Beam selection based on predicted signal condition parameter

By predicting signal condition parameters for 5G networks, the UE improves handover decision reliability and reduces signaling overhead, addressing the inefficiencies in current handover processes within 5G radio access networks.

WO2024235548A1PCT designated stage expired Publication Date: 2024-11-21NOKIA TECHNOLOGIES OY
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
PCT/EP2024/060352
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-17
Filing Date
2024-04-17
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

In 5G radio access networks, the current handover decision process based on real-time signal condition parameters can lead to incorrect decisions and significant signaling overhead, especially when user equipment (UE) with multiple antenna panels performs beam sweeping and reports measurement data to the serving cell.

Method used

The UE predicts signal condition parameters for both serving and candidate target cells using configuration information and machine learning models, allowing for more reliable beam selection and reduced signaling overhead by transmitting predicted beam selection information to the radio node.

Benefits of technology

This approach improves the reliability of handover decisions and reduces signaling overhead by using predicted values instead of real-time measurements, enhancing mobility management in 5G networks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure EP2024060352_21112024_PF_FP_ABST
    Figure EP2024060352_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The disclosure inter alia relates to a user equipment comprising at least one processor and at least one memory, the at least one memory storing instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: receiving configuration information from a radio node of a radio access network; obtaining, for one or more points in time and for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell of the radio access network, a predicted value of at least one signal condition parameter; obtaining a first selection of the one or more beams of the serving cell and / or a second selection of the one or more beams of the at least one candidate target cell; transmitting beam selection information to the radio node, wherein the beam selection information is indicative of the first and / or second selection of beams.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] BEAM SELECTION BASED ON PREDICTED SIGNAL CONDITION PARAMETER

[0002] TECHNOLOGICAL FIELD

[0003] The present disclosure is related to, but not limited to, lower-layer-triggered mobility (LTM) in the context of radio access networks (RAN) as defined by the 3rd Generation Partnership Project (3GPP) standard, such as the 5G standard which is also referred to as New Radio (NR). In particular, the disclosure, in connection with LTM decisions, pertains to the identification of suitable beams created by antenna arrays of base stations using the so- called beamforming technique.

[0004] BACKGROUND

[0005] In a handover procedure, an ongoing communication session of a user equipment (UE) is transferred, for example, from one cell, i.e. the coverage area of a base station such as a gNodeB (gNB), to another cell. In this way, handovers enable seamless connectivity and continuity of service for the user, in particular when the user is moving.

[0006] For signal transmission in 5G RANs, the beamforming technique may be used. Here, instead of broadcasting a signal emitted by an antenna omnidirectionally, i.e. homogeneously in all directions of space, an antenna array is used to create, by means of interference, so-called beams, i.e. spatial regions in which the signal intensity is focussed within a concentrated beam pointing only in a distinct direction. Beamforming may be used by base stations to service a plurality of UEs, wherein a respective beam may be directed towards each of the serviced UEs, for example. Furthermore, the 5G standard also supports UE beamforming, which means that the UE may have one or more antenna panels that also form one or more beams. The beamforming technique may be employed in particular at higher frequencies, for example above 6 GHz, while an omnidirectional irradiation characteristic may be used at lower frequencies.

[0007] User mobility in 5G RANs can be categorized into two types: cell-level mobility and beam-level mobility. For cell-level mobility, a respective handover between two cells may be triggered by control signalling in the radio resource control (RRC) layer, also referred to as L3 layer, and requires RRC reconfiguration. In contrast to this, beam-level mobility may be performed using lower-layer-triggered mobility (LTM). Here, control signalling is only exchanged in the lower layers, more specifically in the physical (PHY) layer, also referred to as LI layer, and in the medium access control (MAC) layer, also referred to as L2 layer, and thus RRC control signalling in the L3 layer is not required. LTM supports both mobility between beams of the same distributed unit (DU), i.e. intra-DU mobility, and mobility between beams of different DUs of the same central unit (CU), i.e. intra-CU- inter-DU mobility. SUMMARY OF SOME EXEMPLARY EMBODIMENTS

[0008] However, there is a problem that according to the present 5G standard, the decision at a specific point in time about a handover of a UE from a serving cell towards a candidate target cell is made on the basis of current values of one or more signal condition parameters, such as a reference signal received power (RSRP), of beams generated by the candidate target cell. For example, if beams that are generated by more than one candidate target cell fulfil predetermined handover criteria for the one or more signal condition parameters at the same time, the handover decision, which is made by the serving cell, may be incorrect and it may turn out at a later point in time that a different handover decision would have been more advantageous. Furthermore, since the serving cell is reliant on the continuous availability of measurement reports regarding the at least one signal condition parameter in order to make handover decisions, such measurement reports must be transmitted from the UE to the serving cell in regular intervals. This may produce a significant signalling overhead, especially in the case of UEs with several antenna panels, since the UE must perform beam sweeping across all beams, and if applicable all panels, and transmit the respective data to the serving cell.

[0009] In view of the above, example embodiments of the present disclosure may have inter alia the effect of improving the decision making regarding a handover, such as a LTM handover, towards a candidate target cell. Furthermore, example embodiments of the present disclosure may have inter alia the effect of reducing signalling overhead.

[0010] According to a first exemplary aspect, a user equipment is disclosed. The user equipment may comprise at least one processor and at least one memory. The at least one memory may store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: receiving configuration information from a radio node of a radio access network; obtaining, for one or more points in time and for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell of the radio access network, a predicted value of at least one signal condition parameter; obtaining a first selection of the one or more beams of the serving cell and / or a second selection of the one or more beams of the at least one candidate target cell; transmitting beam selection information to the radio node, wherein the beam selection information is indicative of the first and / or second selection of beams.

[0011] The user equipment may be a stationary device or a mobile device. In particular, the user equipment may be a mobile device, such as a smartphone, a tablet, a wearable, a smartwatch, a low power device, an loT device, an IIoT device, a vehicle, a truck, a drone, an airplane, or the like. The user equipment may in particular be capable of communicating with (transmitting and receiving signals and / or data to / from) one or more other user equipment. Additionally or alternatively, the user equipment may in particular be capable of communicating with (transmitting and receiving signals and / or data to / from) at least one radio node of a radio access network. Generally, the user equipment may also be any device enabled for communication with a communication network and / or another user equipment. A radio node may be understood as a wireless communication station installed at a fixed or mobile location and may in particular be or comprise an entity of a radio access network of a wireless communication system. For instance, the radio node may be, comprise, or be part of a base station of a wireless communication network of any generation (e.g. a gNB, ng-eNB, eNodeB, NodeB, BTS or the like) of a 3GPP standard. Generally, the radio node may be or comprise a hardware or software component implementing a certain functionality. In an example, the radio node may be a location management function (LMF). In an example, the radio node may be an entity as defined by 3GPP 5G or NR standard (also referred to as gNB). Accordingly, while the radio node may be understood to be implemented in or be a single device or module, the radio node may also be implemented across or comprise multiple devices or modules. As such, the radio node may in particular be implemented in or be a stationary device. Multiple radio nodes may in particular establish a wireless communication system or network, which may in particular be an NR or 5G system or any other wireless communications system defined by a past or future standard, in particular successors of the present 3GPP standards. The radio node may be capable of being in direct and / or indirect communication with other radio nodes or with user equipment. Furthermore, the radio node may be associated with a respective cell, be associated with a respective physical cell identifier (PCI), and / or be associated with a respective transmission and reception point (TRP).

[0012] As used herein, configuration information may be understood as any kind of information based on which a user equipment is or can be configured for obtaining predicted values of at least one signal condition parameter of one or more beams, and / or for obtaining a selection of the one or more beams, and / or for validating the predicted values. For example, the configuration information may comprise information regarding points in time for which the predicted values are to be obtained and / or validated. For example, the configuration information may comprise information regarding the one or more beams for which the predicted values are to be obtained and / or validated. For example, the configuration information may comprise information regarding the modalities of the prediction, and / or the modalities of the selection, and / or the modalities of the validation.

[0013] As used herein, a beam may be understood as a spatial region in which the signal intensity of an antenna or an antenna array, e.g. of a base station, is focussed or concentrated, in particular by using the beamforming technique explained above. For example, the beam may have the shape of an elongated ellipsoid, of an elongated droplet, or the like. For example, the beam may point in a distinct direction of space.

[0014] As used herein, a signal condition parameter may be understood as any physical parameter which is able to characterize a condition related to a signal. For example, the signal condition parameter may relate to a signal intensity, a signal strength, a signal power, a signal quality, or the like. For example, the signal condition parameter may relate to a signal condition of a beam signal or of a cell signal, a signal condition of a reference signal associated with a beam or a cell, or the like. As used herein, a serving cell may be understood as a coverage area of a base station, for example a gNB, which with respect to a current point in time provides services towards a user equipment. For example, the serving cell may comprise one or more beams for providing services towards a user equipment. Furthermore, the serving cell may be associated with a respective serving radio node, be associated with a respective serving PCI, and / or be associated with a respective serving TRP.

