Evaluating time-domain prediction information for cho execution condition

Abstract

According to an aspect, there is provided a method performed by a user equipment, UE The UE is being served by a first cell. The method comprises receiving (702) a conditional handover, CHO, execution condition. The CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell.

Description

[0001] Evaluating time-domain prediction information for CHO execution condition

[0002] Technical Field

[0003] This disclosure relates to time-domain prediction information.

[0004] Background

[0005] Conditional handover (CHO) has been introduced in Release 16 (Rel-16) for New Radio (NR) to improve the mobility robustness i.e. reduce the amount of Radio Link Failure(s) (RLF) and / or Handover failure(s) (HOF) in the user equipment (UE). Failures could be caused by the fact that when the UE is in the cell border, and close to be triggered by the network to perform a handover (HO), the UE may try to send a Layer 3 (L3) Measurement Report (MR) to the network which is either not received by the source gNodeB (gNB) (e.g. due to some interference in the UL and / or poor coverage) or, even if the source gNodeB receives the Measurement Report, the UE does not receive the Handover Command in response to it (e.g. an RRCReconfiguration message including a ReconfigurationWithSync) to trigger the Handover (e.g. due to some interference in the downlink (DL) and / or poor DL coverage). Due to HOF and RLF, the UE would trigger an RRC Re-establishment procedure, which leads to more signaling exchanged between the UE and the network, and higher interruption time, since there is no service continuity. This is illustrated in Fig. 1 . Fig. 1 shows two signaling diagrams which depict how a lack of mobility robustness may lead to RLFs and / or HOFs, which leads to RRC Re-establishment i.e. higher signaling and interruption time.

[0006] To improve mobility robustness, the 3rd Generation Partnership Project (3GPP) introduced in Rel-16 the feature called CHO, which may be defined as a handover that is executed by the UE when one or more handover execution conditions are met. When configured with CHO, the UE starts evaluating the execution condition(s) upon receiving the CHO configuration and stops evaluating the execution condition(s) once a handover is executed.

[0007] The following principles apply to CHO:

[0008] • The CHO configuration contains the configuration of CHO candidate cell(s) generated by the candidate gNB(s) and execution condition(s) generated by the source gNB.

[0009] • An execution condition may consist of one or two trigger condition(s) (CHO events A3 / A5). Only single Reference Signal (RS) type is supported and at most two different trigger quantities (e.g. reference signal received power (RSRP) and reference signal received quality (RSRQ), RSRP and signal to interference and noise ratio (SINR), etc.) can be configured simultaneously for the evaluation of CHO execution condition of a single candidate cell.

[0010] • Before any CHO execution condition is satisfied, upon reception of HO command (without CHO configuration), the UE executes the HO procedure as described in clause 9.2.3.2 of 3GPP Technical Specification (TS) 38.300 version 17.4.0, regardless of any previously received CHO configuration.

[0011] • While executing CHO, i.e. from the time when the UE starts synchronization with target cell, the UE does not monitor source cell.

[0012] Fig. 2 is a signalling diagram showing a signalling flow for CHO. The signals and events labelled 0 through to 8c are described below.

[0013] 0. The UE context within the source gNB contains information regarding roaming and access restrictions which were provided either at connection establishment or at the last tracking area (TA) update.

[0014] 1. The source gNB configures the UE measurement procedures and the UE reports according to the measurement configuration.

[0015] 2. The source gNB decides to use CHO e.g., based on Measurement Report(s) and Radio Resource Management (RRM) information.

[0016] 3. The source gNB requests CHO for one or more candidate cells belonging to one or more candidate gNBs. A CHO request message is sent for each candidate cell.

[0017] 4. Admission Control may be performed by the target gNB (and any other candidate gNB(s)). Slice-aware admission control shall be performed if the slice information is sent to the target gNB. If the protocol data unit (PDU) sessions are associated with non-supported slices the target gNB shall reject such PDU Sessions.

[0018] 5. The candidate gNB(s) sends CHO response (HO REQUEST ACKNOWLEDGE) including configuration of CHO candidate cell(s) to the source gNB. The CHO response message is sent for each candidate cell.

[0019] 6. The source gNB sends an RRCReconfiguration message to the UE, containing the configuration of CHO candidate cell(s) and CHO execution condition(s).

[0020] NOTE 1 : CHO configuration of candidate cells can be followed by other reconfiguration from the source gNB.

[0021] NOTE 1a: A configuration of a CHO candidate cell cannot contain a DAPS handover configuration.

[0022] 7. The UE sends an RRCReconfigurationComplete message to the source gNB.

[0023] 7a. If early data forwarding (EDF) is applied, the source gNB sends the EARLY STATUS TRANSFER message. 8. The UE maintains connection with the source gNB after receiving CHO configuration, and starts evaluating the CHO execution conditions for the candidate cell(s). If at least one CHO candidate cell satisfies the corresponding CHO execution condition, the UE detaches from the source gNB, applies the stored corresponding configuration for that selected candidate cell, synchronises to that candidate cell and completes the RRC handover procedure by sending RRCReconfigurationComplete message to the target gNB. The UE releases stored CHO configurations after successful completion of the RRC handover procedure.

[0024] 8a / b. The target gNB sends the HANDOVER SUCCESS message to the source gNB to inform that the UE has successfully accessed the target cell. In return, the source gNB sends the SN STATUS TRANSFER message following the principles described in step 7 of Intra-AMF / UPF Handover in clause 9.2.3.2.1 of 3GPP TS 38.300 version 17.4.0.

[0025] NOTE 2: Late data forwarding may be initiated as soon as the source gNB receives the HANDOVER SUCCESS message.

[0026] 8c. The source gNB sends the HANDOVER CANCEL message toward the other signalling connections or other candidate target gNBs, if any, to cancel CHO for the UE.

[0027] Artificial Intelligence (Al) / Machine Learning (ML) for PHY Study Item Rel-18

[0028] Artificial Intelligence (Al) and Machine Learning (ML) have been investigated as promising tools to optimize the design of air-interface in wireless communication networks in both academia and industry. Example use cases include using autoencoders for Channel State Information (CSI) compression to reduce the feedback overhead and improve channel prediction accuracy; using deep neural networks for classifying Line of Sight (LOS) and Non-LOS (NLOS) conditions to enhance the positioning accuracy; and using reinforcement learning for beam selection at the network side and / or the UE side to reduce the signaling overhead and beam alignment latency; using deep reinforcement learning to learn an optimal precoding policy for complex Multiple Input and Multiple Output (MIMO) precoding problems.

[0029] In 3GPP NR standardization work, a new release 18 study item on AI / ML for NR air interface has started since May 2022. This study item will explore the benefits of augmenting the airinterface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead.

[0030] AI / ML for beam management is a use case that is particularly relevant to the present disclosure. AI / ML for beam management includes predicting the channel in respect of a beam for a certain time-frequency resource. In other words, the beam management use case for AI / ML includes beam prediction in time and / or spatial domain for overhead and latency reduction, beam selection accuracy improvement. The expected performance of such predictor depends on several different aspects, for example time / frequency variation of channel due to UE mobility or changes in the environment. Due to the inherent correlation in time, frequency and the spatial domain of the channel, an ML-model can be trained to exploit such correlations. The spatial domain can comprise of different beams, where the correlation properties partly depend on the how the gNB antennas forms the different beams, and how UE forms the receiver beams.

[0031] In the latest agreements from 3GPP RAN1 , the one use case for Beam Management based on AI / ML that is of particular interest is called “Temporal Downlink beam prediction”, as described below.

[0032] • BM-Case1 : Spatial-domain Downlink beam prediction for Set A of beams based on measurement results of Set B of beams o Consider: Alt. 1): AI / ML model training and inference at NW side. Alt. 2): AI / ML model training and inference at UE side. o Consider: Alt. i): Set A and Set B are different (Set B is NOT a subset of Set A). Alt. ii): Set B is a subset of Set A. Note: Set A is for DL beam prediction and Set B is for DL beam measurement. The beam patterns of Set A and Set B can be clarified by companies. o AI / ML model input: Alt 1): Only L1-RSRP measurement based on Set B; Alt.2): L1-RSRP measurement based on Set B and assistance information; Alt. 3): CIR based on Set B; Alt. 4): L1-RSRP measurement based on Set B and the corresponding DL Tx and / or Rx beam ID.

[0033] • BM-Case2: Temporal Downlink beam prediction for Set A of beams based on the historic measurement results of Set B of beams o Consider: Alt. 1): AI / ML model training and inference at NW side. Alt. 2): AI / ML model training and inference at UE side. o Consider: Alt. i): Set A and Set B are different (Set B is NOT a subset of Set A). Alt. ii): Set B is a subset of Set A (Set A and Set B are not the same). Alt. iii): Set A and Set B are the same. o AI / ML model input: measurement results of K (K>1) latest measurement instances with the following alternatives: Alt. 1): Only L1-RSRP measurement based on Set B; Alt 2): L1-RSRP measurement based on Set B and assistance information; Alt. 3): L1-RSRP measurement based on Set B and the corresponding DL Tx and / or Rx beam ID. o [AI / ML model output]: F predictions for F future time instances, where each prediction is for each time instance. At least F=1. Set B is a set of beams whose measurements are taken as inputs of the AI / ML model. Note: Beams in Set A and Set B can be in the same Frequency Range.

[0034] For both sub-use cases, the following alternatives are studied for the predicted beams:

[0035] • Alt.1 : DL Tx beam prediction

[0036] • Alt.2: DL Rx beam prediction (deprioritized)

[0037] • Alt.3: Beam pair prediction (a beam pair consists of a DL Tx beam and a corresponding DL Rx beam)

[0038] Note: DL Rx beam prediction may or may not have spec impact.

[0039] The following alternatives for [AI / ML model output] are defined:

[0040] • Alt.1 : Tx and / or Rx Beam ID(s) and / or the predicted L1-RSRP of the N predicted DL Tx and / or Rx beams o e.g., N predicted beams can be the top-N predicted beams

[0041] • Alt.2: Tx and / or Rx Beam ID(s) of the N predicted DL Tx and / or Rx beams and other information o e.g., N predicted beams can be the top-N predicted beams

[0042] • Alt.3: Tx and / or Rx Beam angle(s) and / or the predicted L1-RSRP of the N predicted DL Tx and / or Rx beams o e.g., N predicted beams can be the top-N predicted beams

[0043] All of the outputs in the above alternatives may vary based on whether the AI / ML model inference is at UE side or gNB side. The Top-N beam IDs might have been derived via postprocessing of the ML-model output.

[0044] Fig. 3 provides a summary of the assumptions for AI / ML for Beam Management, as described above.

[0045] Al / ML for Mobility in Rel-19

[0046] The AI / ML for PHY work in Rel-18 has been limited to lower layer features, such as Beam Management, which is sometimes referred to as intra-cell mobility. Other features, such as L3 handovers, RRC measurements, L1 / L2 triggered mobility (LTM), RRC measurement reporting and Conditional Handover has not been of the Rel-18, but initial discussions for Rel-19 seemed to indicate that higher layer features, specified by RAN2, might leverage on AI / ML functions to be possibly specified. Summary

[0047] There currently exist certain challenge(s). The existing CHO procedure can result in CHO failure. The present disclosure improves the performance of Conditional Handovers (CHO) execution by reducing the number of CHO failures.

[0048] A first type of CHO failure is a failure in which a UE executes CHO to a CHO candidate cell X at an instance TO and the connection fails very shortly at cell X (e.g. a Radio Link Failure is declared shortly after the CHO execution, as shown in the signaling diagram of Fig. 4, which is followed by re-establishment), because radio conditions quickly dropped. This leads to the UE initiating a re-establishment procedure, which is more costly in terms of signaling between the UE and the network (which increases overhead over the radio interface and increases battery consumption at the UE) and breaks service continuity. In some cases, the cell in which the UE re-establishes is a cell which was a CHO candidate cell.

[0049] A second type of failure is a failure in which a UE executes CHO to a CHO candidate cell X at an instance TO (from a source cell A) and the connection drops very shortly at cell X (and / or yet another cell becomes better than cell X, possibly cell A) so that a handover is triggered by the target network node, either back to cell A or to another cell Y, or another CHO is executed, as shown in the signaling diagram of Fig. 5. This does not lead to the UE initiating a re-establishment procedure, but handovers followed by further handovers within a short period of time (often called ping-pongs) increases the chances of failures and increases the signaling between the UE and the network (which increases overhead over the radio interface and increases battery consumption at the UE). Thus, such ping-pongs should be avoided or at least reduced.

[0050] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. The techniques disclosed herein thereby improve the performance of Conditional Handovers.

[0051] The present disclosure comprises a method at a User Equipment (UE) in which the UE receives a CHO execution condition, where the CHO execution condition is to be evaluated with respect to prediction information (such as time-domain prediction information derived based on time-domain predictions of measurements). The prediction information may be related to a neighbour cell and / or a serving cell. The UE may further receive a Conditional Handover (CHO) candidate configuration of the neighbour cell (to be applied upon CHO execution). The CHO execution condition may be associated with the CHO candidate configuration.

[0052] The UE may consider the CHO execution condition fulfilled (and thus execute CHO to a neighbour cell) when the neighbour cell (configured as CHO candidate cell) becomes a first offset better than a serving cell (e.g., the Primary Cell (PCell)) AND, in addition, a prediction information (such as time-domain prediction information derived based on time-domain predictions of measurements) for a neighbour cell (and / or a serving cell) indicates that the neighbour cell configured as CHO candidate cell would remain a second offset better than the PCell, e.g., at least for a number of future time instances, or during a future time window. Fig. 6 illustrates an example of time-domain prediction information comprising RSRP for both the neighbour cell and the PCell as a function of time.

[0053] The present disclosure further comprises a method at a source network node in which the source network node transmits, to the UE, a CHO execution condition that is to be evaluated with respect to time-domain prediction information for a neighbour cell.

[0054] According to a first aspect, there is provided a method performed by a user equipment (UE) being served by a first cell. The method comprises receiving a conditional handover (CHO) execution condition. The CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell.

[0055] According to a second aspect, there is provided a method performed by a source network node. A user equipment (UE) is being served by a first cell of the source network node. The method comprises transmitting, to the UE, a conditional handover (CHO) execution condition. The CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell.

[0056] According to a third aspect, there is provided a computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform the method according to the first aspect, the second aspect, or any embodiment thereof.

[0057] According to a fourth aspect, there is provided a user equipment (UE) configured to perform the method according to the first aspect or any embodiment thereof.

[0058] According to a fifth aspect, there is provided a user equipment (UE) comprising a processor and a memory, said memory containing instructions executable by said processor whereby said UE is operative to perform the method according to the first aspect or any embodiment thereof.

[0059] According to a sixth aspect, there is provided a first radio access network (RAN) node, configured to perform the method according to the second aspect or any embodiment thereof.

[0060] According to an seventh aspect, there is provided a first radio access network (RAN) node comprising a processor and a memory, said memory containing instructions executable by said processor whereby said first RAN node is operative to perform the method according to the second aspect or any embodiment thereof.

[0061] Certain embodiments may provide one or more of the following technical advantage(s).

[0062] The present disclosure improves the mobility robustness by improving the performance of CHO executions. This is achieved by reducing the number of CHO failures.

[0063] According to the present disclosure, the CHO execution condition is based on time-domain predictions of the PCell and / or a neighbour cell configured as a CHO candidate cell. Therefore, the UE executes CHO not just when the neighbour cell is an offset better than the PCell, but when time-domain prediction(s) for the PCell and / or the neighbour cell configured as a CHO candidate indicate that the situation remains favourable for CHO, e.g., for a required time period or a required number of time instances.

[0064] The first type of CHO failure described above is reduced by the present disclosure, e.g., because a CHO handover is only executed when the time-domain prediction information indicates that a connection failure shortly after the CHO has been executed is unlikely, e.g., that the radio conditions are unlikely to drop. This reduces the likelihood of the UE needing to initiate a reestablishment procedure, which in turn reduces signaling between the UE and the network, and thus decreases overhead over the radio interface, decreases battery consumption at the UE, and improves service continuity.

[0065] The second type of CHO failure described above is also reduced by the present disclosure, e.g., because a CHO handover is only executed when the time-domain prediction information indicates that the connection is unlikely to drop shortly after the CHO to cell X, and / or the timedomain prediction information indicates that another cell is unlikely to become better than cell X, and therefore a handover is unlikely to be triggered immediately after the CHO. Thus, the present disclosure reduces the occurrence of handovers followed quickly by further handovers (ping- pongs), decreases the chances of failures, decreases the signaling between the UE and the network, decreases overhead over the radio interface, and / or decreases battery consumption at the UE.

[0066] Brief Description of the Drawings

[0067] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings, in which:

[0068] Fig. 1 shows two signalling diagrams which depict how a lack of mobility robustness may lead to higher signalling and interruption time;

[0069] Fig. 2 is a signalling diagram showing a signalling flow for conditional handover;

[0070] Fig. 3 illustrates assumptions for AI / ML for Beam Management;

[0071] Fig. 4 is a signalling diagram showing a scenario in which RLF occurs shortly after CHO execution and is followed by re-establishment;

[0072] Fig. 5 is a signalling diagram showing a scenario in which a handover or CHO occurs shortly after CHO execution;

[0073] Fig. 6 depicts time-domain prediction information according to some embodiments;

[0074] Fig. 7 is a flow chart illustrating a method in accordance with some embodiments;

[0075] Fig. 8 is a flow chart illustrating a method in accordance with some embodiments;

[0076] Fig. 9 shows an example AI / ML model;

[0077] Fig. 10 shows an example AI / ML model;

[0078] Fig. 11 shows an example of time domain cell prediction derivation;

[0079] Fig. 12 shows an example of time domain cell prediction derivation;

[0080] Fig. 13 shows an example of time domain cell prediction derivation;

[0081] Fig. 14 shows examples of Neural Networks used for designing AI / ML models for spatial beam prediction;

[0082] Fig. 15 shows an example of AI / ML model input and output fortime domain beam prediction;

[0083] Fig. 16 depicts an example CHO execution condition according to some embodiments;

[0084] Fig. 17 illustrates a CHO execution condition according to some embodiments;

[0085] Fig. 18 shows an example of a communication system in accordance with some embodiments;

[0086] Fig. 19 shows a UE in accordance with some embodiments;

[0087] Fig. 20 shows a RAN network node in accordance with some embodiments;

[0088] Fig. 21 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized.

[0089] Detailed Description

[0090] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0091] In the context of the present disclosure, the term “ML-model” or “Al-model”, “Model Inference”, “Model Inference function” or “AI / ML model” are used interchangeable. An AI / ML model can be defined, in the context of the present disclosure, as a functionality or be part of a functionality that is deployed / implemented in the UE. An AI / ML model can be defined as a feature or part of a feature that is implemented / supported in a UE. An ML-model (or Model Inference function) may correspond to a function which receives one or more inputs (e.g. measurements performed on reference signal(s) of a neighbor cell, such as Synchronization Signal Blocks (SSBs) and / or Channel State Information - Reference Signals (CSI-RSs)) and provide as outcome one or more prediction(s) / estimates / decisions of a certain type e.g. values of a measurements in the future, such as predicted RSRP values in a future time instance. It may be said that an ML model or Model Inference is a function that provides AI / ML model inference output (e.g. predictions or decisions). The Model inference function may also responsible for data preparation (e.g. data pre-processing and cleaning, formatting, and transformation) based on Inference Data delivered by a Data Collection function. The output may correspond to the inference output of the AI / ML model produced by a Model Inference function.

[0092] In the context of this present disclosure, the predictions are time-domain predictions: thus, the input of the ML-model comprises at least one or more measurements at (or starting at) a time instance to (and / or a timer interval such as T1 or tO+T 1 , which may comprise one or more samples or measurement time occasions, from 1 to K time occasions) of at least one neighbor cell, and the output of the ML-model comprises one or more predicted measurements at (or starting at) a future time instance e.g. to + T, possibly comprising future time instances within a time window of duration T2 and having F predictions. Further terminology may refer to an “actor”, as a function that receives the output from the Model inference function and triggers or performs corresponding actions. The Actor may trigger actions directed to other entities or to itself. In the context of this particular present disclosure, one actor may correspond to CSI / beam prediction reporting (or CSI prediction reporting) functionality at the UE, and / or the functionality at the UE responsible for generating the data structure to transmit the one or more information derived based on the one or more time-domain predictions. In one example, an ML-model may correspond to a function receiving as input one or more measurements of at least one DL RS at time instance to (or a time interval starting or ending at tO), after at least one measurement period, (e.g. transmitted in beam- X, SSB-x, CSI-RS resource index x) and provide as output the prediction of the RS measurement(s) in time instance tO+T (or a time interval starting or ending at tO+T, until tO+T+T2). This future time instance tO+T, obtained at tO, may be in different time units such as in number of slots (frames, sub-frames, OFDM symbols, etc.) after the UE has performed the last measurement or targeting a specific slot in time within the future.

[0093] In the context of the present disclosure, a measurement may correspond to one or more of:

[0094] • A radio measurement i.e. a measurement performed on reference signal(s) received by the UE over the radio interface

[0095] • An RRM measurement, since they assist Radio Resource Management decisions at the network side and / or Layer 3 (L3) or higher layer measurements, since these measurements would be the responsibility of the RRC protocol, also called L3 in the Control Plane Radio Access Network (RAN) protocol stack. A NR measurement and / or an Inter-RAT measurement of E-LITRA frequencies and / or 6G measurements (i.e. performed over the 6G air interface on 6G reference signal(s)) A measurement performed on one or more reference signal(s) of a reference signal type e.g. SSB or Channel State Information - Reference Signal (CSI-RS). For example: o In the case of SSBs these measurements (or in more general terms, measurement information) are:

[0096] ■ Measurement results per SSB, such as:

[0097] • SS reference signal received power (SS-RSRP) o This may be defined as the linear average over the power contributions (in [W]) of the resource elements that carry secondary synchronization signals (SS).

