distributed unit 41, 42 and / or a TRP 10 of the kind shown in Figure 2 which is adapted to provide functionality in accordance with the principles described herein.

[0043] A more detailed diagram of some of the components of the network shown in Figure 2 is provided by Figure 3. In Figure 3, a TRP 10 as shown in Figure 2 comprises, as a simplified representation, a wireless transmitter 30, a wireless receiver 32 and a controller or controlling processor 34 which is configured to control the transmitter 30 and the receiver 32 to transmit and receive radio signals to one or more UEs 14 within a cell 12 formed by the TRP 10. As shown in Figure 3, an example UE 14 is shown to include a corresponding wireless transmitter circuitry 49, wireless receiver circuitry 48 and controller circuitry or controlling processor 44 which is configured to control the transmitter 49 and the receiver 48 to transmit and receive radio signals to the TRP 10. Signals transmitted from the transmitter 49 to the receiver 32 may represent uplink data. Signals transmitted from the transmitter 30 to the receiver 48 may represent downlink data. These signals are transmitted via the wireless access interface of the TRP 10.

[0044] The transmitters 30, 49 and the receivers 32, 48 (as well as other transmitters, receivers and transceivers described in relation to examples and embodiments of the present disclosure) may include radio frequency filters and amplifiers as well as signal processing components and devices in order to transmit and receive radio signals in accordance for example with the 5G / NR standard(s). The controllers 34, 44 (as well as other controllers described in relation to examples and embodiments of the present disclosure) may be, for example, a microprocessor, a CPU, or a dedicated chipset, etc., configured to carry out instructions which are stored on a computer readable medium, such as a non-volatile memory. The processing steps described herein may be carried out by, for example, a microprocessor in conjunction with a random access memory, operating according to instructions stored on a computer readable medium. The transmitters, the receivers and the controllers are schematically shown in Figure 3 as separate elements for ease of representation. However, it will be appreciated that the functionality of these elements can be provided in various different ways, for example using one or more suitably programmed computers, or one or more suitably configured application-specific integrated circuit(s) / circuitry / chip(s) / chipset(s). As will be appreciated the infrastructure equipment / TRP / base station as well as the UE / communications device will in general comprise various other elements associated with their operating functionality. As shown in Figure 3, the TRP 10 also includes a communications interface which connects to the DU 42 via a physical interface 16. The communication interface therefore provides a communication link for data and signalling traffic from the TRP 10 via the DU 42 and the CU 40 to the core network 20.

[0045] The interface 46 between the DU 42 and the CU 40 is known as the Fl interface which can be a physical or a logical interface formed by communications circuitry forming part of the DU42. The Fl interface 46 between CU and DU may operate in accordance with specifications 3GPP TS 38.470 and 3GPP TS 38.473, for example, and may be formed from a fibre optic or other wired or wireless high bandwidth connection. In one example the connection 16 from the TRP 10 to the DU 42 is via fibre optic. The connection between a TRP 10 and the core network 20 can be generally referred to as a backhaul, which comprises the interface 16 from the network interface 50 of the TRP 10 to the DU 42 and the Fl interface 46 from the DU 42 to the CU 40. According to the 5G architecture, functions of a gNB 100, which corresponds to the functions performed generally by base station 1 shown in Figure 1, is formed from a combination of one or more TRPs 10, a DU 42 and the CU 40, also shown in Figure 2.

[0046] Mobility of UEs Operating in Idle / Inactive or Connected Modes

[0047] As 5GNR evolves towards 5 G- Advanced (5 G-NR- Advanced), there are new study items being considered in order to support advanced and extended services as well as additional functionality. One such example is the use of artificial intelligence or machine learning (AI / ML) to support various functions. One such study item is AI / ML aided mobility. According to this proposal, AI / ML is used to assist in network mobility functions such as handover. According to one example radio resource management measurements and event predictions are assisted by an AI / ML model. This can include cell level measurement prediction including intra-and inter-frequency prediction for both UE side and network sided model, intercell beam level measurement prediction, handover failure or radio link failure prediction (UE sided model) and measurement events prediction (UE sided model). Using an AI / ML model to predict measurements can reduce an amount of measurements which a UE needs to take in order to determine whether to report measurements in the case of handover or to perform cell reselection. The AI / ML model can predict future measurements or results based on previous measurements, thereby reducing the number of measurements or increasing the accuracy of events / measurement samples, which are required to have enough information to determine a mobility action. Such an arrangement according to example embodiments is explained in the following paragraphs with reference to Figures 4 to 8.

[0048] An example of a UE’s mobility as it moves through a geographical area served by a plurality of cells is illustrated in Figure 4. In Figure 4, a solid line 120 illustrates a path followed by a UE 14 as it moves through a geographical area served by a radio network part of a wireless communications network. As explained above with reference to Figures 1, 2, and 3, a wireless communications network forms a plurality of cells, which are illustrated in Figure 4 by a cell boundary having a dotted line 12, each cell being formed by a base station or gNBs 100. According to conventional mobility functions, if the UE 14 has an active radio bearer for transmitting or receiving data to or from the wireless communications network, then the UE is in a connected state. As such, as the UE moves along the path 120, it measures and reports, based on configured conditions, various radio resource management (RRM) measurements of the various cells 12 to the network which uses these measurements to make decisions as to whether the UE should handover from one of these cells 12 to another. Alternatively, if the UE 14 does not have an active radio bearer for transmitting or receiving data, then the UE 14 is in idle state in which it is not transmitting or receiving data or an inactive state in which it does not have an active radio bearer but may occasionally transmit small amounts of data in an efficient way using a Dedicated Radio Bearer (DRB) established for a Small Data Transmission (SDT) with an associated context. In an active idle / inactive state, the UE again makes measurements of received radio signals which may be RRM measurements from each of the cells 12, and selects one of those cells to which it attaches, or camps on to, and, under certain conditions like change of tracking area, informs the network that this is the cell at which the UE 14 can receive data such as paging messages. A more detailed explanation of a process involved for supporting mobility in both the connected and the Idle / inactive state to shown in Figures 5A and 5B.