[0015] As used herein, a candidate target cell may be understood as a coverage area of a base station, for example a gNB, which with respect to a future point in time qualifies or may qualify for providing services to a user equipment. In order to enable the candidate target cell to provide services to the user equipment, a handover of the user equipment towards the candidate target cell may be required, for example. Thus, a candidate target cell may also be understood as a base station, for example a gNB, which qualifies or may qualify for a respective handover. Furthermore, the candidate target cell may be associated with a respective candidate target radio node, be associated with a respective candidate target PCI, and / or be associated with a respective candidate target TRP.

[0016] As used herein, obtaining a predicted value may be understood as any suitable action which enables such a predicted value to become available. For example, a user equipment may obtain a predicted value by carrying out a respective prediction. For example, the prediction may be based on a calculation model and / or a machine learning model. For example, the calculation model and / or the machine learning model may be implemented in the user equipment, implemented in one or more radio nodes of a radio access network, or distributed over the user equipment and one or more radio nodes. For example, a user equipment may obtain a predicted value by receiving the predicted value from a radio node, or by accessing a database in which the predicted value is stored.

[0017] As used herein, obtaining a predicted value for one or more points in time may be understood such that at least one predicted value is obtained, wherein each obtained predicted value is associated with a specific point in time, for example a point in time for which a respective prediction has been carried out. For example, one predicted value may be obtained, wherein this one predicted value is associated with one specific point in time. For example, more than one predicted value may be obtained, wherein a first predicted value is associated with a first point in time, a second predicted value is associated with a second point in time, etc. In this context a point in time may also be understood as a moment of time or a time occasion. In particular, the point in time may be a future point in time such as a future point in time for which a prediction is or is to be carried out. The future point of time may be within a prediction interval directed towards the future. The prediction interval may be defined by a number of time steps of a predefined step width.

[0018] As used herein, obtaining a predicted value for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell may be understood such that at least one predicted value is obtained, wherein each obtained predicted value is associated, besides the one or more point in time, also with a specific beam of a serving cell or of a candidate target cell, for example a beam for which a respective prediction has been carried out. For example, one predicted value may be obtained for a specific point in time, wherein this one predicted value is associated with one specific beam. For example, more than one predicted value may be obtained for a specific point in time, wherein a first predicted value is associated with a first beam, a second predicted value is associated with a second beam, etc. For example, the one or more beams may be or comprise at least one beam which is generated by a serving cell and which with respect to a current point in time provides services to the user equipment. For example, the one or more beams may be or comprise at least one beam which is generated by a serving cell and which with respect to a current point in time does not provide services to the user equipment but qualifies or may qualify for providing services with respect to a future point in time after a respective mobility event. For example, the one or more beams may be or comprise at least one beam which is generated by at least one candidate target cell. In this context, the at least one candidate target cell may be or comprise each candidate target cell available in an area, or may be or comprise a selection of candidate target cells available in an area.

[0019] As used herein, obtaining a predicted value of at least one signal condition parameter may be understood such that predicted values are obtained for one signal condition parameter, or for more than one signal condition parameter. For example, predicted values can be obtained for one signal condition parameter such as reference signal received power (RSRP). For example, predicted values can be obtained for two or more signal condition parameters such as RSRP and signal-to-interference-and-noise ratio (SINR), etc. The information about which signal condition parameters are to be predicted may be comprised by the configuration information transmitted from the radio node to the user equipment. This means that the network may configure the user equipment to carry out a prediction of at least one signal condition parameter, such as RSRP and SINR etc, for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell.

[0020] As used herein, obtaining a selection of one or more beams may be understood as any suitable action which enables such a selection to be generated or obtained. For example, the selection of one or more beams may be based on predicted values of at least one signal condition parameter for the one or more beams. As an example of such a selection, each beam having a predicted value exceeding a predefined threshold may be selected. Said predefined threshold may be comprised by the configuration information received by the user equipment from the radio node. As another example of such a selection, a number of beams having the largest predicted values within a plurality of beams may be selected, wherein the number may be an integer such as one, two, three, etc. Said number may be comprised by the configuration information received by the user equipment from the radio node. For example, the top K beams of one or more serving cells and the top N beams of one or more candidate target cells may be selected, wherein K and N are integers, and wherein the expressions “top K” and “top N” relate to the respective number of beams having the largest predicted values of at least one signal condition parameter. As another example of such a selection, the selection may comprise all available beams of one or more respective cells, in particular all available beams of a serving cell or all available beams of at least one candidate target cell. For example, if only one beam is available for the selection, the selection may be or comprise this one beam. For example, a user equipment may obtain the selection by carrying out a respective selection process. For example, a user equipment may obtain the selection by receiving information indicative of the selection from a radio node, or by accessing a database in which information indicative of the selection is stored.

[0021] As used herein, obtaining a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell may be understood such that at least a first selection of one or more beams generated by a serving cell is obtained. As an example, only a first selection of one or more beams generated by a serving cell may be obtained. This may in particular be the case if no candidate target cell and thus no beams generated by a candidate target cell are available. As another example, a first selection of one or more beams generated by a serving cell may be obtained, and additionally, a second selection of one or more beams generated by at least one candidate target cell may be obtained. This may in particular be the case if at least one beam generated by at least one candidate target cell is available besides the one or more beams generated by the serving cell. In this case, the first selection of one or more beams may comprise only beams generated by the serving cell, and the second selection of one or more beams may comprise only beams generated by the at least one candidate target cell. In this context, the at least one candidate target cell may be or comprise each candidate target cell available in an area, or may be or comprise a selection of candidate target cells available in an area. In an embodiment, the first and second selection may be merged.

[0022] Obtaining a predicted value for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell and obtaining a first selection of the one or more beams of the serving cell and / or a second selection of the one or more beams of the at least one candidate target cell may be understood such that obtaining the predicted values and obtaining the first and / or second selection are carried out in any suitable order. As an example, a predicted value may be obtained for each beam of a serving cell and each beam of at least one candidate target cell, and a subsequent selection based on the predicted values may be carried out to obtain a first and / or second selection. As another example, a predicted value may be obtained only for one or more, but not all beams of a serving cell, e.g. only for all available beams, and only for one or more, but not all beams of at least one candidate target cell, e.g. only for all available beams, and a subsequent selection based on the predicted values may be carried out to obtain a first and / or second selection. As another example, a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell may be obtained, and the predicted value may be obtained only for the first and / or second selection. In this case, the first and / or second selection may for example be likewise obtained based on a prediction, for example a prediction of beams having at least one signal condition parameter exceeding a predefined threshold, a prediction of a number of beams having the largest signal condition parameters within a plurality of beams, or the like.

[0023] As used herein, beam selection information may be understood as any suitable piece of information which is indicative of a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell of the radio access network. For example, the beam selection information may be or comprise beam identifiers of the one or more beams included in the first and / or second selection of beams. For example, the beam identifiers may be arranged in a descending order with respect to at least one signal condition parameter. For example, each beam identifier may be associated with a respective value of at least one signal condition parameter for the one or more beams. In exemplary embodiments, the beam selection information may be comprised by status information transmitted from the user equipment to the radio node.

[0024] As used herein, status information may be understood as any information which characterises a status, in particular a current status, of a user equipment. The status information may comprise the beam selection information. Furthermore, the status information may also comprise other information.

[0025] According to the first exemplary aspect, the user equipment may receive configuration information from a radio node of a radio access network. For example, the configuration information may configure the UE to use a specific calculation model and / or a specific machine learning model for carrying out a prediction of at least one signal condition parameter for one or more points in time and for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell. In this context, different calculation models and / or machine learning models may be implemented in the UE, and different UEs may be configured to use different models, for example depending on samples or depending on a size of an input. For example, the configuration information may configure different models based on different measurements as input. Furthermore, the configuration information, for example, may configure the UE to obtain, based on a respective prediction, a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell. Furthermore, the configuration information, for example, may configure the UE to validate predicted values of at least one signal condition parameter. The validation, for example, may be based on at least one report to be sent to a radio node, in particular a report included within status information to be sent to a radio node associated with a serving cell. By the user equipment receiving configuration information from a radio node of a radio access network, it can be achieved that the UE is suitably configured for obtaining and validating predicted values of at least one signal condition parameter.