[0098] • SS reference signal received quality (SS-RSRQ): o This may be defined as the ratio of NxSS-RSRP I NR carrier RSSI, where N is the number of resource blocks in the NR carrier RSSI measurement bandwidth. The measurements in the numerator and denominator shall be made over the same set of resource blocks.

[0099] • SS signal-to-noise and interference ratio (SS-SINR): o This may defined as the linear average over the power contribution (in [W]) of the resource elements carrying secondary synchronisation signals divided by the linear average of the noise and interference power contribution (in [W]) over the resource elements carrying secondary synchronization signals within the same frequency bandwidth.

[0100] ■ Measurement results per cell based on SSBs, for example:

[0101] • A cell-based measurement quantity (e.g. cell based RSRP, cell based RSRQ, cell based SINR)

[0102] • A cell-based measurement quantity derived as the highest beam measurement quantity value e.g. highest Synchronization Signal RSRP (SS-RSRP) of the cell, highest SS-RSRQ of the cell, highest SS-SINR of the cell

[0103] • A cell-based measurement quantity derived as the linear power scale average of the highest beam measurement quantity values above a threshold (e.g. absThreshSS-BlocksConsolidation) where the total number of averaged beams shall not exceed an integer threshold (e.g. nrofSS-BlocksToAverage) e.g. average of SS-RSRP values of the cell.

[0104] ■ SSB indexes (derived based on SSB measurements).

[0105] • SSB indexes of one or more SSBs whose SSB based measurement quantity (e.g. SS-RSRP, SS-RSRQ, SS-SINR) is above a threshold

[0106] ■ cell identification (derived based on cell-based measurement quality) In the case of CSI-RS these measurements (or in more general terms, measurement information) are:

[0107] ■ Measurement results per CSI-RS resource, such as:

[0108] • CSI reference signal received power (CSI-RSRP): o This may be defined as the linear average over the power contributions (in [W]) of the resource elements of the antenna port(s) that carry CSI reference signals configured for RSRP measurements within the considered measurement frequency bandwidth in the configured CSI-RS occasions.

[0109] • CSI reference signal received quality (CSI-RSRQ) o This may be defined as CSI reference signal received quality (CSI-RSRQ) is defined as the ratio of NxCSI- RSRP to CSI-RSSI, where N is the number of resource blocks in the CSI-RSSI measurement bandwidth. The measurements in the numerator and denominator shall be made over the same set of resource blocks.

[0110] • CSI signal-to-noise and interference ratio (CSI-SINR) o This may defined as the linear average over the power contribution (in [W]) of the resource elements carrying CSI reference signals divided by the linear average of the noise and interference power contribution (in [W]) over the resource elements carrying CSI reference signals reference signals within the same frequency bandwidth.

[0111] ■ Measurement results per cell based on CSI-RS resource(s);

[0112] • A cell-based measurement quantity (e.g. cell based RSRP, cell based RSRQ, cell based SINR)

[0113] • A cell-based measurement quantity derived as the highest beam measurement quantity value e.g. highest CSI-RSRP of the cell, highest CSI-RSRQ of the cell, highest CSI-SINR of the cell

[0114] • A cell-based measurement quantity derived as the linear power scale average of the highest beam measurement quantity values above a threshold (e.g. absThreshSS-BlocksConsolidation) where the total number of averaged beams shall not exceed an integer threshold (e.g. nrofSS-BlocksToAverage) e.g. average of CSI-RSRP values of the cell.

[0115] ■ CSI-RS resource measurement identifiers.

[0116] • CSI-RS resource measurement identifiers of one or more CSI- RS resources whose CSI-RS based measurement quantity (e.g. CSI-RSRP, CSI-RSRQ, CSI-SINR) is above a threshold

[0117] ■ Cell identification (derived based on cell-based measurements quality) A measurement which may be associated to a measurement quantity, such as RSRP, RSRQ or SINR. For example, one may say that a “measurement” corresponds to an RSRP value, so that a measurement of a neighbor cell corresponds to an RSRP value of the neighbor cell.

[0118] A measurement of a cell (which may also be called cell quality or cell measurement result), where the measurement of a cell may be performed based on one or more beam measurements.

[0119] A measurement which is filtered according to one or more filter parameters configured by the network e.g. a L3 filtered measurement, with a time-domain filtered.

[0120] A measurement quantity, such as an RSRP and / or RSRQ and / or SINR and / or RSSI value in dB and / or dBm.

[0121] A cell-based measurement result or cell measurement, where a measurement value represents a cell quality e.g. RSRP of a cell, RSRQ of a cell

[0122] A beam-based measurement result or beam measurement, where a measurement value represents a beam quality e.g. RSRP of a beam, RSRQ of a beam, SINR of a beam. A beam-based measurement may also be a RS based measurement when the RS is transmitted on a spatial direction or beam e.g. SSB measurement may correspond to a measurement associated to an SSB index, like an SS-RSRP value; CSI-RS measurement may correspond to a measurement associated to an CSI-RS resource index / identifier, like an CSI-RSRP value. In the context of the present disclosure, the source network node (and / or the candidate network node) may correspond to one or more of:

[0123] • A Radio Access Network (RAN) node

[0124] • A gNodeB (gNB)

[0125] • A 6G RAN node

[0126] • A Centralized Unit gNodeB

[0127] • A distributed Unit gNodeB

[0128] • A Cloud-RAN centralized unit

[0129] The method includes the possibility in which the source network node and the candidate network node are different nodes, or the same. The source network node may also be referred to herein as the serving network node or the network node of the serving cell.

[0130] A neighbor cell may be characterized as a cell which is not configured at the UE as a serving cell. In the context of the present disclosure, the at least one neighbor cell to which the prediction information relates corresponds to one or more of:

[0131] • A neighbor cell which is an intra-frequency neighbor

[0132] • A neighbor cell on the same Synchronization Signal Block (SSB) frequency as the PCell

[0133] • A neighbor cell with the same subcarrier spacing as the PCell

[0134] • A neighbor cell which is an inter-frequency neighbor

[0135] • A neighbor cell on a different SSB frequency as the PCell

[0136] • A neighbor cell with a different subcarrier spacing as the PCell

[0137] • A neighbor cell on an SSB frequency indicated in a Measurement Object which the UE is configured with e.g. IE MeasObjectNR

[0138] • A neighbor cell on the same SSB frequency as the SSB frequency of a Secondary Cell (SCell) of the Master Cell Group (MCG)

[0139] • A neighbor cell with the same subcarrier spacing as the subcarrier spacing of an SCell of the MCG

[0140] • A neighbor cell on a different SSB frequency as the SSB frequency of an SCell of the MCG

[0141] • A neighbor cell with a different subcarrier spacing as the subcarrier spacing of an SCell of the MCG

[0142] • A neighbor cell which is configured at the UE, for example, upon reception of a cell identifier (e.g. physical cell identity) and a frequency information (e.g. SSB frequency in a Measurement Object). • A “best” neighbor cell on a serving frequency e.g. in terms of RSRP, RSRQ, SINR and / or in terms of predicted information. o For example, the predicted information may relate to one or more number of neighbor cell(s) with the same SSB frequency as one of the SCell(s) of the MCG and with highest RSRP values. o For example, the predicted information may relate to one or more number of neighbor cell(s) with the same SSB frequency as the PCell and with highest RSRP values. o For example, the predicted information may relate to the neighbor cell with: the same SSB frequency as each of the SCell(s) of the MCG and with the highest RSRP value.

[0143] A neighbor cell may also be called CHO candidate cell (or simply a CHO candidate or candidate) when that cell is configured as a candidate cell for CHO at the UE. The neighbour cell is also referred to herein as a second cell.

[0144] In the context of the present disclosure, the at least one serving cell for which the UE includes prediction information may correspond to one or more of:

[0145] • For a UE in RRC_CONNECTED not configured with Carrier Aggregation (CA) / Dual Connectivity (DC) there is one serving cell comprising of the primary cell (e.g. PCell). For a UE in RRC_CONNECTED configured with CA / DC the term 'serving cell' is used to denote the set of cells comprising of the Special Cell(s) and all secondary cells.

[0146] • A Primary Cell (PCell), also called the Master Cell Group (MCG) cell, operating on the primary frequency (e.g. an SSB frequency), in which the UE either performs the initial connection establishment procedure, resume procedure or initiates the connection reestablishment procedure.

[0147] • A Secondary Cell (SCell): For a UE configured with CA, a cell providing additional radio resources on top of Special Cell (SpCell). The SCell may be associated to a cell group e.g. Scell of the MCG, or SCell of the Secondary Cell Group (SCG).

[0148] • A Special Cell (SpCell): For DC operation the term Special Cell refers to the PCell of the MCG or the PSCell of the SCG, otherwise the term Special Cell refers to the PCell.

[0149] In the context of the present disclosure, the term Conditional Handover (CHO) may also be considered as a kind of Conditional Reconfiguration in which the UE receives and stores an RRCReconfiguration message associated to a CHO candidate cell. The RRCReconfiguration may include Reconfiguration with sync for the Master Cell Group (MCG). The UE may apply the stored RRCReconfiguration when the CHO execution condition for the corresponding candidate is fulfilled.

[0150] AI / ML models applied for the NR / 6G air interface use cases or NR / 6G higher-layer use cases can be categorized into three types:

[0151] 1) one-sided UE-sided AI / ML models whose inference is performed entirely at the UE-side;

[0152] 2) one-sided NW-sided AI / ML models whose inference is performed entirely at the NW side,

[0153] 3) two-sided AI / ML models, which refers to a paired AI / ML Model(s) over which joint inference is performed, where joint inference comprises AI / ML Inference whose inference is performed jointly across the UE and the network, i.e., the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa.

[0154] Here, model inference refers to a process of using a trained AI / ML model to produce a set of outputs based on a set of inputs. In the context of the present disclosure, the time-domain prediction of one or more measurements of one or more neighboring cell(s) and / or one or more serving cell(s) is achieved via one or more AI / ML model(s), whose inference is performed entirely at the UE. Hence, these models can be referred to as UE-sided AI / ML models.

[0155] Fig. 7 depicts a method in accordance with particular embodiments. The method may be performed by a User Equipment (UE) or wireless device (e.g. the UE 1812 or UE 2000 as described later with reference to Figs. 18 and 20 respectively). The UE is being served by a first cell. The method begins at step 702 with receiving a conditional handover (CHO) execution condition. The CHO execution condition may be referred to as a CHO execution condition for CHO to a second cell. The CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell. The prediction sub-condition is also referred to herein as a second sub-condition. The CHO execution condition may further comprise a measurement sub-condition, also referred to herein as a first sub-condition. The CHO execution condition may comprise one or more combinations of the prediction sub-condition and the measurement sub-condition, and these combinations may be referred to as first or second conditions.

[0156] The time-domain prediction information is also referred to herein as prediction information. Time-domain prediction information for a second cell may refer to any time-domain prediction information that is relevant for evaluating the CHO execution condition for the second cell. As such, the time-domain prediction information for the second cell may be based on, or comprise, at least one time-domain prediction of a measurement of the first cell and / or at least one timedomain prediction of a measurement of the second cell. Further detail about the time-domain prediction information is set out below under the headings: “Prediction information”, “Further details about the prediction information”, and “Further details about the prediction information corresponding to an RLF prediction”.

[0157] The first cell may also be referred to herein as a serving cell or the PCell. The second cell may also be referred to herein as a neighbour cell or a CHO candidate cell.

[0158] In some embodiments, the method in Fig. 7 can further comprise the UE evaluating the CHO execution condition for the second cell.

[0159] The method in Fig. 7 can further comprise the UE determining to execute a CHO from the first cell to the second cell responsive to determining that the CHO execution condition is satisfied by the second cell. On the other hand, the method in Fig. 7 can further comprise the UE determining to maintain connection with the first cell responsive to determining that the CHO execution condition is not satisfied by the second cell.

[0160] The CHO execution condition may further comprise a measurement sub-condition that is to be evaluated with respect to at least one measurement of the first cell and / or at least one measurement of the second cell. In this case, the CHO execution condition may be satisfied if both the measurement sub-condition is satisfied and the prediction sub-condition is satisfied. Alternatively, the CHO execution condition can be satisfied if either the measurement subcondition is satisfied or the prediction sub-condition is satisfied. In another alternative, the CHO execution condition can be satisfied if both the measurement sub-condition is satisfied and the prediction sub-condition is satisfied; or both the measurement sub-condition is satisfied and a likelihood of detecting Radio Link Failure (RLF) in the first cell is high. In this embodiment, the likelihood of detecting RLF in the first cell can be considered high if the measurement subcondition is satisfied while an RLF timer is running.

[0161] In some embodiments, the measurement sub-condition can be satisfied if the at least one measurement of the second cell is a first offset better than the at least one measurement of the first cell. The measurement sub-condition can be satisfied if the at least one measurement of the second cell is a first offset better than the at least one measurement of the first cell for at least a time to trigger (TTT) time period.

[0162] The at least one measurement of the first cell may comprise one or more of: a signal strength value; a quality value; a cell identifier; a RSRP; a RSRQ; a SINR; a beam index; a beam identifier; and a SSB index.

[0163] The at least one measurement of the second cell may comprise one or more of: a signal strength value; a quality value; a cell identifier; a RSRP; a RSRQ; a SINR; a beam index; a beam identifier; and a SSB index.

[0164] In some embodiments, the prediction sub-condition may be satisfied if the time-domain prediction information for the second cell indicates that a measurement quantity of the second cell will be a second offset better than the measurement quantity of the first cell during at least a first future time window or for at least a first number of future time instances.

[0165] In some embodiments, the prediction sub-condition may be satisfied if the time-domain prediction information for the second cell indicates that a measurement quantity of the second cell will be above a threshold during at least a second future time window or for at least a second number of future time instances.

[0166] In some embodiments, the prediction sub-condition is satisfied if a likelihood of detecting RLF in the second cell is low. The likelihood of detecting RLF in the second cell may be considered low if the measurement sub-condition is not satisfied while an RLF timer is running.

[0167] In some embodiments, the time-domain prediction information for the second cell can be based on, or comprises, at least one time-domain prediction of a measurement of the first cell and / or at least one time-domain prediction of a measurement of the second cell.

[0168] The time-domain prediction information for the second cell may comprise one or more of: a predicted signal strength or quality value for the second cell at a future time instance or during a future time window; a predicted cell identifier for the second cell at a future time instance or during a future time window; a cell identifier based on a predicted signal strength or quality value for the second cell at a future time instance or during a future time window; a predicted RSRP of the second cell at a future time instance or during a future time window; a predicted RSRQ of the second cell at a future time instance or during a future time window; a predicted SI NR of the second cell at a future time instance or during a future time window; a predicted beam index and / or beam identifier of the second cell at a future time instance or during a future time window; a predicted SSB index of the second cell at a future time instance or during a future time window; a corresponding confidence indicator of a predicted measurement for the second cell; a corresponding time duration for which a predicted measurement for the second cell is expected to be valid; and a corresponding time duration for which a predicted measurement for the second cell is expected to satisfy a condition.

[0169] The time-domain prediction information for the second cell may be based on a prediction for fulfilment of an event trigger for the second cell. The event trigger comprises an event or condition that triggers transmission by the UE of measurements of the second cell, and / or an event or condition that triggers conditional handover of the UE to the second cell. The timedomain prediction information for the second cell may comprise one or more of: a flag indicating that the event trigger is predicted to remain fulfilled; an indication of a period of time for which the event trigger is predicted to remain fulfilled; and a cell identifier of the second cell as the cell which triggered the event.

[0170] In some embodiments, the time-domain prediction information for the second cell is based on a difference between a prediction of a measurement of the second cell and a prediction of a measurement of the first cell.

[0171] In some embodiments, the time-domain prediction information forthe second cell comprises one or more of: a difference between a predicted signal strength or quality value for the second cell at a future time instance and a predicted signal strength or quality value for the first cell at the future time instance; a cell identifier based on a difference between a predicted signal strength or quality value for the second cell at a future time instance and a predicted signal strength or quality value for the first cell at the future time instance; a predicted measurement quantity difference between the measurement quantity of the second cell and the measurement quantity of the first cell at a future time instance; a cell identifier based on a predicted measurement quantity difference between the measurement quantity of the second cell and the measurement quantity of the first cell at a future time instance; a corresponding confidence indicator for the predicted difference; a corresponding confidence indicator for the cell identifier; a corresponding time duration for which the predicted difference is expected to be valid; a corresponding time duration for which the cell identifier is expected to be valid; and a corresponding time duration for which the predicted difference is expected to satisfy a condition.

[0172] In embodiments where the time-domain prediction information for the second cell is based on, or comprises, at least one time-domain prediction of a measurement of the first cell, or where the time-domain prediction information for the second cell is based on a difference between a prediction of a measurement of the second cell and a prediction of a measurement of the first cell, the prediction of a measurement of the first cell comprises one or more of: a predicted signal strength or quality value for the first cell at a future time instance or during a future time window; a predicted cell identifier for the first cell at a future time instance or during a future time window; a cell identifier for the first cell based on a predicted signal strength or quality value for the first cell at a future time instance or during a future time window; a predicted RSRP of the first cell at a future time instance or during a future time window; a predicted RSRQ of the first cell at a future time instance or during a future time window; a predicted SI NR of the first cell at a future time instance or during a future time window; a predicted beam index and / or beam identifier of the first cell at a future time instance or during a future time window; a predicted SSB index of the first cell at a future time instance or during a future time window; a corresponding confidence indicator of a predicted value for the first cell; a corresponding time duration for which a predicted value for the first cell is expected to be valid; and a corresponding time duration for which a predicted value for the first cell is expected to satisfy a condition.

[0173] In some embodiments, the method further comprises determining the time-domain prediction information for the second cell. The time-domain prediction information for the second cell can be determined using a machine learning model. In these embodiments, determining the time-domain prediction information for the second cell can comprise inputting one or more measurements of the second cell and / or one or more measurements of the first cell into the machine learning model.

[0174] In some embodiments, the second cell is configured as a candidate CHO cell for the UE.

[0175] The second cell may be one or more of: an intra-frequency neighbour cell; an interfrequency neighbour cell; a neighbour cell on the same SSB frequency as the first cell; a neighbour cell on a different SSB frequency to the first cell; a neighbour cell on a serving frequency; a neighbour cell on a serving frequency selected based on at least one measurement of the second cell; a neighbour cell on a serving frequency selected based on the time-domain prediction information for the second cell; a cell of the same network node as the first cell; and a cell of a different network node to the first cell.

[0176] The CHO execution condition may be a trigger condition upon fulfilment of which the UE determines to execute a CHO handover.

[0177] The first cell may be a cell of a source network node. The CHO execution condition may be received from the source network node.

[0178] The method may further comprise executing the CHO to the second cell if the CHO execution condition is satisfied by the second cell.

[0179] The method may further comprise maintaining connection with the first cell if the CHO execution condition is not satisfied by the second cell.

[0180] Complementary methods performed by a source network node are described with respect to Fig. 8. Further detail regarding the method in Fig. 7 and other methods performed by the UE is set out below under the headings: “Embodiments in a UE”, “Detailed Embodiments in a UE”, “CHO execution step”, “Further Details about the CHO configuration(s)”, “Further Details about the definition of CHO execution conditions to be evaluated with respect to prediction information”, and “Al / ML model for RLF prediction”.

[0181] The UE may perform the method in Fig. 7 in response to executing suitably formulated computer readable code. The computer readable code may be embodied or stored on a computer readable medium, such as a memory chip, optical disc, or other storage medium. The computer readable medium may be part of a computer program product.

[0182] Fig. 8 depicts a method in accordance with particular embodiments. The method in Fig. 8 is performed by a source network node. A user equipment is being served by a first cell of the source network node. The source network node may be a RAN network node (e.g. the RAN network node 1810 or RAN network node 2000 as described later with reference to Fig. 18 and 20 respectively). The source network node may also be referred to herein as a serving network node. The method begins at step 802 with transmitting, to the UE, a CHO execution condition. The CHO execution condition may be referred to as a CHO execution condition for CHO to a second cell. The CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell.

[0183] The time-domain prediction information is also referred to herein as prediction information. Time-domain prediction information for a second cell may refer to any time-domain prediction information that is relevant for evaluating the CHO execution condition for the second cell. As such, the time-domain prediction information for the second cell may be based on, or comprise, at least one time-domain prediction of a measurement of the first cell and / or at least one timedomain prediction of a measurement of the second cell. Further detail about the time-domain prediction information is set out below under the headings: “Prediction information”, “Further details about the prediction information”, and “Further details about the prediction information corresponding to an RLF prediction”.

[0184] The first cell may also be referred to herein as a serving cell or the PCell. The second cell may also be referred to herein as a neighbour cell or a CHO candidate cell.

[0185] Complementary methods performed by a UE are described with respect to Fig. 7. Further detail regarding the method in Fig. 8 and other methods performed by the source network node is set out below under the headings: “Further Details about the CHO configuration(s)”, “Further Details about the definition of CHO execution conditions to be evaluated with respect to prediction information”, and “Al / ML model for RLF prediction”.

