Indirect radio link failure prediction method

Abstract

An apparatus configured to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; and transmit, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

Description

INDIRECT RADIO LINK FAILURE PREDICTION METHODTECHNICAL FIELD

[0001] The example and non-limiting embodiments relate generally to radio link failure handling and, more particularly, to prediction of radio link failure based on predicted measurements of a quality of a radio link channel.BACKGROUND

[0002] It is known, in radio link failure prediction, to train an artificial intelligence (Al) and / or machine learning (ML) model to predict radio link failures directly based on one or more radio link failure configurations.SUMMARY

[0003] The following summary is merely intended to be illustrative. The summary is not intended to limit the scope of the claims.

[0004] In accordance with one aspect, an apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed with the at least one processor, cause the apparatus at least to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; and transmit, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0005] In accordance with one aspect, a method comprising: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and transmitting, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window ofpredicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0006] In accordance with one aspect, an apparatus comprising means for: predicting at least one radio link failure based, at least partially, on one or more predicted measurements; and transmitting, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0007] In accordance with one aspect, a computer-readable medium comprising program instructions stored thereon for performing at least the following: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and causing transmitting, to a network node, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0008] In accordance with one aspect, an apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed with the at least one processor, cause the apparatus at least to: receive, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handle the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0009] In accordance with one aspect, a method comprising: receiving, with a network node from a user equipment, a radio link failure prediction report, wherein the radio link failureprediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0010] In accordance with one aspect, an apparatus comprising means for: receiving, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0011] In accordance with one aspect, a computer-readable medium comprising program instructions stored thereon for performing at least the following: causing receiving, with a network node from a user equipment, of a radio link failure prediction report, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0012] In accordance with one aspect, an apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed with the at least one processor, cause the apparatus at least to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; transmit, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failureprediction; and receive, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0013] In accordance with one aspect, a method comprising: predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; transmitting, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and receiving, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0014] In accordance with one aspect, an apparatus comprising means for: predicting at least one radio link failure based, at least partially, on one or more predicted measurements; transmitting, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and receiving, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0015] In accordance with one aspect, a computer-readable medium comprising program instructions stored thereon for performing at least the following: predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; causing transmitting, to a user equipment, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and causing receiving, from the user equipment, of an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0016] According to some aspects, there is provided the subject matter of the independent claims. Some further aspects are defined in the dependent claims.BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The foregoing aspects and other features are explained in the following description, taken in connection with the accompanying drawings, wherein:

[0018] FIG. 1 is a block diagram of one possible and non-limiting example system in which the example embodiments may be practiced;

[0019] FIGs. 2-3 are diagrams illustrating features as described herein;

[0020] FIG. 4 is a flowchart illustrating steps as described herein;

[0021] FIG. 5 is a diagram illustrating features as described herein;

[0022] FIGS. 6A and 6B are charts illustrating features as described herein; and

[0023] FIGs. 7-15 are flowcharts illustrating steps as described herein.DETAILED DESCRIPTION OF EMBODIMENTS

[0024] The following abbreviations that may be found in the specification and / or the drawing figures are defined as follows:Al artificial intelligenceAMF access and mobility management functionBFR beam failure recoveryBHO baseline handoverBLER block error rateCHO conditional handoverCI confidence intervalCNN convolutional neural networkCU central unitDU distributed unit gNB (or gNodeB) base station for 5G / NR, i.e., a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface to the 5GCHO handoverHOF handover failureLTM L1 / L2 triggered mobilityML machine learningNN neural network oos out of syncRLC radio link controlRLF radio link failureRLM radio link monitoringRRM radio resource managementRS reference signalRSRP reference signal received powerRSRQ reference signal received qualityRx receiverSINR signal to interference plus noise ratioSMF session management functionSRS sounding reference signalTx transmitterUE user equipment (e.g., a wireless, typically mobile device)

[0025] Turning to FIG. 1 , this figure shows a block diagram of one possible and non-limiting example in which the examples may be practiced. A user equipment (UE) 110, radio accessnetwork (RAN) node 170, and network element(s) 190 are illustrated. In the example of FIG. 1, the user equipment (UE) 110 is in wireless communication with a wireless network 100. A UE is a wireless device that can access the wireless network 100. The UE 110 includes one or more processors 120, one or more memories 125, and one or more transceivers 130 interconnected through one or more buses 127. Each of the one or more transceivers 130 includes a receiver, Rx, 132 and a transmitter, Tx, 133. The one or more buses 127 may be address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, and the like. A “circuit” may include dedicated hardware or hardware in association with software executable thereon. The one or more transceivers 130 are connected to one or more antennas 128. The one or more memories 125 include computer program code 123. The UE 110 includes a module 140, comprising one of or both parts 140-1 and / or 140-2, which may be implemented in a number of ways. The module 140 may be implemented in hardware as module 140-1, such as being implemented as part of the one or more processors 120. The module 140-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the module 140 may be implemented as module 140-2, which is implemented as computer program code 123 and is executed by the one or more processors 120. For instance, the one or more memories 125 and the computer program code 123 may be configured to, with the one or more processors 120, cause the user equipment 110 to perform one or more of the operations as described herein. The UE 110 communicates with RAN node 170 via a wireless link 111.

[0026] The RAN node 170 in this example is a base station that provides access by wireless devices such as the UE 110 to the wireless network 100. The RAN node 170 may be, for example, a base station for 5G, also called New Radio (NR). In 5G, the RAN node 170 may be a NG-RAN node, which is defined as either a gNB or a ng-eNB. A gNB is a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface to a 5GC (such as, for example, the network element(s) 190). The ng-eNB is a node providing E- UTRA user plane and control plane protocol terminations towards the UE, and connected via the NG interface to the 5GC. The NG-RAN node may include multiple gNBs, which may also include a central unit (CU) (gNB-CU) 196 and distributed unit(s) (DUs) (gNB-DUs), of which DU 195 isshown. Note that the DU may include or be coupled to and control a radio unit (RU). The gNB- CU is a logical node hosting RRC, SDAP and PDCP protocols of the gNB or RRC and PDCP protocols of the en-gNB that controls the operation of one or more gNB-DUs. The gNB-CU terminates the Fl interface connected with the gNB -DU. The Fl interface is illustrated as reference 198, although reference 198 also illustrates a link between remote elements of the RAN node 170 and centralized elements of the RAN node 170, such as between the gNB-CU 196 and the gNB-DU 195. The gNB-DU is a logical node hosting RLC, MAC and PHY layers of the gNB or en-gNB, and its operation is partly controlled by gNB-CU. One gNB-CU supports one or multiple cells. One cell is supported by only one gNB-DU. The gNB-DU terminates the Fl interface 198 connected with the gNB-CU. Note that the DU 195 is considered to include the transceiver 160, e.g., as part of a RU, but some examples of this may have the transceiver 160 as part of a separate RU, e.g., under control of and connected to the DU 195. The RAN node 170 may also be an eNB (evolved NodeB) base station, for LTE (long term evolution), or any other suitable base station, access point, access node, or node.

[0027] The RAN node 170 includes one or more processors 152, one or more memories 155, one or more network interfaces (N / W I / F(s)) 161, and one or more transceivers 160 interconnected through one or more buses 157. Each of the one or more transceivers 160 includes a receiver, Rx, 162 and a transmitter, Tx, 163. The one or more transceivers 160 are connected to one or more antennas 158. The one or more memories 155 include computer program code 153. The CU 196 may include the processor(s) 152, memories 155, and network interfaces 161. Note that the DU 195 may also contain its own memory / memories and processor(s), and / or other hardware, but these are not shown.

[0028] The RAN node 170 includes a module 150, comprising one of or both parts 150-1 and / or 150-2, which may be implemented in a number of ways. The module 150 may be implemented in hardware as module 150-1, such as being implemented as part of the one or more processors 152. The module 150-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the module 150 may be implemented as module 150-2, which is implemented as computer program code 153 and is executed by the one or more processors 152. For instance, the one or more memories 155 and thecomputer program code 153 are configured to, with the one or more processors 152, cause the RAN node 170 to perform one or more of the operations as described herein. Note that the functionality of the module 150 may be distributed, such as being distributed between the DU 195 and the CU 196, or be implemented solely in the DU 195.

[0029] The one or more network interfaces 161 communicate over a network such as via the links 176 and 131. Two or more gNBs 170 may communicate using, e.g., link 176. The link 176 may be wired or wireless or both and may implement, for example, an Xn interface for 5G, an X2 interface for LTE, or other suitable interface for other standards.

[0030] The one or more buses 157 may be address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, wireless channels, and the like. For example, the one or more transceivers 160 may be implemented as a remote radio head (RRH) 195 for LTE or a distributed unit (DU) 195 for gNB implementation for 5G, with the other elements of the RAN node 170 possibly being physically in a different location from the RRH / DU, and the one or more buses 157 could be implemented in part as, for example, fiber optic cable or other suitable network connection to connect the other elements (e.g., a central unit (CU), gNB-CU) of the RAN node 170 to the RRH / DU 195. Reference 198 also indicates those suitable network link(s).

[0031] It is noted that description herein indicates that “cells” perform functions, but it should be clear that equipment which forms the cell will perform the functions. The cell makes up part of a base station. That is, there can be multiple cells per base station. For example, there could be three cells for a single carrier frequency and associated bandwidth, each cell covering one-third of a 360 degree area so that the single base station’s coverage area covers an approximate oval or circle. Furthermore, each cell can correspond to a single carrier and a base station may use multiple carriers. So if there are three 120 degree cells per carrier and two carriers, then the base station has a total of 6 cells.

[0032] The wireless network 100 may include a network element or elements 190 that may include core network functionality, and which provides connectivity via a link or links 181 with a further network, such as a telephone network and / or a data communications network (e.g., the Internet). Such core network functionality for 5G may include access and mobility management function(s) (AMF(s)) and / or user plane functions (UPF(s)) and / or session management function(s) (SMF(s)). Such core network functionality for LTE may include MME (Mobility Management Entity) / SGW (Serving Gateway) functionality. These are merely illustrative functions that may be supported by the network element(s) 190, and note that both 5G and LTE functions might be supported. The RAN node 170 is coupled via a link 131 to a network element 190. The link 131 may be implemented as, e.g., an NG interface for 5G, or an SI interface for LTE, or other suitable interface for other standards. The network element 190 includes one or more processors 175, one or more memories 171, and one or more network interfaces (N / W I / F(s)) 180, interconnected through one or more buses 185. The one or more memories 171 include computer program code 173. The one or more memories 171 and the computer program code 173 are configured to, with the one or more processors 175, cause the network element 190 to perform one or more operations.

[0033] The wireless network 100 may implement network virtualization, which is the process of combining hardware and software network resources and network functionality into a single, software -based administrative entity, a virtual network. Network virtualization involves platform virtualization, often combined with resource virtualization. Network virtualization is categorized as either external, combining many networks, or parts of networks, into a virtual unit, or internal, providing network-like functionality to software containers on a single system. For example, a network may be deployed in a tele cloud, with virtualized network functions (VNF) running on, for example, data center servers. For example, network core functions and / or radio access network(s) (e.g. CloudRAN, O-RAN, edge cloud) may be virtualized. Note that the virtualized entities that result from the network virtualization are still implemented, at some level, using hardware such as processors 152 or 175 and memories 155 and 171, and also such virtualized entities create technical effects.

[0034] It may also be noted that operations of example embodiments of the present disclosure may be carried out by a plurality of cooperating devices (e.g. cRAN).

[0035] The computer readable memories 125, 155, and 171 may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The computer readable memories 125, 155, and 171 may be means for performing storage functions. The processors 120, 152, and 175 may be of any type suitable to the local technical environment, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on a multicore processor architecture, as non-limiting examples. The processors 120, 152, and 175 may be means for performing functions, such as controlling the UE 110, RAN node 170, and other functions as described herein.