[0026] Furthermore, according to the first exemplary aspect, the user equipment may obtain, for one or more points in time and for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell of the radio access network, a predicted value of at least one signal condition parameter. Thereby, it can be achieved that respective predicted values become available, which may be the basis, for example, for obtaining a first selection of the one or more beams of the serving cell and / or the second selection of the one or more beams of the at least one candidate target cell.

[0027] Furthermore, according to the first exemplary aspect, the user equipment may obtain a first selection of the one or more beams of the serving cell and / or a second selection of the one or more beams of the at least one candidate target cell. For example, the first and / or second selection of beams may be based on the predicted values of the at least one signal condition parameter obtained for the one or more points in time and for the one or more beams of the serving cell and / or the one or more beams of the at least one candidate target cell. By obtaining the first and / or second selection of beams, it can be achieved that decision making regarding a handover, such as a LTM handover, towards a candidate target cell is improved, since a decision based on the first and / or second selection of beams may be more reliable. In particular in the case where obtaining the first and / or second selection of beams is based on the predicted values of the at least one signal condition parameter, the decision making can be improved, since the prediction, which may for example be based on a calculation model and / or a machine learning model, may provide more reliable results regarding suitable beams at future points in time compared to only measuring current values of the at least one signal condition parameter. Furthermore, since a decision based on the first and / or second selection of beams does not require measurement reports regarding the at least one signal condition parameter to be continuously transmitted from the UE to the radio node, signalling overhead between the UE and the radio node may be reduced.

[0028] Furthermore, according to the first exemplary aspect, the user equipment may transmit beam selection information to the radio node, wherein the beam selection information is indicative of the first and / or second selection of beams. The beam selection information may be indicative of a first and / or second selection of beams which has been obtained based on predicted values of at least one signal condition parameter, or may be indicative of a first and / or second selection of beams which has been obtained based on predicted and validated values of at least one signal condition parameter. By transmitting beam selection information to the radio node, wherein the beam selection information is indicative of the first and / or second selection of beams, it can be achieved that the first and / or second selection of beams is made available to the radio node, for example as a basis for decision making regarding a handover towards a candidate target cell. For example, the handover may be a LTM handover.

[0029] In example embodiments of the first exemplary aspect, the one or more beams may be one or more channel status information reference signal (CSI-RS) beams and / or one or more synchronization signal block (SSB) beams.

[0030] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: obtaining a selection of candidate target cells.

[0031] As an example of such a selection, the selection of candidate target cells may be based on the second selection of one or more beams of the at least one candidate target cell. For example, the selection of candidate target cells may be or comprise a group of candidate target cells generating beams which are included in the second selection of one or more beams. For example, in a case where the top N beams of one or more candidate target cells are selected, a selection of top M candidate target cells may be obtained as the group of target cells which generate the top N beams. As another example of such a selection, further selection criteria may be applied. For example, only candidate target cells which generate more than a threshold of beams included in the second selection of beams may be selected. Said predefined threshold may be comprised by the configuration information received by the user equipment from the radio node. As another example, only a number of candidate target cells generating the most beams included in the second selection of beams may be selected, wherein the number may be an integer such as one, two, three, etc. Said number may be comprised by the configuration information received by the user equipment from the radio node. For example in a case where the top N beams of one or more candidate target cells are selected, a selection of top M candidate target cells may be made, wherein the expression “top M” relates to the candidate target cells of beams generating the most of the top N beams. In example embodiments, the status information may comprise cell selection information indicative of the selection of candidate target cells. By obtaining a selection of candidate target cells, it can be achieved that decision making regarding a handover towards a candidate target cell is improved further, since suitable candidate target cells may be indicated more easily.

[0032] In example embodiments of the first exemplary aspect, the status information may comprise position information. For example, the position information may be indicative of a current position of the user equipment. For example, the current position may be determined and / or estimated based on measurements of at least one signal condition parameter. By the status information comprising position information, it can be achieved that the radio node is enabled to monitor or track UE mobility.

[0033] In example embodiments of the first exemplary aspect, obtaining, for one or more points in time and for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell of the radio access network, a predicted value of at least one signal condition parameter, may be based on a position of the user equipment. For example, the position of the user equipment may be a current position. For example, the position of the user equipment may be a position estimate based on measurements of at least one signal condition parameter. For example, the position of the user equipment may be an input parameter of a neural network which performs a respective prediction of the at least one signal condition parameter. For example, the position of the user equipment may be an input parameter besides other input parameters, in particular besides signal condition parameters such as RSRP and SINR.

[0034] In example embodiments of the first exemplary aspect, the status information may comprise key performance indicator information. For example, the key performance indicator information may be or comprise one or more key performance indicators. For example, the key performance indicators may relate to a machine learning model, or may relate to a radio connection, in particular to a link quality. By the status information comprising key performance indicator information, it can be achieved that the key performance indicator information is made available to the radio node.

[0035] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: evaluating the predicted value of the at least one signal condition parameter.

[0036] For example, evaluating the predicted value of the at least one signal condition parameter may comprise a plausibility check of the predicted value. By evaluating the predicted value, it can be achieved that the reliability of the predicted value is improved.

[0037] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: transmitting monitoring request information to the radio node.

[0038] For example, the monitoring request information may be indicative of a request to validate the predicted values of the at least one signal condition parameter. For example, the monitoring request information may be transmitted to the radio node together with the beam selection information, and / or together with status information comprising the beam selection information. For example, the monitoring request information may be transmitted to the radio node separate from the beam selection information, and / or separate from status information comprising the beam selection information. By transmitting monitoring request information to the radio node, it can be achieved that a subsequent validation of the predicted values of the at least one signal condition parameter is only performed after being triggered by the network node.

[0039] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: receiving monitoring request acknowledge information from the radio node.

[0040] For example, the monitoring request acknowledge information may be indicative of and acknowledgement of the monitoring request by the radio node. Thereby, it can be achieved that a subsequent validation of the predicted values of the at least one signal condition parameter is triggered by the network node.

[0041] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: obtaining, at least for one of the one or more points in time and at least for the first and / or second selection of beams, a measured value of the at least one signal condition parameter.

[0042] As used herein, obtaining a measured value may be understood as any suitable action which enables such a measured value to become available. For example, a user equipment may obtain a measured value by carrying out a respective measurement. For example, a user equipment may obtain a measured value by receiving the measured value from a radio node, or by accessing a database in which the measured value is stored. As used herein, obtaining a measured value of the at least one signal condition parameter may be understood such that a measured value is obtained for the same signal condition parameter for which a predicted value has already been obtained or is still to be obtained. For example, a measured value of the at least one signal condition parameter may be obtained by the UE by measuring the respective signal condition parameter. As used herein, obtaining the measured value of the at least one signal condition parameter at least for one of the one or more points in time may be understood such that the measured value of the at least one signal condition parameter is obtained at least for one of the one or more points in time for which a predicted value of the at least one signal condition parameter has already been obtained or is still to be obtained. For example, the measured value may be obtained for only one of the respective points in time. For example, the measured value may be obtained for each of the respective points in time. For example, the measured value may be obtained for more than one, but not all of the respective points in time. As used herein, obtaining the measured value of the at least one signal condition parameter at least for the first and / or second selection of beams may be understood such that the measured value of the at least one signal condition parameter may be obtained only for beams that are included in the first and / or second selection of beams, or may additionally be obtained for one or more beams that are not included in the first and / or second selection of beams. For example, the measured value of the at least one signal condition parameter may be obtained for each beam for which a predicted value of the at least one signal condition parameter has already been obtained or is still to be obtained. By obtaining, at least for one of the one or more points in time and at least for the first and / or second selection of beams, a measured value of the at least one signal condition parameter, it can be achieved that such measured values become available, which may be the basis, for example, for validating respective predicted values of the at least one signal condition parameter.

[0043] In example embodiments of the first exemplary aspect, a measurement report is generated based on the obtained measured values of the at least one signal condition parameter. The measurement report may be comprised by status information which is transmitted to the user equipment. For example, a current position of the user equipment may be determined based on the measurement report. By generating the measurement report and transmitting the measurement report to the radio node as part of the status information, it can be achieved that the radio node is enabled to monitor or track UE mobility.

[0044] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: determining, based on the predicted and measured values of the at least one signal condition parameter and based on the configuration information, whether or not a first prediction validation condition is fulfilled.