[0186] The source network node may perform the method in response to executing suitably formulated computer readable code. The computer readable code may be embodied or stored on a computer readable medium, such as a memory chip, optical disc, or other storage medium. The computer readable medium may be part of a computer program product.

[0187] Embodiments in a UE

[0188] The present disclosure comprises a method at a User Equipment (UE) for CHO execution, comprising one or both of: o Receiving a CHO execution condition (and optionally a CHO candidate configuration) for a neighbour cell configured as a CHO candidate cell. The CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to at least one prediction information for the neighbour cell configured as CHO candidate cell. The prediction subcondition is also referred to herein as a second sub-condition. o Evaluating the CHO execution condition for the at least one neighbour cell configured as CHO candidate cell. The CHO execution condition (e.g., the prediction sub-condition) may relate to time-domain prediction information for a neighbour cell. The CHO execution condition (e.g., the prediction sub-condition) may comprise a criterion for time-domain prediction information for a neighbour cell. The CHO execution condition (e.g., the prediction sub-condition) may indicate a requirement for time-domain prediction information for a neighbour cell.

[0189] Time-domain prediction information for a neighbour cell is a general term for time-domain prediction information that is relevant for evaluating the CHO execution condition for CHO to the neighbour cell. ‘Prediction information’ and ‘time-domain prediction information for a neighbour / second cell’ are used interchangeable through the present disclosure.

[0190] The time-domain prediction information for a neighbour cell may comprise or relate to, for example, a first prediction information for the neighbour cell (also referred to herein as the second cell) and / or a second prediction information for a serving cell (also referred to herein as the first cell or PCell).

[0191] The first prediction information for the (at least one) neighbour cell may comprise or be based on at least one time-domain prediction of a measurement of the at least one neighbour cell. The first prediction information may correspond to one or more of:

[0192] • a predicted RSRP value of the neighbour cell at a future time instance “f”. The predicted RSRP value may be an absolute value or a relative value (e.g., with respect to a reference RSRP value, a measurement value of the neighbor cell, etc.),

[0193] • a confidence level / indicator for the predicted RSRP value,

[0194] • a time duration under which the predicted RSRP / cell-identifier is expected to be valid,

[0195] • Radio Link Failure (RLF) prediction for the neighbour cell.

[0196] The second prediction information for the serving cell may comprise or be based on at least one time-domain prediction of a measurement of the at least a serving cell. The second prediction information may correspond to one or more of:

[0197] • a predicted RSRP value of the serving cell at a future time instance “f”, where the predicted RSRP value can be an absolute value or a relative value (e.g., with respect to a reference RSRP value, a measurement value of the neighbor cell, etc.).

[0198] • a confidence level / indicator for the predicted RSRP value,

[0199] • a time duration under which the predicted RSRP / cell-identifier is expected to be valid

[0200] • RLF prediction for the serving cell e.g. PCell

[0201] The prediction information for the at least one neighbour cell may be based on at least one time-domain prediction of a measurement of the at least one neighbour cell AND at least one time-domain prediction of a measurement of the at least a serving cell. The first prediction information may correspond to one or more of:

[0202] • a difference between “a predicted RSRP value of the neighbour cell at a future time instance “f’ minus a predicted RSRP value of the serving cell at the future time instance

[0203] • a confidence level(s) / indicator(s) for the derived RSRP difference.

[0204] • a time duration under which the derived RSRP difference is expected to be valid.

[0205] The prediction information for the at least one neighbour cell in relation to the at least a serving cell may be based on at least one time-domain prediction of a measurement value difference between a measurement of the at least one neighbour cell and a measurement of at least a serving cell. The first prediction information may correspond to:

[0206] • a predicted measurement quantity difference (e.g., RSRP difference) between the measurement quantity of the neighbor cell and the measurement quantity of the serving cell at a future time instance “f”.

[0207] • a confidence level(s) / indicator(s) for the predicted measurement quantity difference.

[0208] • a time duration under which the predicted measurement quantity difference is expected to be valid.

[0209] The first prediction information or / and the second prediction information may include multiple measurement quantity predictions. The measurement quantity predictions may correspond to one or more of:

[0210] • Time-domain predictions of L3 filtered SSB / CSI-RS beam level measurement quantities or / and cell-level measurement quantities of the neighbor cell at a future time instance “f’.

[0211] • Time-domain predictions of L3 filtered SSB / CSI-RS beam level measurement quantities or / and cell-level measurement quantities of the serving cell at a future time instance “f”.

[0212] • Time-domain predictions of L3 filtered SSB / CSI-RS beam level measurement quantity or / and a cell-level measurement quantity of the neighbor cell at one or more multiple future time instance “f1 , f2, ...”.

[0213] • Time-domain predictions of L3 filtered SSB / CSI-RS beam level measurement quantity or / and a cell-level measurement quantity of the serving cell at one or more multiple future time instance “f1 , f2, ...”.

[0214] • any combination of the above bullet points.

[0215] The CHO execution condition may further comprise a measurement sub-condition that is to be evaluated with respect to one or more measurement(s) of the at least one neighbour cell and / or one or more measurements of the at least one serving cell. The measurement sub-condition is also referred to herein as the first sub-condition. In some embodiments, the CHO execution condition may be based on measurements of the PCell and / or a prediction of the PCell and / or measurements of the neighbour cell configured as CHO candidate and / or the predictions of the neighbour cell configured as CHO candidate.

[0216] The CHO execution condition may correspond to a first condition type (AND condition). The first condition type may comprise a first sub-condition and a second sub-condition. The first condition may be considered fulfilled when both the first sub-condition is considered fulfilled AND the second sub-condition is considered fulfilled.

[0217] A3-like for measurement and A3-like for predictions

[0218] The CHO execution condition may be considered fulfilled upon fulfillment of a first condition as follows:

[0219] (first sub-condition / measurement sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a first duration defined by a time to trigger (e.g. Time To Trigger (TTT), configured at the UE) AND

[0220] (second sub-condition / prediction sub-condition) the prediction of a neighbour cell measurement quantity (e.g. predicted RSRP) is a second offset better than the measurement quantity of the prediction of the PCell measurement quantity (e.g. predicted RSRP), for a number of future time instances (e.g. F, configured at the UE) or for a second duration defined by a prediction time horizon (e.g., T2, configured at the UE).

[0221] (A3-like for measurement and A3-like for predictions) OR (A3-like for measurement and high RLF likelihood for the PCell)

[0222] The UE may consider the second sub-condition part of the first condition or not, based on a high likelihood of detecting a Radio Link Failure (RLF) in source PCell.

[0223] The UE may be configured with a CHO execution condition comprising the first condition (at least as described above) and a second condition, both associated by a logical operator “OR”. The UE may consider the CHO execution condition fulfilled when either the first condition is fulfilled OR the second condition is fulfilled. The second condition may be characterized as follows:

[0224] (first sub-condition of the second condition, the same as first sub-condition of the first condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a duration defined by a time to trigger (e.g. TTT, configured at the UE) AND (second sub-condition of second condition) likelihood of detecting RLF in source PCell is HIGH e.g., first sub-condition of the second condition is fulfilled while RLF timer is running.

[0225] The resulting CHO execution condition, including first and second conditions associated with logical operator “OR”, may be characterized as follows:

[0226] [ (first sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a first duration defined by a time to trigger (e.g. TTT, configured at the UE) AND (second sub-condition) the prediction of a neighbour cell measurement quantity (e.g. predicted RSRP) is a second offset better than the measurement quantity of the prediction of the PCell measurement quantity (e.g. predicted RSRP), for a number of future time instances (e.g. F, configured at the UE) or for a second duration defined by a prediction time horizon (e.g., T2, configured at the UE).] OR

[0227] [(first sub-condition of the second condition, the same as first sub-condition of the first condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a first duration defined by a time to trigger (e.g. TTT, configured at the UE) AND (second sub-condition of second condition) likelihood of detecting RLF in source PCell is HIGH e.g. first sub-condition of the second condition is fulfilled while RLF timer is running]

[0228] A3-like for measurement and low RLF likelihood for the neighbour cell

[0229] The CHO execution condition may be considered fulfilled upon fulfillment of a condition as follows:

[0230] (first sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a first duration defined by a time to trigger (e.g. TTT, configured at the UE) AND

[0231] (second sub-condition) the prediction of a neighbour cell measurement quantity (e.g. predicted RSRP) is above a threshold for a measurement quantity for a number of future time instances (e.g. F, configured at the UE) or for a second duration defined by a prediction time horizon (e.g., T2, configured at the UE).

[0232] The CHO execution condition may be considered fulfilled upon fulfillment of a condition as follows:

[0233] (first sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a duration defined by a time to trigger (e.g. TTT, configured at the UE) AND

[0234] (second sub-condition) the low RLF prediction of a neighbour cell

[0235] The CHO execution condition may be considered fulfilled upon fulfillment of an OR condition, in which both are configured but the UE considers the condition fulfilled when at least one is fulfilled, as follows:

[0236] (first sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a duration defined by a time to trigger (e.g. TTT, configured at the UE) OR

[0237] (second sub-condition) the low RLF prediction of a neighbour cell.

[0238] Detailed Embodiments in a UE

[0239] The present disclosure comprises a method at a User Equipment (UE) for CHO execution, comprising one or both of:

[0240] Receiving a CHO configuration including a CHO execution condition and a CHO candidate configuration for a neighbour cell configured as CHO candidate cell. The CHO execution condition may be based on at least a first prediction information of the neighbour cell configured as CHO candidate cell,

[0241] Evaluating the CHO execution condition associated to the at least one neighbour cell configured as CHO candidate cell.

[0242] The CHO execution condition may be based on a second prediction information for at least a serving cell.

[0243] The first prediction information for the at least one neighbour cell may be based on at least one time-domain prediction of a measurement of the at least one neighbour cell. The first prediction information may correspond to one or more of:

[0244] • a predicted RSRP value of the neighbour cell at a future time instance “f”. The predicted RSRP value may be an absolute value or a relative value (e.g., with respect to a reference RSRP value, a measurement value of the neighbor cell, etc.).

[0245] • a confidence level / indicator for the predicted RSRP value,

[0246] • a time duration under which the predicted RSRP / cell-identifier is expected to be valid,

[0247] • RLF prediction for the neighbour cell.

[0248] The second prediction information for the at least a serving cell may be based on at least one time-domain prediction of a measurement of the at least a serving cell. The second prediction information may correspond to one or more of: • a predicted RSRP value of the serving cell at a future time instance “f”, where the predicted RSRP value can be an absolute value or a relative value (e.g., with respect to a reference RSRP value, a measurement value of the neighbor cell, etc.),

[0249] • a confidence level / indicator for the predicted RSRP value,

[0250] • a time duration under which the predicted RSRP / cell-identifier is expected to be valid,

[0251] • RLF prediction for the serving cell.

[0252] The first prediction information for the at least one neighbour cell may be based on at least one time-domain prediction of a measurement of the at least one neighbour cell AND at least one time-domain prediction of a measurement of the at least a serving cell. The first prediction information may correspond to one or more of:

[0253] • a difference between “a predicted RSRP value of the neighbour cell at a future time instance “f”” minus a predicted RSRP value of the serving cell at the future time instance “f”.

[0254] • a confidence level(s) / indicator(s) for the derived RSRP difference.

[0255] • a time duration under which the derived RSRP difference is expected to be valid.

[0256] The first prediction information for the at least one neighbour cell in relation to the at least a serving cell may be based on at least one time-domain prediction of a measurement value difference between a measurement of the at least one neighbour cell and a measurement of at least a serving cell. The first prediction information may correspond to one or more of:

[0257] • a predicted measurement quantity difference (e.g., RSRP difference) between the measurement quantity of the neighbor cell and the measurement quantity of the serving cell at a future time instance “f”,

[0258] • a confidence level(s) / indicator(s) for the predicted measurement quantity difference,

[0259] • a time duration under which the predicted measurement quantity difference is expected to be valid.

[0260] The first prediction information or / and the second prediction information may include multiple measurement quantity predictions. The measurement quantity predictions may correspond to one or more of:

[0261] • Time-domain predictions of L3 filtered SSB / CSI-RS beam level measurement quantities or / and cell-level measurement quantities of the neighbor cell at a future time instance “f”,

[0262] • Time-domain predictions of L3 filtered SSB / CSI-RS beam level measurement quantities or / and cell-level measurement quantities of the serving cell at a future time instance “f”,

[0263] • Time-domain predictions of L3 filtered SSB / CSI-RS beam level measurement quantity or / and a cell-level measurement quantity of the neighbor cell at one or more multiple future time instance “f1 , f2, ...”, • Time-domain predictions of L3 filtered SSB / CSI-RS beam level measurement quantity or / and a cell-level measurement quantity of the serving cell at one or more multiple future time instance “f1 , f2, ...”,

[0264] • any combination of the above bullet points.

[0265] The CHO execution condition may be further based on one or more measurement(s) of the at least one neighbour cell and / or one or more measurements of the at least one serving cell.

[0266] In some embodiments, the CHO execution condition may be based on measurements of the PCell and / or prediction of the PCell and / or measurements of the neighbour cell configured as CHO candidate and / or the predictions of the neighbour cell configured as CHO candidate.

[0267] The CHO execution condition may correspond to a first condition type (AND condition). The first condition type may comprise a first sub-condition and a second sub-condition. The first condition may be considered fulfilled when both the first sub-condition is considered fulfilled AND the second sub-condition is considered fulfilled.

[0268] According to the present disclosure, the UE may receive a CHO execution condition. One or more of the following may apply:

[0269] • The CHO execution condition is comprised in a CHO configuration.

[0270] • The UE receives the CHO configuration in a first RRC Reconfiguration message (e.g. RRCReconfiguration) and, in response to it, the UE transmits an RRC Reconfiguration Complete message (e.g. RRCReconfigurationComplete).

[0271] • The CHO configuration comprises the configuration of one or more CHO candidate cell(s) generated by the candidate network node(s) e.g. candidate gNB(s)

[0272] • The CHO configuration comprises CHO execution condition(s) generated by the source network node e.g. source gNB.

[0273] • The CHO execution condition (or simply execution condition) may comprise one or two trigger condition(s) each configured as a Measurement ID associated to a reporting / trigger configuration (i.e. CHO events A3 / A5, as defined in 3GPP TS 38.331 version 17.4.0).

[0274] • The UE executes CHO, e.g., the UE applies a stored RRCReconfiguration message and starts synchronization with a candidate cell which fulfills the CHO execution condition, and transmits an RRCReconfigurationComplete.

[0275] Prediction information Throughout the present disclosure, the terms ‘prediction information’ and ‘time-domain prediction information’ are used interchangeably. ‘Time-domain’ may indicate that the prediction information is a prediction for one or more future time instance(s) and / or a future time period.

[0276] The prediction information for the at least one neighbour cell (sometimes referred to herein as the first prediction information) may be based on at least one time-domain prediction of a measurement of the at least one neighbour cell. The prediction information may correspond to or comprise one or more of:

[0277] • At least one predicted measurement quantity (e.g. predicted RSRP value, predicted RSRQ value, predicted SI NR value) of the neighbour cell at a future time instance “f”.

[0278] • At least a confidence level / indicator for the predicted measurement quantity.

[0279] • At least a time duration under which the predicted measurement quantity is expected to be valid.

[0280] • At least a likelihood of detecting a RLF in the neighbour cell.

[0281] • Further details about the prediction information are provided under the heading “Further Details about the prediction information”.

[0282] The second prediction information for the at least a serving cell may be based on at least one time-domain prediction of a measurement of the at least a serving cell. The prediction information may correspond to or comprise one or more of:

[0283] • At least one predicted measurement quantity (e.g. predicted RSRP value, predicted RSRQ value, predicted SINR value) of the serving cell (e.g. PCell) at a future time instance “f”.

[0284] • At least a confidence level / indicator for the predicted measurement quantity.

[0285] • At least a time duration under which the predicted measurement quantity is expected to be valid.

[0286] • At least a likelihood of detecting a RLF in the serving cell.

[0287] • Further details about the prediction information are provided under the heading “Further Details about the prediction information”.

[0288] In some embodiments, the UE may derive the prediction information.

[0289] The UE may derive prediction information for the at least one neighbour cell. For example, based on at least one AI / ML model which receives as input one or more measurements of the at least one neighbour cell and provides one or more output(s) based on which the prediction information is derived.

[0290] The UE may derive a second prediction information for the at least one serving cell. For example, based on at least one AI / ML model which receives as input one or more measurements of the at least one serving cell and provides one or more output(s) based on which the prediction information is derived.

[0291] CHO execution steps

[0292] The method may further comprise the UE applying the stored CHO candidate configuration for the at least one neighbour cell and / or accessing the at least one neighbour cell when the CHO execution condition is fulfilled.

[0293] Accessing the at least one neighbour cell when the CHO execution condition is fulfilled may comprise the UE transmitting a random access preamble to the neighbour cell, receiving a Random Access Response from the neighbour cell and transmitting an RRC Reconfiguration Complete message to the neighbour cell.

[0294] The UE may transmit a complete message (e.g. RRC Reconfiguration Complete) to the source network node in response to receiving a CHO configuration including a CHO execution condition and a CHO candidate configuration for the at least one neighbour cell. the UE may receive the CHO configuration including a CHO execution condition and a CHO candidate configuration for the at least one neighbour cell which further comprises a Contention- Free Random Access (CFRA) resource configuration. The CFRA resource configuration may be associated to at least one beam of the neighbour cell (e.g. SSB index, CSI-RS identifier) mapped to the CFRA resource (SSB index=X, mapped to the CFRA resource with preamble index Y, Time / Frequency Physical Random Access Channel (PRACH) resource Z). The prediction information may be for the at least one beam of the neighbour cell e.g. predicted RSRP values of that beam indicating that close a CHO execution the beam would have a predicted RSRP value above a threshold (thus it would be a good beam for CFRA configuration).

[0295] The CHO configuration including a CHO execution condition and a CHO candidate configuration for the at least one neighbour cell may further comprise an indication that the cell is configured for a fast recovery procedure (e.g. attemptCondReconfig set to ‘true’) in which upon a failure detection (e.g. Radio Link Failure, Handover Failure, CHO Failure) the UE initiates reestablishment, selects the neighbour cell and performs CHO execution (i.e. the UE applies the stored CHO candidate configuration of the at least one neighbour cell).

[0296] Further details about the prediction information

[0297] The UE may evaluate a CHO execution condition based on a first prediction information for at least one neighbour cell and / or a second prediction information for at least a serving cell (in general terms: prediction information for a neighbour cell). The first prediction information for the at least one neighbour cell and / or the second prediction information for at least a serving cell may correspond to one or more of:

[0298] • A Spatial-domain Downlink (DL) beam prediction for a Set A of beams o In some embodiments, the Spatial-domain Downlink (DL) beam prediction for a Set A of beams based on measurement results of Set B of beams o In some embodiments, both the Set A of beams and the Set B of beams are of the same neighbor cell. For example, the Set A of beams are DL beams transmitting SSBs of the neighbor cell, i.e., each SSB of the Set A comprises a physical Cell identity (PCI) of the neighbor cell and is transmitted in the SSB frequency of the neighbor cell. Or, in other words, the UE assumes that different SSBs of the same cell are transmitted in different beams, meaning they are transmitted in different spatial direction. o ln some embodiments, the Spatial-domain DL beam prediction comprises a prediction of a measurement quantity of a reference signal, such as an SSB or CSI-RS. For example, assuming beams transmitting SSBs, and assuming that Set A corresponds to [SSB(1), SSB(2), SSB (3), SSB (4)] and that Set B corresponds to [SSB(5), SSB(6), SSB (7), SSB (8)] the prediction information the UE derives may correspond to SS-RSRP for SSB (1), to SS-RSRP for SSB (2), to SS-RSRP for SSB (3), to SS-RSRP for SSB (4), based on the SS-RSRP for SSB (5), to SS- RSRP for SSB (6), to SS-RSRP for SSB (7), to SS-RSRP for SSB (8). o ln some embodiments, the Spatial-domain DL beam prediction comprises a beam identifier (e.g. SSB index, CSI-RS resource identity, beam ID) derived based on a prediction of a measurement quantity of a reference signal in which the beam is transmitted. For example, the UE predicts an RSRP of a beam in Set A whose beam ID = X1 and includes the beam ID=X1 in the prediction information e.g. when the predicted RSRP of that beam is above a threshold. o In some embodiments, Set A and Set B are different i.e. Set B is not a subset of Set A. For instance, Set B consists of SSB beams whereas Set A consists of CSI-RS beams. o In some embodiments, Set B is a subset of Set A. o In some embodiments, to derive one or more Spatial DL beam prediction(s) as an output of an AI / ML model, the AI / ML model receives as input one or more of:

[0299] ■ At least a L1-RSRP measurement based on Set B; ■ At least a L1-RSRP measurement based on Set B and assistance information e.g. beam pattern information and / or a configuration information related to one or more network transmission(s)

[0300] ■ At least a Cl R based on Set B;

[0301] ■ At least one L1-RSRP measurement based on Set B and the corresponding DL Tx and / or Rx beam ID. In some embodiments, the one or more Spatial DL beam prediction(s) are one or more outputs of an AI / ML model In some embodiments, a Spatial DL beam prediction corresponds to one or more of:

[0302] ■ Tx and / or Rx Beam ID(s) and / or

[0303] • For example, that may correspond to one or more Reference signal (RS) identifiers transmitted in a spatial direction or beam, such as an SSB Index (or SSB identifier) or a CSI-RS resource identity, and possibly derived based on prediction of measurements on the corresponding RS e.g. SSB ID=X corresponds to a predicted information when the predicted value of SS-RSRP of SSB ID=X is above a threshold.