[0036] In general, the various example embodiments of the user equipment 110 can include, but are not limited to, cellular telephones such as smart phones, tablets, personal digital assistants (PDAs) having wireless communication capabilities, portable computers having wireless communication capabilities, image capture devices such as digital cameras having wireless communication capabilities, gaming devices having wireless communication capabilities, music storage and playback appliances having wireless communication capabilities, Internet appliances permitting wireless Internet access and browsing, tablets with wireless communication capabilities, as well as portable units or terminals that incorporate combinations of such functions.

[0037] Having thus introduced one suitable but non-limiting technical context for the practice of the example embodiments of the present disclosure, example embodiments will now be described with greater specificity.

[0038] Features as described herein may generally relate to artificial intelligence (Al) and machine learning (ML), for example with respect to mobility in NR. AI / ML may comprise the use of models, for example neural networks, to determine information based on input. Example embodiments of the present disclosure may use Al model(s), ML model(s), and / or AI / ML model(s) to perform prediction. AI / ML may be used for predicting or determining radio resource management (RRM) measurements and event predictions as discussed in the 3GPP Rel. 19 SI. Forexample, for a UE sided model, handover (HO) failure and / or radio link failure (RLF) prediction may be performed using AI / ML. UE assistance information may be used for network side models.

[0039] RLF prediction may be based on temporal domain cell measurement predictions (e.g. SINR); future study may focus on RLF due to T310 expiry (i.e. in-synch / out-of-synch case) as the representative RLF case for direct and indirect prediction.

[0040] In the present disclosure “direct” may be used to refer to prediction of RLF based on one or more current measurements of radio link quality. In the present disclosure “indirect” may be used to refer to prediction of RLF based on one or more predicted measurements of radio link quality. Indirect prediction for RLF may comprise using AI / ML to predict RRM measurements, and detecting, estimating, or predicting RLF by using the predicted measurements. An indirect RLF procedure may be any procedure which involves first calculating an intermediate metric (e.g. predicted measurements), and then using that metric to predict RLF.

[0041] Features as described herein may generally relate to RLF detection, for example in 5G NR. There are various triggers for UE failure detection; some common ones are illustrated in FIG. 2. At 210, an out of sync (OOS) detection method is illustrated, where the UE may initiate out-of-sync indications when the radio link quality belonging to all the monitored reference signals is worse than Qout. This method may depend on Bler-out / Bler-in (targets), n310 / T310, and n311 / T311. At 220, a handover failure detection / T304 method is illustrated, where handover failure may be declared when the maximum waiting time for successful HO execution expires. At 230, a max UL radio link control (RLC) retransmission detection method is illustrated, where the UE may declare RLF when the maximum RLC retransmission is reached. This method may depend on ULPollingTimer, MaxULHARQTransNum, and MaxULRLCTrans. At 240, a random access procedure is illustrated, where a random access procedure may fail due to reaching the maximum number of preamble transmissions.

[0042] Example embodiments of the present disclosure may relate to the OOS UE detection method, where the UE's physical layer may send an OOS signal to the radio resource control (RRC) layer when the quality of all monitored reference signals drops below a certain level (Qout).

[0043] In the OOS UE detection method, the gNB may configure the UE with a pair of block error rate (BLER) targets: BLERout corresponds to a quality level (Qout) at which the radio link is categorized as being unreliable; and BLERin corresponds to a quality level (Qin) at which the radio link is considered reliable. 3GPP TS 38.133 specifies that Qout corresponds to a quality at which the BLER belonging to a hypothetical physical downlink control channel (PDCCH) transmission is worse than BLERout, i.e. PDCCH reception is not reliable.

[0044] Referring now to FIG. 3, illustrated is a signaling flow of RLF detection at a UE. In the example of FIG. 3, the UE lower layer may transmit, to the UE higher layer, out of sync indication(s) (310) N310 times (320). Then, during a time period measured by timer T310 (350), the UE lower layer may transmit, to the UE higher layer, in sync indication(s) (330) N311 times (340).

[0045] The UE RRC layer uses the OOS indications in combination with N310, T310 and N311 to detect radio link failure, where the timer T310 is started if the RRC layers receive N310 consecutive OOS indications. The timer T310 is stopped and reset if the RRC layer subsequently receives N311 consecutive in sync indications.

[0046] Radio link failure is detected if T310 expires, and the transmission of UL data is turned off after the timer t310 is expired. After T310 expiry, the UE may start a RLF reestablishment procedure. T311 governs the time the UE must reselect and access the gNB after the RLF has occurred, i.e., UE initiates RRC Connection Reestablishment Request. T301 governs the duration where the UE has to wait for a RRC Connection Reestablishment response from the gNB.

[0047] It may be noted that example embodiments of the present disclosure are not limited to the RLF detection procedure / configuration illustrated in FIG. 3. For example, different threshold values and / or timers, or a different number of threshold values and / or timers, may be used to determine whether RLF has, or will, occur.

[0048] The direct RLF prediction model usually relies on a classification approach, in which an ML model is trained with a dataset labelled with actual RLFs declared by the UEs. Such modelslearn to predict RLFs only for RLF configurations (Qin, Qout, N310, T310) that have been used in the training data. If the configuration is changed, a new training dataset may need to be collected, and a new ML model instance may have to be retrained.

[0049] Indirect RLF prediction uses processing of predicted measurements, for example comparing predicted radio link quality (e.g. SINR, samples (from L1 / L3 RSRP, RSRQ) versus Qout threshold), to predict RLFs. Although it may be potentially more challenging to reach sufficient accuracy, the indirect RLF prediction approach may enable reconfiguring of the configuration of the predicted RLFs without requiring model re-training. How to efficiently handle the predicted radio measurements from time domain at the UE and / or the NW is open for RLF determination. For example, it may need to be determined how to configure the UE to perform the indirect RLF prediction based on the predicted radio measurements. For example, it may need to be determined how the UE and / or the network should process time series radio measurements and determine the RLF status. For example, it may need to be determined how the gNB should manage the processing and prediction of RLF. For example, it may need to be determined what should be included in the RLF prediction report to encompass both the prediction and the actual radio link monitoring status.

[0050] In the present disclosure, the term “RLF status” may refer to whether or not a radio link channel is, or is expected to be, in a failure condition. In the present disclosure, the term “RLM status” may refer to monitoring of the quality of a radio link, for example by the UE. An example of poor radio link quality may be low signal strength, for example as measured by RSRP or RSRQ.

[0051] In an example embodiment, an indirect RLF prediction mechanism may be used based on predicted RRM measurements. RAN2 has agreed to investigate cell-level RRM measurement prediction using both UE-based and NW-based models. Example embodiments of the present disclosure may provide both UE-side and NW-side approaches.

[0052] In an example embodiment, a new RRC configuration and report may be applied for both UE-sided and NW-sided embodiments.

[0053] In an example embodiment, the new configuration message may comprise a new UE capability information flag to support the indirect RLF prediction based on predicted RRM measurements allowing changing the configuration of the predicted RLFs.

[0054] In an example embodiment, the network / gNB may configure the UE with RRC configuration parameters for executing indirect REF prediction.

[0055] In an example embodiment, a measurement prediction accuracy monitoring window (T_ML_monitor) may be configured, and may be used for ML reliability performance monitoring before the RLF evaluation by using predicted measurements. The effectiveness of RLF detection may hinge on the reliability of the underlying ML regression model. Therefore, careful configuration of this model may be paramount for accurate indirect prediction of RLF events. A technical effect of example embodiments of the present disclosure may be to provide reliable predicted measurements for decision making. In an example embodiment, the UE may be configured to perform the ML performance monitoring before the RLF evaluation by processing the predicted measurements. The UE may be configured to monitor the ML metric fEversus the network configured reliability threshold, thres_ML_Monitor within the monitoring time window T_ML_monitor. It may be assumed that the monitoring data set within this window is Devai).

[0056] In an example embodiment, the monitoring of the predicted measurements may be performed based, at least partially, on prediction accuracy: fE= (yi=Yi)> whereyi is the prediction and ytis the ground truth for the i-th sample. !(■) is the indicator function. In an example embodiment, the monitoring of the predicted measurements may be performed based, at least partially, on mean square error (MSE): fE= where ytis theprediction and ytis the ground truth for the i-th sample. In an example embodiment, the monitoring of the predicted measurements may be performed based, at least partially, on a (mean) confidence value: / EPi ■ where pLis the confidence score of the i-th prediction.As an example, the exact probabilistic value for pt may be obtained from the output of a softmax activation function in the output layer. In an example embodiment, the monitoring of the predicted measurements may be performed based, at least partially, on negative log likelihood: fE=pt is the confidence score of the i-th prediction.As an example, the exact probabilistic value for pLmay be obtained from the output of a softmax activation function in the output layer. Pr( ; = yt) denotes the model accuracy. In an example embodiment, the monitoring of the predicted measurements may be performed based, at least partially, on a confidence interval (CI). The CI may provide a range within which future observations are expected to fall with a certain probability. They may account for both the uncertainty in the model's prediction and the inherent variability of the data. A bootstrapping method may be used to calculate e.g., 95% CI.

[0057] In the present disclosure, the terms “confidence”, “accuracy”, and “reliability” may be used interchangeably. For example, the reliability of one or more predicted measurements may comprise, or be described using, a confidence score and / or an accuracy associated with an underlying AI / ML model.

[0058] Additionally or alternatively, the new configuration message may comprise a RLF evaluation window, which may comprise two parts. The first part of the time window T _evaluate _OOS) may account for evaluation of OOS indication N310 time, and the second part of the time window T_RLF_evaluate) may be configured for evaluation of RLF during T310 duration. N310 may refer to the evaluation of maximum number of Out-of-Sync (OOS) indication reception. T310 time duration may account for the RLF evaluation time based on the predicted SINR. These two time windows may be used to handle different aspects in RLF evaluation. T_evaluate_OOS may be used to detect if predicted SINR falls below Qout, and OOS indication processing time may be included. T_RLF_evaluate may ensure that predicted SINR is not higher than, for example, a Qin threshold for the maximum number of in sync indication (e.g. N311).

[0059] In an example embodiment, the configuration(s) of the measurement prediction accuracy monitoring window and the RLF evaluation window may have the technical effect of ensuring that the UE RLF prediction follows the same steps as the RLF detection procedure, but applied for a predicted radio link quality (instead of a measured radio link quality) with the flexibility to use different RRC IES and field values that are designed specifically for AI / ML purposes.

[0060] Additionally or alternatively, the new configuration message may comprise a measurement prediction window (T _predict) to output the predicted RRM measurements in timeseries. It may be that T _predict > T_evaluate_OOS + T_RLF _evaluate. This configuration of the measurement prediction window may have the technical effect of allowing the UE to report a predicted RLF within T_predict before the radio link quality falls below Qout threshold, thereby allowing the network to react earlier.

[0061] Alternatively, a positive time offset value T_offset may be configured by the network, a technical effect of which may be to ensure the prediction time window is relatively larger for the network to react upon reception of RLF prediction report. In this scenario, it may be that T _pr edict = T _evaluate _O OS + T_RLF_evaluate + T_offset.

[0062] Additionally or alternatively, the new configuration message may comprise other configuration parameters, for example a RLF prediction report format, UE behavior / actions, etc. In an example embodiment, the indirect RLF prediction report may at least include the legacy radio link monitoring (RLM) status (e.g., adding additional bits) so that the network may make, if needed, a more robust decision on the validity of the predicted RLF. In an example embodiment, the RLF prediction report may be a simple 2 bits indication, along with a time window T _pr edict. Alternatively, the RLF prediction report may be / comprise a compact N bits indication along with a time window T _predict. Alternatively, the RLF prediction report may be formulated as a triplet, such as {RLF prediction status, RLM actual status, ML reliability measure, i.e., RRM measurement accuracy in X% or confidence interval } .

[0063] In an example embodiment, the UE may indicate, to the serving gNB in the RLF prediction report, whether the timer T310 has started, for how long T310 has been running in absolute or percentage values, etc.