[0045] As used herein, a prediction validation condition may be understood as a condition which, in the case where it is fulfilled, is indicative of the predicted values of the at least one signal condition parameter being valid, i.e. sufficiently reliable. Thus, determining whether the prediction validation condition is fulfilled is an example of validating the predicted values of the at least one signal condition parameter. As used herein, determining whether or not a first prediction validation condition is fulfilled based on the predicted and measured values of the at least one signal condition parameter and based on the configuration information may be understood such that the fact whether the first prediction validation condition is fulfilled is a function of both the predicted and measured values of the at least one signal condition parameter and the configuration information. An example of a prediction validation condition is a condition whether a prediction error, such as a parameter characteristic of an average difference between the predicted and measured values of the at least one signal condition parameter, does not exceed a predetermined threshold. Another example of a prediction validation condition is a condition whether the sum of a prediction error and a prediction error offset does not exceed a predetermined threshold. Both are also examples of how determining whether or not a first prediction validation condition is fulfilled may be based on the predicted and measured values of the at least one signal condition parameter. For example, said prediction error may be a mean squared error. Furthermore, said predetermined threshold and / or said prediction error offset may be comprised by the configuration information, for example. This is an example of how determining whether or not a first prediction validation condition is fulfilled is based on the configuration information. By determining, based on the predicted and measured values of the at least one signal condition parameter and based on the configuration information, whether or not a first prediction validation condition is fulfilled, it can be achieved that decision making regarding a handover towards a candidate target cell is improved further, since validating the predicted values based on respective measured values and based on the first prediction validation condition being fulfilled may increase the reliability of the predicted values.

[0046] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: based on the first prediction validation condition being fulfilled, transmitting monitoring output information to the radio node.

[0047] For example, the monitoring output information may be indicative of a result of the monitoring, i.e. of the validation of the predicted values of the at least one signal condition parameter. For example, the monitoring output information may be indicative of the predicted values of the at least one signal condition parameter being valid, i.e. sufficiently reliable. For example, the monitoring output information may be indicative of the predicted values of the at least one signal condition parameter being invalid, i.e. not sufficiently reliable. As used herein, transmitting monitoring output information to the radio node based on the first prediction validation condition being fulfilled may be understood such that the monitoring output information is transmitted to the radio node if the first prediction validation condition is fulfilled. However, transmitting monitoring output information to the radio node may depend on further conditions, for example further prediction validation conditions, to be fulfilled. By transmitting monitoring output information to the radio node based on the first prediction validation condition being fulfilled, it can be achieved that information about whether the predicted values of the at least one signal condition parameter are valid or not, is made available to the radio node.

[0048] In example embodiments of the first exemplary aspect, the monitoring output information may comprise updated beam selection information. For example, the updated beam selection information may be indicative of an updated first selection of one or more beams of a serving cell and / or an updated second selection of one or more beams of at least one candidate target cell. For example, the updated beam selection information may be intended to replace the beam selection information, or may be intended to supplement the beam selection information. As an example for the case where the updated beam selection information is intended to replace the beam selection information, the updated beam selection information may be or comprise beam identifiers of the one or more beams included in the updated first and / or second selection of beams. For example, the beam identifiers may be arranged in a descending order with respect to at least one signal condition parameter. For example, each beam identifier may be associated with a respective updated value of at least one signal condition parameter for the one or more beams. For example, the updated value may be or be obtained from a measured value of at least one signal condition parameter for the one or more beams. As an example for the case where the updated beam selection information is intended to supplement the beam selection information, the updated beam selection information may be indicative of a difference between the first and / or second selection of beams and the updated first and / or second selection of beams.

[0049] In example embodiments of the first exemplary aspect, the configuration information may comprise at least one of the following: a first time information indicative of the one or more points in time for which the predicted value of the at least one signal condition parameter is to be obtained for the one or more beams of the serving cell and / or the one or more beams of the at least one candidate target cell; a second time information indicative of the at least one point in time for which the measured value of the at least one signal condition parameter is to be obtained for at least the first and / or second selection of beams; at least one prediction validation condition parameter based on which it is to be determined whether or not the first prediction validation condition is fulfilled.

[0050] The first time information is an example of information based on which the user equipment is or can be configured by the radio node for obtaining predicted values of at least one signal condition parameter of one or more beams. Furthermore, in the case where the first and / or second selection of beams is based on the predicted values, the first time information is also an example of how the configuration information may configure the UE to obtain the first and / or second selection of beams. In example embodiments of the first exemplary aspect, the first time information may be a number of time steps of a predefined step width. For example, the predicted value of the at least one signal condition parameter is to be obtained for each time step. The second time information is an example of how the configuration information may configure the UE to validate the predicted values of the at least one signal condition parameter. In example embodiments of the first exemplary aspect, the second time information may be a prediction validation measurement interval. For example, the measured value of the at least one signal condition parameter is to be obtained at a point in time defined by the end of the prediction validation measurement interval. For example, the prediction validation measurement interval may be a multiple of said predefined step width. The at least one prediction validation condition parameter is an example of how the configuration information may configure the modalities of the validation. In example embodiments of the first exemplary aspect, the at least one prediction validation condition parameter may be a prediction error threshold and / or a prediction error offset. For example, the first prediction validation condition may be a function of the prediction error threshold and / or the prediction error offset.

[0051] In example embodiments of the first exemplary aspect, obtaining the predicted value of the at least one signal condition parameter and / or obtaining the first and / or second selection of beams may be carried out using a neural network. For example, the neural network may be implemented in the UE. For example, the neural network may be implemented in the form of a machine learning model. For example, the machine learning model may be a proprietary machine learning model of the UE. For example, the machine learning model may have been deployed in the UE during manufacture and may have been trained at least partially beforehand. For example, the machine learning model may have been transmitted at least partially to the UE by a radio node of a radio access network and may have been trained at least partially beforehand. For example, the trained machine learning model may be continuously updated by a radio node of a radio access network, in particular by a serving cell transmitting respective training information. For example, the training information may be comprised by the configuration information transmitted to the UE from the radio node. For example, the machine learning model may be continuously trained by the UE based on suitable data of at least one signal condition parameter, in particular at least one signal condition parameter of which predicted vales are to be obtained. For example, the data of the at least one signal condition parameter may be obtained from respective measurements. By using a neural network to carry out obtaining the predicted value of the at least one signal condition parameter and / or obtaining the first and / or second selection of beams, it can be achieved that reliable predicted values of the at least one signal condition parameter are obtained, compared for example to a more simple calculation model.

[0052] In example embodiments of the first exemplary aspect, the neural network may be at least one of the following: a long short-term memory (LSTM) neural network; a recurrent neural network (RNN); a convolutional neural network (CNN); a transformer.

[0053] For example, the neuronal network may be a LSTM-RNN. The mentioned types of neural networks, i.e. LSTM neural networks, RNNs, CNNs and transformers are examples neural networks which may be implemented in the UE in the form of a machine learning model. By using an LSTM neural network, it can be achieved that sequence prediction can be handled more effectively, compared to a CNN model for example, since the CNN does not memorize previous time series patterns. By using a transformer, it can be achieved that more complex relationships between elements can be learned, compared to LSTM neural networks and RNNs for example, due to the self-attention mechanism of a transformer. Any of the mentioned neural networks may be a trained neural network. For example, the neural network may be continuously trained by the UE based on suitable data of at least one signal condition parameter, in particular at least one signal condition parameter of which predicted vales are to be obtained. For example, the data of the at least one signal condition parameter may be obtained from respective measurements. For example, the training of the neural network by the UE may be controlled by a radio node or by a network of radio nodes, in that a radio node associated with a serving cell transmits respective model training configuration information to the user equipment. For example, the model training configuration information may be comprised by the configuration information mentioned above. For example, the model training configuration information may be transmitted separate from said configuration information. In particular, the training of the neural network may be performed by the UE if the UE has enough processing capability for such training. In embodiments, the UE may use a machine learning model trained beforehand for performing the prediction.

[0054] In example embodiments of the first exemplary aspect, obtaining the predicted value of the at least one signal condition parameter may be based on at least one of the following: a current value of at least one signal condition parameter for the one or more beams of the serving cell and / or the one or more beams of the at least one candidate target cell; a window length associated with the respective one or more beams; a beam identifier associated with the respective one or more beams.

[0055] The mentioned quantities are examples of data based on which the neural model may provide the predicted value of the at least one signal condition parameter. In this context, obtaining the predicted value of the at least one signal condition parameter based at least on a current value of at least one signal condition parameter may be understood such that the predicted value is obtained based on a current value of one signal condition parameter, or based on a current value of more than one signal condition parameters. Furthermore, it may be understood such that predicted values of more than one signal condition parameter are obtained like this. Furthermore, it may be understood such that the at least one signal condition parameter of which predicted values are obtained is the same signal condition parameter as the signal condition parameter of which current values are used as basis for the prediction, or may be understood such that the at least one signal condition parameter of which predicted values are obtained is a signal condition parameter other than the signal condition parameter of which current values are used as basis for the prediction. The current value of at least one signal condition parameter may be a current value of a reference signal received power (RSRP) such as Ll-RSRP or L2-RSRP. Furthermore, the current value of at least one signal condition parameter may be a filtered value or a normalized value, e.g. a filtered or normalized value of Ll-RSRP or L2-RSRP. Furthermore, the beam identifier may be understood as any piece of information which enables identification of the one or more beams, such as a string of characters associated with each beam. For example, the beam identifier may be an identifier of a pool of beams such as a pool of a serving cell and at least one candidate target cell. For example, the beam identifier may be a unique beam identifier such as a unique string of characters of a specific beam.