[0304] ■ The predicted L1-RSRP of the N predicted DL Tx and / or Rx beam(s) e.g. top N predicted beams

[0305] • For example, that may correspond to N predicted RSRP values (Layer 1 RSRP) or other measurement quantities per beam and / or per RS transmitted on a spatial direction or beam, such as SS- RSRP, SS-RSRQ, SS-SINR, CSI-RSRP, CSI-RSRQ, CSI-SINR.

[0306] ■ Tx and / or Rx Beam angle(s) and / or the predicted L1-RSRP of the N predicted DL Tx and / or Rx beams

[0307] Fig. 9 is an example of the AI / ML model using the RSRP measurements from beams in Set B (beams denoted by shaded circles) as input predicts the best beam in set A (beams denoted by white circles). The output of the AI / ML model could be predicted beam IDs with / without predicted RSRP values.

[0308] Fig. 10 is an example of the AI / ML model using the RSRP measurements from beams in Set B (beams denoted by shaded circles) as input predicts the Top-K beams in set A (beams denoted by white circles). The output of the AI / ML model could be predicted beam IDs with / without predicted RSRP values. • A Spatial-domain cell prediction for a cell X o The spatial-domain cell prediction for a cell X may correspond to the value of a measurement quantity (e.g. an RSRP value, an RSRQ value, an SINR value) representing the measurement quantity of cell X (or a cell quality or cell measurement result). The spatial-domain cell prediction for cell X can be calculated based on one or more spatial-domain DL beam prediction(s) of a Set A of beams of cell X e.g. predicted RSRP values for each beam in the Set A of beams.

[0309] ■ In some embodiments, the beam prediction(s) for a Set A of beams of cell X is calculated based on measurements of a Set B of beams of cell X. For example, assuming beams transmitting SSBs, and assuming that Set A corresponds to [SSB(1), SSB(2), SSB (3), SSB (4)] and that Set B corresponds to [SSB(5), SSB(6), SSB (7), SSB (8)] the UE derives as prediction information the values of SS-RSRP for SSB (1), SS-RSRP for SSB (2), SS-RSRP for SSB (3), SS-RSRP for SSB (4), based on the SS- RSRP for SSB (5), SS-RSRP for SSB (6), SS-RSRP for SSB (7), SS-RSRP for SSB (8). Then, the UE uses the obtained predictions of SS-RSRP for SSB (1), SS-RSRP for SSB (2), to SS-RSRP for SSB (3), to SS-RSRP for SSB (4) to calculate the prediction of cell X e.g. highest SS-RSRP value out of SS-RSRP for SSB (1), SS-RSRP for SSB (2), SS-RSRP for SSB (3), to SS-RSRP for SSB (4).

[0310] ■ In some embodiments, the beam prediction(s) for a Set A of beams of cell X is calculated based on measurements of a Set B of beams of cell Y. For example, assuming beams transmitting SSBs, and assuming that Set A corresponds to [SSB(1), SSB(2), SSB (3), SSB (4)] of cell X and that Set B corresponds to [SSB(5), SSB(6), SSB (7), SSB (8)] of cell Y the UE derives as prediction information the values of SS-RSRP for SSB (1), SS-RSRP for SSB (2), SS-RSRP for SSB (3), SS-RSRP for SSB (4) of Cell X, based on the SS-RSRP for SSB (5), SS-RSRP for SSB (6), SS-RSRP for SSB (7), SS-RSRP for SSB (8). Then, the UE uses the obtained predictions of SS-RSRP for SSB (1), SS-RSRP for SSB (2), SS-RSRP for SSB (3), SS- RSRP for SSB (4) to calculate the prediction of cell X e.g. highest SS- RSRP value out of SS-RSRP for SSB (1), SS-RSRP for SSB (2), SS-RSRP for SSB (3), to SS-RSRP for SSB (4). o The spatial-domain cell prediction for cell X may correspond to the value of a measurement quantity (e.g. an RSRP value, an RSRQ value, an SINR value) representing the measurement quantity of cell X (or a cell quality or cell measurement result). The spatial-domain cell prediction for neighbor cell X may be calculated based on one or more spatial-domain DL beam prediction(s) of a Set A of beams of cell X (e.g. predicted RSRP values for each beam in the Set A of beams) and / or measurements on a Set B of beams of cell X.

[0311] ■ In some embodiments, the beam prediction(s) for a Set A of beams of cell X is calculated based on measurements of a Set B of beams of cell X. For example, assuming beams transmitting SSBs, and assuming that Set A corresponds to [SSB(1), SSB(2), SSB (3), SSB (4)] and that Set B corresponds to [SSB(5), SSB(6), SSB (7), SSB (8)] the UE derives as prediction information the values of SS-RSRP for SSB (1), SS-RSRP for SSB (2), SS-RSRP for SSB (3), SS-RSRP for SSB (4), based on the SS- RSRP for SSB (5), SS-RSRP for SSB (6), SS-RSRP for SSB (7), SS- RSRP for SSB (8). Then, the UE uses the obtained predictions of SS- RSRP for SSB (1), SS-RSRP for SSB (2), SS-RSRP for SSB (3), SS-RSRP for SSB (4), AND the SS-RSRP for SSB (5), SS-RSRP for SSB (6), SS- RSRP for SSB (7), to SS-RSRP for SSB (8) to calculate the prediction of cell X e.g. highest SS-RSRP value out of the predicted SS-RSRP values (of Set A) and the actual SS-RSRP measurements for Set B.

[0312] • A Time-domain Downlink (DL) beam prediction for a Set A of beams of a cell X o The Time-domain Downlink (DL) beam prediction for a Set A of beams of a cell X may be derived based on measurement results of Set B of beams of a cell X. The Set A and Set B may be the same, or Set B may be a subset of Set A, or Set A and Set B are non-overlapping. o The time-domain DL beam prediction for a Set A of beams may correspond to F predictions for F future time instances. Each prediction may be for each time instance and may be associated to each beam in the Set A for which the prediction is performed. o The time-domain DL beam prediction for a Set A of beams may correspond to one or more beam ID(s) of the Set A of beams, associated to a future time instance ‘f’ (out of multiple future time instances F, where F may be configured at the UE) and a respective time-domain prediction of a measurement quantity. A beam ID may correspond to a Reference Signal ID or index (such as an SSB index, denoted herein as SSB(k), for SSB with index number ‘k’) for an RS which is transmitted in that beam. For example, a predicted information may correspond to an SS-RSRP value for the corresponding SSB index SSB(k) of a cell (where a measurement quantity may also be configured). For example, assuming Set A of beams corresponds to SSB(1), SSB(2), SSB(3), SSB(4), the prediction information may correspond to:

[0313] ■ For future time instance f=1 ;

[0314] • SS-RSRP=x1 , for SSB(1);

[0315] • SS-RSRP=x2, for SSB(2);

[0316] • SS-RSRP=x3, for SSB(3);

[0317] • SS-RSRP=x4, for SSB(4);

[0318] ■ For future time instance f=2;

[0319] • SS-RSRP=x1*, for SSB(1);

[0320] • SS-RSRP=x2*, for SSB(2);

[0321] • SS-RSRP=x3*, for SSB(3);

[0322] • SS-RSRP=x4*, for SSB(4);

[0323] ■ For future time instance f=3;

[0324] • SS-RSRP=x1**, for SSB(1);

[0325] • SS-RSRP=x2**, for SSB(2);

[0326] • SS-RSRP=x3**, for SSB(3);

[0327] • SS-RSRP=x4**, for SSB(4);

[0328] ■ For future time instance f=4;

[0329] • SS-RSRP=x1***, for SSB(1);

[0330] • SS-RSRP=x2***, for SSB(2);

[0331] • SS-RSRP=x3***, for SSB(3);

[0332] • SS-RSRP=x4***, for SSB(4); e time-domain DL beam prediction for a Set A of beams may correspond to one or more beam ID(s) of the Set A of beams, associated to a future time instance ‘f, and a respective time-domain prediction of a measurement quantity, and a respective predicted time window within which the predicted beam ID(s) is / are valid. A beam ID may correspond to a Reference Signal ID or index (such as an SSB index, denoted herein as SSB(k), for SSB with index number ‘k’) for an RS which is transmitted in that beam. For example, a predicted information may correspond to an SS-RSRP value for the corresponding SSB index SSB(k) of a cell (where a measurement quantity may also be configured) and a time window during which the predicted SS-RSRP value is valid. For example, assuming Set A of beams corresponds to SSB(1), SSB(2), SSB(3), SSB(4), the prediction information may correspond to:

[0333] ■ For future time instance f;

[0334] • SS-RSRP=x1 , for SSB(1); valid time window = t1

[0335] • SS-RSRP=x2, for SSB(2); valid time window = t2

[0336] • SS-RSRP=x3, for SSB(3); valid time window = t3

[0337] • SS-RSRP=x4, for SSB(4); valid time window = t4

[0338] ■ a common valid time window may be used to indicate the time duration where all predicted beams are valid, in that case, t1=t2=t3=t4=t. e time-domain DL beam prediction for a Set A of beams may correspond to one or more beam ID(s) of the Set A of beams, associated to a given time instance (out of multiple future time instances F, where F may be configured at the UE). The one or more beam ID(s) may be selected based on respective time-domain prediction of a measurement quantity e.g. predicted value of an SS-RSRP for the corresponding SSB index of a neighbor cell. For example, assuming Set A of beams = Set B and correspond to SSB(1), SSB(2), SSB(3), SSB(4), the predicted information per time instance ‘f’ may correspond to the beam ID(s) of the beams whose measurement quantity (e.g. RSRP) is above a threshold (e.g. configured at the UE), or / and only top-K beams are reported. Assume that K=4 for the example case, as an example, the following predicted information is reported:

[0339] • For future time instance f=1 ; o SSB(1); o The UE includes SSB(1) for f=1 as a reported information because the predicted SS-RSRP for SSB(1) is above the threshold, while the predicted SS-RSRP values for f=1 for SSB(2), SSB(3), SSB(4) are not above threshold.

[0340] • For future time instance f=2; o SSB(1); o The UE includes SSB(1) for f=2 as a reported information because the predicted SS-RSRP for SSB(1) is above the threshold, while the predicted SS-RSRP values for f=2 for SSB(2), SSB(3), SSB(4) are not above threshold.

[0341] • For future time instance f=3; O SSB(1); o SSB(2); o The UE includes SSB(1) and SSB(2) for f=3 since reported information because the predicted SS-RSRP for SSB(1) and SSB(2) are both above the threshold, while the predicted SS-RSRP values for f=3 for SSB(3), SSB(4) are not above threshold.

[0342] • For future time instance f=4; o SSB(1); o SSB(2); o SSB(4); o The UE includes SSB(1), SSB(2), SSB(3), SSB(4) for f=4 since reported information because the predicted SS-RSRP for SSB(1), SSB(2), SSB(3), SSB(4) are above the threshold. e time-domain DL beam prediction for a Set A of beams may correspond to one or more beam ID(s) of the Set A of beams at a future time instance f, and one or more predicted time window(s) within which the predicted beam ID(s) is / are valid. The one or more beam ID(s) may be selected based on respective time-domain prediction of a measurement quantity. For example, assuming Set A of beams = Set B and correspond to SSB(1), SSB(2), SSB(3), SSB(4), the predicted information may correspond to the beam ID(s) of the beams whose measurement quantity (e.g. RSRP) is above a threshold (e.g. configured at the UE), and the predicted validation time for each beam.

[0343] It may be assumed that the following prediction information can be reported

[0344] ■ For future time instance f;

[0345] • SSB(1); valid time window = t1

[0346] • SSB(2); valid time window =t2

[0347] • The UE includes SSB(1) and SSB(2) for f in reported information because the predicted SS-RSRP for SSB(1) and SSB(2) are both above the threshold, while the predicted SS-RSRP values for f=3 for SSB(3), SSB(4) are not above threshold, the SS-RSRP for SSB(1) and the SS-RSRP for SSB (2) are predicted to be above the threshold for time windows of t1 and t2, respectively. • A Time-domain cell prediction for a cell X o In some embodiments the time-domain cell prediction for a cell X corresponds to the value of a measurement quantity (e.g. an RSRP value, an RSRQ value, an SINR value), or rather a predicted value, representing the measurement quantity of cell X at a future time instance ‘f’ (or a predicted cell quality or predicted cell measurement result) for a future time instance ‘f’ o In some embodiments, the time-domain cell prediction for cell X is calculated based on one or more time-domain DL beam prediction(s) of a Set A of beams of cell X e.g. predicted RSRP values for each beam in the Set A of beams. o In some embodiments, both the prediction of the measurement quantity and the cell identifier associated to the cell X are included in the prediction information, for a given future time instance which may also be included in the prediction information, o For example, the UE obtains the following time-domain DL beam prediction of a Set A of beams of cell X (e.g., predicted best beam with predicted SS-RSRP value) for the future time instances as follows (e.g. as described above)

[0348] • Future time instance f=1 o SS-RSRP=x, for the predicted best beam / Top-1 beam among SSB(1), SSB(2), SSB(3) and SSB(4).

[0349] • For future time instance f=2; o SS-RSRP=x*, for the predicted best beam / Top-1 beam among SSB(1), SSB(2), SSB(3) and SSB(4).

[0350] • For future time instance f=3; o SS-RSRP=x**, for the predicted best beam / Top-1 beam among SSB(1), SSB(2), SSB(3) and SSB(4).

[0351] • For future time instance f=4; o SS-RSRP=x***, for the predicted best beam / Top-1 beam among SSB(1), SSB(2), SSB(3) and SSB(4).

[0352] ■ In some embodiments, the UE considers as the predicted RSRP for cell X in time instance f=1 to be the predicted SS-RSRP value x of predicted best beam / Top-1 / strongest beam among SSB(1), SSB(2), SSB(3) and SSB(4); the predicted RSRP for cell X in time instance f=2 to be the predicted SS- RSRP value x* of predicted best beam / Top-1 beam among SSB(1), SSB(2), SSB(3) and SSB(4); the predicted RSRP for cell X in time instance f=3 to be the predicted SS-RSRP value x** of predicted best beam / Top-1 beam among SSB(1), SSB(2), SSB(3) and SSB(4); and the predicted RSRP for cell X in time instance f=4 to be the predicted SS-RSRP value x*** of predicted best beam / Top-1 beam among SSB(1), SSB(2), SSB(3) and SSB(4). Thus, what is included in the prediction information may be, for example, the following:

[0353] • Future time instance f=1 -> predicted RSRP for cell X= x;

[0354] • Future time instance f=2 -> predicted RSRP for cell X= x*;

[0355] • Future time instance f=3 -> predicted RSRP for cell X= x**;

[0356] • Future time instance f=4 -> predicted RSRP for cell X= x***.

[0357] Fig. 11 is an example of time domain cell prediction derivation based on predicted RSRP value of predicted best beam / Top-1 beam of set A beams of Cell X For example, the UE obtains the following time-domain DL beam prediction(s) of a Set A of beams of cell X for the future time instances as follows (e.g. as described above)

[0358] • Future time instance f=1 o SS-RSRP=x1 , for SSB(1); SS-RSRP=x2, for SSB(2); SS- RSRP=x3, for SSB(3); SS-RSRP=x4, for SSB(4).

[0359] • For future time instance f=2; o SS-RSRP=x1*, for SSB(1); SS-RSRP=x2*, for SSB(2); SS- RSRP=x3*, for SSB(3); SS-RSRP=x4*, for SSB(4);

[0360] • For future time instance f=3; o SS-RSRP=x1**, for SSB(1); SS-RSRP=x2**, for SSB(2); SS-RSRP=x3**, for SSB(3); SS-RSRP=x4**, for SSB(4);

[0361] • For future time instance f=4; o SS-RSRP=x1***, for SSB(1); SS-RSRP=x2***, for SSB(2); SS-RSRP=x3***, for SSB(3); SS-RSRP=x4***, for SSB(4);

[0362] ■ In some embodiments, the UE considers as the predicted RSRP for cell X in time instance f=1 to be the highest predicted SS-RSRP value out of x1 , x2, x3, x4; the predicted RSRP for cell X in time instance f=2 to be the highest predicted SS-RSRP value out of x1*, x2*, x3*, x4*; the predicted RSRP for cell X in time instance f=3 to be the highest predicted SS-RSRP value out of x1**, x2**, x3**, x4**; and the predicted RSRP for cell X in time instance f=4 to be the highest predicted SS-RSRP value out of x1***, x2***, x3***, x4*. Thus, what is included in the prediction information may be, for example, the following: • Future time instance f=1 - predicted RSRP for cell X= Max (x1 , x2, x3, x4)

[0363] • Future time instance f=2 -> predicted RSRP for cell X= Max (x1*, x2*, x3*, x4*);

[0364] • Future time instance f=3 -> predicted RSRP for cell X= Max (x1**, x2**,x3**x4**);

[0365] • predicted RSRP for cell X= Max

[0366] ■ In some embodiments, the UE considers as the predicted RSRP for cell X in time instance f=1 to be an average of the highest predicted SS-RSRP values e.g. highest SS-RSRP value averaged with the SS-RSRP values of the other SSBs whose SS-RSRP is above a threshold, up to a certain configurable value e.g. N. For simplicity this is simply denoted as an Average() function, as follows:

[0367] • Future time instance f=1 predicted RSRP for cell X= Average

[0368] (x1 , x2, x3, x4)

[0369] Future time instance f=2 predicted RSRP for cell X= Average

[0370] (x1*, x2*, x3*, x4*);

[0371] Future time instance f=3 predicted RSRP for cell X= Average

[0372] (x1**,x2**x3**x4**);

[0373] Future time instance f=4 predicted RSRP for cell X= Average

[0374] (x1*** x2*** x3*** x4***)'

[0375] Fig. 12 is an example of time domain cell prediction derivation based on Max().

[0376] Fig. 13 is an example of time domain cell prediction derivation based one AverageQ. ln some embodiments the time-domain cell prediction for neighbor cell X corresponds to a cell identifier such as a Cell ID and / or a PCI + SSB frequency, derived based on the predicted value of a measurement quantity (e.g. an RSRP value, an RSRQ value, an SINR value) representing the measurement quantity of cell X at a future time instance ‘f (or a predicted cell quality or predicted cell measurement result) In some embodiments, for a future time instance the time-domain cell prediction for neighbor cell X is calculated based on one or more time-domain DL beam prediction(s) of a Set A of beams of cell X e.g. predicted RSRP values for each beam in the Set A of beams. some embodiments, the UE obtains the following time-domain DL beam prediction(s) of a Set A of beams of cell X for the future time instances as follows

[0377] • Future time instance f=1 o SS-RSRP=x1, for SSB(1); SS-RSRP=x2, for SSB(2); SS- RSRP=x3, for SSB(3); SS-RSRP=x4, for SSB(4).

[0378] • For future time instance f=2; o SS-RSRP=x1*, for SSB(1); SS-RSRP=x2*, for SSB(2); SS- RSRP=x3*, for SSB(3); SS-RSRP=x4*, for SSB(4);

[0379] • For future time instance f=3; o SS-RSRP=x1**, for SSB(1); SS-RSRP=x2**, for SSB(2); SS-RSRP=x3**, for SSB(3); SS-RSRP=x4**, for SSB(4);

[0380] • For future time instance f=4; o SS-RSRP=x1***, for SSB(1); SS-RSRP=x2***, for SSB(2); SS-RSRP=x3***, for SSB(3); SS-RSRP=x4***, for SSB(4);

[0381] ■ In some embodiments, the UE considers as the predicted RSRP for cell X in time instance f=1 to be the highest predicted SS-RSRP value out of x1 , x2, x3, x4; the predicted RSRP for cell X in time instance f=2 to be the highest predicted SS-RSRP value out of x1*, x2*, x3*, x4*; the predicted RSRP for cell X in time instance f=3 to be the highest predicted SS-RSRP value out of x1**, x2**, x3**, x4**; and the predicted RSRP for cell X in time instance f=4 to be the highest predicted SS-RSRP value out of x1***, x2***, x3***, x4*. Thus, the UE calculates the following and determines to include a Cell ID or not as the predicted information as follows:

[0382] • Future time instance f=1 - predicted RSRP for cell X= Max (x1 , x2, x3, x4) o When the predicted RSRP for cell X= Max (x1 , x2, x3, x4) > threshold, UE includes the Cell ID of cell X as predicted information for time instance f=1

[0383] • Future time instance f=2 -> predicted RSRP for cell X= Max (x1*, x2*, x3*, x4*); o When the predicted RSRP for cell X= Max (x1*, x2*, x3*, x4*) > threshold, UE includes the Cell ID of cell X as predicted information for time instance f=2 • Future time instance f=3 -> predicted RSRP for cell X= Max (x1**, x2**,x3**X4**); o When the predicted RSRP for cell X= Max (x1**, x2**, x3**, x4**) > threshold, UE includes the Cell ID of cell X as predicted information for time instance f=3

[0384] • Future time instance f=4 -> predicted RSRP for cell X= Max (x1***, x2***,x3*** x4***); o When the predicted RSRP for cell X= Max (x1***, x2***, x3*** x4***) > threshold, UE includes the Cell ID of cell X as predicted information for time instance f=4

[0385] • Following that logic, for each future time instance to be included in the prediction information, e.g. f=1 , f=2, f=3, f=4, the UE may include one or more cell ID(s). The cell ID may be included for a future time instance when the predicted value of the measurement quantity of that cell for that time instance fulfills a criterion, e.g., being above a threshold in the examples above, or being an offset better than the predicted measurement quantity of the PCell (e.g. the entry condition of an Event A3 but based on time-domain prediction of a measurement quantity of a cell). An example of a prediction information may be the following: o Future time instance f=1 -> Cell ID=X, cell ID=Y o Future time instance f=2 -> Cell I D=X o Future time instance f=3 -> Cell ID=X o Future time instance f=4 -> Cell ID=X, cell ID=Z o That reported information would indicate that the cell whose cell ID=X has a predicted measurement quantity (RSRP) which fulfills the criteria (e.g. being above a threshold) in the future time instances f=1 , f=2, f=3, f=4, while the cell with Cell ID=Y only fulfills the criteria in f=1 , and the cell with cell ID= z in f=4.