[0064] In the present disclosure, the term “window” may be used to refer to a time window, for example a period of time defined by a timer, or a time interval.

[0065] In an example embodiment, the network may provide a configuration of a threshold and time duration that may be used by the UE to assess whether an RLF is likely to occur basedon the predicted radio link quality (e.g., SINR). For example, the UE may be configured to detect RLF if the predicted radio link quality measurement is below a threshold for a certain time duration. In an example embodiment, the network may configure the UE to perform a simplified RLF detection method. In an example embodiment, the UE may be configured with a time window to predict the RLF status: T _predict = T310 + T_offset. For simplicity, only one time window may be used for prediction and RLF evaluation. In another example, T_predict may be set to a much shorter value than T310 + T_offset, a technical effect of which may be that the accuracy of the predicted measurement may remain high. In an example embodiment, the UE may be configured with a threshold to compare the predicted SINR: the legacy Qout threshold value may be used within a certain error margin, for example thres_RLF _predict = Qout ± offset.

[0066] Example embodiments of the present disclosure may use an (indirect) RLF prediction configuration that comprises parameters for multiple time windows (e.g. T_predict, T_ML_monitor, and RLF evaluation window) or, alternatively, an (indirect) RLF prediction configuration that comprises parameters for a single time window.

[0067] It may be noted that the indirect RLF prediction method highly relies on the RRM prediction results; the predicted measurement accuracy may be limited to the output window length, T _predict.

[0068] In an example embodiment, where RLF prediction may occur at the UE-side, the UE may behave as a host entity to perform the RRM measurement prediction, ML reliability performance monitoring, predicted measurement processing, RLF prediction detection, and / or RLF prediction reporting.

[0069] In an example embodiment, where RLF prediction may occur at the NW-side, the NW may behave as a host entity to perform the RRM measurement prediction, ML reliability performance monitoring, predicted measurement processing, RLF prediction detection, and / or RLF prediction reporting.

[0070] In an example embodiment, where RLF prediction may occur at the NW-side, inter- gNB coordination for failure prediction may be performed.

[0071] In an example embodiment, the RLF parameters, such as Qin, Qout, N310, N311, T310, and T312, may use the same parameters for the baseline RLF process and the parametrization of the predicted RLFs, or a different configuration using a different set of parameters may be provided for the two. There may be an additional reporting condition configured by the network, e.g., a confidence or probability threshold, for reporting a predicted RLF. This may be used to configure the trade-off between true and false positive prediction rates.

[0072] Referring now to FIG. 4, illustrated is an example of indirect RLF prediction. In an input data frame (405), L1 / L3 measurement data collection (410) may be performed. This may prepare the measurement data for the ML model. In one example, L3 cell level RSRP may be used for input. At 415, preprocessing and feature engineering may be performed. This may involve cleaning, transforming, and extracting relevant features from the raw measurement data.

[0073] In a ML module (420), input / preprocessed data may be fed into the ML model as a time series of radio measurements from a past window (425). At 430, the ML model, for example a convolutional neural network (CNN) or long short-term memory (LSTM) may be used to learn patterns and predict future radio measurements. CNNs are effective for spatial data and can capture local dependencies in the time series, while LSTMs are designed to handle sequential data and can capture long-term dependencies. At 435, the model may output a time series of predicted radio measurements for a future time window (T jiredict). In one example, the model may generate L3 cell level RSRP sequence in the time domain as output. Then, predicted RSRP processing may be required to generate serving cell SINR for RLF detection, as shown in FIGs. 5- 6. Alternatively, a time series serving cell SINR data frame may be generated explicitly from model.

[0074] In a ML monitoring module (440), the accuracy monitoring window (T_ML_monitor) (445) may begin. This phase may involve continuously monitoring the accuracy of the measurement predictions over a specific time window. The accuracy may be assessed (450) using various metrics, such as mean squared error, root mean squared error, or other relevant metrics to ensure the predictions are reliable. If the accuracy falls below a predefined threshold, the systemmay trigger alerts or initiate a process to re-evaluate and adjust the model (460). If the accuracy is sufficient, at 455 the predicted measurements may be applied.

[0075] In a RLF evaluation module (465), RLF detection (470) may be performed. The UE (or gNB) may evaluate whether the predicted measurements indicate any RLF within a specific evaluation window _RLF_evaluate). The RLF evaluation may consider the parametrization of the predicted RLFs.

[0076] At output (475), a RLF prediction report may be generated (480). Based on the RLF evaluation, the UE (or gNB) may generate a predicted RLE status based on the output of a measurement prediction model. As shown in EIG. 5, the output for RLE indicator may include both predicted RLE status and actual RLM status. Additionally, it may indicate a confidence or probability for a predicted RLE.

[0077] Referring now to EIG. 5, illustrated is an example of RLE detection based on L3 RSRP prediction. At 510, time domain RSRP prediction may be performed in a prediction time window T _predict [ms]. At 520, predicted SINR traces may be derived in a prediction time window T _predict [ms]. At 530, the RLE status may be determined in an RLE evaluation window [ms],

[0078] Referring now to EIGs. 6A and 6B, illustrated are examples of RLE detection base on L3 RSRP prediction (e.g. with 95% confidence interval). PIG. 6A illustrates the actual vs predicted RSRP for gNBs over time. PIG. 6B illustrates actual vs predicted SINR for the serving gNB over time.

[0079] Referring now to PIG. 7, illustrated is an example of indirect RLE prediction at the UE side. At 705, the UE may send its capability information to the gNB. This may include the support for AEML-based indirect RLF prediction. While not illustrated in FIG. 7, additional UE capability enquiry signaling from the gNB to the UE may be transmitted before the UE sends its capability information. At 710, the gNB may send the configuration details for the indirect RLF prediction to the UE. This may include information about time windows, triggering conditions, measurement prediction methods (e.g. prediction of SINR time series or prediction of RSRP timeseries then derive SINR), reporting requirements, and / or other potential actions that may be performed by the UE to mitigate / lighten RLF issues.

[0080] At 715, the UE may collect LI and L3 radio measurements for training, inference, monitoring, etc. under the current use case for indirect RLF prediction. At 720, the UE may use the collected measurements to predict future L1 / L3 RSRP or SINR time series according to the configure prediction time window T_predict in ms (725). At 730, the UE may continuously monitor the reliability of the ML model to ensure its measurement predictions are trustworthy. This may involve evaluating the ML metrics / Eversus the network configured reliability threshold, thres_ML_Monitor. This may be performed during time window T_ML_montior (735). At 740, the UE may continue monitoring the ML model reliability until the applied metricmeets the pre-defined conditions (e.g. versus / compared with threshold thres_ML_Monitor). This may ensure that the measurement predictions are accurate and reliable for use in RLF management.

[0081] At 745, the UE may generate the predicted serving cell SINR in time series by using predicted time domain RSRP data frame (e.g. as shown in FIGs. 6A-6B). This step may be optional if the measurement prediction model can directly output the time series SINR data frame at step 3 (720). At 750, the UE may detect if RLF occurs in the RLF evaluation window (755) based on the predicted serving cell SINR. If the predicted SINR falls below Qout threshold in the T_evaluate_OOS time window, and it will not increase above Qin threshold for a certain time duration / or number of samples within T_RLF_evaluate, the RLF prediction may hold true. Otherwise, the prediction of RLF may be considered / determined to be false. The UE may apply offsets to the configured Qin and Qout to align with the requested confidence or probability threshold for reporting a predicted RLF. This may be used to configure the trade-off between true and false positive prediction rates. It may be noted that the value of T_predict may be larger than the reception time of maximum number of N310 instances plus T310 duration, so that the processing of predicted SINR time frame may be evaluated versus the Qin threshold and the maximum number of in sync indication reception time.

[0082] At 760, the UE may send the RLF prediction report to the gNB for further actions to trigger failure handling. The report may include the prediction status, and may also include theactual radio link status. In an example embodiment, the RLF prediction report may be a simple 2 bits indication along with a time window T _predict. The first bit may indicate if the RLF prediction is true or false. The second bit may indicate the actual RLM status, e.g., 1 may mean the quality of an instantaneous radio link, e.g., SINR, is lower than a threshold, 0 may mean that the instantaneous SINR is higher than a threshold, etc. In another example embodiment, the RLF prediction report may be a compact N bits indication along with a time window T_predict. The first bit may indicate if the RLF prediction is true or false. The remaining N - 1 bits may indicate the actual radio link quality, where the instantaneous SINR may be compared and quantized against multiple thresholds. Additionally or alternatively, the UE may indicate to the serving gNB in the RLF prediction report whether the timer T310 has started, for how long T310 has been running in absolute or percentage values, etc. In another example embodiment, the RLF prediction report may be in another format (i.e. it may not be limited to a bitstring). For example, the RLF prediction report may comprise a triplet such as {RLF prediction status, RLM actual status, RRM measurement accuracy in X% } . In another example embodiment, the RLF prediction report may additionally contain the confidence or probability of the predicted RLF. In an example embodiment, RRC signaling may be used to convey the RLF prediction report. Alternatively, L1 / L2 signaling may be used, such as uplink control information (UCI) or MAC control element (CE). At 765, the gNB may initiate one or more actions for the failure handling.

[0083] Referring now to FIG. 8, illustrated is an example of indirect RLF prediction at the UE side, with network collaboration. For simplicity, description of FIG. 8 that overlaps with the description of FIG. 7 may be omitted.

[0084] Previously, UE-side RLF prediction relied solely on internal mechanisms, lacking network collaboration despite the network's ability to configure static RRC parameters for indirect RLF prediction. However, effective indirect RLF prediction hinges on accurate RRM measurement prediction before RLF detection. In an example embodiment, time constraints for UE-based indirect RLF prediction may be configured.

[0085] In an example embodiment, the network may participate in dynamic configuration adaptation during the ML monitoring window. A technical effect of example embodiments of the present disclosure may be to enhance prediction accuracy.

[0086] In an example embodiment, the UE may report RRM measurement prediction results, including the prediction window and ML metrics (e.g., accuracy within a 95% confidence interval), to the network. Based on this report, along with the configuration updating request, the network may assess the current configuration's viability, and may trigger updated indirect configurations for the UE. This may have the technical effect of improving RLF detection in subsequent procedures.

[0087] In an alternative example embodiment, the UE may adjust the parameters, weights, etc. of an AI / ML model used to predict measurements without receiving updated configuration parameters.

[0088] In the example of FIG. 8, at 805 the UE, based on its monitoring of the ML reliability conditions (step 4, 730), may send a request to the gNB to update the indirect RLF prediction configuration. This request may signal that the current configuration may not be optimal and / or may need adjustment. The UE may report RRM measurement prediction results, including the prediction window and / or ML metrics (e.g., accuracy in X% or 95% confidence interval), to the network. This may provide the gNB with data to analyze the effectiveness of the current configuration and make informed decisions about adjustments. The UE may also report the current status of the radio specific monitoring key performance indicators (KPIs). The KPIs may include accumulated radio KPIs, for example windowed throughput [kbps], packet loss percentage, number of PDUs received within a certain delay budget, etc. Additionally or alternatively, the KPIs may include mobility related counters, for example accumulated beam failure instances, running status of beam failure detection / recovery timer, number of received N310 or N311 indications, running status of T310 timer, etc.

[0089] At 810, the gNB may receive the configuration updating request from the UE. It may analyze the monitoring outcome (from step 4) to determine the cause of the ML reliability and / orradio performance issues. Based on this analysis, the gNB may prepare a new configuration for the indirect RLF prediction. This new configuration may involve adjustments to parameters like time windows, triggering thresholds, measurement prediction methods, or reporting intervals.

[0090] At 815, the gNB may send a response to the UE acknowledging the configuration updating request and providing the new configuration parameters. The UE may then update its internal configuration to reflect the new settings. This may have the technical effect of ensuring that the indirect RLF prediction process operates with the most appropriate parameters based on the current network conditions and ML model performance.