[0056] In example embodiments of the first exemplary aspect, the at least one signal condition parameter may be one or more of the following: a received signal strength indicator (RS SI); a reference signal received power (RSRP); a reference signal received quality (RSRQ); a signal-to-interference-plus-noise ratio (SINR); a block error rate (BLER).

[0057] RSSI, RSRP, RSRQ, SINR and BLER are examples of at least one signal condition parameter of which predicted and / or measured values can be obtained according to the first exemplary aspect. For example, the at least one signal condition parameter may also be a parameter which combines two or more of the mentioned signal condition parameters.

[0058] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: based on the first prediction validation condition being fulfilled, determining, based on the predicted and measured values of the at least one signal condition parameter and based on the configuration information, whether or not at least one further prediction validation condition is fulfilled, wherein the monitoring output information is only transmitted to the radio node based on both the first prediction validation condition and at least one of the at least one further prediction validation condition being fulfilled.

[0059] For example, the at least one further prediction validation condition may require a predicted value of at least one signal condition parameter to exceed or to not exceed a predefined threshold. Thereby, it can be achieved that decision making regarding a handover towards a candidate target cell is improved further, since validating the predicted values not only based on the first prediction validation condition being fulfilled, but also based on at least one of the at least one further prediction validation condition being fulfilled, may increase the reliability of the predicted values.

[0060] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: based on the first prediction validation condition being not fulfilled, obtaining updated configuration information.

[0061] As used herein, obtaining updated configuration information may be understood such that the UE switches to an updated configuration information itself. As an example of obtaining updated configuration information, the UE may update and / or process the initially received configuration information. As another example of obtaining updated configuration information, the UE may select a different part of the initially received configuration information, Thereby, it can be achieved that updated configuration information becomes available to the UE without the radio not having to transmit the updated configuration information.

[0062] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: based on the first prediction validation condition being not fulfilled, transmitting configuration update request information to the radio node.

[0063] For example, the configuration update request information may be indicative of a request by the UE towards the radio node to transmit updated configuration information back to the UE. By transmitting configuration update request information to the radio node, it can be achieved that the radio node is informed about the first prediction validation condition being not fulfilled, i.e. the predicted values of the at least one signal condition parameter being or becoming invalid. In response, the radio node may transmit updated configuration information to the UE, which may be the basis of a further prediction and / or validation of the at least one signal condition parameter, such that a change of the signal condition may be taken into account, for example.

[0064] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: initiating signalling exchange with the radio node.

[0065] Thereby, the user equipment and the radio node may be enabled to exchange signalling with each other.

[0066] In example embodiments of the first exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: transmitting signalling information to the radio node.

[0067] For example, the signalling information may be indicative of a machine learning capability of the UE, in particular by indicating that a machine learning model is implemented in the UE. Thereby, it can be achieved that the radio node is informed about such machine learning capability of the UE. According to the first exemplary aspect, a respective method is disclosed, too. The method according to the first exemplary aspect may be performed by a user equipment. The method may comprise at least the following: receiving configuration information from a radio node of a radio access network; obtaining, for one or more points in time and for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell of the radio access network, a predicted value of at least one signal condition parameter; obtaining a first selection of the one or more beams of the serving cell and / or a second selection of the one or more beams of the at least one candidate target cell; transmitting beam selection information to the radio node, wherein the beam selection information is indicative of the first and / or second selection of beams.

[0068] Within the first exemplary aspect, the disclosure of any instruction that, when executed by the at least one processor of the user equipment, causes the user equipment to perform an action shall also be considered as a disclosure of a respective action of the method.

[0069] According to the first exemplary aspect, a respective apparatus is disclosed, too. The apparatus according to the first exemplary aspect may comprise means for performing a method according to the first exemplary aspect. Within the first exemplary aspect, the disclosure of any method action shall also be considered as a disclosure of means for performing the respective method action. Likewise, the disclosure of any means for performing a method action shall also be considered as a disclosure of the method action itself. The apparatus according to the first exemplary aspect may be a user equipment.

[0070] The means or functionality of the user equipment according to the first exemplary aspect can be implemented in hardware and / or software. They may comprise one or multiple modules or units providing the respective functionality. They may for instance comprise at least one processor for executing computer program code for performing the required functions, at least one memory storing the program code, or both. Alternatively, they could comprise for instance circuitry that is designed to implement the required functions, for instance implemented in a chipset or a chip, like an integrated circuit. In general, the means may comprise for instance one or more processing means or processors.

[0071] According to the first exemplary aspect, a respective computer-readable medium is disclosed, too. The computer-readable medium may be non-transitory. The computer-readable medium according to the first exemplary aspect may comprise program instructions that, when executed by a user equipment, cause the user equipment to perform at least a method according to the first exemplary aspect.

[0072] The computer-readable medium according to the first exemplary aspect could for example be a disk or a memory or the like. The program instructions could be stored in the computer-readable medium in the form of instructions encoding the computer-readable medium. The computer-readable medium may be intended for taking part in the operation of a device, like an internal or external memory, for instance a Read-Only Memory (ROM) or hard disk of a computer, or be intended for distribution of the program, like an optical disc. According to the first exemplary aspect, a respective computer program is disclosed, too. The computer program according to the first exemplary aspect may comprise instructions which, when executed by a user equipment, cause the user equipment to at least perform a method according to the first exemplary aspect.

[0073] The computer program according to the first exemplary aspect may be stored on a computer-readable storage medium, in particular a tangible and / or non-transitory computer-readable storage medium. In particular, the computer program according to the first exemplary aspect may be stored on a non-transitory computer-readable medium according to the first exemplary aspect.

[0074] According to a second exemplary aspect, a radio node of a radio access network is disclosed. The radio node may comprise at least one processor and at least one memory. The at least one memory may store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: transmitting configuration information to a user equipment; receiving beam selection information from the user equipment, wherein the beam selection information is indicative of a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell.

[0075] By transmitting configuration information to a user equipment, it can be achieved that the radio node suitably configures the UE for obtaining and validating predicted values of at least one signal condition parameter, as already explained in the in the context of the first exemplary aspect. By receiving beam selection information from the user equipment, wherein the beam selection information is indicative of a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell, it can be achieved that the first and / or second selection of beams is made available to the radio node, for example as a basis for decision making regarding a handover towards a candidate target cell. Since a respective decision based on the first and / or second selection of beams may be more reliable, for example compared to only measuring current values of the at least one signal condition parameter, the decision making can be improved, as already explained in the in the context of the first exemplary aspect. Furthermore, since a decision based on the first and / or second selection does of beams not require measurement reports regarding the at least one signal condition parameter to be continuously transmitted from the UE to the radio node, signalling overhead between the UE and the radio node may be reduced, as also already explained in the in the context of the first exemplary aspect.

[0076] In example embodiments of the second exemplary aspect, the beam selection information may be comprised by status information received by the radio node from the user equipment.

[0077] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: determining, based on key performance indicator information comprised by the status information, whether or not at least one key performance indicator condition is fulfilled. For example, the key performance indicator condition may be a condition whether a key performance indicator exceeds or does not exceed a predefined threshold. For example, the key performance indicator condition may be a condition whether or not a key performance indicator is within a target interval. By determining, based on key performance indicator information comprised by the status information, whether or not at least one key performance indicator condition is fulfilled, it can be achieved that the radio node is enabled to monitor one or more key performance indicators obtained from the user equipment. In cases where the respective thresholds and targets are not met, the radio node may, for example, transmit updated configuration information to the user equipment.

[0078] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: receiving monitoring request information from the user equipment.

[0079] Thereby, it can be achieved that a validation of predicted values of the at least one signal condition parameter is only performed after being triggered by the network node, as already explained in the in the context of the first exemplary aspect.

[0080] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: transmitting monitoring request acknowledge information to the user equipment.

[0081] Thereby, it can be achieved that the validation of the predicted values of the at least one signal condition parameter is triggered by the network node, as already explained in the in the context of the first exemplary aspect.

[0082] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: receiving monitoring output information from the user equipment.

[0083] Thereby, it can be achieved that information about whether the predicted values of the at least one signal condition parameter are valid or not, is made available to the radio node, which may increase the reliability of the predicted values, as already explained in the in the context of the first exemplary aspect.

[0084] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: processing the beam selection information and / or the monitoring output information.