[0386] An AI / ML model can be designed to realize the beam-level measurement prediction in spatial domain or / and time-domain. Utilizing the predicted beam-level measurement quality(ies) or / and beam IDs generated from the AI / ML model output, a predicted cell-level measurement quality for a cell X can be derived using the approaches described above. An AI / ML model can also be designed to directly output the predicted cell-level measurement by taking L3 measurements of a set of beams as model input. Besides predicted beam-level or / and cell-level measurement quantities and beam / cell IDs, the model may also provide additional information such as confidence level of the model output, the validation time of the predicted measurements, etc.

[0387] The designed AI / ML model can be deployed at the UE and associated to a beam prediction feature or a RRM prediction feature. When connecting to a network node, a UE can report its support of the AI / ML model for the beam prediction feature or RRM prediction feature to the network node via UE capability reporting. Based on the received UE capability, together with other conditions, the network node can make decisions on whether to configure / active the AI / ML model at the UE or not.

[0388] Below are multiple examples on how to design an AI / ML model to achieve the beam / cell- level measurement quality prediction in spatial or / and time domain.

[0389] For the AI / ML model used for cell prediction, in an example, it is composed of multiple connected neurons. Optionally it contains one or a few of input layer, one or a few of hidden layer, and one output layer. For the input layer, it takes UE measurements results as the model input, where the measurement results are obtained based on measuring some reference signals, e.g., SSBs and / or CSI-RSs. Optionally, the measurement results would be normalized before input to the hidden layers. The normalization can change the value of the numeric variable in the dataset to a typical scale which improve model training. For the hidden layer(s), it is located between the input and output, in which the function applies weights to the inputs and directs them through an activation function to the output layer. Optionally, activation function can be one of Softmax function, Sigmoid function, ReLU function, Leaky ReLU, tanh function and Maxout. For the output layer, the output can be predicted RSRP values for each beam. Optionally, the output can be the probability values where each value means the probability of the beam to be the best beam.

[0390] In an example for the AI / ML model, the AI / ML model used for cell prediction is based on convolutional neural networks, optionally it contains one or a few of input layers, one of a few of convolution layer, one or a few of pooling layer and output layer. For the input layer, it takes UE measurements results as the model input, where the measurement results are obtained based on measuring some reference signals, e.g., SSBs and / or CSI-RSs. Optionally, the measurement results would be normalized before input to the convention layers. The normalization can change the value of the numeric variable in the dataset to a typical scale which improve model training. For the convention layer(s), it is used to extract the feature from the input. It applies a set of learnable filters(known as the kernels) to the input with smaller size than the whole input. These filters and kernels slide over the input data and computes the dot product between kernel weight and the corresponding input. The output of convention layer is referred as feature maps coming from the input measured RSRP values. For pooling layers, it involves sliding a two-dimensional filter over each channel of feature map and summarizing the features lying within the region covered by the filter. Before the output layer, there can be a fully connected layer to interpret / summarize the features obtained and directs them through activation function to the output layer. For the output layer, the output can be predicted RSRP values for each beam. Optionally, the output can be the probability values where each value means the probability of the beam to be the best beam.

[0391] In another set of examples, an AI / ML model is designed to realize the beam-level measurement prediction in the spatial domain. A predicted cell-level measurement quality for a cell X can be derived based on the predicted beam-level measurement quality(ies) or / and beam IDs generated from the AI / ML model output. Different design options for AI / ML based spatial domain beam prediction can be considered. Three example design options are listed below.

[0392] • Option 1) the AI / ML model predicts Top-1 / K beam ID(s), where the model takes the

[0393] (postprocessed) RSRP measurements of the beams in set B as model input and directly outputs the top-1 / K beam ID(s) of the beams in Set A.

[0394] • Option 2) the AI / ML model predicts Top-1 / K beam ID(s) and the associated predicted RSRP values, where the model takes the (postprocessed) RSRP measurements of the beams in set B as model input and directly outputs the top-1 / K beam ID(s) and the predicted RSRP values of these beams in set A.

[0395] • Option 3) the AI / ML model predicts top-1 / K beam ID(s) with / without the associated predicted RSRP values, where the model takes the (postprocessed) RSRP measurements of the beams in set B or / and the assistance information like UE position as model input.

[0396] As an example, the AI / ML model mentioned in the above three design options can be based on neural network architectures, e.g., convolutional neural network (CNN), fully connected neural network (NN), Residual Networks (ResNet). Fig. 14 shows two examples of model architectures, where Neural network B (NN B) is a model with higher complexity in comparison to Neural network A (NN A). The number of nodes in the dense layers equals the number of beams in Set A, NSetA. The model input takes RSRP of SSB and / or CSI RS of set B beams (one real value per measured beam, normalized based on min and max values per sample. Normalization is based on scaling the beam RSRP values in dB per sample to yield the range 0.0 to 1.0 for RSRP values for each sample. In case assistance information, such as UE location information, is also used as input to the neural network, that information is concatenated to the RSRP values after being separately scaled by a fixed scaling factor designed to yield values with maximum magnitudes in the order of 1 . A softmax cross-entropy function is used to generate the probability of a beam being the strongest beam, used to derive top-1 / K beams.

[0397] As noted above, Fig. 15 shows examples of Neural Networks used for designing AI / ML models for spatial beam prediction. The number of nodes in the dense layers equals the number of beams N_SetA in Set A.

[0398] In another set of examples, an AI / ML model is designed to realize the beam-level measurement prediction in the time domain (which includes spatial and time domain prediction as a special case).

[0399] Fig. 15 illustrates an example of model input and model output selection when designing an AI / ML model for time domain beam prediction. The AI / ML model inputs are the L1-RSRPs measured from 5 consecutive time instances. So, the observation duration T1=5*40ms=200ms. Prediction is at the time instance immediately following the last observation window time instance, and a prediction at 160ms ahead for comparison. Hence the time duration for the best beam evaluation is T2= 40 ms or 160 ms. An example of the AI / ML model is described as the following.

[0400] As an example, the AI / ML model can be designed based on recurrent neural network (RNN), long short term memory network (LSTM), or transformer network architectures. An example model architecture can consist of two LSTM layers, a Dropout layer, Dense-Relu and a Dense-softmax, which are sequentially connected. The AI / ML model input size is (Nip, 5), where Nip is the number of L1-RSRPs measured at each of the five time instance. For model output, a categorical cross entropy loss function is used to generate a softmax output vector, whose size is equal to the number of beams contained in the set A, based on which the top-1 / K beams with the highest probability can be generated for each prediction time instance.

[0401] Further Details about the CHO confiquration(s)

[0402] In the method the UE can receive a CHO configuration including a CHO execution condition according to any of:

[0403] • The UE receives the CHO configuration in a first RRCReconfiguration and, in response to it, the UE transmits an RRCReconfigurationComplete.

[0404] • The CHO configuration contains the configuration of CHO candidate cell(s) generated by the candidate network node(s) e.g. candidate gNB(s) and CHO execution condition(s) generated by the source network node e.g. source gNB.

[0405] • The CHO execution condition (or simply execution condition) may consist of one or two trigger condition(s) each configured as a Measurement ID associated to a reporting / trigger configuration (i.e. CHO events A3 / A5, as defined in 3GPP TS 38.331 v17.4.0). • When the UE executes CHO, i.e. the UE applies a stores RRCReconfiguration message and starts synchronization with a candidate cell which fulfills the CHO execution condition, and transmits an RRCReconfigurationComplete.

[0406] In a set of embodiments, the UE can receive a CHO configuration including a CHO execution condition and a CHO candidate configuration for the at least one neighbor cell.

[0407] The CHO configuration may correspond to the field conditionalReconfiguration-r16 and / or the Information Element Conditional Reconfiguration-^ 6, included in an RRC Reconfiguration message (e.g. RRCReconfiguration), and defined as follows:

[0408] The CHO configuration can comprise one or more of the following:

[0409] • An indication of a fast recovery e.g. parameter attemptCondReconfig. When that is present, the UE performs CHO if selected cell is a target candidate cell

[0410] • One of more CHO candidate configuration(s) e.g. in the IE CondReconfigToAddModList

[0411] • One of more indications for removing CHO candidate cell configuration(s) e.g. in the IE CondReconfigToRemoveList

[0412] The CHO candidate configuration may correspond to one or more of:

[0413] • An instance within the IE CondReconfigToAddModList e.g. the IE CondReconfigToAddMod and / or parameters within and / or

[0414] • The actual RRCReconfiguration message associated to the CHO candidate cell and to be applied when the CHO execution condition is stored e.g. field condRRCReconfig and / or the IE OCTET STRING (CONTAINING RRCReconfiguration)

[0415] The CHO execution condition may correspond to an indication of the execution condition that needs to be fulfilled in order to trigger the execution of a CHO. That may comprise one or more measurement identifiers and a measurement object (e.g. indicating the SSB frequency and other parameters for cell quality derivation). Each measurement identifier may be associated to a reporting configuration for CHO in which the actual execution condition parameters are included. For example, the CHO execution condition for a candidate cell may be indicated to the UE as a SEQUENCE of one or more IE(s) Measld(s).

[0416] Further Details about the definition of CHO execution conditions to be evaluated with respect to prediction information

[0417] A3-like for measurement and A3-like for predictions

[0418] In a set of embodiments, the CHO execution condition may be considered fulfilled upon fulfillment of a first condition as follows:

[0419] (first sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a first duration defined by a time to trigger (e.g. TTT, configured at the UE)

[0420] AND

[0421] (second sub-condition) the prediction of a neighbour cell measurement quantity (e.g. predicted RSRP) is a second offset better than the measurement quantity of the prediction of the PCell measurement quantity (e.g. predicted RSRP), for a number of future time instances (e.g. F, configured at the UE) or for a second duration defined by a prediction time horizon (e.g., T2, configured at the UE).

[0422] An example CHO execution condition according to some of these embodiments is depicted in Fig. 16.

[0423] In some embodiments, one or more of the following may apply:

[0424] - The UE may be configured with first and second offset(s) by a single parameter e.g. a3- Offset included in a reporting or triggering configuration. Consequently, the same value may be used for the measurement(s) and the time-domain predictions. - The UE may be configured with first and second offset(s) by different parameters. Consequently, different values may be set for the measurements and for the predictions.

[0425] - The UE may be configured with a measurement quantity used for the part of the condition related to the measurement of the PCell (first sub-condition) and the measurement of the neighbour cell. That measurement quantity may be configured as a trigger quantity set to RSRP or RSRQ or SINR.

[0426] - The UE may be configured with a measurement quantity used for the part of the condition related to the time-domain prediction of the PCell (first sub-condition) and the time-domain prediction of the neighbour cell. That measurement quantity may be configured as a trigger quantity set to RSRP or RSRQ or SINR. o The measurement quantity configured for the predictions may be the same as the measurement quantity configured for the measurements, configured at the UE by a single parameter e.g. the IE MeasTriggerQuantityOffset. For example, if RSRP is configured as the measurement quantity to be used as the trigger quantity, the condition may correspond to:

[0427] ■ neighbour cell RSRP is a first offset better than the PCell RSRP, for a first duration defined by a time to trigger (e.g. TTT, configured at the UE) AND the prediction of the neighbour cell RSRP is a second offset better than the prediction of the PCell RSRP), for a number of future time instances (e.g. F, configured at the UE) or for a second duration defined by a prediction time horizon (e.g., T2, configured at the UE). o The measurement quantity configured for the predictions may be configured as a different parameter compared to the measurement quantity configured for the measurements i.e. these may be set to different values. For example, if RSRP is configured as the measurement quantity to be used as the trigger quantity for measurements, and RSRQ is be configured as the measurement quantity to be used as the trigger quantity for the predictions, the condition may correspond to:

[0428] ■ neighbour cell RSRP is a first offset better than the PCell RSRP, for a first duration defined by a time to trigger (e.g. TTT, configured at the UE) AND the prediction of the neighbour cell RSRQ is a second offset better than the prediction of the PCell RSRQ, for a number of future time instances (e.g. F, configured at the UE) or for a second duration defined by a prediction time horizon (e.g., T2, configured at the UE).

[0429] - The UE may be configured with a single hysteresis parameter, associated with the first and second sub-conditions e.g. field hysteresis included in a reporting or triggering configuration. Consequently, the same value may be used for the measurement(s) and the time-domain predictions.

[0430] - The UE may be configured with a first hysteresis parameter, associated with the first sub-condition, and a second hysteresis parameter, associated with the second subcondition, e.g. two hysteresis fields included in a reporting or triggering configuration. Consequently, different values may be set for the measurement(s) and the time-domain predictions.

[0431] In more general terms, for the first condition, the first and second sub-conditions may have some similarities, except that the first is related to measurements and the second sub-conditions for the prediction(s) e.g. time-domain predictions. In other words, at least when same values are used for the offsets and / or thresholds the reasoning for executing CHO based on both the first and the second sub-conditions is that it would not be enough to have fulfilled CHO execution condition based on measurements (as in legacy), but predictions shall also indicate that the conditions remain fulfilled for a number of time instances, which makes the neighbour cell a good cell for the CHO execution and prevents the scenarios such as an RLF shortly after the CHO execution to the neighbour cell configured as CHO candidate.

[0432] In a set of embodiments, the UE may be configured with the CHO execution condition based on prediction information of the neighbour cell and / or the serving cell (e.g. condExecutionCond) as part of the CHO configuration associated to a CHO configuration identifier (e.g. condReconfigld), where the UE receives for the CHO execution condition a first measurement identifier (e.g. IE MeasID) and a second measurement identifier (e.g. MeasID). The first measurement identifier may be associated to a measurement configuration (e.g. including a reporting or CHO triggering configuration, and a measurement object configuration) and the second measurement identifier may be associated to a prediction configuration (e.g. including a reporting or CHO triggering configuration). An execution condition according to some of these embodiments is illustrated in Fig. 17.

[0433] In a set of embodiments, the UE may be configured with the CHO execution condition based on prediction information of the neighbour cell and / or the serving cell (e.g. condExecutionCond) as part of the CHO configuration associated to a CHO configuration identifier (e.g. condReconfigld), where the UE receives for the CHO execution condition a single measurement identifier (e.g. IE MeasID) associated to a measurement configuration (e.g. including a reporting or CHO triggering configuration, and a measurement object configuration) which includes a prediction configuration (e.g. including a reporting or CHO triggering configuration), for the prediction event in addition to the measurement event. In a set of embodiments, the UE may perform one or more measurements and one or more time-domain prediction(s) to be used as input to the CHO execution condition, based on a measurement configuration and / or a prediction configuration which the UE receives.

[0434] For example, when the UE is configured with the CHO execution condition based on prediction information of the neighbour cell and / or the serving cell (e.g. condExecutionCond) as part of the CHO configuration associated to a CHO configuration identifier (e.g. condReconfigld), where the UE receives for the CHO execution condition a first measurement identifier (e.g. IE MeasID) and a second measurement identifier (e.g. MeasID), the UE may perform one or more measurements based on the configuration(s) associated to the first measurement identifier and performs one or more time-domain prediction(s) based on the configuration(s) associated to the second measurement identifier.

[0435] For example, when the UE is configured with the CHO execution condition based on prediction information of the neighbour cell and / or the serving cell (e.g. condExecutionCond) as part of the CHO configuration associated to a CHO configuration identifier (e.g. condReconfigld), where the UE receives for the CHO execution condition a single measurement identifier (e.g. IE MeasID) associated to a measurement configuration (e.g. including a reporting or CHO triggering configuration, and a measurement object configuration) which includes a prediction configuration (e.g. including a reporting or CHO triggering configuration), for the prediction event in addition to the measurement event, the UE may perform both the measurements and time-domain prediction(s) based on the configuration(s) associated to that single measurement identifier.

[0436] In a set of embodiments, the first condition may be called “an event” comprising a measurement event for the first sub-condition (referred below as an entering condition) and a prediction event for the second sub-condition (referred below as an entering condition for predictions). One example to characterize the first condition is shown as below:

[0437] The UE shall:

[0438] 1> consider the entering condition for this event to be satisfied when condition A3-1 and A3-lb. as specified below, is fulfilled;

[0439] [...]

[0440] 1> use the SpCell for Mp, Ofp and Ocp.

[0441] NOTE 1 : The cell(s) that triggers the event has reference signals indicated in the measObjectNR associated to this event which may be different from the NR SpCell measObjectNR.

[0442] Inequality A3-1 (Entering condition) Mn + Ofn + Ocn - Hys > Mp + Ofp + Ocp + Off

[0443] Inequality A3-lb (Entering condition for predictions)

[0444] The variables in the formula are defined as follows:

[0445] Mn is the measurement result of the neighbouring cell, not taking into account any offsets.

[0446] Ofn is the measurement object specific offset of the reference signal of the neighbour cell (i.e. offsetMO as defined within measObjectNR corresponding to the neighbour cell).

[0447] Ocn is the cell specific offset of the neighbour cell (i.e. celllndividualOffset as defined within measObjectNR corresponding to the frequency of the neighbour cell), and set to zero if not configured for the neighbour cell.

[0448] Mp is the measurement result of the SpCell, not taking into account any offsets.

[0449] Ofp is the measurement object specific offset of the SpCell (i.e. offsetMO as defined within measObjectNR corresponding to the SpCell).

[0450] Ocp is the cell specific offset of the SpCell (i.e. celllndividualOffset as defined within measObjectNR corresponding to the SpCell), and is set to zero if not configured for the SpCell.

[0451] Hys is the hysteresis parameter for this event (i.e. hysteresis as defined within reportConfigNR for this event).

[0452] Off is the offset parameter for this event (i.e. a3-Offset as defined within reportConfigNR for this event).

[0453] Mn, Mp are expressed in dBm in case of RSRP, or in dB in case of RSRQ and RS-SINR.

[0454] Ofn, Ocn, Ofp, Ocp, Hys, Off are expressed in dB.

[0455] Mnis the time-domain prediction of a measurement result of the neighbouring cell, not taking into account any offsets.

[0456] ()fnis the specific offset of the reference signal of the neighbour cell (i.e. offsetMO as defined within measObjectNR corresponding to the neighbour cell) for a time-domain prediction of a measurement result

[0457] Ocn<l’>is the cell specific offset of the neighbour cell and set to zero if not configured for the neighbour cell for time-domain prediction of a measurement result

[0458] Mpis the time-domain prediction of a measurement result of the SpCell, not taking into account any offsets.

[0459] ()fpis the specific offset of the SpCell for a time-domain prediction of a measurement result

[0460] Ocpis the cell specific offset of the SpCell for a time-domain prediction of a measurement result and is set to zero if not configured for the SpCell.

[0461] Mn, Mpare expressed in dBm in case of RSRP, or in dB in case of RSRQ and RS-SINR.

[0462] Ofn(p>, Ocn(p>, Ofp(p>, Ocp(p>, Hys(p>, Off(p>are expressed in dB.

[0463] NOTE 2: The definition of Event A3 also applies to CondEvent A3. Another example to characterize the first condition is shown as below:

[0464] The UE shall:

[0465] 1> consider the entering condition for this event to be satisfied when condition A3-1 and A3-lb. as specified below, is fulfilled;

[0466] [ .]

[0467] 1> use the SpCell for Mp, Ofp and Ocp.

[0468] NOTE 1 : The cell(s) that triggers the event has reference signals indicated in the measObjectNR associated to this event which may be different from the NR SpCell measObjectNR.

[0469] Inequality A3-1 (Entering condition)

[0470] Mn + Ofn + Ocn - Hys > Mp + Ofp + Ocp + Off

[0471] Inequality A3-lb (Entering condition for predictions)

[0472] The variables in the formula are defined as follows:

[0473] Mn is the measurement result of the neighbouring cell, not taking into account any offsets.

[0474] Ofn is the measurement object specific offset of the reference signal of the neighbour cell (i.e. offsetMO as defined within measObjectNR corresponding to the neighbour cell).

[0475] Ocn is the cell specific offset of the neighbour cell (i.e. celllndividualOffset as defined within measObjectNR corresponding to the frequency of the neighbour cell), and set to zero if not configured for the neighbour cell.

[0476] Mp is the measurement result of the SpCell, not taking into account any offsets.

[0477] Ofp is the measurement object specific offset of the SpCell (i.e. offsetMO as defined within measObjectNR corresponding to the SpCell).

[0478] Ocp is the cell specific offset of the SpCell (i.e. celllndividualOffset as defined within measObjectNR corresponding to the SpCell), and is set to zero if not configured for the SpCell.

[0479] Hys is the hysteresis parameter for this event (i.e. hysteresis as defined within reportConfigNR for this event).