[0091] The process of collecting measurements (715), performing measurement prediction (720), monitoring the reliability of predicted measurements (730), and requesting and receiving updated RLF prediction configuration parameters (805, 815), may be repeated (820) until a condition for the predicted measurements is verified or met. Once the predicted measurements are suitable for RLF failure prediction according to one or more metrics included in the RLF prediction configuration, at 815 the UE may, optionally, generate generated predicted SINR traces from the RSRP prediction (see, e.g., 745). At 830, the UE may perform RLF prediction based on predicted (or derived) SINR traces during the RLF evaluation window (835) (see, e.g., 750). At 840, the UE may transmit, to the gNB, an RLF prediction report, which may include an RLF status (from prediction), and / or an RLM status (see, e.g., 760). At 845, the gNB may perform an action for RLF handling (see, e.g., 765).

[0092] Referring now to FIG. 9, illustrated is an example of indirect RLF prediction at the NW side. For simplicity, description of FIG. 9 that overlaps with the description of FIG. 7 may be omitted.

[0093] At 905, the UE may transmit, to the gNB, UE capability information, which may include an indication that the UE supports AI / ML based indirect RLF prediction (see, e.g., 705). At 910, the source gNB may send the configuration details for the indirect RLF prediction to the UE. Since the RLF prediction is executed at the network side, the indirect RLF prediction related configuration may not be transmitted at this step. However, the source gNB may configure theUE to perform periodic L1 / L3 measurement reporting for the network sided DL SINR prediction. At 915, the UE may send the periodic measurement report to the gNB for DL SINR prediction. At 920, the gNB may collect L1 / L3 radio measurements for training, inference, monitoring, etc. (see, e.g., 715). At 925, the gNB may perform temporal RRM measurement prediction during a window T _predict (930) (see, e.g., 720). The predicted measurements may comprise L1 / L3 RSRP time series (or SINR time series). At 935, the gNB may monitor ML reliability conditions during a time window T_ML_monitor (940) (see, e.g., 730). During monitoring, the gNB may determine reliability of the predicted measurements based on measurement prediction accuracy, measurement prediction confidence, or other ML metrics. The steps of collecting measurements (920), predicting measurements (925), and monitoring reliability conditions (935) may be repeated until a condition is verified (945) (see, e.g., 740). At 950, the gNB may, optionally, generate predicted SINR traces from the RSRP prediction (see, e.g., 745). At 955, the gNB may predict RLE based on the predicted (or derived) SINR traces during the RLE evaluation window (960) (see, e.g., 750).

[0094] At 965, the gNB may send an RLE prediction report to the UE. The RLF detection may be done / performed at step 8 (955) based on the predicted measurements. As the gNB is unaware of the UE RLM status, it may only include a prediction report indicating the future status, rather than the current radio link quality, in the RLF prediction report. In an example embodiment, the RLF prediction report may be a simple 1 -bit indication along with a time window T _pr edict. The first bit may indicate if RLF prediction is true or false. In another example embodiment, the RLF prediction report may also be other formats (e.g. not limited to the bitstring). For example, it may cover the prediction results with the accuracy metric, such as {RLF prediction status, RRM measurement accuracy in X% } . In another example embodiment, the RLF prediction report may additionally contain the confidence or probability of the predicted RLF. RRC signaling may be used to convey the RLF prediction report. Alternatively, L1 / L2 signaling may be used, such as downlink control information (DCI) or MAC control element (CE).

[0095] At 970, the UE may internally analyze its own current RLM status. At 975, the UE may send, to the gNB, an indication of an actual RLM status, for example an RLF confirmation indication or an indication of RLM non-confirmation / not confirm / disagreement. Without loss ofgenerality, this indication report may be formulated similar as UE embodiment, while only the actual RLM status is sent to the gNB. In an example embodiment, this confirmation signal may be a simple 1-bit indication which accounts for the actual RLM status, e.g., 1 may mean the instantaneous SINR is lower than a threshold, 0 may mean the instantaneous SINR is higher than a threshold, etc. In another example embodiment, this confirmation signal may be compact N bits information, where the instantaneous SINR may be compared and quantized against multiple thresholds. Additionally or alternatively, the UE may indicate to the serving gNB in the RLF prediction report whether the timer T310 has started, for how long T310 has been running in absolute or percentage values, etc. In another example embodiment, this confirmation signal may also be other formats (not limited to the bitstring). RRC signaling may be used to convey the RLF prediction report. Alternatively, L1 / L2 signaling may be used such as UCI or MAC CE. At 980, the gNB may initiate action(s) for the failure handling.

[0096] Referring now to FIG. 10, illustrated is an example of inter-gNB coordination for failure prediction. For simplicity, description of FIG. 10 that overlaps with the description of FIG. 9 may be omitted. In the example of FIG. 10, the target gNB may participate in the prediction loop. This may include providing additional information about the potential handover failure status based on the UL signal quality estimated by the target gNB, if the UE is configured with sounding reference signal (SRS) transmission in the UL. At 1002, the UE may send its capability information to the gNB. The capability information may include the support for AI / ML-based indirect RLF prediction. It may be noted that the additional UE capability enquiry signaling from the gNB to the UE (before step 0, 1002) is omitted in the example of FIG. 10. At 1004, the source and target gNBs may exchange the inter-gNB coordination capability signaling with potential handover failure estimation configuration for the target gNB side. The Xn signaling interface may be used for the exchange of inter-gNB coordination capability signaling if the inter-gNB coordination happens at a CU. Alternatively, a Fl signaling interface may also be used, given that the coordination may also happen at DU. At 1006, the source gNB may send the configuration details for the indirect RLF prediction to the UE. Since the RLF prediction may be executed at the network side, an indirect RLF prediction related configuration may not be transmitted to the UE at this step. However, the source gNB may configure the UE with the necessary referencesignal configuration, for example an SRS configuration for the UL SINR estimation. At 1008, the UE may send the periodic measurement report to the gNB for DL SINR prediction. At 1010 and 1012, the UE may perform SRS transmission in the UL, for example to the source gNB and one or more target gNB.

[0097] In an example embodiment, the source gNB may predict RLF. Similar steps may be applied as in the NW-sided embodiment (see, e.g., FIG. 9) where the source gNB may collect DL and UL measurements as the model input for training, inference and monitoring etc. The output, for simplicity, may be the serving cell SINR in the time window T _pr edict. Then, the source gNB may detect RLF occurrence based on the predicted SINR time series data frame. At 1014, the source gNB may collect DL and UL measurements as input for training, inference, monitoring, etc. (see, e.g., 920). At 1016, the source gNB may perform temporal RRM measurement prediction, for example in a DL SINR time series, during time window T _predict (1018) (see, e.g., 925). While not illustrated in FIG. 10, the reliability of the predicted RRM measurements may be monitored (see, e.g., 935). While not illustrated in FIG. 10, the collection of measurements, measurement prediction, and reliability monitoring may be repeated until a condition is verified (see, e.g., 945). At 1020, the source gNB may perform RLF detection based on predicted DL SINR traces during the RLF evaluation window 1022 (see, e.g., 955).

[0098] In an example embodiment, the target gNB may estimate handover failure (HOF). At 1024, the target gNB may gather UL SRS measurements and calculate the corresponding UL SINR. This information may allow the target gNB to assess the likelihood of a handover failure if the UE is going to handover to it. At 1026, the evaluation may be performed by comparing the instantaneous SINR against a pre-configured threshold set by the source gNB, within a designated HOF evaluation window 1028. At 1030, the target gNB may send an HOF evaluation report to the source gNB. The HOF evaluation report may indicate the likelihood of a handover failure if the UE is to handover to the target gNB. At 1032, the source gNB may integrate RLF prediction results from its prediction approach with the HOF evaluation report received from the target gNB. At 1034, the gNB may send a failure prediction report (including RLF and HOF) to the UE. The failure detection may be done at both source and target gNBs. Alternatively, the serving gNB may send to the UE a failure prediction report including only information about RLF. The handoverfailure information received from the target gNB(s) may be used by the source gNB to decide on the target cell of handover, and triggering the handover to the selected cell; this may be considered an example action in step 15 (1040). At 1036, the UE may internally analyze its own current RLM status (see, e.g. 970). At 1038, the UE may send a failure confirmation indication to the gNB including the actual RLM status (see, e.g. 975). At 1040, the gNB may initiate actions for the failure handling, i.e., triggering the handover to one of the earlier prepared target cell or adjusting the measurement configuration such that the measurement report (initiating the handover) is sent earlier to the serving gNB.

[0099] While FIG. 10 illustrates an example of RLF prediction at the NW side, this is not limiting; inter-gNB coordination according to the example of FIG. 10 may be performed if RLF prediction occurs at the UE side.

[0100] Referring now to FIG. 11, illustrated is an example of RLF handling when L1 / L2 triggered mobility (LTM) is configured, where RLF prediction is performed at the UE side. For simplicity, description of FIG. 11 that overlaps with the description of FIG. 7 may be omitted.

[0101] For both UE and network embodiments (e.g. FIGs. 8-9), there may be a step where the network processes the RLF after the prediction is validated at the gNB. In the example of FIG. 11, predicted RLF may be handled. At 1105, the source gNB may transmit, to the UE, a RLF prediction configuration and related rules (see, e.g. 710) as well as an LTM configuration, which may comprise configuration parameters for an LTM report RLF prediction. In an example embodiment, when the UE is configured with LTM, at 1110 the UE may be configured to initiate finding a suitable target-cell based on one or a combination of: 1) available measurements; 2) measurement prediction of potential target cell(s); and / or 3) performing additional measurement. Based on the network configuration, the UE capability, and the required time to search / measure / evaluate the target-cell, the procedure may be initiated either after RLF window (i.e. prediction of RLF) or earlier (i.e. during the initial phase of RLF prediction), which may have the technical effect of ensuring that the UE has enough time to find and evaluate target-cell and report it. At 1115, along with the RLF prediction report, the UE may send a list of candidate target cell(s) to the gNB (potentially with target cell measurement). The network may configure athreshold (e.g., RSRP above a certain threshold) for reporting target cells. The report may include LI or L3 measurement and / or LI or L3 measurement prediction of target cells (for LTM, in legacy, DU receives LI reports). In an alternative example embodiment, instead of measuremen t / measurement prediction of target-cells, the UE may predict and report the probability of successful HO (or RLF recovery) for each target cell. For ETM, the UE may be configured to send the information to the DU (as the DU makes the final HO decision). The DU may forward (part of) them to the CU. Alternatively, the UE may be configured to send the report to the CU. In this case, the CU may then share them with the DU and coordinate about appropriate actions. At 1120, the gNB may then analyze the prediction report and target cells, and at 1125 the source gNB may instruct the UE to handover to one suitable prepared target cell. At 1130, HO may be performed.

[0102] Referring now to FIG. 12, illustrated is an example an example of RLF handling when conditional handover (CHO) is configured, where RLF prediction is performed at the UE side. For simplicity, description of FIG. 12 that overlaps with the description of FIG. 7 may be omitted.

[0103] At 1205, the source gNB may transmit, to the UE, an RLF prediction configuration and related rules (see, e.g. 710) as well as a CHO configuration, which may include parameters for performing CHO after RLF prediction. After RLF prediction (750), at 1210 the UE may be configured to initiate the search for a suitable target-cell (as detailed in step 8 for LTM case, see 1110). Once a suitable target cell is identified by the UE (e.g. based on threshold configured by the network), the UE may execute the CHO procedure to the target gNB (1215) by applying the stored CHO configuration and sending random-access. The UE may be further configured to inform the target cell about the cause of HO (i.e., the UE may inform the target cell that handover is performed as the result of RLF prediction and, for example, not legacy measurement). This information may be sent as part of for example, Msgl (by sending specific configured preamble), or as part of Msg3. Additional information, such as a prediction / measurement report, may also be stored by the UE and sent to the target cell. The UE may also be configured to continue monitoring / measuring previous serving cell and other potential target cells (and compare them with measurement of the current serving cell) to evaluate (and report) the reliability / accuracy of prediction.