[0085] As used herein, processing the beam selection information and / or the monitoring output information may be understood such that further information, which is based on the beam selection information and / or the monitoring output information is obtained. As an example of such processing, one or more beams of at least one candidate target cell may be selected based on the beam selection information and / or the monitoring output information. For example, the selection of the one or more beams of the at least one candidate target cell may be based on the beam selection information comprised by the status information, or may be based on updated beam selection information which may be comprised by the monitoring output information. As a further example of such processing, a decision about a handover towards at least one candidate target cell may be made. For example, the decision may be based on values of at least one signal condition parameter for one or more beams of the at least one candidate target cell, which values may be comprised by the beam selection information and / or the monitoring output information. By processing the beam selection information and / or the monitoring output information, it can thus inter alia be achieved that an improved decision about a handover towards at least one candidate target cell may be made, for example a decision on the basis of the beam selection information and / or the monitoring output information, and thus ultimately on the basis of more reliable predicted and possibly validated values of at least one signal condition parameter.

[0086] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: preparing a handover of the user equipment towards at least one candidate target cell.

[0087] For example, the handover may be a handover which has been decided about in the context of processing the beam selection information and / or the monitoring output information. For example, the handover may be a handover towards one or more specific beams of the at least one candidate target cell. For example, the handover may be a LTM handover. By preparing a handover of the user equipment towards at least one candidate target cell, it can be achieved that an advantageous decision about the handover is prepared to be realised. In embodiments, the handover may also be carried out after being prepared.

[0088] In example embodiments of the second exemplary aspect, the configuration information may comprise at least one of the following: a first time information indicative of one or more points in time for which a predicted value of at least one signal condition parameter is to be obtained for the one or more beams of the serving cell and / or the one or more beams of the at least one candidate target cell; a second time information indicative of at least one of the one or more points in time for which a measured value of the at least one signal condition parameter is to be obtained for at least the first and / or second selection of beams; at least one prediction validation condition parameter based on which it is to be determined whether or not a first prediction validation condition is fulfilled.

[0089] For example, the first time information may be a number of time steps of a predefined step width. For example, the second time information may be a prediction validation measurement interval. For example, the at least one prediction validation condition parameter may be a prediction error threshold and / or a prediction error offset. With respect to this, reference to the first exemplary aspect is made.

[0090] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: receiving configuration update request information from the user equipment. Thereby, it can be achieved that the radio node is informed about the first prediction validation condition being not fulfilled, i.e. the predicted values of the at least one signal condition parameter being or becoming invalid, as already explained in the in the context of the first exemplary aspect. In response, the radio node may transmit updated configuration information to the UE, which may be the basis of a further prediction and / or validation of the at least one signal condition parameter, such that a change of the signal condition may be taken into account, for example.

[0091] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: initiating signalling exchange with the user equipment.

[0092] Thereby, the user equipment and the radio node may be enabled to exchange signalling with each other, as already explained in the in the context of the first exemplary aspect.

[0093] In example embodiments of the second exemplary aspect, the at least one memory may further store instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: receiving signalling information from the user equipment.

[0094] Thereby, it can be achieved that the radio node is informed about a machine learning capability of the UE, as already explained in the in the context of the first exemplary aspect.

[0095] According to the second exemplary aspect, a respective method is disclosed, too. The method according to the second exemplary aspect may be performed by a radio node of a radio access network. The method may comprise at least the following: transmitting configuration information to a user equipment; receiving beam selection information from the user equipment, wherein the beam selection information is indicative of a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell.

[0096] Within the second exemplary aspect, the disclosure of any instruction that, when executed by the at least one processor of the radio node, causes the radio node to perform an action shall also be considered as a disclosure of a respective action of the method.

[0097] According to the second exemplary aspect, a respective apparatus is disclosed, too. The apparatus according to the second exemplary aspect may comprise means for performing a method according to the second exemplary aspect. Within the second exemplary aspect, the disclosure of any method action shall also be considered as a disclosure of means for performing the respective method action. Likewise, the disclosure of any means for performing a method action shall also be considered as a disclosure of the method action itself. The apparatus according to the second exemplary aspect may be a radio node.

[0098] The means or functionality of the radio node according to the second exemplary aspect can be implemented in hardware and / or software. They may comprise one or multiple modules or units providing the respective functionality. They may for instance comprise at least one processor for executing computer program code for performing the required functions, at least one memory storing the program code, or both. Alternatively, they could comprise for instance circuitry that is designed to implement the required functions, for instance implemented in a chipset or a chip, like an integrated circuit. In general, the means may comprise for instance one or more processing means or processors.

[0099] According to the second exemplary aspect, a respective computer-readable medium is disclosed, too. The computer-readable medium may be non-transitory. The computer-readable medium according to the second exemplary aspect may comprise program instructions that, when executed by a radio node, cause the radio node to perform at least a method according to the second exemplary aspect.

[0100] The computer-readable medium according to the second exemplary aspect could for example be a disk or a memory or the like. The program instructions could be stored in the computer-readable medium in the form of instructions encoding the computer-readable medium. The computer-readable medium may be intended for taking part in the operation of a device, like an internal or external memory, for instance a Read-Only Memory (ROM) or hard disk of a computer, or be intended for distribution of the program, like an optical disc.

[0101] According to the second exemplary aspect, a respective computer program is disclosed, too. The computer program according to the second exemplary aspect may comprise instructions which, when executed by a radio node, cause the radio node to at least perform a method according to the second exemplary aspect.

[0102] The computer program according to the second exemplary aspect may be stored on a computer-readable storage medium, in particular a tangible and / or non-transitory computer-readable storage medium. In particular, the computer program according to the second exemplary aspect may be stored on a non-transitory computer- readable medium according to the second exemplary aspect.

[0103] It is to be understood that the presentation of the embodiments disclosed herein is merely by way of examples and non-limiting.

[0104] Other features of the present disclosure will become apparent from the following detailed description considered in conjunction with the accompanying drawings. It is to be understood, however, that the drawings are designed solely for purposes of illustration and not as a definition of the limits of the present disclosure, for which reference should be made to the appended claims. It should be further understood that the drawings are not drawn to scale and that they are merely intended to conceptually illustrate the structures and procedures described herein. BRIEF DESCRIPTION OF THE FIGURES

[0105] Some example embodiments will now be described with reference to the accompanying drawings in which

[0106] FIG. 1 exemplarily illustrates, in a schematic diagram, a radio environment in which example embodiments of the present disclosure may be performed;

[0107] FIG. 2 shows, in a signalling flow chart, example embodiments of methods according to the first and second aspect;

[0108] FIG. 3 shows, in a schematic block diagram, an example embodiment of a user equipment according to the first aspect;

[0109] FIG. 4 shows, in a schematic block diagram, an example embodiment of a radio node according to the second aspect;

[0110] FIG. 5 shows, in a schematic illustration, examples of tangible and non-transitory computer-readable storage media.

[0111] DETAILED DESCRIPTION OF THE FIGURES

[0112] The following description serves to deepen the understanding of the present disclosure and shall be understood to complement and be read together with the description of example embodiments of the present disclosure as provided in the above SUMMARY section of this specification.

[0113] In the following and with reference to FIG. 1, an example radio environment, in which the present disclosure may be applied, is described. While the specific radio system in the examples below is a 5G system, this is to be considered only as a non-limiting example.

[0114] FIG. 1 exemplarily illustrates, as an example of a UE according to the first exemplary aspect, a user equipment (UE) 101, and as respective examples of a radio node according to the second exemplary aspect, gNBs 102, 103, 104. Together, gNBs 102, 103, 104 may establish a wireless communication system or network serving a geographical area within which UE 101 is located. In the example shown in FIG 1, gNB 102 is associated with a serving cell for the UE, and gNBs 103, 104 are associated with candidate target cells for the UE.

[0115] As shown in FIG. 1, gNBs 102, 103, 104 utilise the beam forming technique. Exemplarily, beams 102a, 102b, 102c and 102d are shown for gNB 102. Exemplarily, beams 103a, 103b, 103c and 103d are shown for gNB 103. Exemplarily, beams 104a, 104b, 104c and 104d are shown for gNB 104. In this example, UE 101 likewise supports beam forming, which is not mandatory however. Exemplarily, beams 101a and 101b are shown for UE 101. UE 101 may be connected with one or more of gNBs 102, 103, 104 by means of radio links (not shown), which may for example correspond to the 5G / NR Un interface. gNBs 102, 103, 104 may be connected with one another by means of radio links (not shown), which may for example correspond to the 5G / NR Xn interface. The radio links may enable transmitting and / or receiving of information and / or signals between the respective devices.