[0049] Connected Mode Cell Coverage

[0050] Figure 5A shows a part schematic, part message flow diagram illustrating operations at a high level which are involved in a UE 14 performing handover as part of mobility in a connected state. As shown in Figure 5A, in a first step 500, the wireless communications network transmits control information which configures the UE to perform cell measurements which include radio resource control (RRC) configuration parameters. The RRC configuration parameters control a level of sensitivity to which the UE needs to perform cell measurements and to report these measurements. In step 502, the UE 14 performs measurements of neighbouring cells in connected mode, in order to determine whether it should report those measurements to the network. With a message 504, the UE reports cell measurements having determined that these measurements should be reported to the network based on for example a received signal level or quality which will be explained in more detail below. In step 506, based on the cell measurements received from the UE, the network determines that the UE should handover from one cell to another. Accordingly, in message step 508, the gNB 100 transmits a handover message directing the UE 14 to handover from one cell to another. As will be appreciated from this brief explanation, handover is carried out when the UE is in RRC Connected mode and active user data transmission takes place. With the RRC configuration parameters in step 500, the network can set a rather conservative threshold for handover compared to cell reselection. Handover takes place when both source and target cells are still providing good coverage. This is not needed in idle mode and the UE may stay in idle / inactive camped cell for longer to avoid ping-pong and power consumption. In fact, the cell reselection requires reading target cell system information which consumes UE power.

[0051] Idle Mode Cell Coverage

[0052] A simplified representation of operations performed for cell reselection when the UE is in idle / inactive mode is shown in Figure 5B. As a first step 520, the network transmits control information to configure the UE 14 to perform cell measurements and sets RRC configuration parameters for performing cell reselection, normally broadcasted in system information. The UE 14 then evaluates the measurements it performs in an operation 522. As indicated above measurements performed by the UE in step 522 include generating signal level quality based on detected synchronisation signal blocks (SSB) or transmissions in physical broadcast channel (PBCH). Based on these measurements, the UE 14 evaluates a quality of signals detected from any of the surrounding cells. The UE 14 then determines whether it should reselect another cell. After determining that it should reselect another cell, the UE 14 transmits information informing the network of a cell it has reselected in message 524 in some cases as mentioned above. According to idle mode operation, a UE stays in one cell for longer time before it moves out or starts performing measurements and tries to save as much of power as possible. As such, a threshold below which UE 14 starts performing measurements and at which the UE performs cell reselection can be higher than that for handover in order to save UE power consumption.

[0053] Cell Measurements An example of measurements performed in a connected state, according to 3GPP specification TS 38.300, is briefly summarised in more detail in the following paragraphs and illustrated by a schematic block diagram of a measurement model shown in Figure 6 reproduced from TS 38.300. As shown in Figure 6, in an RRC connected mode, a UE performs measurements of multiple beams in a cell and neighbouring cells by detecting radio signals from each of the beams and from each base station 600, such as a Synchronisation Signal Block (SSB). These measurements detected from each of the beams are fed to a layer 1 filtering process 602, so that a filtering operation is performed at the physical layer for each of the samples of the detected radio signals from each beam before these are fed to beam consolidation and selection process 604 and a Layer 3 or radio link control layer beam filtering process 606. Each of the filtered outputs for each of the beams is then fed to a beam selection for reporting process 608 in which one or more of the best beams are selected for reporting back to the network or used by the UE to select a beam for transmitting or receiving. An output from the beam consolidation and selection process 604 is fed to a Layer 3 filtering for cell quality process 612 which generates a metric of an overall quality from the beam measurements, which is sent to an evaluation reporting criteria process 614. The evaluation of reporting criteria 614 determines whether the measured cell quality should be reported because for example this has fallen below a threshold adjusted for the measurement being for handover. The determined report is presented on an output 616, and the measurement is reported to the wireless communications network. For each of the processes as shown in Figure 6, RRC configuration parameters 620 are fed to the respective processes 604, 606, 608, 612, 614 for controlling whether measurements are evaluated and reported and for which an action is determined.

[0054] According to this illustration of the measurement model shown in Figure 6, when the UE is in an RRC connected state (RRC CONNECTED), the UE measures multiple beams (at least one) of a cell and the measurements results (power values) are averaged to derive the cell quality. In doing so, the UE is configured to consider a subset of the detected beams. Filtering takes place at two different levels: at the physical layer (LI) to derive beam quality and then at RRC level (L3) to derive cell quality from multiple beams. Cell quality from beam measurements is derived in the same way for the serving cell(s) and for the non-serving cell(s). Measurement reports may contain the measurement results of the A best beams if the UE is configured to do so by the gNB, which is indicated above are presented as an output 610.

[0055] According to TS 38.300, intra-frequency neighbour (cell) measurements and inter-frequency cells measurements are based on detecting an SSB for intra-frequency measurements or measurements can be taken based on cell specific indicator - reference signals (CSI-RS). The network may also request the UE to measure NR and or E- UTRA carriers in RRC idle or RRC inactive modes via system information or via dedicated measurement configuration. The UE can be directed by the gNB to provide corresponding measurement results in an RRC resume message or an RRC resume complete message for early measurement results. Alternatively, UE may be provided an indication of the availability of the measured early measurement results to the gNB in an RRC complete message and the gNB can then request the UE to provide this measurement results.