[0480] Off is the offset parameter for this event (i.e. a3-Offset as defined within reportConfigNR for this event).

[0481] Mn, Mp are expressed in dBm in case of RSRP, or in dB in case of RSRQ and RS-SINR.

[0482] Ofn, Ocn, Ofp, Ocp, Hys, Off are expressed in dB.

[0483] Mdiff n p(p>is the time-domain prediction of a measurement quantity difference between the neighbouring cell and the SpCell, not taking into account any offsets.

[0484] Ofn<l’>is the specific offset of the reference signal of the neighbour cell (i.e. offsetMO as defined within measObjectNR corresponding to the neighbour cell) for a time-domain prediction of a measurement result

[0485] Ocn<l’>is the cell specific offset of the neighbour cell and set to zero if not configured for the neighbour cell for time-domain prediction of a measurement result.

[0486] Ofp<l’>is the specific offset of the SpCell for a time-domain prediction of a measurement result ()cpis the cell specific offset of the SpCell for a time-domain prediction of a measurement result and is set to zero if not configured for the SpCell.

[0487] Mdiff n pis expressed in dBm in case of RSRP, or in dB in case of RSRQ and RS-SINR.

[0488] Ofn(p>, Ocn(p>, Ofp(p>, Ocp(p>, Hys(p>, Off(p>are expressed in dB.

[0489] NOTE 2: The definition of Event A3 also applies to CondEvent A3.

[0490] In a set of embodiments, the first condition comprises a measurement event for the first sub-condition associated to an Event A3, and a prediction event for the second sub-condition (referred below as an entering condition for predictions) referred as prediction Event A3. The prediction Event A3 may be characterized as follows:

[0491] The UE shall:

[0492] 1> consider the entering condition for this event to be satisfied when condition A3-1, as specified below, is fulfilled;

[0493] [...]

[0494] 1> use the SpCell for Mp, Ofp and Ocp.

[0495] NOTE 1 : The cell(s) that triggers the event has reference signals indicated in the measObjectNR associated to this event which may be different from the NR SpCell measObjectNR.

[0496] Inequality A3-l(p)(Entering condition for predictions)

[0497] The variables in the formula are defined as follows:

[0498] Ofn, Ocn, Ofp, Ocp, Hys, Off are expressed in dB.

[0499] Mnis the time-domain prediction of a measurement result of the neighbouring cell, not taking into account any offsets.

[0500] Ofnis the specific offset of the reference signal of the neighbour cell (i.e. offsetMO as defined within measObjectNR corresponding to the neighbour cell) for a time-domain prediction of a measurement result

[0501] Ocnis the cell specific offset of the neighbour cell and set to zero if not configured for the neighbour cell for time-domain prediction of a measurement result

[0502] Mpis the time-domain prediction of a measurement result of the SpCell, not taking into account any offsets.

[0503] ()fpis the specific offset of the SpCell for a time-domain prediction of a measurement result ()cpis the cell specific offset of the SpCell for a time-domain prediction of a measurement result and is set to zero if not configured for the SpCell.

[0504] Mn, Mpare expressed in dBm in case of RSRP, or in dB in case of RS RO and RS-SINR.

[0505] Ofn(p>, Ocn(p>, Ofp(p>, Ocp(p>, Hys(p>, Off(p>are expressed in dB.

[0506] NOTE 2: The definition of Event A3 also applies to CondEvent A3.

[0507] As another example, the prediction Event A3 may be characterized as follows:

[0508] The UE shall:

[0509] 1> consider the entering condition for this event to be satisfied when condition A3-1, as specified below, is fulfilled;

[0510] [ .]

[0511] 1> use the SpCell for Mp, Ofp and Ocp.

[0512] NOTE 1 : The cell(s) that triggers the event has reference signals indicated in the measObjectNR associated to this event which may be different from the NR SpCell measObjectNR.

[0513] Inequality A3-l(p)(Entering condition for predictions)

[0514] The variables in the formula are defined as follows:

[0515] Ofn, Ocn, Ofp, Ocp, Hys, Off are expressed in dB.

[0516] Mdiff n pis the time-domain prediction of a measurement quantity difference between the neighbouring cell and the SpCell, not taking into account any offsets.

[0517] Ofnis the specific offset of the reference signal of the neighbour cell (i.e. offsetMO as defined within measObjectNR corresponding to the neighbour cell) for a time-domain prediction of a measurement result

[0518] Ocnis the cell specific offset of the neighbour cell and set to zero if not configured for the neighbour cell for time-domain prediction of a measurement result

[0519] Ofpis the specific offset of the SpCell for a time-domain prediction of a measurement result

[0520] Ocpis the cell specific offset of the SpCell for a time-domain prediction of a measurement result and is set to zero if not configured for the SpCell.

[0521] Mdiff n pis expressed in dBm in case of RSRP, or in dB in case of RSRQ and RS-SINR.

[0522] Ofn(p>, Ocn(p>, Ofp(p>, Ocp(p>, Hys(p>, Off(p>are expressed in dB. NOTE 2: The definition of Event A3 also applies to CondEvent A3.

[0523] The CHO execution condition may correspond to a condition (AND condition), where the first condition type is comprised by a plurality of sub-conditions. The condition may be considered fulfilled when all sub-conditions of the plurality of sub-conditions are fulfilled.

[0524] One advantage of the first condition is that the first sub-condition is similar to the existing CHO execution condition in legacy CHO. Thus, defining the first condition with a second subcondition could lead to fewer CHO executions. That effect may give the possibility back to the network to receive measurement reports and trigger handovers. It may be argued that the introduction of the second sub-condition makes the UE to hold for longer the connection with the PCell, giving back the control to the network for triggering handovers (except when the neighbour cell is shown to remain an offset better than the PCell for future time instances). Another benefit is that this prevents the deletion of CHO candidates unnecessarily, in case the UE triggers CHO execution and shortly comes back to the source PCell.

[0525] There may be scenarios in which there would only be beneficial to delay the CHO execution (or prevent it) based on time domain predictions of measurements of the PCell and / or the neighboru cell (e.g. based on a second sub-condition) when the PCell quality remains acceptable and / or the chances of an RLF in the source PCell are very low.

[0526] In some embodiments, the UE may consider the second sub-condition part of the first condition or not, based on a high likelihood of detecting a Radio Link Failure (RLF) in source PCell.

[0527] The UE may consider the likelihood of detecting a RLF in source PCell to be HIGH when the first sub-condition is fulfilled while an RLF timer is running. In other words, if the measurements indicate that the neighbour cell is an offset better than the PCell, and an RLF timer is running at the PCell (which means the connection suffers from radio problems) the UE may execute CHO regardless of what the predictions indicate in the second sub-condition. The RLF timer may correspond to a timer which is started when a radio problem has been detected e.g. number of out of sync indications from lower layers. The RLF timer may correspond to a timer in which an RLF is detected when that timer expires e.g. timer T310 defined in 3GPP TS 38.331 .

[0528] The UE may consider the likelihood of detecting a RLF in source PCell to be HIGH when the first sub-condition is fulfilled and the number of out of sync indication(s) is above a configured counter e.g. N310p. In other words, if the measurements indicate that the neighbour cell is an offset better than the PCell, and the number of out of sync indications (from the lower layers) at the PCell is above a configured value (which means the connection is suffering from radio problems) the UE executes CHO regardless of what the predictions indicate in the second subcondition.

[0529] The UE may consider the likelihood of detecting a RLF in source PCell to be HIGH when the first sub-condition is fulfilled and a measurement quantity of the PCell (e.g. SINR) is below a threshold. In other words, if the measurements indicate that the neighbour cell is an offset better than the PCell, and the PCell measurement quantity (e.g. SINR) is below a configured threshold, the UE may execute CHO regardless of what the predictions indicate in the second sub-condition.

[0530] The UE may consider the likelihood of detecting a RLF in source PCell to be HIGH when the first sub-condition is fulfilled and an AI / ML model for RLF prediction provides as the output of an inference function an indication of a higher likelihood of RLF.

[0531] In some embodiments, the UE may be configured with a CHO execution condition comprising the first condition (at least as described above) and a second condition, both associated by a logical operator “OR”. The UE may consider the CHO execution condition fulfilled when either the first condition is fulfilled OR the second condition is fulfilled. The second condition may be characterized as follows:

[0532] (first sub-condition of the second condition, the same as first sub-condition of the first condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a duration defined by a time to trigger (e.g. TTT, configured at the UE) AND

[0533] (second sub-condition of second condition) likelihood of detecting RLF in source PCell is HIGH e.g. first sub-condition of the second condition is fulfilled while RLF timer is running.

[0534] According to this set of embodiments, the resulting CHO execution condition, including first and second conditions associated with logical operator “OR”, may be characterized as follows:

[0535] [ (first sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a first duration defined by a time to trigger (e.g. TTT, configured at the UE) AND (second sub-condition) the prediction of a neighbour cell measurement quantity (e.g. predicted RSRP) is a second offset better than the measurement quantity of the prediction of the PCell measurement quantity (e.g. predicted RSRP), for a number of future time instances (e.g. F, configured at the UE) or for a second duration defined by a prediction time horizon (e.g., T2, configured at the UE).]

[0536] OR

[0537] [(first sub-condition of the second condition, the same as first sub-condition of the first condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a duration defined by a time to trigger (e.g. TTT, configured at the UE) AND (second sub-condition of second condition) likelihood of detecting RLF in source PCell is HIGH e.g. first sub-condition of the second condition is fulfilled while RLF timer is running]

[0538] A3-like for measurement and low RLF likelihood for the neighbour cell

[0539] The CHO execution condition may be considered fulfilled upon fulfillment of a condition as follows:

[0540] (first sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a first duration defined by a time to trigger (e.g. TTT, configured at the UE) AND

[0541] (second sub-condition) the prediction of a neighbour cell measurement quantity (e.g. predicted RSRP) is above a threshold for a measurement quantity for a number of future time instances (e.g. F, configured at the UE) or for a second duration defined by a prediction time horizon (e.g., T2, configured at the UE).

[0542] The CHO execution condition may be considered fulfilled upon fulfillment of a condition as follows:

[0543] (first sub-condition) neighbour cell measurement quantity (e.g. RSRP) a first offset better than the PCell measurement quantity (e.g. RSRP), for a duration defined by a time to trigger (e.g. TTT, configured at the UE) AND

[0544] (second sub-condition) the low RLF prediction of a neighbour cell.

[0545] Further details about the prediction information corresponding to an RLF prediction

[0546] The term predictions of RLF related information (or likelihood of RLF) also comprises predictions of a handover failure, or, in more general terms, predictions of a failure related to a reconfiguration with sync procedure. For example, there could be an indication that a reconfiguration with sync failure may be declared, indication of the reason why a reconfiguration with sync failure may be declared (such as due to potential expiry of timer T304, potential MAC protocol problems due to a possibly reach of the maximum number of preamble transmission attempts, etc.), predictions of further details concerning reconfiguration with sync failure declaration such as predictions of beam-specific measurements (e.g. SSB specific measurements) used for random access resource selection as defined in the MAC specifications.

[0547] Predictions of RLF related information (or simply RLF predictions) may be performed by the UE according to configurations (i.e. fields and associated lEs containing further fields / parameters) included in a measConfig of IE MeasConfig. Alternatively, the predictions of RLF related information may be configured by a new field (e.g. called rlfPredConfig of IE RlfPredConfig) containing the configurations of predictions to be performed.

[0548] In this context, “predictions of RLF related information” corresponds to at least one of these (or any combination of them):

[0549] - At least one indication that an RLF may be declared; o That indication may comprise a flag (e.g. that may be set to TRUE or FALSE, or something like that); o That indication may comprise an associated time information, indicating when the RLF may occur; o In the case of multiple indications, that may be a list (or equivalent structure like a SEQUENCE) of indications, for different time instances. In the case of multiple indications, that may be a list of indications for different time instances to indicate whether RLF is predicted to occur at a given point in time. For example, a list like this one [true true true true false] indicates that RLF is predicted to occur from the first time instance until the fourth, but not at the fifth. o That indication may comprise a probability value indicating how likely is that RLF is going to be declared;

[0550] - At least one indication of the reason an RLF may possibly be declared according to the prediction; that may comprise at least one of the following; o Physical layer problems; Expiry of timer T310; MAC protocol problems, due to a possibly reach of the maximum number of preamble transmission attempts, or any other random access problems; Radio Link Control (RLC) problems due to a possibly reach of the maximum number of retransmissions); Expiry of timer T304; MAC protocol problems with a target cell while timer T304 is running, e.g., if UE would reach a maximum number of preamble transmission attempts.

[0551] Predictions of further details concerning RLF declaration such as at least one of the following, for a particular possible problem: o Predictions related to the physical layer, such as at least one of the following: Predictions of the occurrence(s) of Out-of-Sync (OOS) events or In-Sync (IS) events; Predictions of the SI NR measurement used as input to determine an OOS event or IS event, etc.; Predictions of when timer T310 is to expiry; or how much time would be left until that occurs; Predictions of when N310 is to reach its maximum value (according to the configuration); Predictions of measurements (e.g. SINR of the SpCell) that is used as input to indicate that an OOS event or IS event is declared.

[0552] Information concerning an ongoing RLF declaration procedure (not necessarily a prediction, but rather a state information), such as: o Related to PHY layer:

[0553] ■ An indication related to timer T310;

[0554] • In one embodiment, that indication is indicating that timer T310 is running, if running; In one embodiment, that indication is the remaining time left for timer T310 to expiry, if running; In one embodiment, that indication is how much time has already passed since T310 has started, if running;

[0555] ■ An indication related for N310

[0556] • In one embodiment, that indication is indicating that timer N310 has started to get counted, if it has; In one embodiment, that indication is the number of OOS events left for reaching the maximum number for N310; In one embodiment, that indication is the number of OOS events that have occurred (indicating how close to maximum value N310 it is);

[0557] ■ An indication related for N311 (similar to N310); o Related to MAC layer:

[0558] ■ An indication related to number of preamble transmissions;

[0559] • In one embodiment, that indication is indicating that UE is performing random access (i.e. it has transmitted at least one preamble and / or at least one retransmission); In one embodiment, that indication is indicating the number of preamble transmissions left for reaching the maximum number of attempts; In one embodiment, that indication is indicating the number of preamble transmissions that occurred, as another way to indicate how far from reaching the maximum number of attempts the UE is when the information is reported; o Related to RLC layer:

[0560] ■ An indication related to number of RLC transmissions;

[0561] • In one embodiment, that indication is indicating that UE is performing RLC retransmissions; In one embodiment, that indication is indicating the number of RLC retransmissions left for reaching the maximum number of retransmissions; In one embodiment, that indication is indicating the number of RLC retransmissions that occurred, as another way to indicate how far from reaching the maximum number of RLC retransmissions the UE is when the information is reported;

[0562] In another embodiment predictions of RLF related information may be performed for a neighbour cell (e.g. in a serving frequency or in a neighbour frequency), e.g., when RLF predictions are used as input to the CHO execution conditions.

[0563] In another embodiment predictions of RLF related information are performed for a best neighbour in serving frequencies (e.g. if configured).

[0564] One aspect of the present disclosure relates to how the UE derives predictions of RLF related information e.g. which inputs are used, which models, etc. Some possible ways to derive predictions of RLF related information are described below. Possible parameters that may be used by the prediction model are also described below.

[0565] Al / ML model for RLF prediction

[0566] There may be different possibilities related to how the prediction of RLF related information is performed at the UE e.g. choice of the prediction model used by the UE.

[0567] The UE may receive a prediction model / function from the network (e.g., from a network node). The prediction model may be implemented as a software function that is provided from the network to the UE, for example, in a procedure where the UE downloads this software function. An alternative solution relies on Application Protocol Interfaces (APIs) that are exposed by the UE to the network, so an entity at the network side is able to configure a prediction model at the UE. In that case, there could be a procedure where the UE indicates to the network a capability related information i.e. UE indicates to the network that it can download I receive a prediction model from the network (for example, for mobility prediction information) according to the method. This capability may be related to the software and hardware aspects at the UE, availability of sensors, etc. Once the UE has the function available, it may be further configured by the network to use it e.g. in a measurement configuration like reporting configuration, measurement object configuration, RLF configuration, RLM configuration, etc.

[0568] The network may take different input from the UE to make a decision concerning the prediction model to provide the UE and / or its configurations. For example, a network node (e.g., a BS or a cloud) may receive UEs’ measurement reports and use them to train a neural network (NN), or the network can use RLF reports and information within (indicating that RLF has occurred at some point in time). To train the NN, one can use as input to the NN signal measurements (e.g., RSRP, RSRQ or SINR) at instant “t”, and / or RLF reports, and as output, the indication of whether RLF occurs or not at instant “t+X”. Thus, the NN would be able to predict if RLF occurs or not, “X” instants of time in advance. Since a NN can be characterized by the number of layers, number of nodes per layer and the nodes’ weights, after the training process, the network node broadcasts to the UEs the NN parameters in order to allow the UEs to reconstruct the NN and use it to predict future occurrences of RLF. Since this is an example of supervised learning, from time to time, the network node updates the NN weights based on new UEs’ measurement reports and / or RLF reports. The predicted values at instant “t” can be compared to the actual RLF occasions at instant “t+X” (if any) in order to validate if the NN accuracy and to force, if necessary, the NN weights update.

[0569] The method may also comprise the possibility to rely on federated learning (FL). A group of UEs may download the model and train (e.g., SGD) the model with their local data (RSRP, etc) on device. After a certain time, UEs can send their trained model to the network and then network can take the average.

[0570] The method may comprise an alternative where the UE has stored a prediction model / function (e.g., UE proprietary prediction model) to perform the RLF related prediction(s). In that case, there could be a procedure where the UE indicates to the network a capability related to that i.e. indicate that it can perform a certain prediction according to the method (e.g. prediction of RLF related information). A capability may be reported to the network in different levels of granularity such as i) UE has a prediction model and / or ii) which exact prediction model the UE has available, e.g., out of a list defined in the specifications and / or iii) which kinds of predictions the model(s) the UE has available performs and / or iv) what kinds of input the model(s) the UE has available take into account, etc.

[0571] The method may comprise an alternative where it is standardized at least one prediction model to be implemented at the UE and configured by the network, with a set of parameters. Many possibilities can be considered, for example: a NN (the UE already knows that it will implement a NN of “L” layers, where each layer “i” has “Ni” nodes, and each node “j” has a set of weights “Wj”, but the values of “L”, “Ni” and “Wj” are set by the network. Another possible model could be a Random Forest, where the network must set the number of estimators (trees in the forest), the depth of each tree and the threshold of each leaf. A capability may be reported to the network in different levels of granularity such as i) UE has a prediction model and / or ii) which exact prediction model the UE has available, e.g., out of a list defined in the specifications and / or iii) which kinds of predictions the model(s) the UE has available performs and / or iv) what kinds of input the model(s) the UE has available take into account, etc.

[0572] When it comes to the exact prediction model, it may be considered that a radio link usually has less chance of being in a failure condition than of being in good conditions. So, one may consider this when preparing the data to be used to train a model, if a supervised learning method is going to be used. Otherwise, if there is not a good balance between failure and success, the model might be biased for one of the radio link states.

[0573] If the expected output is fail or success, traditional prediction models may be used and / or also classification ones. Regarding prediction model, it may be a feed-forward Neural Network, where the inputs could be (but are not restrict to) current and / or predicted signal quality (e.g., RSRP, RSRQ, SI NR) of serving and / or neighbor BSs / SSBs, current and / or predicted value of T310 and OOS, etc. Regarding classification models, e.g., Support Vector Machines (SVM) and K-nearest neighbor (KNN) may be used. The main idea of these models is to cluster data based on similar features into groups and then map new data to these formed groups.

[0574] The method may also comprise the usage of different prediction models, based on different set of parameters known at the UE.

[0575] The method may comprise the usage of “real / current measurements” as input parameters for the RLF related prediction model (e.g., RSRP, RSRQ, SI NR at a certain point in time TO for the same cells the UE perform predictions, based on an RS type like SSB and / or CSI-RS and / or DRMS), either instantaneous values or filtered values (e.g. with L3 filter parameters configured by RRC) from the serving and / or neighbor cells and / or serving or neighbour beams.

[0576] The method may comprise the usage of parameters from sensors, such as UE positioning information (e.g. GPS coordinates, barometric sensor information or other indicators of height), rotation sensors, proximity sensors, and mobility such as, location information, previous connected BSs history, speed and mobility direction, information from mapping / guiding applications (e.g. Google maps, Apple maps).

[0577] The method may comprise the usage of metrics related to UE connection, such as average package delay. The UE may also use input from sensors such as rotation, movement, etc. UE uses some route information (e.g. current location, final destination and route) as input.

[0578] The method may comprise the usage of UE mobility history information such as last visited beams, last visited cells, last visited tracking areas, last visited registration areas, last visited RAN areas, last visited PLMNs, last visited countries, last visited cities, last visited states, etc.

[0579] The method may comprise the usage of time information such as the current time (e.g. 10:15 am) and associated time zone (e.g. 10:15 GMT). That may be relevant if the UE has a predictable trajectory and it is typical that at a certain time the UE is in a certain location.