[0104] FIG. 13 illustrates the potential steps of an example method 1300. The example method 1300 may include: predicting at least one radio link failure based, at least partially, on one or more predicted measurements, 1310; and transmitting, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status, 1320. The example method 1300 may be performed, for example, with a UE.

[0105] FIG. 14 illustrates the potential steps of an example method 1400. The example method 1400 may include: receiving, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status, 1410; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report, 1420. The example method 1400 may be performed, for example, with a network node, a base station, a gNB, a serving cell, a source gNB, etc.

[0106] FIG. 15 illustrates the potential steps of an example method 1500. The example method 1500 may include: predicting at least one radio link failure based, at least partially, on one or more predicted measurements, 1510; transmitting, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction, 1520; and receiving, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report, 1530. The example method 1500 may be performed, for example, with a network node, a base station, a gNB, a serving cell, a source gNB, etc.

[0107] In accordance with one example embodiment, an apparatus may comprise: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; and transmit, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status. The one or more predicted measurements may comprise at least one of: one or more predicted radio resource management measurements for mobility, one or more predicted radio link quality measurements, one or more predicted signal to interference plus noise ratios, one or more predicted reference signal received power measurements, or one or more predicted reference signal received quality measurements. The at least one reliability metric associated with the one or more predicted measurements may comprise at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value. The example apparatus may be further configured to: transmit, to the network node, a capability of the example apparatus, wherein the capability of the example apparatus may comprise, at least, an indication that the example apparatus supports indirect radio link failure prediction based on the one or more predicted measurements. The example apparatus may be further configured to: receive a radio link failure prediction configuration; predict the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration; and monitor a reliability of the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration. The radio link failure prediction configuration may comprise a configuration for radio link failure prediction based on predicted measurements. The radio link failure prediction configuration may comprise at least one of: a window for obtaining the one or more predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predicted measurements to determine the reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failureprediction report. The radio link failure prediction configuration may comprise at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, at least one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report. The format for the radio link failure prediction report may comprise a bitmap format, wherein the radio link failure prediction report may be transmitted via at least one of: lower layer signaling, or dedicated radio resource control signaling. The at least one radio link failure prediction may be determined within the at least one radio link failure evaluation window. The at least one radio link failure evaluation window may be associated with a first timer, wherein the at least one radio link failure evaluation window may comprise, at least, a first time window and a second time window, wherein determining the radio link failure prediction may comprise the example apparatus being further configured to: determine, during the first time window, whether the one or more predicted measurements fall below a first threshold value; and determine, during the second time window, whether at least one parameter for evaluating radio link failure is fulfilled. Monitoring the reliability of the one or more predicted measurements may comprise the example apparatus being further configured to: monitor, during the measurement prediction reliability monitoring window, one or more of the at least one reliability metric associated with the one or more predicted measurements to determine a reliability value. The example apparatus may be further configured to: compare the reliability value with a defined threshold; and in response to the reliability value being below the defined threshold, at least one of: cause adjustment of at least one of a machine learning model, or an artificial intelligence model, that was used to predict the one or more predicted measurements; transmit, to the network node, a request for an updated radio link failure prediction configuration; or receive, from the network node, at least one updated configuration parameter for the radio link failure prediction configuration. The request for the updated radio link failure prediction configuration may comprise at least one of: the reliability value associated with the one or more predicted measurements, the measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators. The window for determining the one or more predicted measurements may be larger than the at least one radio linkfailure evaluation window. The radio link failure prediction configuration may further comprise a lower layer triggered mobility configuration, wherein the example apparatus may be further configured to: determine at least one target cell based, at least partially, one at least one of: one or more available measurements of one or more candidate cells, one or more predicted measurements of the one or more candidate cells, one or more additional measurements of the one or more candidate cells, or at least one threshold value associated with the one or more candidate cells, wherein the radio link failure prediction report may further comprise at least one of: the at least one determined target cell, measurements associated with the at least one determined target cell, a probability of successful handover for respective ones of the at least one determined target cell, or a probability of radio link failure recovery for the respective ones of the at least one determined target cell. The example apparatus may be further configured to: receive, from the network node, an indication to perform handover to a target cell of the at least one determined target cell; and perform handover with the target cell. The radio link failure prediction configuration may further comprise a conditional handover configuration, wherein the example apparatus may be further configured to: determine at least one target cell based, at least partially, on the conditional handover configuration and the at least one radio link failure prediction; and perform a conditional handover to the at least one determined target cell. The example apparatus may be further configured to: transmit, to the network node, an indication of a cause of the conditional handover. The example apparatus may be further configured to: receive, from the network node, a sounding reference signal configuration; and transmit, to the network node and at least one target network node, one or more sounding reference signal reports based, at least partially, on the sounding reference signal configuration. The example apparatus may be further configured to: receive, from the network node, a handover failure report, wherein the handover failure report may comprise, at least, an indication of a likelihood of failure of handover of the apparatus to a target network node. The reliability of the one or more predicted measurements may be monitored based, at least partially, on the at least one reliability metric associated with the one or more predicted measurements. The predicted radio link failure status may comprise an indication of whether the at least one radio link failure prediction is true or false. The radio link monitoring status may comprise at least one of: an indication of whether a first timer has started, an indication of how long the first timer has been running, an indication of whether a quality of a radio link between theapparatus and the network node is lower or higher than a threshold value, or a value of the quality of the radio link.

[0108] In accordance with one aspect, an example method may be provided comprising: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and transmitting, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status. The one or more predicted measurements may comprise at least one of: one or more predicted radio resource management measurements for mobility, one or more predicted radio link quality measurements, one or more predicted signal to interference plus noise ratios, one or more predicted reference signal received power measurements, or one or more predicted reference signal received quality measurements. The at least one reliability metric associated with the one or more predicted measurements may comprise at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value. The example method may further comprise: transmitting, to the network node, a capability of the user equipment, wherein the capability of the user equipment may comprise, at least, an indication that the user equipment supports indirect radio link failure prediction based on the one or more predicted measurements. The example method may further comprise: receiving a radio link failure prediction configuration; predicting the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration; and monitoring a reliability of the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration. The radio link failure prediction configuration may comprise a configuration for radio link failure prediction based on predicted measurements. The radio link failure prediction configuration may comprise at least one of: a window for obtaining the one or more predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predictedmeasurements to determine the reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failure prediction report. The radio link failure prediction configuration may comprise at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, at least one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report. The format for the radio link failure prediction report may comprise a bitmap format, wherein the radio link failure prediction report may be transmitted via at least one of: lower layer signaling, or dedicated radio resource control signaling. The at least one radio link failure prediction may be determined within the at least one radio link failure evaluation window. The at least one radio link failure evaluation window may be associated with a first timer, wherein the at least one radio link failure evaluation window may comprise, at least, a first time window and a second time window, wherein the determining of the radio link failure prediction may comprise: determining, during the first time window, whether the one or more predicted measurements fall below a first threshold value; and determining, during the second time window, whether at least one parameter for evaluating radio link failure is fulfilled. The monitoring of the reliability of the one or more predicted measurements may comprise: monitoring, during the measurement prediction reliability monitoring window, one or more of the at least one reliability metric associated with the one or more predicted measurements to determine a reliability value. The example method may further comprise: comparing the reliability value with a defined threshold; and in response to the reliability value being below the defined threshold, at least one of: causing adjustment of at least one of a machine learning model, or an artificial intelligence model, that was used to predict the one or more predicted measurements; transmitting, to the network node, a request for an updated radio link failure prediction configuration; or receiving, from the network node, at least one updated configuration parameter for the radio link failure prediction configuration. The request for the updated radio link failure prediction configuration may comprise at least one of: the reliability value associated with the one or more predicted measurements, the measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators. The window fordetermining the one or more predicted measurements may be larger than the at least one radio link failure evaluation window. The radio link failure prediction configuration may further comprise a lower layer triggered mobility configuration, and the example method may further comprise: determining at least one target cell based, at least partially, one at least one of: one or more available measurements of one or more candidate cells, one or more predicted measurements of the one or more candidate cells, one or more additional measurements of the one or more candidate cells, or at least one threshold value associated with the one or more candidate cells, wherein the radio link failure prediction report may further comprise at least one of: the at least one determined target cell, measurements associated with the at least one determined target cell, a probability of successful handover for respective ones of the at least one determined target cell, or a probability of radio link failure recovery for the respective ones of the at least one determined target cell. The example method may further comprise: receiving, from the network node, an indication to perform handover to a target cell of the at least one determined target cell; and performing handover with the target cell. The radio link failure prediction configuration may further comprise a conditional handover configuration, and the example method may further comprise: determining at least one target cell based, at least partially, on the conditional handover configuration and the at least one radio link failure prediction; and performing a conditional handover to the at least one determined target cell. The example method may further comprise: transmitting, to the network node, an indication of a cause of the conditional handover. The example method may further comprise: receiving, from the network node, a sounding reference signal configuration; and transmitting, to the network node and at least one target network node, one or more sounding reference signal reports based, at least partially, on the sounding reference signal configuration. The example method may further comprise: receiving, from the network node, a handover failure report, wherein the handover failure report may comprise, at least, an indication of a likelihood of failure of handover of the user equipment to a target network node. The reliability of the one or more predicted measurements may be monitored based, at least partially, on the at least one reliability metric associated with the one or more predicted measurements. The predicted radio link failure status may comprise an indication of whether the at least one radio link failure prediction is true or false. The radio link monitoring status may comprise at least one of: an indication of whether a first timer has started, an indication of how long the first timer has been running, an indicationof whether a quality of a radio link between the user equipment and the network node is lower or higher than a threshold value, or a value of the quality of the radio link.