[0056] In summary, when the UE is in a connected mode, the UE performs measurements on beams and performs filtering for both LI and L3 of these measurement samples. Based on these filtered measurements a trigger is evaluated based on consolidated cell level averaging of the filtered measurements. A number of good beams may be reported. The UE may also be configured to perform measurements based on either SSB or CSI-RS. Furthermore, a list of cell specific offsets, a list of exclude-listed cells and a list of allow-listed cells are provided to the UE, as explained in TS 38.331. The network may consider intra-frequency and inter-frequency measurements to include a frequency / time location and subcarrier spacing of the reference signal to be measured as well as configuring a list of cell specific offsets a list of excluded cells and a list of allowed cells. These are provided in the RRC configuration parameters 620 shown in Figure 6.

[0057] In some examples, a list of allow or exclude cells is service dependent e.g. cells not supporting IMS (in cases where voice is supported over legacy networks) may be included in exclude list, when UE is performing an IMS call but these cells may be supporting other services and are included in allow-listed cells list when UE is in connected mode due to other services.

[0058] As explained above, there are parameters which are configured differently when the UE is performing measurements in idle / inactive mode and connected mode. TS 38.300 provides further examples of some parameters for performing measurements in connected mode like absThreshSS-BlocksConsolidation, nrofSS- BlocksTo Average, offsetMO, allowed and excluded cell list.

[0059] Similarly, RRC configuration parameters are indicated in SIB2 for UEs to take into account while in idle / inactive mode. In addition to the above parameters, the UE may be configured with relaxed measurements in idle / inactive mode with parameters such as cellReselectionlnfoCommon with optional parameters such as nrofSS-

[0060] BlocksTo Average, absThresholdSS-BlocksConsolidation, rangeToBestCell and q-Hyst as an enumerated type. These parameters like e.g. a number of beams to measure, threshold and offset values are the same for connected and idle / inactive states but configured with different values in order to adjust effective coverage of a cell for different RRC states.

[0061] AI / ML Model Life Cycle Management

[0062] AI / ML Life Cycle Management (LCM) is an aspect which formed part of studies for development of Release- 18 of the 3GPP standard. The studies considered use of AI / ML, which developed certain terms which are identified in TR 21.905 [3] including development of an AI / ML model for model inference which uses a training of an AI / ML model to produce a set of outputs based on a set of inputs for model inference. This also considered federated leaming / federated training in which a machine learning technique trains an AI / ML model across multiple decentralised edge nodes for example UEs and gNB’s, each performing a local model training using local data samples. There is also considered model monitoring and model parameter update as well as model switching in which inference performance of the AI / ML model is monitored and updated or alternative models are selected for the same AI / ML enabled feature. There is also considered off-line field data and off-line training in which data collected from an operating field are used for off-line training of an AI / ML model for inference. Further examples are disclosed in TR2 1.905 [3],

[0063] Model inference, federated learning, model monitoring, model parameters update, model selection switching, and selection depend on the quality of input data. If a UE does not distinguish measurement samples collected when it was in idle or connected mode or which set of parameters it used to collect measurement samples, AI / ML model for mobility may not work well.

[0064] Embodiments of the present technique seek to address potential problems which may occur when there are some differences in the way measurement samples are collected / used in idle and connected modes and if this information is not fed to an AI / ML model then prediction results may be wrong. Consider the example shown in Figure 7 which is based on the example shown in Figure 4, in which a UE moves along a path 120 within a geographical area served by four cells. Each of the cells is represented by an inner circle 700 and an outer circle 702 which represent an offset measurement of a threshold value respectively for performing handover (higher signal quality required to remain in the cell; therefore inner circle) and performing cell reselection (lower signal quality required to remain in the cell rather than reselecting a different cell; therefore outer circle). According to the illustration shown in Figure 7, the UE performs various actions at different points and transitions between different modes of connected and idle depending on its requirement for transmitting and receiving data as it moves along the path 120 and performs measurement collection. The different actions are represented by arrows. According to a first action 710, the UE moves to an RRC connected mode in the first cell because it needs to transmit or receive data and then collects its first measurement samples based on CSI-RS configuration. As shown in the second arrow 712, whilst in the connected mode, the UE samples beams of the gNB providing the cell 700 as well as neighbouring cells and identifies that there are five good beams determined from a reference signal received power (RSRP) determined from on CSI-RS. Later, based on measurements and reports (not shown in Figure 7) the UE performs a handover, represented by the third arrow 714, and moves to the next cell using offset and other parameters in measconfig in connected mode. The UE then collects further measurement results, as represented by fourth and fifth arrows 716, 718, in which the UE collects two measurement samples: first with five good beams 716 and another with four good beams 718. The assumption is that there will be fewer good beams towards the centre of a cell compared to cell edge. The UE then performs another handover to a third cell as represented by an arrow 720 and in the third cell, it moves to idle or inactive mode as represented by an arrow 722.

[0065] The UE continues to collect measurement samples based on an idle / inactive configuration, as it moves along the path 120, and when in the idle or inactive mode the UE performs a cell re-selection based on those measurements as represented by an arrow 724. These measurements are performed based on a detected SSB and beam width measurements and may be wider than CSI-RS beams. When the UE finally moves to connected mode as represented by an arrow 726, where it is required to perform prediction of measurement results, a handover failure or radio link failure may occur if the UE has used measurement data collected both during idle and connected modes with different received signal types, or has performed handover / cell reselection based on different set of parameters such as offset, hysteresis etc. Furthermore, the measurement sample collection could be impacted by features like relaxed measurements in idle / inactive mode where the UE may have collected less measurement samples as a result of the relaxed measurements.

[0066] Considering filtering or weightage being applied to measurement samples and the UE having idle mode measurements as the latest samples and having higher weightage, prediction for connected mode, mobility may not work well. For example, the UE may predict a wrong neighbouring CSI-RS beam whereas this beam is still covered by the same SSB beam, which the UE would have predicted based on idle mode measurements, which is represented as an arrow 728. This inaccuracy in prediction represents a technical problem which should be addressed.