[0116] At some point in time, as indicated by the arrow 110, UE 101 moves from a first position to a second position. Whereas at the first position the UE is served by a serving cell associated with gNB 102, a candidate target cell associated with gNBs 103, 104 may be serving the UE at the second position. Thus, during the movement of UE 101 along arrow 110, a handover of UE 101 from gNB 102 to at least one of gNBs 103, 104 may be prepared or performed. For example, the handover may be a LTM handover.

[0117] Turning now to FIG. 2, a signalling flow chart of example embodiments of methods according to the first and second aspect is shown. More specifically, the succession of actions and signalling between a user equipment (UE) 101 and a radio node, here a gNodeB (gNB) 102, is shown. As a non-limiting example, the gNB acts here as a distributed unit (DU). Furthermore, UE 101 is served by a serving cell associated with gNB 102 in this example, more specifically by a beam generated by gNB 102 by means of beamforming.

[0118] Within action 202, UE 101 and gNB 102 initiate signalling exchange for machine-leaming-based (ML) radio resource management (RRM) capability (ML-RRM) with one another.

[0119] Within action 204, UE 101 transmits signalling information to gNB 102. Here, UE 101 exemplarily transmits ML-based beam and cell prediction and validation (monitoring) signalling to gNB 102 as an example of signalling information. The signalling information is indicative of ML capability of the UE by indicating that a ML model is implemented in the UE. As a non-limiting example, a LSTM-RNN is implemented in UE 101 to provide the ML model. In embodiments, a transformer may be implemented in UE 101 to provide the ML model.

[0120] In an embodiment, UE 101 may receive training information (not shown in FIG. 2) for updating the training of the ML model.

[0121] Within action 206, gNB 102 transmits, as an example of configuration information, the following parameters to UE 101: a number of prediction steps Up, a prediction validation measurement interval nm, a prediction error threshold THpe, a prediction error offset OSpe.

[0122] The number of prediction steps Up is an integer indicating the number of future time steps of predefined step width At for which a prediction of the signal condition parameter RSRP is to be carried out by the ML model for one or more beams of the serving cell and one or more beams of the candidate target cells, in order to obtain respective predicted values. As such, Up is an example of a first time information according to the first and second aspect. For illustration, np= 20 in this non-limiting example. The prediction validation measurement interval nmis an integer indicating a future time step after which a validation measurement of the signal condition parameter RSRP is to be carried out by UE 101 for the one or more beams of the serving cell and the one or more beams of the candidate target cells, in order to obtain respective measured values. As such, nmis an example of a second time information according to the first and second aspect. For illustration, nm= 5 in this non-limiting example. The prediction error threshold THpeis a threshold which must not be exceeded for a first validation condition to be fulfilled, as will be described in more detail below. The prediction error offset OSpeis a fixed value to be added to a prediction error, as will be described in more detail below. As such, THpeand OSpeare examples of prediction validation condition parameters according to the first and second aspect.

[0123] Within action 208, UE 101 obtains, as an example for predicted values of at least one signal condition parameter, predicted RSRP values by carrying out a prediction using the ML model. The predicted values are obtained for the points in time to + At, to + 2 At, ... , to + npAt and for the one or more beams of the serving cell and the one or more beams of the candidate target cells. Here, to indicates a current point in time serving as a reference. As a non-limiting example, to may be equal to the point in time at which the configuration information is received by UE 101.

[0124] As input for the ML model, a two-dimensional matrix as represented by TAB. 1 is used. In this example, RSRP values are predicted by the ML model based on a unique beam identifier (ID), a current RSRP value for each beam ID and a window length for each RSRP. For better illustration, the beam ID in this example is an integer between 1 and Z, but it may generally be any suitable piece of information, such as a string of characters, uniquely identifying the respective beam. In embodiments, the prediction may be based on further input parameters, such as additional signal condition parameters associated with the respective beam IDs. The RSRP values relate to the reference time to, i.e. to a current time, and thus are an example of current values of at least one signal condition parameter according to the first aspect. In embodiments, the RSRP values may be LI -RSRP values or L2-RSRP values. In embodiments, the RSRP values may be filtered values, such as filtered values of LI -RSRP or L2-RSRP.

[0125] TABLE 1 : representation of two-dimensional matrix as input for ML model. Based on the two-dimensional input matrix, the ML model provided by the LSTM-RNN predicts RSRP values for beams 1 to Z and for to + At, to + 2 At, ... , to + Up At. In this example, beams 1 to X are generated by gNB 102 associated with a serving cell, beams X+l to Y are generated by gNB 103 associated with a first candidate target cell, and beams Y+l to Z are generated by gNB 104 associated with a second candidate target cell.

[0126] Based on the prediction for to + At, to + 2 At, ..., to + npAt, UE 101 selects the top K beams of the serving cell and the top N beams of the candidate target cells, wherein K and N are integers, and wherein the expressions “top K” and “top N” relate to the respective number of beams having the largest predicted RSRP values. In example embodiments, further selection criteria may be applied to obtain also a selection of top M candidate target cells, wherein M is an integer, or to obtain a selection of top N beams of top M candidate target cells. In an embodiment, the values of K, M and / or N may be included in the configuration information transmitted from gNB 102 to UE 101 within action 206. In another embodiment, the values of K, M and / or N may be predetermined globally.

[0127] Within action 210, UE 101 measures RSRP of beams 1 to Z. The measurement is carried out at to + nmAt according to the prediction validation measurement interval. In an embodiment, the measurement may be carried out only for the selected top K beams of the serving cell and the top N beams of the candidate target cells.

[0128] Within action 212, UE 101 performs a plausibility check of the predicted RSRP values, and transmits status information and a validation (monitoring) request to gNB 102. The status information comprises position information indicative of an estimate of a current position of UE 101. Furthermore, the status information comprises the beam IDs of the selected top K beams of the serving cell and top N beams of the candidate target cells, which is an example of beam selection information according to the first and second aspect. In embodiments, UE 101 may transmit only the beam selection information.

[0129] Within action 214, gNB 102 transmits monitoring request acknowledge to UE 101.

[0130] In an embodiment, action 212 is carried out only after action 214 has been completed.

[0131] Within action 216, UE 101 performs model validation by calculating, as an example of a prediction error, a mean squared error (MSE) for the predicted and measured RSRP values and for point in time to + nmAt, for which both predicted and measured RSRP values are available. The MSE is calculated as follows: with RSRPpj denoting the predicted RSRP values obtained within action 208 for beams i = 1 ... Z and RSRPm,i denoting the measured RSRP values obtained within action 210 for beams i = 1 ... Z. In an embodiment, the MSE may be calculated only for the selected top K beams of the serving cell and the top N beams of the candidate target cells. Based on the calculated MSE, UE then determines whether the condition MSE + OSpe< THpe, which is an example of a first prediction validation condition according to the first aspect, is fulfilled. For this example, it is assumed that the condition MSE + OSpe< THpeis fulfilled, and thus that the predicted RSRP values are sufficiently reliable.

[0132] Within action 218, UE 101 determines whether further prediction validation conditions are fulfilled. As a second prediction validation condition, UE 101 determines whether the predicted RSRP value for each of the top K beams of the serving cell and each of the top N beams of the candidate target cells exceeds a predefined threshold. In an embodiment, the UE 101 may use the measured RSRP values instead of the predicted RSRP values for determining whether the second prediction validation condition is fulfilled. As a third prediction validation condition, UE 101 determines whether a BLER value for each of the top K beams of the serving cell and each of the top N beams of the candidate target cells does not exceed a predefined threshold. The BLER values may be predicted and / or measured similarly to the RSRP values as described above. In this example embodiment, the second and third prediction validation conditions are checked as further prediction validation conditions. In embodiments, more than the second and third prediction validation condition may be checked as further prediction validation conditions. For example, as a fourth prediction validation condition, UE 101 may determine whether a SINR value for each of the top K beams of the serving cell and each of the top N beams of the candidate target cells exceeds a predefined threshold. The SINR values may be predicted and / or measured similarly to the RSRP values as described above. For this example, it is assumed that the second and third prediction validation conditions are also fulfilled.

[0133] Based on determining within action 216 that the first prediction validation condition is fulfilled, and based on determining within action 218 that also the second and third prediction validation conditions are fulfilled, UE 101 then proceeds with action 222. Generally however, action 218 may be optional and UE 101 may already proceed with action 222 based on determining within action 216 that the first prediction validation condition is fulfilled.

[0134] Action 220 is only performed based on determining within action 216 that the first prediction validation condition is not fulfilled, and is thus not performed in this example. Within action 220, UE 101 discards the predictions and proceeds by re-performing action 208 with an updated ML model and / or updated configuration information. In an embodiment, UE 101 may obtain such updated configuration information by updating and / or processing the configuration information received within action 206. In another embodiment, UE 101 may obtain such updated configuration information by selecting a different part of the configuration information received within action 206. In yet another embodiment, UE 101 may obtain such updated configuration information by transmitting a configuration update request to the gNB 102 which, in response, transmits the updated configuration information to UE 101. Within action 222, UE 101 transmits monitoring output information to gNB 102 to indicate, as a result of the monitoring, that the predicted RSRP values are valid. In this example, the monitoring output information also comprises model identification information which is indicative of an identification of the ML model used for the prediction.