[0580] The method may comprise any RLF related variable at time instance to to predict the possible occurrence of RLF at time instance tO+k*T such as at least one of the following (or any combination):

[0581] Related to PHY layer: o An indication related to timer T310, indicating one or more of: that timer T310 is running, if running; and / or the remaining time left for timer T310 to expiry, if running; how much time has already passed since T310 has started, if running; o An indication related for N310, indicating one or more of: that timer N310 has started to get counted, if it has; the number of OOS events left for reaching the maximum number for N310; the number of OOS events that have occurred (indicating how close to maximum value N310 it is); o An indication related for N311 (similar to N310);

[0582] Related to MAC layer: o An indication related to number of preamble transmissions, indicating one or more of: that UE is performing random access (i.e. it has transmitted at least one preamble and / or at least one retransmission); the number of preamble transmissions left for reaching the maximum number of attempts; the number of preamble transmissions that occurred, as another way to indicate how far from reaching the maximum number of attempts the UE is when the information is reported;

[0583] Related to RLC layer: o An indication related to number of RLC transmissions, indicating one or more of: that UE is performing RLC retransmissions; the number of RLC retransmissions left for reaching the maximum number of retransmissions; the number of RLC retransmissions that occurred, as another way to indicate how far from reaching the maximum number of RLC retransmissions the UE is when the information is reported.

[0584] Fig. 18 shows an example of a communication system 1800 in accordance with some embodiments.

[0585] In the example, the communication system 1800 includes a telecommunication network 1802 that includes an access network 1804, such as a radio access network (RAN), and a core network 1806, which includes one or more core network nodes 1808. The access network 1804 includes one or more access network nodes, such as access network nodes 1810a and 1810b (which are interchangeably referred to as RAN network nodes 1810 herein), or any other similar 3rdGeneration Partnership Project (3GPP) access node or non-3GPP access point (AP). Moreover, as will be appreciated by those of skill in the art, a RAN network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 1802 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 1802 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 1802, including one or more network nodes 1810 and / or core network nodes 1808.

[0586] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O- CU user plane (O-CU-UP), a RAN intelligent controller (RIC) (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1 , F1 , W1 , E1 , E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies.

[0587] The access network nodes 1810 facilitate direct or indirect connection of wireless devices (also referred to interchangeably herein as user equipment (UE)), such as by connecting UEs 1812a, 1812b, 1812c, and 1812d (one or more of which may be generally referred to as UEs 1812) to the core network 1806 over one or more wireless connections. The access network nodes 1810 may be, for example, access points (APs) (e.g. radio access points), base stations (BSs) (e.g. radio base stations, Node Bs, evolved Node Bs (eNBs) and New Radio (NR) NodeBs (gNBs)).

[0588] Unless otherwise indicated, the general term ‘network node’ as used herein refers to access network nodes 1810 and core network nodes 1808.

[0589] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 1800 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 1800 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0590] The wireless devices / UEs 1812 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1810 and other communication devices. Similarly, the access network nodes 1810 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 1812 and / or with other network nodes or equipment in the telecommunication network 1802 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 1802.

[0591] In the depicted example, the core network 1806 connects the access network nodes 1810 to one or more hosts, such as host 1816. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1806 includes one more core network nodes (e.g. core network node 1808) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the wireless devices / UEs, access network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 1808. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (ALISF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0592] The host 1816 may be under the ownership or control of a service provider other than an operator or provider of the access network 1804 and / or the telecommunication network 1802, and may be operated by the service provider or on behalf of the service provider. The host 1816 may host a variety of applications to provide one or more services. Examples of such applications include the provision of live and / or pre-recorded audio / video content, data collection services, for example, retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0593] As a whole, the communication system 1800 of Fig. 18 enables connectivity between the wireless devices / UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2ndGeneration (2G), 3rdGeneration (3G), 4thGeneration (4G), 5thGeneration (5G) standards, or any applicable future generation standard (e.g. 6thGeneration (6G)); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0594] In some examples, the telecommunication network 1802 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 1802 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 1802. For example, the telecommunications network 1802 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive Internet of Things (loT) services to yet further UEs.

[0595] In some examples, the UEs 1812 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 1804 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1804. Additionally, a UE may be configured for operating in single- or multi-radio access technology (RAT) or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved- UTRA (UMTS Terrestrial Radio Access) Network) New Radio - Dual Connectivity (EN-DC).

[0596] In the example illustrated in Fig. 18, the hub 1814 communicates with the access network 1804 to facilitate indirect communication between one or more UEs (e.g. UE 1812c and / or 1812d) and access network nodes (e.g. access network node 1810b). In some examples, the hub 1814 may be a controller, router, a content source and analytics node, or any of the other communication devices described herein regarding UEs. For example, the hub 1814 may be a broadband router enabling access to the core network 1806 for the UEs. As another example, the hub 1814 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 1810, or by executable code, script, process, or other instructions in the hub 1814. As another example, the hub 1814 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1814 may be a content source. For example, for a UE that is a Virtual Reality VR headset, display, loudspeaker or other media delivery device, the hub 1814 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1814 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1814 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy Internet of Things (loT) devices.

[0597] The hub 1814 may have a constant / persistent or intermittent connection to the network node 1810b. The hub 1814 may also allow for a different communication scheme and / or schedule between the hub 1814 and UEs (e.g. UE 1812c and / or 1812d), and between the hub 1814 and the core network 1806. In other examples, the hub 1814 is connected to the core network 1806 and / or one or more UEs via a wired connection. Moreover, the hub 1814 may be configured to connect to a Machine-to-Machine (M2M) service provider over the access network 1804 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1810 while still connected via the hub 1814 via a wired or wireless connection. In some embodiments, the hub 1814 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 1810b. In other embodiments, the hub 1814 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1810b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0598] Fig. 19 shows a wireless device or UE 1900 in accordance with some embodiments.

[0599] As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a wireless device / UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless camera, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0600] A wireless device / UE may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to- everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g. a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g. a smart power meter).

[0601] The UE 1900 includes processing circuitry 1902 that is operatively coupled via a bus 1904 to an input / output interface 1906, a power source 1908, a memory 1910, a communication interface 1912, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Fig. 19. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc. The processing circuitry 1902 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 1910. The processing circuitry 1902 may be implemented as one or more hardware-implemented state machines (e.g. in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 1902 may include multiple central processing units (CPUs). The processing circuitry 1902 may be operable to provide, either alone or in conjunction with other UE 1900 components, such as the memory 1910, to provide UE 1900 functionality. For example, the processing circuitry 1902 may be configured to cause the UE 1902 to perform the methods as described with reference to Fig. W1.

[0602] In the example, the input / output interface 1906 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 1900. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g. a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0603] In some embodiments, the power source 1908 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g. an electricity outlet), photovoltaic device, or power cell, may be used. The power source 1908 may further include power circuitry for delivering power from the power source 1908 itself, and / or an external power source, to the various parts of the UE 1900 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 1908. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 1908 to make the power suitable for the respective components of the UE 1900 to which power is supplied.

[0604] The memory 1910 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 1910 includes one or more application programs 1914, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1916. The memory 1910 may store, for use by the UE 1900, any of a variety of various operating systems or combinations of operating systems.

[0605] The memory 1910 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a Universal Subscriber Identity Module (USIM) and / or integrated SIM (ISIM), other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUlCC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 1910 may allow the UE 1900 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to offload data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 1910, which may be or comprise a device- readable storage medium.

[0606] The processing circuitry 1902 may be configured to communicate with an access network or other network using the communication interface 1912. The communication interface 1912 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1922. The communication interface 1912 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g. another UE or a network node in an access network). Each transceiver may include a transmitter 1918 and / or a receiver 1920 appropriate to provide network communications (e.g. optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1918 and receiver 1920 may be coupled to one or more antennas (e.g. antenna 1922) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0607] In some embodiments, communication functions of the communication interface 1912 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) or other Global Navigation Satellite System (GNSS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11 , Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, NR, UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0608] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 1912, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g. once every 15 minutes if it reports the sensed temperature), random (e.g. to even out the load from reporting from several sensors), in response to a triggering event (e.g. when moisture is detected an alert is sent), in response to a request (e.g. a user initiated request), or a continuous stream (e.g. a live video feed of a patient).

[0609] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or controls a robotic arm performing a medical procedure according to the received input.

[0610] A UE, when in the form of an loT device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are devices which are or which are embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a head-mounted display for Augmented Reality (AR) or VR, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence on the intended application of the loT device in addition to other components as described in relation to the UE 1900 shown in Fig. 19.

[0611] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-loT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0612] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0613] Fig. 20 shows an access network node 2000 or RAN network node 2000 in accordance with some embodiments.

[0614] As used herein, access network node or RAN network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other RAN network nodes or equipment or core network nodes, in a telecommunication network. Examples of access network nodes include, but are not limited to, access network nodes such as APs (e.g. radio access points), base stations (BSs) (e.g. radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), Open RAN (O-RAN) nodes or components of an O- RAN node (e.g., O-RU, O-DU, O-CU)..

[0615] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A RAN network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node), and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0616] Other examples of access network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g. Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0617] The RAN network node 2000 includes processing circuitry 2002, a memory 2004, a communication interface 2006, and a power source 2008, and / or any other component, or any combination thereof. The RAN network node 2000 may be composed of multiple physically separate components (e.g. a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the RAN network node 2000 comprises multiple separate components (e.g. BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the RAN network node 2000 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g. separate memory 2004 for different RATs) and some components may be reused (e.g. a same antenna 2010 may be shared by different RATs). The RAN network node 2000 may also include multiple sets of the various illustrated components for different wireless technologies integrated into RAN network node 2000, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within RAN network node 2000.

[0618] The processing circuitry 2002 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other RAN network node 2000 components, such as the memory 2004, to provide network node 2000 functionality. For example, the processing circuitry 2002 may be configured to cause the RAN network node to perform the methods as described with reference to Fig. W2.

[0619] In some embodiments, the processing circuitry 2002 includes a system on a chip (SOC). In some embodiments, the processing circuitry 2002 includes one or more of radio frequency (RF) transceiver circuitry 2012 and baseband processing circuitry 2014. In some embodiments, the radio frequency (RF) transceiver circuitry 2012 and the baseband processing circuitry 2014 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 2012 and baseband processing circuitry 2014 may be on the same chip or set of chips, boards, or units.

[0620] The memory 2004 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 2002. The memory 2004 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 2002 and utilized by the RAN network node 2000. The memory 2004 may be used to store any calculations made by the processing circuitry 2002 and / or any data received via the communication interface 2006. In some embodiments, the processing circuitry 2002 and memory 2004 is integrated.

[0621] The communication interface 2006 is used in wired or wireless communication of signalling and / or data between network nodes, the access network, the core network, and / or a UE. As illustrated, the communication interface 2006 comprises port(s) / terminal(s) 2016 to send and receive data, for example to and from a network over a wired connection.

[0622] The communication interface 2006 also includes radio front-end circuitry 2018 that may be coupled to, or in certain embodiments a part of, the antenna 2010. Radio front-end circuitry 2018 comprises filters 2020 and amplifiers 2022. The radio front-end circuitry 2018 may be connected to an antenna 2010 and processing circuitry 2002. The radio front-end circuitry may be configured to condition signals communicated between antenna 2010 and processing circuitry 2002. The radio front-end circuitry 2018 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 2018 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 2020 and / or amplifiers 2022. The radio signal may then be transmitted via the antenna 2010. Similarly, when receiving data, the antenna 2010 may collect radio signals which are then converted into digital data by the radio front-end circuitry 2018. The digital data may be passed to the processing circuitry 2002. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0623] In certain alternative embodiments, the access network node 2000 does not include separate radio front-end circuitry 2018, instead, the processing circuitry 2002 includes radio frontend circuitry and is connected to the antenna 2010. Similarly, in some embodiments, all or some of the RF transceiver circuitry 2012 is part of the communication interface 2006. In still other embodiments, the communication interface 2006 includes one or more ports or terminals 2016, the radio front-end circuitry 2018, and the RF transceiver circuitry 2012, as part of a radio unit (not shown), and the communication interface 2006 communicates with the baseband processing circuitry 2014, which is part of a digital unit (not shown).

[0624] The antenna 2010 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 2010 may be coupled to the radio front-end circuitry 2018 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 2010 is separate from the network node 2000 and connectable to the RAN network node 2000 through an interface or port.

[0625] The antenna 2010, communication interface 2006, and / or the processing circuitry 2002 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 2010, the communication interface 2006, and / or the processing circuitry 2002 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0626] The power source 2008 provides power to the various components of RAN network node 2000 in a form suitable for the respective components (e.g. at a voltage and current level needed for each respective component). The power source 2008 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 2000 with power for performing the functionality described herein. For example, the RAN network node 2000 may be connectable to an external power source (e.g. the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 2008. As a further example, the power source 2008 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0627] Embodiments of the RAN network node 2000 may include additional components beyond those shown in Fig. 20 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the RAN network node 2000 may include user interface equipment to allow input of information into the RAN network node 2000 and to allow output of information from the RAN network node 2000. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the RAN network node 2000.

[0628] Fig. 21 is a block diagram illustrating a virtualization environment 2100 in which functions implemented by some embodiments may be virtualized.

[0629] In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 2100 hosted by one or more of hardware nodes, such as a hardware computing device that operates as an access network node, a wireless device / UE, a core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g. a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 2100 includes components defined by the Open-RAN (O-RAN) Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface.

[0630] Applications 2102 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 2100 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0631] Hardware 2104 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 2106 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 2108a and 2108b (one or more of which may be generally referred to as VMs 2108), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 2106 may present a virtual operating platform that appears like networking hardware to the VMs 2108.

[0632] The VMs 2108 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 2106. Different embodiments of the instance of a virtual appliance 2102 may be implemented on one or more of VMs 2108, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0633] In the context of NFV, a VM 2108 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 2108, and that part of hardware 2104 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs 2108 on top of the hardware 2104 and corresponds to the application 2102.

[0634] Hardware 2104 may be implemented in a standalone network node with generic or specific components. Hardware 2104 may implement some functions via virtualization. Alternatively, hardware 2104 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 2110, which, among others, oversees lifecycle management of applications 2102. In some embodiments, hardware 2104 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signalling can be provided with the use of a control system 2112 which may alternatively be used for communication between hardware nodes and radio units.

[0635] Although the computing devices described herein (e.g. UEs, RAN network nodes, core network node, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0636] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device- readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0637] The foregoing merely illustrates the principles of the disclosure. Various modifications and alterations to the described embodiments will be apparent to those skilled in the art in view of the teachings herein. It will thus be appreciated that those skilled in the art will be able to devise numerous systems, arrangements, and procedures that, although not explicitly shown or described herein, embody the principles of the disclosure and can be thus within the scope of the disclosure. Various exemplary embodiments can be used together with one another, as well as interchangeably therewith, as should be understood by those having ordinary skill in the art. The following numbered statements set out various optional embodiments for this disclosure:

[0638] Group A Embodiments (UE)

[0639] 1. A method performed by a user equipment, UE, being served by a first cell, the method comprising: receiving (VV102) a conditional handover, CHO, execution condition, wherein the CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell.

[0640] 2. The method of embodiment 1 , wherein the method further comprises: evaluating the CHO execution condition for the second cell.

[0641] 3. The method of any preceding embodiment, wherein the method further comprises: responsive to determining that the CHO execution condition is satisfied by the second cell, determining to execute a CHO from the first cell to the second cell.

[0642] 4. The method of any preceding embodiment, wherein the method further comprises: responsive to determining that the CHO execution condition is not satisfied by the second cell, determining to maintain connection with the first cell.

[0643] 5. The method of any preceding embodiment, wherein the CHO execution condition further comprises a measurement sub-condition that is to be evaluated with respect to at least one measurement of the first cell and / or at least one measurement of the second cell.

[0644] 6. The method of embodiment 5, wherein the CHO execution condition is satisfied if both the measurement sub-condition is satisfied and the prediction sub-condition is satisfied.

[0645] 7. The method of embodiment 5, wherein the CHO execution condition is satisfied if either the measurement sub-condition is satisfied or the prediction sub-condition is satisfied.

[0646] 8. The method of embodiment 5, wherein the CHO execution condition is satisfied if: both the measurement sub-condition is satisfied and the prediction sub-condition is satisfied; or both the measurement sub-condition is satisfied and a likelihood of detecting Radio Link Failure, RLF, in the first cell is high. 9. The method of embodiment 8, wherein the likelihood of detecting RLF in the first cell is considered high if the measurement sub-condition is satisfied while an RLF timer is running.

[0647] 10. The method of any of embodiments 5-9, wherein the measurement sub-condition is satisfied if the at least one measurement of the second cell is a first offset better than the at least one measurement of the first cell.

[0648] 11. The method of any of embodiments 5-10, wherein the measurement sub-condition is satisfied if the at least one measurement of the second cell is a first offset better than the at least one measurement of the first cell for at least a time to trigger, TTT, time period.

[0649] 12. The method of any of embodiments 5-11 , wherein the at least one measurement of the first cell comprises one or more of: a signal strength value; a quality value; a cell identifier; a Reference Signal Received Power, RSRP; a Reference Signal Received Quality, RSRQ; a Signal to Interference plus Noise Ratio, SINR; a beam index; a beam identifier; and a Synchronization Signal Block, SSB, index.

[0650] 13. The method of any of embodiments 5-12, wherein the at least one measurement of the second cell comprises one or more of: a signal strength value; a quality value; a cell identifier; a Reference Signal Received Power, RSRP; a Reference Signal Received Quality, RSRQ; a Signal to Interference plus Noise Ratio, SINR; a beam index; a beam identifier; and a Synchronization Signal Block, SSB, index.

[0651] 14. The method of any preceding embodiment, wherein the prediction sub-condition is satisfied if the time-domain prediction information for the second cell indicates that a measurement quantity of the second cell will be a second offset better than the measurement quantity of the first cell during at least a first future time window or for at least a first number of future time instances.

[0652] 15. The method of any preceding embodiment, wherein the prediction sub-condition is satisfied if the time-domain prediction information for the second cell indicates that a measurement quantity of the second cell will be above a threshold during at least a second future time window or for at least a second number of future time instances. 16. The method of any of embodiments 1-13, wherein the prediction sub-condition is satisfied if a likelihood of detecting Radio Link Failure, RLF, in the second cell is low.

[0653] 17. The method of embodiment 16, wherein the likelihood of detecting RLF in the second cell is considered low if the measurement sub-condition is not satisfied while an RLF timer is running.

[0654] 18. The method of any preceding embodiment, wherein the time-domain prediction information for the second cell is based on, or comprises, at least one time-domain prediction of a measurement of the first cell and / or at least one time-domain prediction of a measurement of the second cell.

[0655] 19. The method of any previous embodiment, wherein the time-domain prediction information for the second cell comprises one or more of: a predicted signal strength or quality value for the second cell at a future time instance or during a future time window; a predicted cell identifier for the second cell at a future time instance or during a future time window; a cell identifier based on a predicted signal strength or quality value for the second cell at a future time instance or during a future time window; a predicted Reference Signal Received Power, RSRP, of the second cell at a future time instance or during a future time window; a predicted Reference Signal Received Quality, RSRQ, of the second cell at a future time instance or during a future time window; a predicted Signal to Interference plus Noise Ratio, SI NR, of the second cell at a future time instance or during a future time window; a predicted beam index and / or beam identifier of the second cell at a future time instance or during a future time window; a predicted Synchronization Signal Block, SSB, index of the second cell at a future time instance or during a future time window; a corresponding confidence indicator of a predicted measurement for the second cell; a corresponding time duration for which a predicted measurement for the second cell is expected to be valid; and a corresponding time duration for which a predicted measurement for the second cell is expected to satisfy a condition. 20. The method of any preceding embodiment, wherein the time-domain prediction information for the second cell is based on a prediction for fulfilment of an event trigger for the second cell.

[0656] 21 . The method of embodiment 20, wherein the event trigger comprises an event or condition that triggers transmission by the UE of measurements of the second cell, and / or an event or condition that triggers conditional handover of the UE to the second cell.

[0657] 22. The method of embodiment 20 or 21 , wherein the time-domain prediction information for the second cell comprises one or more of: a flag indicating that the event trigger is predicted to remain fulfilled; an indication of a period of time for which the event trigger is predicted to remain fulfilled; and a cell identifier of the second cell as the cell which triggered the event.

[0658] 23. The method of any preceding embodiment, wherein the time-domain prediction information for the second cell is based on a difference between a prediction of a measurement of the second cell and a prediction of a measurement of the first cell.

[0659] 24. The method of any preceding embodiment, wherein the time-domain prediction information for the second cell comprises one or more of: a difference between a predicted signal strength or quality value for the second cell at a future time instance and a predicted signal strength or quality value for the first cell at the future time instance; a cell identifier based on a difference between a predicted signal strength or quality value for the second cell at a future time instance and a predicted signal strength or quality value for the first cell at the future time instance; a predicted measurement quantity difference between the measurement quantity of the second cell and the measurement quantity of the first cell at a future time instance; a cell identifier based on a predicted measurement quantity difference between the measurement quantity of the second cell and the measurement quantity of the first cell at a future time instance; a corresponding confidence indicator for the predicted difference; a corresponding confidence indicator for the cell identifier; a corresponding time duration for which the predicted difference is expected to be valid; a corresponding time duration for which the cell identifier is expected to be valid; and a corresponding time duration for which the predicted difference is expected to satisfy a condition.