[0067] Example embodiments can provide a UE and a method of operating a UE to communicate via a wireless communications network, the method comprising receiving signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, and receiving radio resource control, RRC, configuration parameters including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with measurements, and measuring one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals. The UE then operates to generate predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the measurement actions, such as handover or cell re-selection. The UE is receiving the signals to generate the measurement samples when in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values. The generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

[0068] Example embodiments can provide an improvement in respect of an accuracy with which measurements are predicted by an AI / ML model by adapting the samples use the AI / ML model to reduce a likelihood of an incorrect prediction and therefore reduce a likelihood of radio link failure, handover failure or handover to a wrong cell. The actions may vary between different vendors of user equipment, radio network infrastructure equipment and mobile network operator policies, for example some vendors may accept errors whereas others will not.

[0069] According to example embodiments, a UE informs the network or takes into account whether the measurement samples which are used for prediction were collected during idle mode or connected mode. In other words, it might have an impact on model update, federated learning, offline model training, online training, reinforced learning, and model inference.

[0070] Example embodiments can be implemented with a measurement model running on the UE side or the network side. If a model is running on the network side, then the UE is configured to send measurement reports as would be performed for a conventional or legacy device. Currently, UEs either perform measurements for idle / inactive or connected mode and never combine these together and these are also not combined on the network side. The UE performs measurements and reports these measurement results in the connected mode. Then there are early measurements, as specified in 3GPP, which allow a UE to perform measurements in idle / inactive state and report these measurements while transitioning to connected mode. There are clear procedures / messages to retrieve such measurements performed in idle mode, so that the network does not have any ambiguity as to whether the measurements were derived when it was in connected mode or whilst in idle mode. The UE reports the measurements when in connected mode.

[0071] Any network side model may be left to network implementation unless there is a feedback to the UE or the network wants to know if a new measurement reporting structure is designed.

[0072] For a UE sided model, the UE can perform measurements and send a prediction to the network. The network may configure the UE as to how to perform measurements or ask the UE how the UE achieved a prediction to assess its prediction accuracy. The UE sided model is explained below and some of these aspects could be used for a network sided model and therefore a conventional measurement acquisition and reporting would be adapted accordingly. An example embodiment is illustrated by a part flow diagram illustrating an operation of a UE which uses an adapted AI / ML model to perform measurements and generate predicted measurements in connected mode for handover. The AI / ML model is adapted in accordance with a mode in which the UE was operating when it generated these measurements. As shown in Figure 8, a UE 14 corresponding to a UE 14 shown in Figures 2 and 3 comprises a transmitter circuit 49 and a receiver circuit 48 and a controller circuit 44 which operate in combination to form an adapted measurement generation technique for determining handover represented by the flow diagram. Generally, the flow diagram corresponds to the measurement model illustrated in Figure 6 simplified and adapted according to example embodiments.

[0073] As shown in Figure 8, as a first operation 800, the controller circuit 44 and receiver circuit 48 operate in combination to perform measurements of beams for each cell by detecting a S SB in each beam and each cell. In accordance with the explanation of Figure 6, each of these measurements may be subject to layer 1 filtering and / or layer 3 filtering. The measurement samples are then fed to an AI / ML prediction model 802 and also to a storage unit 804 which stores previous sample measurements for use by the AI / ML prediction model to generate prediction of measurement values based on samples generated in the first operation 800. The generated measurement samples produced from prediction by the AI / ML model 802 are then fed to an evaluation reporting criteria process 806 which corresponds to the evaluation of reporting process 614 in Figure 6. The predicted measurements and evaluated measurements generated from received signals are then combined for evaluation against criteria set by the RRC parameters. Based on the criteria set for reporting the predicted and evaluated measurements the control circuit 44 at step 808, determines whether it should report the measurements to the network. For example, the measurements may indicate that a measured cell quality has fallen or will fall soon below a desire threshold. In response the network may transmit a handover command to the UE so that the controller circuit 44 is configured to assess whether to perform a handover at step 810. If the handover is performed then processing proceeds to execute handover at step 812. Otherwise processing proceeds back to the measurement operation 800.

[0074] As shown in Figure 8 the flow diagram includes an operation process block 814 for prediction adaptation which has inputs to the AI / ML prediction model 802 and the storage unit 804. The prediction adapting process block 814 is representative of the control input to the AI / ML model which adapts the prediction generated by the model based on whether the measurement samples used to perform a prediction were acquired during either a connected mode or an idle mode. For example, the prediction adapting block 814 may ensure that only measurement samples generated during the connected mode are used in the prediction model or may adapt the samples to ensure that they correspond to the mode in which prediction is being performed. To this end, the prediction adapting block 814 receives an input indicating a time at which the UE was in connected mode, or idle mode from process block 816.

[0075] A corresponding example of using adapted AI / ML model 802 for generating or predicting measurement samples when the UE operates to perform cell reselection in idle mode is shown in Figure 9. Generally operations shown in Figure 9 correspond to those shown in Figure 8 and have corresponding reference numerals. As shown in Figure 9, as a first step 900, measurements are performed in idle mode to evaluate received samples from each beam from each cell. The samples are fed to the AI / ML prediction model 802 and to the storage unit 804 and generally are used to generate prediction of samples evaluated from received signals such as the SSB formed in the first step 900. As an output of the AI / ML prediction model 802, predicted samples are generated which can be combined with evaluated measured samples from received signals and fed to an evaluate reselection criteria process block 906 to determine whether the control circuit 44 should perform a cell reselection at operation 908. If it is determined by the control circuit 44 at step 908 that it should perform a cell reselection, then at step 910 the UE performs a cell reselection. Optionally, depending on whether the UE has selected a cell in a different Tracking Area (TA), a change of the TA requires that the UE informs the network and so at step 912 the UE informs the network that it has camped on to a new cell in a new TA in accordance with a conventional arrangement. If there has been no change in TA, then there is no transmission at step 912 by the UE and the UE internally manages the cell reselection and so step 912 would not happen. Otherwise, if it is determined that cell reselection should not be performed at step 908 then processing proceeds back to the measurement block 900. As for the example shown in Figure 8, a cell reselection process based on AI / ML predictions is adapted with a prediction adapting block 814, which is used to control the AI / ML prediction model 802 and the storage unit 804 to adapt the prediction based on whether the samples were generated in a connected mode or an idle mode as fed as an input by block 816.