[0109] In accordance with one example embodiment, an apparatus may comprise: circuitry configured to perform: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and circuitry configured to perform: transmitting, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0110] In accordance with one example embodiment, an apparatus may comprise: processing circuitry; memory circuitry including computer program code, the memory circuitry and the computer program code configured to, with the processing circuitry, enable the apparatus to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; and transmit, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0111] As used in this application, the term “circuitry” or “means” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and (b) combinations of hardware circuits and software, such as (as applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.” This definitionof circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0112] In accordance with one example embodiment, an apparatus may comprise means for: predicting at least one radio link failure based, at least partially, on one or more predicted measurements; and transmitting, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status. The one or more predicted measurements may comprise at least one of: one or more predicted radio resource management measurements for mobility, one or more predicted radio link quality measurements, one or more predicted signal to interference plus noise ratios, one or more predicted reference signal received power measurements, or one or more predicted reference signal received quality measurements. The at least one reliability metric associated with the one or more predicted measurements may comprise at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value. The means may be further configured for: transmitting, to the network node, a capability of the apparatus, wherein the capability of the apparatus may comprise, at least, an indication that the apparatus supports indirect radio link failure prediction based on the one or more predicted measurements. The means may be further configured for: receiving a radio link failure prediction configuration; predicting the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration; and monitoring a reliability of the one or more predicted measurements based, at least partially, on theradio link failure prediction configuration. The radio link failure prediction configuration may comprise a configuration for radio link failure prediction based on predicted measurements. The radio link failure prediction configuration may comprise at least one of: a window for obtaining the one or more predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predicted measurements to determine the reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failure prediction report. The radio link failure prediction configuration may comprise at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, at least one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report. The format for the radio link failure prediction report may comprise a bitmap format, wherein the radio link failure prediction report may be transmitted via at least one of: lower layer signaling, or dedicated radio resource control signaling. The at least one radio link failure prediction may be determined within the at least one radio link failure evaluation window. The at least one radio link failure evaluation window may be associated with a first timer, wherein the at least one radio link failure evaluation window may comprise, at least, a first time window and a second time window, wherein the means configured for determining the radio link failure prediction may comprise means configured for: determining, during the first time window, whether the one or more predicted measurements fall below a first threshold value; and determining, during the second time window, whether at least one parameter for evaluating radio link failure is fulfilled. The means configured for monitoring the reliability of the one or more predicted measurements may comprise means configured for: monitoring, during the measurement prediction reliability monitoring window, one or more of the at least one reliability metric associated with the one or more predicted measurements to determine a reliability value. The means may be further configured for: comparing the reliability value with a defined threshold; and in response to the reliability value being below the defined threshold, at least one of: causing adjustment of at least one of a machine learning model, or an artificial intelligence model, that was used to predict the one or more predicted measurements; transmitting, to the network node, a request for an updated radio link failure prediction configuration; or receiving,from the network node, at least one updated configuration parameter for the radio link failure prediction configuration. The request for the updated radio link failure prediction configuration may comprise at least one of: the reliability value associated with the one or more predicted measurements, the measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators. The window for determining the one or more predicted measurements may be larger than the at least one radio link failure evaluation window. The radio link failure prediction configuration may further comprise a lower layer triggered mobility configuration, wherein the means may be further configured for: determining at least one target cell based, at least partially, one at least one of: one or more available measurements of one or more candidate cells, one or more predicted measurements of the one or more candidate cells, one or more additional measurements of the one or more candidate cells, or at least one threshold value associated with the one or more candidate cells, wherein the radio link failure prediction report may further comprise at least one of: the at least one determined target cell, measurements associated with the at least one determined target cell, a probability of successful handover for respective ones of the at least one determined target cell, or a probability of radio link failure recovery for the respective ones of the at least one determined target cell. The means may be further configured for: receiving, from the network node, an indication to perform handover to a target cell of the at least one determined target cell; and performing handover with the target cell. The radio link failure prediction configuration may further comprise a conditional handover configuration, wherein the means may be further configured for: determining at least one target cell based, at least partially, on the conditional handover configuration and the at least one radio link failure prediction; and performing a conditional handover to the at least one determined target cell. The means may be further configured for: transmitting, to the network node, an indication of a cause of the conditional handover. The means may be further configured for: receiving, from the network node, a sounding reference signal configuration; and transmitting, to the network node and at least one target network node, one or more sounding reference signal reports based, at least partially, on the sounding reference signal configuration. The means may be further configured for: receiving, from the network node, a handover failure report, wherein the handover failure report may comprise, at least, an indication of a likelihood of failure of handover of the apparatusto a target network node. The reliability of the one or more predicted measurements may be monitored based, at least partially, on the at least one reliability metric associated with the one or more predicted measurements. The predicted radio link failure status may comprise an indication of whether the at least one radio link failure prediction is true or false. The radio link monitoring status may comprise at least one of: an indication of whether a first timer has started, an indication of how long the first timer has been running, an indication of whether a quality of a radio link between the apparatus and the network node is lower or higher than a threshold value, or a value of the quality of the radio link.

[0113] A processor, memory, and / or example algorithms (which may be encoded as instructions, program, or code) may be provided as example means for providing or causing performance of operation.

[0114] In accordance with one example embodiment, a (non-transitory) computer-readable medium comprising instructions stored thereon which, when executed with at least one processor, cause the at least one processor to: predict, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and cause transmitting, to a network node, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0115] In accordance with one example embodiment, a (non-transitory) computer-readable medium comprising program instructions stored thereon for performing at least the following: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and causing transmitting, to a network node, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status. The one or more predictedmeasurements may comprise at least one of: one or more predicted radio resource management measurements for mobility, one or more predicted radio link quality measurements, one or more predicted signal to interference plus noise ratios, one or more predicted reference signal received power measurements, or one or more predicted reference signal received quality measurements. The at least one reliability metric associated with the one or more predicted measurements may comprise at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing transmitting, to the network node, of a capability of the user equipment, wherein the capability of the user equipment may comprise, at least, an indication that the user equipment supports indirect radio link failure prediction based on the one or more predicted measurements. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing receiving of a radio link failure prediction configuration; predicting the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration; and monitoring a reliability of the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration. The radio link failure prediction configuration may comprise a configuration for radio link failure prediction based on predicted measurements. The radio link failure prediction configuration may comprise at least one of: a window for obtaining the one or more predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predicted measurements to determine the reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failure prediction report. The radio link failure prediction configuration may comprise at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, at least one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report. The format for the radio link failure prediction report may comprise a bitmap format, wherein the radio link failureprediction report may be transmitted via at least one of: lower layer signaling, or dedicated radio resource control signaling. The at least one radio link failure prediction may be determined within the at least one radio link failure evaluation window. The at least one radio link failure evaluation window may be associated with a first timer, wherein the at least one radio link failure evaluation window may comprise, at least, a first time window and a second time window, wherein the program instructions for performing determining the radio link failure prediction may comprise program instructions for performing: determining, during the first time window, whether the one or more predicted measurements fall below a first threshold value; and determining, during the second time window, whether at least one parameter for evaluating radio link failure is fulfilled. The program instructions for performing monitoring the reliability of the one or more predicted measurements may comprise program instructions for performing: monitoring, during the measurement prediction reliability monitoring window, one or more of the at least one reliability metric associated with the one or more predicted measurements to determine a reliability value. The example computer-readable medium may further comprise program instructions stored thereon for performing: comparing the reliability value with a defined threshold; and in response to the reliability value being below the defined threshold, at least one of: causing adjustment of at least one of a machine learning model, or an artificial intelligence model, that was used to predict the one or more predicted measurements; causing transmitting, to the network node, of a request for an updated radio link failure prediction configuration; or causing receiving, from the network node, of at least one updated configuration parameter for the radio link failure prediction configuration. The request for the updated radio link failure prediction configuration may comprise at least one of: the reliability value associated with the one or more predicted measurements, the measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators. The window for determining the one or more predicted measurements may be larger than the at least one radio link failure evaluation window. The radio link failure prediction configuration may further comprise a lower layer triggered mobility configuration, wherein the example computer-readable medium may further comprise program instructions stored thereon for performing: determining at least one target cell based, at least partially, one at least one of: one or more available measurements of one or more candidate cells,one or more predicted measurements of the one or more candidate cells, one or more additional measurements of the one or more candidate cells, or at least one threshold value associated with the one or more candidate cells, wherein the radio link failure prediction report may further comprise at least one of: the at least one determined target cell, measurements associated with the at least one determined target cell, a probability of successful handover for respective ones of the at least one determined target cell, or a probability of radio link failure recovery for the respective ones of the at least one determined target cell. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing receiving, from the network node, of an indication to perform handover to a target cell of the at least one determined target cell; and causing performing of handover with the target cell. The radio link failure prediction configuration may further comprise a conditional handover configuration, wherein the example computer-readable medium may further comprise program instructions stored thereon for performing: determining at least one target cell based, at least partially, on the conditional handover configuration and the at least one radio link failure prediction; and performing a conditional handover to the at least one determined target cell. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing transmitting, to the network node, of an indication of a cause of the conditional handover. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing receiving, from the network node, of a sounding reference signal configuration; and causing transmitting, to the network node and at least one target network node, of one or more sounding reference signal reports based, at least partially, on the sounding reference signal configuration. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing receiving, from the network node, of a handover failure report, wherein the handover failure report may comprise, at least, an indication of a likelihood of failure of handover of the user equipment to a target network node. The reliability of the one or more predicted measurements may be monitored based, at least partially, on the at least one reliability metric associated with the one or more predicted measurements. The predicted radio link failure status may comprise an indication of whether the at least one radio link failure prediction is true or false. The radio link monitoring status may comprise at least one of: an indication of whether a first timer has started, an indication of how long the first timer has beenrunning, an indication of whether a quality of a radio link between the user equipment and the network node is lower or higher than a threshold value, or a value of the quality of the radio link.

[0116] In accordance with another example embodiment, a (non-transitory) program storage device readable by a machine may be provided, tangibly embodying instructions executable by the machine for performing operations, the operations comprising: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and causing transmitting, to a network node, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0117] In accordance with another example embodiment, a (non-transitory) computer- readable medium comprising instructions that, when executed by an apparatus, cause the apparatus to perform at least the following: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and causing transmitting, to a network node, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0118] A computer implemented system comprising: at least one processor and at least one (non-transitory) memory storing instructions that, when executed by the at least one processor, cause the system at least to perform: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and causing transmitting, to a network node, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at leastone reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0119] A computer implemented system comprising: means for predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and means for causing transmitting, to a network node, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

[0120] In accordance with one example embodiment, an apparatus may comprise: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handle the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report. The at least one reliability metric associated with the one or more predicted measurements may comprise at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value. The example apparatus may be further configured to: receive, from the user equipment, a capability of the user equipment, wherein the capability of the user equipment may comprise, at least, an indication that the user equipment supports indirect radio link failure prediction based on the one or more predicted measurements. The example apparatus may be further configured to: transmit, to the user equipment, a radio link failure prediction configuration. The radio link failure prediction configuration may comprise a configuration for radio link failure prediction based on predicted measurements. The radio link failure prediction configuration may comprise at least one of: a window for obtaining the one ormore predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predicted measurements to determine reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failure prediction report. The radio link failure prediction configuration may comprise at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, at least one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report. The format for the radio link failure prediction report may comprise a bitmap format, wherein the radio link failure prediction report may be received via at least one of: lower layer signaling, or dedicated radio resource control signaling. The at least one radio link failure evaluation window may be associated with a first timer, wherein the at least one radio link failure evaluation window may comprise, at least, a first time window and a second time window. The radio link failure prediction configuration may further comprise a lower layer triggered mobility configuration, wherein the radio link failure prediction report may further comprise at least one of: at least one target cell for lower layer triggered mobility, measurements associated with the at least one target cell, a probability of successful handover for respective ones of the at least one target cell, or a probability of radio link failure recovery for the respective ones of the at least one target cell; wherein handling the at least one radio link failure prediction may comprise the example apparatus being further configured to: determine a target cell, of the at least one target cell, for handover; and transmit, to the user equipment, an indication to perform handover to the determined target cell. The radio link failure prediction configuration may further comprise a conditional handover configuration, wherein the example apparatus may be further configured to: receive an indication of a cause of conditional handover performed based, at least partially, on the conditional handover configuration. The example apparatus may be further configured to: transmit, to at least one target network node, capability information associated with the apparatus, wherein the capability information associated with the apparatus comprises, at least, a handover failure estimation configuration; receive, from the at least one target network node, capability information associated with the at least one target network node; transmit, to the user equipment, a sounding reference signal configuration; receive, from the user equipment, one or more soundingreference signal reports based, at least partially, on the sounding reference signal configuration; receive, from the at least one target network node, a handover failure report, wherein the handover failure report may comprise, at least, an indication of a likelihood of failure of handover of the user equipment to the at least one target network node; and transmit, to the user equipment, the handover failure report. The example apparatus may be further configured to: receive, from the user equipment, a request for an updated radio link failure prediction configuration; determine at least one updated configuration parameter based, at least partially, on the received request; and transmit, to the user equipment, the at least one updated configuration parameter. The request for the updated radio link failure prediction configuration may comprise at least one of: a reliability value associated with the one or more predicted measurements, a measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators. The predicted radio link failure status may comprise an indication of whether the at least one radio link failure prediction is true or false. The radio link monitoring status may comprise at least one of: an indication of whether a first timer has started, an indication of how long the first timer has been running, an indication of whether a quality of a radio link between the user equipment and the apparatus is lower or higher than a threshold value, or a value of the quality of the radio link.