[0660] 25. The method of any preceding embodiment, wherein the time-domain prediction information for the second cell comprises one or more of: a predicted signal strength or quality value for the first cell at a future time instance or during a future time window; a predicted cell identifier for the first cell at a future time instance or during a future time window; a cell identifier for the first cell based on a predicted signal strength or quality value for the first cell at a future time instance or during a future time window; a predicted Reference Signal Received Power, RSRP, of the first cell at a future time instance or during a future time window; a predicted Reference Signal Received Quality, RSRQ, of the first cell at a future time instance or during a future time window; a predicted Signal to Interference plus Noise Ratio, SINR, of the first cell at a future time instance or during a future time window; a predicted beam index and / or beam identifier of the first cell at a future time instance or during a future time window; a predicted Synchronization Signal Block, SSB, index of the first cell at a future time instance or during a future time window; a corresponding confidence indicator of a predicted value for the first cell; a corresponding time duration for which a predicted value for the first cell is expected to be valid; and a corresponding time duration for which a predicted value for the first cell is expected to satisfy a condition.

[0661] 26. The method of any preceding embodiment, wherein the method further comprises: determining the time-domain prediction information for the second cell.

[0662] 27. The method of embodiment 26, wherein the time-domain prediction information for the second cell is determined using a machine learning model.

[0663] 28. The method of embodiment 27, wherein determining the time-domain prediction information for the second cell comprises inputting one or more measurements of the second cell and / or one or more measurements of the first cell into the machine learning model. 29. The method of any preceding embodiment, wherein the second cell is configured as a candidate CHO cell for the UE.

[0664] 30. The method of any preceding embodiment, wherein the second cell is one or more of: an intra-frequency neighbour cell; an inter-frequency neighbour cell; a neighbour cell on the same Synchronization Signal Block, SSB, frequency as the first cell; a neighbour cell on a different SSB frequency to the first cell; a neighbour cell on a serving frequency; a neighbour cell on a serving frequency selected based on at least one measurement of the second cell; a neighbour cell on a serving frequency selected based on the time-domain prediction information for the second cell; a cell of the same network node as the first cell; and a cell of a different network node to the first cell.

[0665] 31 . The method of any preceding embodiment, wherein the CHO execution condition is a trigger condition upon fulfilment of which the UE determines to execute a CHO handover.

[0666] 32. The method of any preceding embodiment, wherein the first cell is a cell of a source network node.

[0667] 33. The method of embodiment 32, wherein the CHO execution condition is received from the source network node.

[0668] 34. The method of any preceding embodiment, wherein the method further comprises: executing the CHO to the second cell if the CHO execution condition is satisfied by the second cell.

[0669] 35. The method of any preceding embodiment, wherein the method further comprises: maintaining connection with the first cell if the CHO execution condition is not satisfied by the second cell.

[0670] Group B Embodiments (source network node)

[0671] 36. A method performed by a source network node, wherein a user equipment, UE, is being served by a first cell of the source network node, the method comprising: transmitting (W202), to the UE, a conditional handover, CHO, execution condition, wherein the CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell. 37. The method of embodiment 36, wherein the CHO execution condition further comprises a measurement sub-condition that is to be evaluated with respect to at least one measurement of the first cell and / or at least one measurement of the second cell.

[0672] 38. The method of embodiment 37, wherein the CHO execution condition is satisfied if both the measurement sub-condition is satisfied and the prediction sub-condition is satisfied.

[0673] 39. The method of embodiment 37, wherein the CHO execution condition is satisfied if either the measurement sub-condition is satisfied or the prediction sub-condition is satisfied.

[0674] 40. The method of embodiment 37, wherein the CHO execution condition is satisfied if: both the measurement sub-condition is satisfied and the prediction sub-condition is satisfied; or both the measurement sub-condition is satisfied and a likelihood of detecting Radio Link Failure, RLF, in the first cell is high.

[0675] 41. The method of embodiment 40, wherein the likelihood of detecting RLF in the first cell is considered high if the measurement sub-condition is satisfied while an RLF timer is running.

[0676] 42. The method of any of embodiments 37-41 , wherein the measurement sub-condition is satisfied if the at least one measurement of the second cell is a first offset better than the at least one measurement of the first cell.

[0677] 43. The method of any of embodiments 37-43, wherein the measurement sub-condition is satisfied if the at least one measurement of the second cell is a first offset better than the at least one measurement of the first cell for at least a time to trigger, TTT, time period.

[0678] 44. The method of any of embodiments 37-43, wherein the at least one measurement of the first cell comprises one or more of: a signal strength value; a quality value; a cell identifier; a Reference Signal Received Power, RSRP; a Reference Signal Received Quality, RSRQ; a Signal to Interference plus Noise Ratio, SINR; a beam index; a beam identifier; and a Synchronization Signal Block, SSB, index.

[0679] 45. The method of any of embodiments 37-44, wherein the at least one measurement of the second cell comprises one or more of: a signal strength value; a quality value; a cell identifier; a Reference Signal Received Power, RSRP; a Reference Signal Received Quality, RSRQ; a Signal to Interference plus Noise Ratio, SINR; a beam index; a beam identifier; and a Synchronization Signal Block, SSB, index.

[0680] 46. The method of any of embodiments 36-45, wherein the prediction sub-condition is satisfied if the time-domain prediction information for the second cell indicates that a measurement quantity of the second cell will be a second offset better than the measurement quantity of the first cell during at least a first future time window or for at least a first number of future time instances.

[0681] 47. The method of any of embodiments 36-46, wherein the prediction sub-condition is satisfied if the time-domain prediction information for the second cell indicates that a measurement quantity of the second cell will be above a threshold during at least a second future time window or for at least a second number of future time instances.

[0682] 48. The method of any of embodiments 36-47, wherein the prediction sub-condition is satisfied if a likelihood of detecting Radio Link Failure, RLF, in the second cell is low.

[0683] 49. The method of embodiment 48, wherein the likelihood of detecting RLF in the second cell is considered low if the measurement sub-condition is not satisfied while an RLF timer is running.

[0684] 50. The method of any of embodiments 36-49, wherein the time-domain prediction information for the second cell is based on, or comprises, at least one time-domain prediction of a measurement of the first cell and / or at least one time-domain prediction of a measurement of the second cell.

[0685] 51 . The method of any of embodiments 36-50, wherein the time-domain prediction information for the second cell comprises one or more of: a predicted signal strength or quality value for the second cell at a future time instance or during a future time window; a predicted cell identifier for the second cell at a future time instance or during a future time window; a cell identifier based on a predicted signal strength or quality value for the second cell at a future time instance or during a future time window; a predicted Reference Signal Received Power, RSRP, of the second cell at a future time instance or during a future time window; a predicted Reference Signal Received Quality, RSRQ, of the second cell at a future time instance or during a future time window; a predicted Signal to Interference plus Noise Ratio, SI NR, of the second cell at a future time instance or during a future time window; a predicted beam index and / or beam identifier of the second cell at a future time instance or during a future time window; a predicted Synchronization Signal Block, SSB, index of the second cell at a future time instance or during a future time window; a corresponding confidence indicator of a predicted measurement for the second cell; a corresponding time duration for which a predicted measurement for the second cell is expected to be valid; and a corresponding time duration for which a predicted measurement for the second cell is expected to satisfy a condition.

[0686] 52. The method of any of embodiments 36-51 , wherein the time-domain prediction information for the second cell is based on a prediction for fulfilment of an event trigger for the second cell.

[0687] 53. The method of embodiment 52, wherein the event trigger comprises an event or condition that triggers transmission by the UE of measurements of the second cell, and / or an event or condition that triggers conditional handover of the UE to the second cell.

[0688] 54. The method of embodiment 52 or 53, wherein the time-domain prediction information for the second cell comprises one or more of: a flag indicating that the event trigger is predicted to remain fulfilled; an indication of a period of time for which the event trigger is predicted to remain fulfilled; and a cell identifier of the second cell as the cell which triggered the event.

[0689] 55. The method of any of embodiments 36-54, wherein the time-domain prediction information for the second cell is based on a difference between a prediction of a measurement of the second cell and a prediction of a measurement of the first cell.

[0690] 56. The method of any of embodiments 36-55, wherein the time-domain prediction information for the second cell comprises one or more of: a difference between a predicted signal strength or quality value for the second cell at a future time instance and a predicted signal strength or quality value for the first cell at the future time instance; a cell identifier based on a difference between a predicted signal strength or quality value for the second cell at a future time instance and a predicted signal strength or quality value for the first cell at the future time instance; a predicted measurement quantity difference between the measurement quantity of the second cell and the measurement quantity of the first cell at a future time instance; a cell identifier based on a predicted measurement quantity difference between the measurement quantity of the second cell and the measurement quantity of the first cell at a future time instance; a corresponding confidence indicator for the predicted difference; a corresponding confidence indicator for the cell identifier; a corresponding time duration for which the predicted difference is expected to be valid; a corresponding time duration for which the cell identifier is expected to be valid; and a corresponding time duration for which the predicted difference is expected to satisfy a condition.

[0691] 57. The method of any of embodiments 36-56, wherein the time-domain prediction information for the second cell comprises one or more of: a predicted signal strength or quality value for the first cell at a future time instance or during a future time window; a predicted cell identifier for the first cell at a future time instance or during a future time window; a cell identifier for the first cell based on a predicted signal strength or quality value for the first cell at a future time instance or during a future time window; a predicted Reference Signal Received Power, RSRP, of the first cell at a future time instance or during a future time window; a predicted Reference Signal Received Quality, RSRQ, of the first cell at a future time instance or during a future time window; a predicted Signal to Interference plus Noise Ratio, SINR, of the first cell at a future time instance or during a future time window; a predicted beam index and / or beam identifier of the first cell at a future time instance or during a future time window; a predicted Synchronization Signal Block, SSB, index of the first cell at a future time instance or during a future time window; a corresponding confidence indicator of a predicted value for the first cell; a corresponding time duration for which a predicted value for the first cell is expected to be valid; and a corresponding time duration for which a predicted value for the first cell is expected to satisfy a condition.

[0692] 58. The method of any of embodiments 36-57, wherein the second cell is configured as a candidate CHO cell for the UE.

[0693] 59. The method of any of embodiments 36-58, wherein the second cell is one or more of: an intra-frequency neighbour cell; an inter-frequency neighbour cell; a neighbour cell on the same Synchronization Signal Block, SSB, frequency as the first cell; a neighbour cell on a different SSB frequency to the first cell; a neighbour cell on a serving frequency; a neighbour cell on a serving frequency selected based on at least one measurement of the second cell; a neighbour cell on a serving frequency selected based on the time-domain prediction information for the second cell; a cell of the same network node as the first cell; and a cell of a different network node to the first cell.

[0694] 60. The method of any of embodiments 36-59, wherein the CHO execution condition is a trigger condition upon fulfilment of which the UE determines to execute a CHO handover.

[0695] 61 . The method of any of embodiments 36-60, wherein the first cell is a cell of a source network node.

[0696] Group C Embodiments

[0697] 62. A computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform the method of any of the Group A embodiments or the Group B embodiments.

[0698] 63. A user equipment, UE, configured to perform the method of any of the Group A embodiments. 64. A user equipment, UE, comprising a processor and a memory, said memory containing instructions executable by said processor whereby said UE is operative to perform the method of any of the Group A embodiments.

[0699] 65. A first radio access network, RAN, node, configured to perform the method of any of the Group B embodiments.

[0700] 66. A first radio access network, RAN, node comprising a processor and a memory, said memory containing instructions executable by said processor whereby said first RAN node is operative to perform the method of any of the Group B embodiments.

[0701] 67. A user equipment, UE, comprising: processing circuitry configured to cause the user equipment to perform any of the steps of any of the Group A embodiments; and power supply circuitry configured to supply power to the processing circuitry.

[0702] 68. A network node, the network node comprising: processing circuitry configured to cause the network node to perform any of the steps of any of the Group B embodiments; power supply circuitry configured to supply power to the processing circuitry.

[0703] 69. A user equipment, UE, the UE comprising: an antenna configured to send and receive wireless signals; radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry; the processing circuitry being configured to perform any of the steps of any of the Group A embodiments; an input interface connected to the processing circuitry and configured to allow input of information into the UE to be processed by the processing circuitry; an output interface connected to the processing circuitry and configured to output information from the UE that has been processed by the processing circuitry; and a battery connected to the processing circuitry and configured to supply power to the UE.

Claims

CLAIMS1. A method performed by a user equipment, UE, being served by a first cell, the method comprising: receiving (702) a conditional handover, CHO, execution condition, wherein the CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell.

2. The method of claim 1 , wherein the method further comprises: evaluating the CHO execution condition for the second cell.

3. The method of any preceding claim, wherein the method further comprises: responsive to determining that the CHO execution condition is satisfied by the second cell, determining to execute a CHO from the first cell to the second cell.

4. The method of any preceding claim, wherein the method further comprises: responsive to determining that the CHO execution condition is not satisfied by the second cell, determining to maintain connection with the first cell.

5. The method of any preceding claim, wherein the CHO execution condition further comprises a measurement sub-condition that is to be evaluated with respect to at least one measurement of the first cell and / or at least one measurement of the second cell.

6. The method of claim 5, wherein the CHO execution condition is satisfied if both the measurement sub-condition is satisfied and the prediction sub-condition is satisfied.

7. The method of claim 5, wherein the CHO execution condition is satisfied if either the measurement sub-condition is satisfied or the prediction sub-condition is satisfied.

8. The method of claim 5, wherein the CHO execution condition is satisfied if: both the measurement sub-condition is satisfied and the prediction sub-condition is satisfied; or both the measurement sub-condition is satisfied and a likelihood of detecting Radio Link Failure, RLF, in the first cell is high.

9. The method of claim 8, wherein the likelihood of detecting RLF in the first cell is considered high if the measurement sub-condition is satisfied while an RLF timer is running.

10. The method of any of claims 5-9, wherein the measurement sub-condition is satisfied if the at least one measurement of the second cell is a first offset better than the at least one measurement of the first cell.

11. The method of any of claims 5-10, wherein the measurement sub-condition is satisfied if the at least one measurement of the second cell is a first offset better than the at least one measurement of the first cell for at least a time to trigger, TTT, time period.

12. The method of any of claims 5-11 , wherein the at least one measurement of the first cell comprises one or more of: a signal strength value; a quality value; a cell identifier; a Reference Signal Received Power, RSRP; a Reference Signal Received Quality, RSRQ; a Signal to Interference plus Noise Ratio, SINR; a beam index; a beam identifier; and a Synchronization Signal Block, SSB, index.

13. The method of any of claims 5-12, wherein the at least one measurement of the second cell comprises one or more of: a signal strength value; a quality value; a cell identifier; a Reference Signal Received Power, RSRP; a Reference Signal Received Quality, RSRQ; a Signal to Interference plus Noise Ratio, SINR; a beam index; a beam identifier; and a Synchronization Signal Block, SSB, index.

14. The method of any preceding claim, wherein the prediction sub-condition is satisfied if the time-domain prediction information for the second cell indicates that a measurement quantity of the second cell will be a second offset better than the measurement quantity of the first cell during at least a first future time window or for at least a first number of future time instances.

15. The method of any preceding claim, wherein the prediction sub-condition is satisfied if the time-domain prediction information for the second cell indicates that a measurement quantity of the second cell will be above a threshold during at least a second future time window or for at least a second number of future time instances.

16. The method of any of claims 1-13, wherein the prediction sub-condition is satisfied if a likelihood of detecting Radio Link Failure, RLF, in the second cell is low.

17. The method of claim 16, wherein the likelihood of detecting RLF in the second cell is considered low if the measurement sub-condition is not satisfied while an RLF timer is running.

18. The method of any preceding claim, wherein the time-domain prediction information for the second cell is based on, or comprises, at least one time-domain prediction of a measurement of the first cell and / or at least one time-domain prediction of a measurement of the second cell.

19. The method of any previous claim, wherein the time-domain prediction information for the second cell comprises one or more of: a predicted signal strength or quality value for the second cell at a future time instance or during a future time window; a predicted cell identifier for the second cell at a future time instance or during a future time window; a cell identifier based on a predicted signal strength or quality value for the second cell at a future time instance or during a future time window; a predicted Reference Signal Received Power, RSRP, of the second cell at a future time instance or during a future time window; a predicted Reference Signal Received Quality, RSRQ, of the second cell at a future time instance or during a future time window; a predicted Signal to Interference plus Noise Ratio, SI NR, of the second cell at a future time instance or during a future time window; a predicted beam index and / or beam identifier of the second cell at a future time instance or during a future time window; a predicted Synchronization Signal Block, SSB, index of the second cell at a future time instance or during a future time window; a corresponding confidence indicator of a predicted measurement for the second cell; a corresponding time duration for which a predicted measurement for the second cell is expected to be valid; and a corresponding time duration for which a predicted measurement for the second cell is expected to satisfy a condition.

20. The method of any preceding claim, wherein the time-domain prediction information for the second cell is based on a prediction for fulfilment of an event trigger for the second cell.

21. The method of claim 20, wherein the event trigger comprises an event or condition that triggers transmission by the UE of measurements of the second cell, and / or an event or condition that triggers conditional handover of the UE to the second cell.

22. The method of claim 20 or 21 , wherein the time-domain prediction information for the second cell comprises one or more of: a flag indicating that the event trigger is predicted to remain fulfilled; an indication of a period of time for which the event trigger is predicted to remain fulfilled; and a cell identifier of the second cell as the cell which triggered the event.

23. The method of any preceding claim, wherein the time-domain prediction information for the second cell is based on a difference between a prediction of a measurement of the second cell and a prediction of a measurement of the first cell.

24. The method of any preceding claim, wherein the time-domain prediction information for the second cell comprises one or more of: a difference between a predicted signal strength or quality value for the second cell at a future time instance and a predicted signal strength or quality value for the first cell at the future time instance; a cell identifier based on a difference between a predicted signal strength or quality value for the second cell at a future time instance and a predicted signal strength or quality value for the first cell at the future time instance; a predicted measurement quantity difference between the measurement quantity of the second cell and the measurement quantity of the first cell at a future time instance; a cell identifier based on a predicted measurement quantity difference between the measurement quantity of the second cell and the measurement quantity of the first cell at a future time instance; a corresponding confidence indicator for the predicted difference; a corresponding confidence indicator for the cell identifier; a corresponding time duration for which the predicted difference is expected to be valid; a corresponding time duration for which the cell identifier is expected to be valid; and a corresponding time duration for which the predicted difference is expected to satisfy a condition.

25. The method of claim 18 or 23, wherein the prediction of a measurement of the first cell comprises one or more of: a predicted signal strength or quality value for the first cell at a future time instance or during a future time window; a predicted cell identifier for the first cell at a future time instance or during a future time window; a cell identifier for the first cell based on a predicted signal strength or quality value for the first cell at a future time instance or during a future time window; a predicted Reference Signal Received Power, RSRP, of the first cell at a future time instance or during a future time window; a predicted Reference Signal Received Quality, RSRQ, of the first cell at a future time instance or during a future time window; a predicted Signal to Interference plus Noise Ratio, SINR, of the first cell at a future time instance or during a future time window; a predicted beam index and / or beam identifier of the first cell at a future time instance or during a future time window; a predicted Synchronization Signal Block, SSB, index of the first cell at a future time instance or during a future time window; a corresponding confidence indicator of a predicted value for the first cell; a corresponding time duration for which a predicted value for the first cell is expected to be valid; and a corresponding time duration for which a predicted value for the first cell is expected to satisfy a condition.

26. The method of any preceding claim, wherein the method further comprises: determining the time-domain prediction information for the second cell.

27. The method of claim 26, wherein the time-domain prediction information for the second cell is determined using a machine learning model.

28. The method of claim 27, wherein determining the time-domain prediction information for the second cell comprises inputting one or more measurements of the second cell and / or one or more measurements of the first cell into the machine learning model.

29. The method of any preceding claim, wherein the second cell is configured as a candidate CHO cell for the UE.

30. The method of any preceding claim, wherein the second cell is one or more of: an intrafrequency neighbour cell; an inter-frequency neighbour cell; a neighbour cell on the same Synchronization Signal Block, SSB, frequency as the first cell; a neighbour cell on a different SSB frequency to the first cell; a neighbour cell on a serving frequency; a neighbour cell on a serving frequency selected based on at least one measurement of the second cell; a neighbour cell on a serving frequency selected based on the time-domain prediction information for the second cell; a cell of the same network node as the first cell; and a cell of a different network node to the first cell.

31. The method of any preceding claim, wherein the CHO execution condition is a trigger condition upon fulfilment of which the UE determines to execute a CHO handover.

32. The method of any preceding claim, wherein the first cell is a cell of a source network node.

33. The method of claim 32, wherein the CHO execution condition is received from the source network node.

34. The method of any preceding claim, wherein the method further comprises: executing the CHO to the second cell if the CHO execution condition is satisfied by the second cell.

35. The method of any preceding claim, wherein the method further comprises: maintaining connection with the first cell if the CHO execution condition is not satisfied by the second cell.

36. A method performed by a source network node, wherein a user equipment, UE, is being served by a first cell of the source network node, the method comprising: transmitting (802), to the UE, a conditional handover, CHO, execution condition, wherein the CHO execution condition comprises a prediction sub-condition that is to be evaluated with respect to time-domain prediction information for a second cell.

37. A computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform the method of any of claims 1-35.

38. A user equipment, UE, configured to perform the method of any of claims 1-35.

39. A user equipment, UE, comprising a processor and a memory, said memory containing instructions executable by said processor whereby said UE is operative to perform the method of any of claims 1-35.

40. A first radio access network, RAN, node, configured to perform the method of claim 36.

41. A first radio access network, RAN, node comprising a processor and a memory, said memory containing instructions executable by said processor whereby said first RAN node is operative to perform the method of claim 36.

Images