[0076] As will be appreciated from the flow diagrams illustrating the processes of measurement prediction and reporting in either the connected state (Figure 8) or the idle / inactive state (Figure 9) a difference in operation is based on the RRC configuration parameters. As explained above these parameters may for example include in both the connected and idle / inactive states the same parameters such as a number of beams to measure, threshold and offset values but configured with different values in order to adjust effective coverage of a cell for different RRC states. Accordingly adapting the AI / ML prediction with respect to these values can improve an accuracy of the prediction and / or a decision relating to measurements action, such as handover.

[0077] Example embodiments therefore provide a prediction model based on AI / ML which is adapted to control samples used for the prediction in order to reduce or avoid errors which may occur without prediction causing a radio link failure or handover failure. The network may control the predictions to improve accuracy by commanding the UE to predict based on absolute RSRP / RSRQ / RSSI measurement results and not take any cell specific and parameters which are different for idle and connected mode like hysteresis and offset values. The following are example criteria for controlling the AI / ML prediction model illustrated in Figures 10A, 10B, and 10C:

[0078] 1. UE performs measurements only in connected mode.

[0079] • This is either configured by the network (as shown in Figure 10A) or informed by the UE as directed by the network (as shown in Figure 10B) or pre-configured, that is, a requirement indicated and defined in a 3GPP specifications.

[0080] 2. UE is capable of performing measurements in both idle and connected mode

[0081] • UE is configured to perform either connected mode only such as illustrated in Figure 10C or idle and connected mode by the network, for example as shown in Figure 10B

[0082] • Alternatively, the UE informs the network if it performed measurements or collected data based on either connected mode only or idle and connected mode and prediction is based on these assumptions

[0083] 3. In another embodiment, the UE informs how it reached the predicted measurements i.e. whether it took into account the received or reference signal type, hysteresis or offset into account or not.

[0084] This may be reported if configured by network to report.

[0085] Event Prediction

[0086] Measurement prediction based on samples collected in idle and connected mode might have less impact on prediction accuracy unless a reference or received signal type is different. However, event prediction will be impacted by offset, number of beams to be taken into account, hysteresis parameters and it is therefore important to know how a UE predicted an event.

[0087] 4. In one embodiment, the network or the mobile network operator policy or a UE vendor configures the UE to take either connected mode parameters into account or both idle and connected mode parameters. In this case, network may not wait for a response i.e. the network configures and the UE performs prediction accordingly. Time based event prediction for NTN is easier as it does not depend on measurements and depends on satellite speed and trajectory.

[0088] Not allowed Cell list handling

[0089] 5. In one embodiment, the UE performs measurement prediction based on the allowed cell list received in a connected mode. The network may support IMS voice call over a selected few cells, for example a cell not having overlaid 4G coverage. So if the UE is performing a voice call in 5G NR then the allowed cell list will be a subset of available cells. However, the UE may be allowed in cells not supporting voice call for other services.

[0090] A UE with an ongoing voice call may predict measurements for a limited number of cells whereas the same UE may predict measurements for a wider number of cells when connected for a different service or in idle / inactive mode. So, in one embodiment, the UE informs the network if prediction was done when a voice call was ongoing. The network will be aware of an ongoing voice call and also limited to a cell list using MRL, so gNB correlate a service and predicted measurements.

[0091] Further example embodiments of the present disclosure are defined by the following numbered paragraphs: Paragraph 1. A method of operating a communications device to communicate via a wireless communications network, the method comprising receiving radio resource control, RRC, configuration parameters including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with the measurements, receiving signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, measuring one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, generating predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the actions associated with the measurements, wherein the communications device is receiving the signals to generate the measurement samples when in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values, or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

[0092] Paragraph 2. A method of paragraph 1, wherein the adapting the prediction of the samples using the AI / ML model comprises selecting only the measurement samples which were generated for each of the one or more cells when the communications device is in the connected mode. Paragraph 3. A method of paragraph 1, wherein the adapting the prediction of the samples using the AI / ML model comprises selecting only the measurement samples which were generated for each of the one or more cells when the communications device is in both the connected mode and the idle or inactive mode.

[0093] Paragraph 4. A method of paragraph 2 or 3, comprising transmitting to the wireless communications network an indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode or the idle or inactive mode.

[0094] Paragraph 5. A method of paragraph 4, comprising receiving a request from the wireless communications network for an indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model, and in response to the request, transmitting the indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model to the wireless communications network. Paragraph 6. A method of any of paragraphs 1 to 5, wherein the RRC configuration parameters include a threshold value for triggering a measurement action and an offset value for offsetting predicted measurement values, the threshold value and the offset value of the first set for the connected mode being different from the threshold value and the offset value of the second set for the idle / inactive mode.

[0095] Paragraph 7. A method of operating a communications device to communicate via a wireless communications network, the method comprising receiving radio resource control configuration parameters including an indication of one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode, receiving signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, measuring one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, generating predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with the measurements, wherein the communications device is receiving the signals to generate the measurement samples in a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model to use measurement samples which were generated from the one or more allowed cells when in the connected mode.

[0096] Paragraph 8. A method of paragraph 7, comprising transmitting to the wireless communications network an indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model using the measurement samples generated from the one or more allowed cells, Paragraph 9. A method of paragraph 7 or 8, wherein the one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode are one or more cells which can support voice calls in the connected mode.