[0121] In accordance with one aspect, an example method may be provided comprising: receiving, with a network node from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report. The at least one reliability metric associated with the one or more predicted measurements may comprise at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value. The example method may further comprise: receiving, from theuser equipment, a capability of the user equipment, wherein the capability of the user equipment may comprise, at least, an indication that the user equipment supports indirect radio link failure prediction based on the one or more predicted measurements. The example method may further comprise: transmitting, to the user equipment, a radio link failure prediction configuration. The radio link failure prediction configuration may comprise a configuration for radio link failure prediction based on predicted measurements. The radio link failure prediction configuration may comprise at least one of: a window for obtaining the one or more predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predicted measurements to determine reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failure prediction report. The radio link failure prediction configuration may comprise at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, at least one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report. The format for the radio link failure prediction report may comprise a bitmap format, wherein the radio link failure prediction report may be received via at least one of: lower layer signaling, or dedicated radio resource control signaling. The at least one radio link failure evaluation window may be associated with a first timer, wherein the at least one radio link failure evaluation window may comprise, at least, a first time window and a second time window. The radio link failure prediction configuration may further comprise a lower layer triggered mobility configuration, wherein the radio link failure prediction report may further comprise at least one of: at least one target cell for lower layer triggered mobility, measurements associated with the at least one target cell, a probability of successful handover for respective ones of the at least one target cell, or a probability of radio link failure recovery for the respective ones of the at least one target cell; wherein the handling of the at least one radio link failure prediction may comprise: determining a target cell, of the at least one target cell, for handover; and transmitting, to the user equipment, an indication to perform handover to the determined target cell. The radio link failure prediction configuration may further comprise a conditional handover configuration, and the example method may further comprise: receiving an indication of a cause of conditional handover performed based, at leastpartially, on the conditional handover configuration. The example method may further comprise: transmitting, to at least one target network node, capability information associated with the network node, wherein the capability information associated with the network node may comprise, at least, a handover failure estimation configuration; receiving, from the at least one target network node, capability information associated with the at least one target network node; transmitting, to the user equipment, a sounding reference signal configuration; receiving, from the user equipment, one or more sounding reference signal reports based, at least partially, on the sounding reference signal configuration; receiving, from the at least one target network node, a handover failure report, wherein the handover failure report may comprise, at least, an indication of a likelihood of failure of handover of the user equipment to the at least one target network node; and transmitting, to the user equipment, the handover failure report. The example method may further comprise: receiving, from the user equipment, a request for an updated radio link failure prediction configuration; determining at least one updated configuration parameter based, at least partially, on the received request; and transmitting, to the user equipment, the at least one updated configuration parameter. The request for the updated radio link failure prediction configuration may comprise at least one of: a reliability value associated with the one or more predicted measurements, a measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators. The predicted radio link failure status may comprise an indication of whether the at least one radio link failure prediction is true or false. The radio link monitoring status may comprise at least one of: an indication of whether a first timer has started, an indication of how long the first timer has been running, an indication of whether a quality of a radio link between the user equipment and the network node is lower or higher than a threshold value, or a value of the quality of the radio link.

[0122] In accordance with one example embodiment, an apparatus may comprise: circuitry configured to perform: receiving, with a network node from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radiolink failure prediction, or a radio link monitoring status; and circuitry configured to perform: handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0123] In accordance with one example embodiment, an apparatus may comprise: processing circuitry; memory circuitry including computer program code, the memory circuitry and the computer program code configured to, with the processing circuitry, enable the apparatus to: receive, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handle the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0124] In accordance with one example embodiment, an apparatus may comprise means for: receiving, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report. The at least one reliability metric associated with the one or more predicted measurements may comprise at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value. The means may be further configured for: receiving, from the user equipment, a capability of the user equipment, wherein the capability of the user equipment may comprise, at least, an indication that the user equipment supports indirect radio link failure prediction based on the one or more predicted measurements. The means may be further configured for: transmitting, to the user equipment, a radio link failure prediction configuration. The radio link failure prediction configuration may comprise a configuration for radio link failure prediction based on predictedmeasurements. The radio link failure prediction configuration may comprise at least one of: a window for obtaining the one or more predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predicted measurements to determine reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failure prediction report. The radio link failure prediction configuration may comprise at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, at least one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report. The format for the radio link failure prediction report may comprise a bitmap format, wherein the radio link failure prediction report may be received via at least one of: lower layer signaling, or dedicated radio resource control signaling. The at least one radio link failure evaluation window may be associated with a first timer, wherein the at least one radio link failure evaluation window may comprise, at least, a first time window and a second time window. The radio link failure prediction configuration may further comprise a lower layer triggered mobility configuration, wherein the radio link failure prediction report may further comprise at least one of: at least one target cell for lower layer triggered mobility, measurements associated with the at least one target cell, a probability of successful handover for respective ones of the at least one target cell, or a probability of radio link failure recovery for the respective ones of the at least one target cell; wherein the means configured for handling the at least one radio link failure prediction may comprise means configured for: determining a target cell, of the at least one target cell, for handover; and transmitting, to the user equipment, an indication to perform handover to the determined target cell. The radio link failure prediction configuration may further comprise a conditional handover configuration, wherein the means may be further configured for: receiving an indication of a cause of conditional handover performed based, at least partially, on the conditional handover configuration. The means may be further configured for: transmitting, to at least one target network node, capability information associated with the apparatus, wherein the capability information associated with the apparatus may comprise, at least, a handover failure estimation configuration; receiving, from the at least one target network node, capability informationassociated with the at least one target network node; transmitting, to the user equipment, a sounding reference signal configuration; receiving, from the user equipment, one or more sounding reference signal reports based, at least partially, on the sounding reference signal configuration; receiving, from the at least one target network node, a handover failure report, wherein the handover failure report may comprise, at least, an indication of a likelihood of failure of handover of the user equipment to the at least one target network node; and transmitting, to the user equipment, the handover failure report. The means may be further configured for: receiving, from the user equipment, a request for an updated radio link failure prediction configuration; determining at least one updated configuration parameter based, at least partially, on the received request; and transmitting, to the user equipment, the at least one updated configuration parameter. The request for the updated radio link failure prediction configuration may comprise at least one of: a reliability value associated with the one or more predicted measurements, a measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators. The predicted radio link failure status may comprise an indication of whether the at least one radio link failure prediction is true or false. The radio link monitoring status may comprise at least one of: an indication of whether a first timer has started, an indication of how long the first timer has been running, an indication of whether a quality of a radio link between the user equipment and the apparatus is lower or higher than a threshold value, or a value of the quality of the radio link.

[0125] In accordance with one example embodiment, a (non-transitory) computer-readable medium comprising instructions stored thereon which, when executed with at least one processor, cause the at least one processor to: cause receiving, with a network node from a user equipment, of a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handle the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0126] In accordance with one example embodiment, a (non-transitory) computer-readable medium comprising program instructions stored thereon for performing at least the following: causing receiving, with a network node from a user equipment, of a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report. The at least one reliability metric associated with the one or more predicted measurements may comprise at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing receiving, from the user equipment, of a capability of the user equipment, wherein the capability of the user equipment may comprise, at least, an indication that the user equipment supports indirect radio link failure prediction based on the one or more predicted measurements. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing transmitting, to the user equipment, of a radio link failure prediction configuration. The radio link failure prediction configuration may comprise a configuration for radio link failure prediction based on predicted measurements. The radio link failure prediction configuration may comprise at least one of: a window for obtaining the one or more predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predicted measurements to determine reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failure prediction report. The radio link failure prediction configuration may comprise at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, at least one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report. The format forthe radio link failure prediction report may comprise a bitmap format, wherein the radio link failure prediction report may be received via at least one of: lower layer signaling, or dedicated radio resource control signaling. The at least one radio link failure evaluation window may be associated with a first timer, wherein the at least one radio link failure evaluation window may comprise, at least, a first time window and a second time window. The radio link failure prediction configuration may further comprise a lower layer triggered mobility configuration, wherein the radio link failure prediction report may further comprise at least one of: at least one target cell for lower layer triggered mobility, measurements associated with the at least one target cell, a probability of successful handover for respective ones of the at least one target cell, or a probability of radio link failure recovery for the respective ones of the at least one target cell; wherein the program instructions for performing handling of the at least one radio link failure prediction may comprise program instructions for performing: determining a target cell, of the at least one target cell, for handover; and causing transmitting, to the user equipment, of an indication to perform handover to the determined target cell. The radio link failure prediction configuration may further comprise a conditional handover configuration, wherein the example computer-readable medium may further comprise program instructions stored thereon for performing: causing receiving of an indication of a cause of conditional handover performed based, at least partially, on the conditional handover configuration. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing transmitting, to at least one target network node, of capability information associated with the network ode, wherein the capability information associated with the network node may comprise, at least, a handover failure estimation configuration; causing receiving, from the at least one target network node, of capability information associated with the at least one target network node; causing transmitting, to the user equipment, of a sounding reference signal configuration; causing receiving, from the user equipment, of one or more sounding reference signal reports based, at least partially, on the sounding reference signal configuration; causing receiving, from the at least one target network node, of a handover failure report, wherein the handover failure report may comprise, at least, an indication of a likelihood of failure of handover of the user equipment to the at least one target network node; and causing transmitting, to the user equipment, of the handover failure report. The example computer-readable medium may further comprise program instructions stored thereon forperforming: causing receiving, from the user equipment, of a request for an updated radio link failure prediction configuration; determining at least one updated configuration parameter based, at least partially, on the received request; and causing transmitting, to the user equipment, of the at least one updated configuration parameter. The request for the updated radio link failure prediction configuration may comprise at least one of: a reliability value associated with the one or more predicted measurements, a measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators. The predicted radio link failure status may comprise an indication of whether the at least one radio link failure prediction is true or false. The radio link monitoring status may comprise at least one of: an indication of whether a first timer has started, an indication of how long the first timer has been running, an indication of whether a quality of a radio link between the user equipment and the network node is lower or higher than a threshold value, or a value of the quality of the radio link.

[0127] In accordance with another example embodiment, a (non-transitory) program storage device readable by a machine may be provided, tangibly embodying instructions executable by the machine for performing operations, the operations comprising: causing receiving, with a network node from a user equipment, of a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0128] In accordance with another example embodiment, a (non-transitory) computer- readable medium comprising instructions that, when executed by an apparatus, cause the apparatus to perform at least the following: causing receiving, with a network node from a user equipment, of a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handlingthe at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0129] A computer implemented system comprising: at least one processor and at least one (non-transitory) memory storing instructions that, when executed by the at least one processor, cause the system at least to perform: causing receiving, with a network node from a user equipment, of a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0130] A computer implemented system comprising: means for causing receiving, with a network node from a user equipment, of a radio link failure prediction report, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and means for handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

[0131] In accordance with one example embodiment, an apparatus may comprise: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; transmit, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and receive, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report. The indication of the radio link monitoring status may comprise at least one of: an indication that a signal to interference plusnoise ratio is higher or lower than a threshold, or a quantized value associated with the signal to interference plus noise ratio. The example apparatus may be further configured to: transmit, to the user equipment, a radio link failure prediction configuration, wherein the radio link failure prediction configuration may comprise, at least, a configuration for reporting one or more measurements. The example apparatus may be further configured to: receive, from the user equipment, one or more measurements; predict the one or more predicted measurements based, at least partially, on the one or more received measurements; and monitor a reliability of the one or more predicted measurements. The example apparatus may be further configured to: handle the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report and the indication of the radio link monitoring status.

[0132] In accordance with one aspect, an example method may be provided comprising: predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; transmitting, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and receiving, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report. The indication of the radio link monitoring status may comprise at least one of: an indication that a signal to interference plus noise ratio is higher or lower than a threshold, or a quantized value associated with the signal to interference plus noise ratio. The example method may further comprise: transmitting, to the user equipment, a radio link failure prediction configuration, wherein the radio link failure prediction configuration may comprise, at least, a configuration for reporting one or more measurements. The example method may further comprise: receiving, from the user equipment, one or more measurements; predicting the one or more predicted measurements based, at least partially, on the one or more received measurements; and monitoring a reliability of the one or more predicted measurements. The example method may further comprise: handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report and the indication of the radio link monitoring status.