[0097] Paragraph 10. A method of any of paragraphs 1 to 9, wherein the communications device receives the signals to generate the measurement samples when in the connected mode, and the evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with measurements comprises evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to report the predicted samples to the wireless communications network in association with a handover from one cell to another.

[0098] Paragraph 11. A method of any of paragraphs 1 to 9, wherein the communications device receives the signals to generate the measurement samples when in the idle or the inactive mode, and the evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with the measurements comprises evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to reselect one of the cells

[0099] Paragraph 12. A method of paragraph 11, wherein the communications device receives the signals to generate the measurement samples when in the idle or the inactive mode, and transitions to operate in the connected mode, and the evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with the measurements comprises evaluating the predicted samples for each of the one or more cells generated when the communications device was in the idle mode to determine whether to report the predicted samples to the wireless communications network in association with a handover from one cell to another, when in the connected mode.

[0100] Paragraph 13. A method of operating an infrastructure equipment forming part of a radio network of a wireless communications network, the method comprising transmitting radio resource control, RRC, configuration parameters to a communications device including one or more parameter values associated with performing measurements which are used by the communications device to determine whether to perform one or more actions associated with the measurements, receiving measurement samples of one or more parameters from the communications device, the measurement samples being one or more measured parameters of signals received from the wireless communications network by the communications device from one or more of a plurality of cells of a radio network part of the wireless communications network, generating predicted samples from the received measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the actions associated with the measurements, wherein the measurement samples were measured from the signals received by the communications device, when the communications device was in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values, or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

[0101] Paragraph 14. A method of paragraph 13, wherein the adapting the prediction of the samples using the AI / ML model comprises selecting only the measurement samples which were generated for each of the one or more cells when the communications device is in the connected mode. Paragraph 15. A method of paragraph 13, wherein the adapting the prediction of the samples using the AI / ML model comprises selecting only the measurement samples which were generated for each of the one or more cells when the communications device is in both the connected mode and the idle or inactive mode.

[0102] Paragraph 16. A method of paragraph 13, comprising transmitting a request to the communications device for an indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model, and in response to the request, receiving the indication of whether the measurement samples were generated in the connected mode or the idle / inactive mode.

[0103] Paragraph 17. A method of any of paragraphs 13 to 16, wherein the RRC configuration parameters include a threshold value for triggering an action associated with the measurements and an offset value for offsetting predicted measurement values, the threshold value and the offset value of the first set for the connected mode being different from the threshold value and the offset value of the second set for the idle / inactive mode. Paragraph 18. A method of operating an infrastructure equipment forming part of a radio network of a wireless communications network, the method comprising transmitting radio resource control, RRC, configuration parameters to a communications device including an indication one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode, receiving measurement samples of one or more parameters from the communications device, the measurement samples being one or more measured parameters of signals received from the wireless communications network by the communications device from one or more of a plurality of cells of a radio network part of the wireless communications network, generating predicted samples from the received measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether the communications device should perform one or more actions associated with the measurements, wherein the communications device generates the measurement samples in a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model to use measurement samples which were generated by the communication device from signals received the one or more allowed cells when in the connected mode.

[0104] Paragraph 19. A method of paragraph 18, comprising receiving from the wireless communications network an indication of the one or more allowed cells from which the measurement samples which were generated when in the connected mode for adapting the prediction of the samples using the AI / ML model.

[0105] Paragraph 20. A method of paragraph 18 or 19, wherein the one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode are one or more cells which can support voice calls in the connected mode.

[0106] Paragraph 21. A communications device for operating to communicate via a wireless communications network, the communications device comprising transceiver circuitry configured for transmitting signals via a wireless access interface provided by the wireless communications network, and for receiving signals transmitter from the infrastructure equipment via the wireless access interface, and controller circuitry configured with the transceiver circuitry to receive radio resource control, RRC, configuration parameters including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with the measurements, to receive signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, to measure one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, to generate predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the actions associated with the measurements, wherein the communications device is receiving the signals to generate the measurement samples when in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values, or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, wherein the controller circuit is configured to adapt the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

[0107] Paragraph 22. A communications device for operating to communicate via a wireless communications network, the communications device comprising transceiver circuitry configured for transmitting signals via a wireless access interface provided by the wireless communications network, and for receiving signals transmitter from the infrastructure equipment via the wireless access interface, and controller circuitry configured with the transceiver circuitry to receive radio resource control configuration parameters including an indication one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode, to receive signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, to measure one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, to generate predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with the measurements, wherein the communications device is receiving the signals to generate the measurement samples in a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model to use measurement samples which were generated from the one or more allowed cells when in the connected mode.

[0108] Paragraph 23. An infrastructure equipment forming part of a radio network of a wireless communications network, the infrastructure equipment comprising transceiver circuitry configured for receiving signals transmitted by communications devices via a wireless access interface provided by the wireless communications network, and for transmitting signals to the communications devices via the wireless access interface, and controller circuitry configured with the transceiver circuitry to transmit radio resource control, RRC, configuration parameters to a communications device including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with the measurements, to receive measurement samples of one or more parameters from the communications device, the measurement samples being one or more measured parameters of signals received from the wireless communications network by the communications device from one or more of a plurality of cells of a radio network part of the wireless communications network, to generate predicted samples from the received measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the actions associated with the measurements, wherein the measurement samples were measured from the signals received by the communications device, when the communications device was in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values, or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, wherein the controller circuitry is configured to adapt the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

[0109] Paragraph 24. An infrastructure equipment forming part of a radio network of a wireless communications network, the infrastructure equipment comprising transceiver circuitry configured for receiving signals transmitted by communications devices via a wireless access interface provided by the wireless communications network, and for transmitting signals to the communications devices via the wireless access interface, and controller circuitry configured with the transceiver circuitry to transmit radio resource control, RRC, configuration parameters to a communications device including an indication of one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode, to receive measurement samples of one or more parameters from the communications device, the measurement samples being one or more measured parameters of signals received from the wireless communications network by the communications device from one or more of a plurality of cells of a radio network part of the wireless communications network, to generate predicted samples from the received measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether the communications device should perform one or more of the actions associated with the measurements, wherein the communications device generates the measurement samples in a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells, wherein the controller circuitry is configured to adapt the prediction of the samples using the AI / ML model to use measurement samples which were generated by the communication device from signals received from the one or more allowed cells when in the connected mode.

[0110] Numerous modifications and variations of the present disclosure are possible in light of the above teachings. It is therefore to be understood that, within the scope of the claims, the disclosure may be practiced otherwise than as specifically described herein.

[0111] In so far as embodiments of the disclosure have been described as being implemented, at least in part, by one or more software-controlled information processing apparatuses, it will be appreciated that a machine-readable medium (in particular, a non-transitory machine-readable medium) carrying such software, such as an optical disk, a magnetic disk, semiconductor memory or the like, is also considered to represent an embodiment of the present disclosure. In particular, the present disclosure should be understood to include a non-transitory storage medium comprising code components which cause a computer to perform any of the disclosed method(s).

[0112] It will be appreciated that the above description for clarity has described embodiments with reference to different functional units, circuitry and / or processors. However, it will be apparent that any suitable distribution of functionality between different functional units, circuitry and / or processors may be used without detracting from the embodiments.

[0113] Described embodiments may be implemented in any suitable form including hardware, software, firmware or any combination of these. Described embodiments may optionally be implemented at least partly as computer software running on one or more computer processors (e.g. data processors and / or digital signal processors). The elements and components of any embodiment may be physically, functionally and logically implemented in any suitable way. Indeed, the functionality may be implemented in a single unit, in a plurality of units or as part of other functional units. As such, the disclosed embodiments may be implemented in a single unit or may be physically and functionally distributed between different units, circuitry and / or processors.

[0114] Although the present disclosure has been described in connection with some embodiments, it is not intended to be limited to these embodiments. Additionally, although a feature may appear to be described in connection with particular embodiments, one skilled in the art would recognize that various features of the described embodiments may be combined in any manner suitable to implement the present disclosure.

[0115] REFERENCES

[0116] [1] Holma H. and Toskala A, “LTE for UMTS OFDMA and SC-FDMA based radio access”, John Wiley and Sons, 2009.

[0117] [2] TR 38.300

[0118] [3] TR 21.905

Claims

CLAIMS1. A method of operating a communications device to communicate via a wireless communications network, the method comprising receiving radio resource control, RRC, configuration parameters including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with the measurements, receiving signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, measuring one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, generating predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the actions associated with the measurements, wherein the communications device is receiving the signals to generate the measurement samples when in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values, or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

2. A method of claim 1, wherein the adapting the prediction of the samples using the AI / ML model comprises selecting only the measurement samples which were generated for each of the one or more cells when the communications device is in the connected mode.

3. A method of claim 1, wherein the adapting the prediction of the samples using the AI / ML model comprises selecting only the measurement samples which were generated for each of the one or more cells when the communications device is in both the connected mode and the idle or inactive mode.

4. A method of claim 2, comprising transmitting to the wireless communications network an indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode or the idle or inactive mode.

5. A method of claim 4, comprising receiving a request from the wireless communications network for an indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model, andin response to the request, transmitting the indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model to the wireless communications network.

6. A method of claim 1, wherein the RRC configuration parameters include a threshold value for triggering a measurement action and an offset value for offsetting predicted measurement values, the threshold value and the offset value of the first set for the connected mode being different from the threshold value and the offset value of the second set for the idle / inactive mode.

7. A method of operating a communications device to communicate via a wireless communications network, the method comprising receiving radio resource control configuration parameters including an indication of one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode, receiving signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, measuring one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, generating predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with the measurements, wherein the communications device is receiving the signals to generate the measurement samples in a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model to use measurement samples which were generated from the one or more allowed cells when in the connected mode.

8. A method of claim 7, comprising transmitting to the wireless communications network an indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model using the measurement samples generated from the one or more allowed cells,9. A method of claim 7, wherein the one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode are one or more cells which can support voice calls in the connected mode.

10. A method of claim 1, wherein the communications device receives the signals to generate the measurement samples when in the connected mode, and the evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with measurements comprises evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to report the predicted samples to the wireless communications network in association with a handover from one cell to another.

11. A method of claim 1, wherein the communications device receives the signals to generate the measurement samples when in the idle or the inactive mode, and the evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with the measurements comprises evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to reselect one of the cells12. A method of claim 11, wherein the communications device receives the signals to generate the measurement samples when in the idle or the inactive mode, and transitions to operate in the connected mode, and the evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with the measurements comprises evaluating the predicted samples for each of the one or more cells generated when the communications device was in the idle mode to determine whether to report the predicted samples to the wireless communications network in association with a handover from one cell to another, when in the connected mode.

13. A method of operating an infrastructure equipment forming part of a radio network of a wireless communications network, the method comprising transmitting radio resource control, RRC, configuration parameters to a communications device including one or more parameter values associated with performing measurements which are used by the communications device to determine whether to perform one or more actions associated with the measurements, receiving measurement samples of one or more parameters from the communications device, the measurement samples being one or more measured parameters of signals received from the wireless communications network by the communications device from one or more of a plurality of cells of a radio network part of the wireless communications network, generating predicted samples from the received measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the actions associated with the measurements, wherein the measurement samples were measured from the signals received by the communications device, when the communications device was in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values, or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

14. A method of claim 13, wherein the adapting the prediction of the samples using the AI / ML model comprises selecting only the measurement samples which were generated for each of the one or more cells when the communications device is in the connected mode.