[0133] In accordance with one example embodiment, an apparatus may comprise: circuitry configured to perform: predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; circuitry configured to perform: transmitting, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and circuitry configured to perform: receiving, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0134] In accordance with one example embodiment, an apparatus may comprise: processing circuitry; memory circuitry including computer program code, the memory circuitry and the computer program code configured to, with the processing circuitry, enable the apparatus to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; transmit, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and receive, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0135] In accordance with one example embodiment, an apparatus may comprise means for: predicting at least one radio link failure based, at least partially, on one or more predicted measurements; transmitting, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and receiving, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report. The indication of the radio link monitoring status may comprise at least one of: an indication that a signal to interference plus noise ratio is higher or lower than a threshold, or a quantized value associated with the signal to interferenceplus noise ratio. The means may be further configured for: transmitting, to the user equipment, a radio link failure prediction configuration, wherein the radio link failure prediction configuration may comprise, at least, a configuration for reporting one or more measurements. The means may be further configured for: receiving, from the user equipment, one or more measurements; predicting the one or more predicted measurements based, at least partially, on the one or more received measurements; and monitoring a reliability of the one or more predicted measurements. The means may be further configured for: handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report and the indication of the radio link monitoring status.

[0136] In accordance with one example embodiment, a (non-transitory) computer-readable medium comprising instructions stored thereon which, when executed with at least one processor, cause the at least one processor to: predict, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; cause transmitting, to a user equipment, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and cause receiving, from the user equipment, of an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0137] In accordance with one example embodiment, a (non-transitory) computer-readable medium comprising program instructions stored thereon for performing at least the following: predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; causing transmitting, to a user equipment, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and causing receiving, from the user equipment, of an indication of a radio link monitoring status in response to the radio link failure prediction report. The indication of the radio link monitoring status may comprise at least one of: an indication that a signal to interferenceplus noise ratio is higher or lower than a threshold, or a quantized value associated with the signal to interference plus noise ratio. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing transmitting, to the user equipment, of a radio link failure prediction configuration, wherein the radio link failure prediction configuration may comprise, at least, a configuration for reporting one or more measurements. The example computer-readable medium may further comprise program instructions stored thereon for performing: causing receiving, from the user equipment, of one or more measurements; predicting the one or more predicted measurements based, at least partially, on the one or more received measurements; and monitoring a reliability of the one or more predicted measurements. The example computer-readable medium may further comprise program instructions stored thereon for performing: handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report and the indication of the radio link monitoring status.

[0138] In accordance with another example embodiment, a (non-transitory) program storage device readable by a machine may be provided, tangibly embodying instructions executable by the machine for performing operations, the operations comprising: predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; causing transmitting, to a user equipment, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and causing receiving, from the user equipment, of an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0139] In accordance with another example embodiment, a (non-transitory) computer- readable medium comprising instructions that, when executed by an apparatus, cause the apparatus to perform at least the following: predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; causing transmitting, to a user equipment, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least oneof: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and causing receiving, from the user equipment, of an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0140] A computer implemented system comprising: at least one processor and at least one (non-transitory) memory storing instructions that, when executed by the at least one processor, cause the system at least to perform: predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; causing transmitting, to a user equipment, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and causing receiving, from the user equipment, of an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0141] A computer implemented system comprising: means for predicting, with a network node, at least one radio link failure based, at least partially, on one or more predicted measurements; means for causing transmitting, to a user equipment, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report may comprise at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and means for causing receiving, from the user equipment, of an indication of a radio link monitoring status in response to the radio link failure prediction report.

[0142] The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e. tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0143] It should be understood that the foregoing description is only illustrative. Various alternatives and modifications can be devised by those skilled in the art. For example, features recited in the various dependent claims could be combined with each other in any suitablecombination(s). In addition, features from different embodiments described above could be selectively combined into a new embodiment. Accordingly, the description is intended to embrace all such alternatives, modification and variances which fall within the scope of the appended claims.

Claims

CLAIMSWhat is claimed is:

1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed with the at least one processor, cause the apparatus at least to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; and transmit, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

2. The apparatus of claim 1, wherein the one or more predicted measurements comprise at least one of: one or more predicted radio resource management measurements for mobility, one or more predicted radio link quality measurements, one or more predicted signal to interference plus noise ratios, one or more predicted reference signal received power measurements, or one or more predicted reference signal received quality measurements.

3. The apparatus of claim 1 or 2, wherein the at least one reliability metric associated with the one or more predicted measurements comprises at least one of: a reliability value associated with the one or more predicted measurements, a reliability interval associated with the one or more predicted measurements, a reliability of radio resource management prediction of the one or more predicted measurements, a mean square error value, or a negative log likelihood value.

4. The apparatus of any one of claims 1 through 3, wherein the instructions, when executed with the at least one processor, cause the apparatus to: transmit, to the network node, a capability of the apparatus, wherein the capability of the apparatus comprises, at least, an indication that the apparatus supports indirect radio link failure prediction based on the one or more predicted measurements.

5. The apparatus of any one of claims 1 through 4, wherein the instructions, when executed with the at least one processor, cause the apparatus to: receive a radio link failure prediction configuration; predict the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration; and monitor a reliability of the one or more predicted measurements based, at least partially, on the radio link failure prediction configuration.

6. The apparatus of claim 5, wherein the radio link failure prediction configuration comprises a configuration for radio link failure prediction based on predicted measurements.

7. The apparatus of claim 5 or 6, wherein the radio link failure prediction configuration comprises at least one of: a window for obtaining the one or more predicted measurements and the at least one radio link failure prediction, a threshold value against which to compare the one or more predicted measurements to determine the reliability, a format for the radio link failure prediction report, or a reliability threshold for transmitting the radio link failure prediction report.

8. The apparatus of claim 5 or 6, wherein the radio link failure prediction configuration comprises at least one of: a measurement prediction reliability monitoring window, a time offset for timing control of the measurement prediction reliability monitoring window, atleast one radio link failure evaluation window, a time offset for timing control of the radio link failure evaluation window, a window for determining the one or more predicted measurements, or a format for the radio link failure prediction report.

9. The apparatus of claim 8, wherein the format for the radio link failure prediction report comprises a bitmap format, wherein the radio link failure prediction report is transmitted via at least one of: lower layer signaling, or dedicated radio resource control signaling.

10. The apparatus of claim 8 or 9, wherein the at least one radio link failure prediction is determined within the at least one radio link failure evaluation window.

11. The apparatus of any one of claims 8 through 10, wherein the at least one radio link failure evaluation window is associated with a first timer, wherein the at least one radio link failure evaluation window comprises, at least, a first time window and a second time window, wherein determining the radio link failure prediction comprises the instructions, when executed with the at least one processor, cause the apparatus to: determine, during the first time window, whether the one or more predicted measurements fall below a first threshold value; and determine, during the second time window, whether at least one parameter for evaluating radio link failure is fulfilled.

12. The apparatus of any one of claims 8 through 11, wherein monitoring the reliability of the one or more predicted measurements comprises the instructions, when executed with the at least one processor, cause the apparatus to: monitor, during the measurement prediction reliability monitoring window, one or more of the at least one reliability metric associated with the one or more predicted measurements to determine a reliability value.

13. The apparatus of claim 12, wherein the instructions, when executed with the at least one processor, cause the apparatus to:compare the reliability value with a defined threshold; and in response to the reliability value being below the defined threshold, at least one of: cause adjustment of at least one of a machine learning model, or an artificial intelligence model, that was used to predict the one or more predicted measurements; transmit, to the network node, a request for an updated radio link failure prediction configuration; or receive, from the network node, at least one updated configuration parameter for the radio link failure prediction configuration.

14. The apparatus of claim 13, wherein the request for the updated radio link failure prediction configuration comprises at least one of: the reliability value associated with the one or more predicted measurements, the measurement prediction reliability monitoring window, the at least one reliability metric associated with the one or more predicted measurements, or a report of one or more performance indicators.

15. The apparatus of any one of claims 8 through 14, wherein the window for determining the one or more predicted measurements is larger than the at least one radio link failure evaluation window.

16. The apparatus of any one of claims 5 through 15, wherein the radio link failure prediction configuration further comprises a lower layer triggered mobility configuration, wherein the instructions, when executed with the at least one processor, cause the apparatus to: determine at least one target cell based, at least partially, one at least one of: one or more available measurements of one or more candidate cells, one or more predicted measurements of the one or more candidate cells, one or more additionalmeasurements of the one or more candidate cells, or at least one threshold value associated with the one or more candidate cells, wherein the radio link failure prediction report further comprises at least one of: the at least one determined target cell, measurements associated with the at least one determined target cell, a probability of successful handover for respective ones of the at least one determined target cell, or a probability of radio link failure recovery for the respective ones of the at least one determined target cell.

17. The apparatus of claim 16, wherein the instructions, when executed with the at least one processor, cause the apparatus to: receive, from the network node, an indication to perform handover to a target cell of the at least one determined target cell; and perform handover with the target cell.

18. The apparatus of any one of claims 5 through 17, wherein the radio link failure prediction configuration further comprises a conditional handover configuration, wherein the instructions, when executed with the at least one processor, cause the apparatus to: determine at least one target cell based, at least partially, on the conditional handover configuration and the at least one radio link failure prediction; and perform a conditional handover to the at least one determined target cell.

19. The apparatus of claim 18, wherein the instructions, when executed with the at least one processor, cause the apparatus to: transmit, to the network node, an indication of a cause of the conditional handover.

20. The apparatus of any one of claims 16 through 19, wherein the instructions, when executed with the at least one processor, cause the apparatus to:receive, from the network node, a sounding reference signal configuration; and transmit, to the network node and at least one target network node, one or more sounding reference signal reports based, at least partially, on the sounding reference signal configuration.

21. The apparatus of claim 20, wherein the instructions, when executed with the at least one processor, cause the apparatus to: receive, from the network node, a handover failure report, wherein the handover failure report comprises, at least, an indication of a likelihood of failure of handover of the apparatus to a target network node.

22. The apparatus of any one of claims 5 through 21 , wherein the reliability of the one or more predicted measurements is monitored based, at least partially, on the at least one reliability metric associated with the one or more predicted measurements.

23. The apparatus of any one of claims 1 through 22, wherein the predicted radio link failure status comprises an indication of whether the at least one radio link failure prediction is true or false.

24. The apparatus of any one of claims 1 through 23, wherein the radio link monitoring status comprises at least one of: an indication of whether a first timer has started, an indication of how long the first timer has been running, an indication of whether a quality of a radio link between the apparatus and the network node is lower or higher than a threshold value, or a value of the quality of the radio link.

25. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed with the at least one processor, cause the apparatus at least to:receive, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handle the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

26. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed with the at least one processor, cause the apparatus at least to: predict at least one radio link failure based, at least partially, on one or more predicted measurements; transmit, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and receive, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report.

27. A method comprising: predicting at least one radio link failure based, at least partially, on one or more predicted measurements; andtransmitting, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

28. A method comprising: receiving, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

29. A method comprising: predicting at least one radio link failure based, at least partially, on one or more predicted measurements; transmitting, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; and receiving, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report.

30. An apparatus comprising means for:predicting at least one radio link failure based, at least partially, on one or more predicted measurements; and transmitting, to a network node, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

31. An apparatus comprising means for: receiving, from a user equipment, a radio link failure prediction report, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with one or more predicted measurements used to determine at least one radio link failure prediction, or a radio link monitoring status; and handling the at least one radio link failure prediction based, at least partially, on the radio link failure prediction report.

32. An apparatus comprising means for: predicting at least one radio link failure based, at least partially, on one or more predicted measurements; transmitting, to a user equipment, a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, or a reliability associated with the at least one radio link failure prediction; andreceiving, from the user equipment, an indication of a radio link monitoring status in response to the radio link failure prediction report.

33. A computer-readable medium comprising program instructions stored thereon for performing at least the following: predicting, with a user equipment, at least one radio link failure based, at least partially, on one or more predicted measurements; and causing transmitting, to a network node, of a radio link failure prediction report based, at least partially, on the at least one radio link failure prediction, wherein the radio link failure prediction report comprises at least one of: a predicted radio link failure status, a window of predicted radio link failure, at least one reliability metric associated with the one or more predicted measurements, or a radio link monitoring status.

Images