15. A method of claim 13, wherein the adapting the prediction of the samples using the AI / ML model comprises selecting only the measurement samples which were generated for each of the one or more cells when the communications device is in both the connected mode and the idle or inactive mode.

16. A method of claim 13, comprising transmitting a request to the communications device for an indication of the measurement samples which were used to generate the prediction of the samples using the AI / ML model, and in response to the request, receiving the indication of whether the measurement samples were generated in the connected mode or the idle / inactive mode.

17. A method of claim 13, wherein the RRC configuration parameters include a threshold value for triggering an action associated with the measurements and an offset value for offsetting predicted measurement values, the threshold value and the offset value of the first set for the connected mode being different from the threshold value and the offset value of the second set for the idle / inactive mode.

18. A method of operating an infrastructure equipment forming part of a radio network of a wireless communications network, the method comprising transmitting radio resource control, RRC, configuration parameters to a communications device including an indication one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode, receiving measurement samples of one or more parameters from the communications device, the measurement samples being one or more measured parameters of signals received from the wireless communications network by the communications device from one or more of a plurality of cells of a radio network part of the wireless communications network, generating predicted samples from the received measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and evaluating the predicted samples for each of the one or more cells with respect to criteria to determine whether the communications device should perform one or more actions associated with the measurements, wherein the communications device generates the measurement samples in a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model to use measurement samples which were generated by the communication device from signals received the one or more allowed cells when in the connected mode.

19. A method of claim 18, comprising receiving from the wireless communications network an indication of the one or more allowed cells from which the measurement samples which were generated when in the connected mode for adapting the prediction of the samples using the AI / ML model.

20. A method of claim 18, wherein the one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode are one or more cells which can support voice calls in the connected mode.

21. A communications device for operating to communicate via a wireless communications network, the communications device comprising transceiver circuitry configured for transmitting signals via a wireless access interface provided by the wireless communications network, and for receiving signals transmitter from the infrastructure equipment via the wireless access interface, and controller circuitry configured with the transceiver circuitry to receive radio resource control, RRC, configuration parameters including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with the measurements, to receive signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, to measure one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, to generate predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the actions associated with the measurements, wherein the communications device is receiving the signals to generate the measurement samples when in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values, or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, wherein the controller circuit is configured to adapt the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

22. A communications device for operating to communicate via a wireless communications network, the communications device comprising transceiver circuitry configured for transmitting signals via a wireless access interface provided by the wireless communications network, and for receiving signals transmitter from the infrastructure equipment via the wireless access interface, and controller circuitry configured with the transceiver circuitry to receive radio resource control configuration parameters including an indication one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode, to receive signals from the wireless communications network from one or more of a plurality of cells of a radio network part of the wireless communications network, to measure one or more parameters of the received signals to generate measurement samples from each of the one or more cells based on the one or more measured parameters of the received signals, to generate predicted samples from the measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more actions associated with the measurements, wherein the communications device isreceiving the signals to generate the measurement samples in a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells, and the generating the predicted samples from the measurement samples from each of the one or more cells, comprises adapting the prediction of the samples using the AI / ML model to use measurement samples which were generated from the one or more allowed cells when in the connected mode.

23. An infrastructure equipment forming part of a radio network of a wireless communications network, the infrastructure equipment comprising transceiver circuitry configured for receiving signals transmitted by communications devices via a wireless access interface provided by the wireless communications network, and for transmitting signals to the communications devices via the wireless access interface, and controller circuitry configured with the transceiver circuitry to transmit radio resource control, RRC, configuration parameters to a communications device including one or more parameter values associated with measurements which are used by the communications device to determine whether to perform one or more actions associated with the measurements, to receive measurement samples of one or more parameters from the communications device, the measurement samples being one or more measured parameters of signals received from the wireless communications network by the communications device from one or more of a plurality of cells of a radio network part of the wireless communications network, to generate predicted samples from the received measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether to perform one or more of the actions associated with the measurements, wherein the measurement samples were measured from the signals received by the communications device, when the communications device was in either a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells and the RRC configuration parameters have a first set of one or more values, or an idle or inactive mode in which the RRC configuration parameters have a second set of one or more values, which are different to the first set of values, wherein the controller circuitry is configured to adapt the prediction of the samples using the AI / ML model based on whether the measurement samples were generated in one or both of the connected mode using the first set of values for the RRC configuration parameters or the idle or inactive mode using the second set of values for the RRC configuration parameters.

24. An infrastructure equipment forming part of a radio network of a wireless communications network, the infrastructure equipment comprising transceiver circuitry configured for receiving signals transmitted by communications devices via a wireless access interface provided by the wireless communications network, and for transmitting signals to the communications devices via the wireless access interface, and controller circuitry configured with the transceiver circuitry to transmit radio resource control, RRC, configuration parameters to a communications device including an indication of one or more cells of a radio network part of the wireless communications network, which the communications device can access in a connected mode, to receive measurement samples of one or more parameters from the communications device, the measurement samples being one or more measured parameters of signals received from the wirelesscommunications network by the communications device from one or more of a plurality of cells of a radio network part of the wireless communications network, to generate predicted samples from the received measurement samples from each of the one or more cells using an artificial intelligence or machine learning, AI / ML, model, and to evaluate the predicted samples for each of the one or more cells with respect to criteria to determine whether the communications device should perform one or more of the actions associated with the measurements, wherein the communications device generates the measurement samples in a connected mode in which it is transmitting or receiving data via a radio bearer established with one of the plurality of cells, wherein the controller circuitry is configured to adapt the prediction of the samples using the AI / ML model to use measurement samples which were generated by the communication device from signals received from the one or more allowed cells when in the connected mode.

Images