[0135] Within action 224, gNB 102 performs post-processing of the beam selection information and the monitoring output information. Here, gNB 102, based on the information that the predicted RSRP values are valid, selects a specific beam generated by the first candidate target cell and decides that a handover of UE 101 towards the first candidate target cell associated with gNB 103, more precisely towards the specific beam, is to be performed. Since the decision is based on the selected top K beams of the serving cell and top N beams of the candidate target cells, which are in turn based on the prediction carried out within action 208, the decision is made on the basis of more reliable information regarding suitable beams for a respective handover, which eventually results in an improved decision. Furthermore, the decision does not require measurement reports regarding a signal condition parameter such as RSRP to be continuously transmitted from UE 101 to gNB 102, and thus signalling overhead between UE 101 and gNB 102 is reduced.

[0136] Within action 226, gNB 102 prepares the handover of UE 101 towards the first candidate target cell generated by gNB 103, more precisely towards the specific beam selected within action 224. In this example, the handover is a LTM handover.

[0137] Turning now to FIG. 3, there is shown a block diagram of an example embodiment of a UE 300 according to the first aspect. For example, UE 300 may be one of a smartphone, a tablet computer, a notebook computer, a smart watch, a smart band, an loT device or a vehicle or a part thereof.

[0138] UE 300 comprises a processor 301. Processor 301 may represent a single processor or two or more processors, which are for instance at least partially coupled, for instance via a bus. Processor 301 executes program code stored in program memory 302 (for instance program code causing UE 300 in connection with gNB 400 to perform one or more of the embodiments of a method according to the present disclosure or parts thereof, when executed on processor 301) and interfaces with a main memory 303. Program memory 302 may also contain an operating system for processor 301. Some or all of memories 302 and 303 may also be included into processor 301.

[0139] One or both of a main memory and a program memory of a processor (e.g. program memory 302 and main memory 303) could be fixedly connected to the processor (e.g. processor 301) or at least partially removable from the processor, for instance in the form of a memory card or stick.

[0140] A program memory (e.g. program memory 302) may for instance be a non-volatile memory. It may for instance be a FLASH memory (or a part thereof), any of a ROM, PROM, EPROM, MRAM or a FeRAM (or a part thereof) or a hard disc (or a part thereof), to name but a few examples. For example, a program memory may for instance comprise a first memory section that is fixedly installed, and a second memory section that is removable from, for instance in the form of a removable SD memory card.

[0141] A main memory (e.g. main memory 303) may for instance be a volatile memory. It may for instance be a DRAM memory, to give non-limiting example. It may for instance be used as a working memory for processor 301 when executing an operating system, an application, a program, and / or the like.

[0142] Processor 301 may further control a communication interface 304 (e.g. radio interface) configured to receive and / or transmit data and / or information. For instance, communication interface 304 may be configured to transmit and / or receive radio signals from a radio node, such as a radio node, in particular as described herein. It is to be understood that any computer program code based processing required for receiving and / or evaluating radio signals may be stored in an own memory of communication interface 304 and executed by an own processor of communication interface 304 and / or it may be stored for example in memory 303 and executed for example by processor 301.

[0143] Communication interface 304 may in particular be configured to communicate according to a cellular communication system like a 2G / 3G / 4G / 5G or future generation cellular communication system. UE 300 may use radio interface 304 to communicate with a radio node, in particular as described herein.

[0144] For example, communication interface 304 may further comprise a BLE and / or Bluetooth radio interface including a BLE transmitter, receiver or transceiver. For example, radio interface 304 may additionally or alternatively comprise a WLAN radio interface including at least a WLAN transmitter, receiver or transceiver.

[0145] The components 302, 303 and 304 of UE 300 may for instance be connected with processor 301 by means of one or more serial and / or parallel busses.

[0146] It is to be understood that UE 300 may comprise various other components. For example, UE 300 may optionally comprise a user interface (e.g. a touch-sensitive display, a keyboard, a touchpad, a display, etc.).

[0147] FIG. 4 is a block diagram of an example embodiment of a radio node 400, such as a gNB 400. For instance, radio node 400 may be configured for scheduling and / or transmitting signals to UE 300, and / or to one or more further radio nodes 400.

[0148] Radio node 400 comprises a processor 401. Processor 401 may represent a single processor or two or more processors, which are for instance at least partially coupled, for instance via a bus. Processor 401 executes a program code stored in program memory 402 (for instance program code causing radio node 400 to perform alone, together with UE 300, and / or together with one or more further radio nodes 400, one or more of the embodiments of a method according to the present disclosure or parts thereof, when executed on processor 401), and interfaces with a main memory 403. Program memory 402 may also comprise an operating system for processor 401. Some or all of memories 402 and 403 may also be included into processor 401.

[0149] Moreover, processor 401 may control a communication interface 404 which is for example configmed to communicate according to a cellular communication system like a 2G / 3G / 4G / 5G cellular communication system. Communication interface 404 of radio node 400 may be realized by radio heads for instance and may be provided for communication between network device and terminal device. Communication interface 404 of radio node 400 may support beamforming.

[0150] The components 402, 403 and 404 of radio node 400 may for instance be connected with processor 401 by means of one or more serial and / or parallel busses.

[0151] It is to be understood that radio node 400 may comprise various other components.

[0152] FIG. 5 is a schematic illustration of examples of tangible and non-transitory computer-readable storage media according to the present disclosure that may for instance be used to implement memory 302 of FIG. 3 or memory 402 of FIG. 4. To this end, FIG. 5 displays a flash memory 500, which may for instance be soldered or bonded to a printed circuit board, a solid-state drive 501 comprising a plurality of memory chips (e.g. Flash memory chips), a magnetic hard drive 502, a Secure Digital (SD) card 503, a Universal Serial Bus (USB) memory stick 504, an optical storage medium 505 (such as for instance a CD-ROM or DVD) and a magnetic storage medium 506.

[0153] Any presented connection in the described embodiments is to be understood in a way that the involved components are operationally coupled. Thus, the connections can be direct or indirect with any number or combination of intervening elements, and there may be merely a functional relationship between the components.

[0154] Further, as used in this text, the term ‘circuitry’ refers to any of the following:

[0155] (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry);

[0156] (b) combinations of circuits and software (and / or firmware), such as:

[0157] (i) a combination of processor(s), or

[0158] (ii) sections of processor(s) / software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone, to perform various functions); and

[0159] (c) circuits, such as a microprocessors) or a section of a microprocessor(s), that require software or firmware for operation, even if the software or firmware is not physically present.

[0160] This definition of ‘circuitry’ applies to all uses of this term in this text, including in any claims. As a further example, as used in this text, the term ‘circuitry’ also covers an implementation of merely a processor (or multiple processors) or section of a processor and its (or their) accompanying software and / or firmware. The term ‘circuitry’ also covers, for example, a baseband integrated circuit or applications processor integrated circuit for a mobile phone.

[0161] Any of the processors mentioned in this text, in particular but not limited to processors 301 and 401 of FIGs. 3 and 4, could be a processor of any suitable type. Any processor may comprise but is not limited to one or more microprocessors, one or more processor(s) with accompanying digital signal processor(s), one or more processor(s) without accompanying digital signal processor(s), one or more special-purpose computer chips, one or more field-programmable gate arrays (FPGAS), one or more controllers, one or more application-specific integrated circuits (ASICS), or one or more computer(s). The relevant structure / hardware has been programmed in such a way to carry out the described function.

[0162] Moreover, any of the actions or steps described or illustrated herein may be implemented using executable instructions in a general-purpose or special-purpose processor and stored on a computer-readable storage medium (e.g. disk, memory, or the like) to be executed by such a processor. References to ‘computer-readable storage medium’ should be understood to encompass specialized circuits such as FPGAs, ASICs, signal processing devices, and other devices.

[0163] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0164] The wording “A, or B, or C, or a combination thereof’ or “at least one of A, B and C” may be understood to be not exhaustive and to include at least the following: (i) A, or (ii) B, or (iii) C, or (iv) A and B, or (v) A and C, or (vi) B and C, or (vii) A and B and C.

[0165] It will be understood that the embodiments disclosed herein are only exemplary, and that any feature presented for a particular exemplary embodiment may be used with any aspect of the present disclosure on its own or in combination with any feature presented for the same or another particular exemplary embodiment and / or in combination with any other feature not mentioned. It will further be understood that any feature presented for an example embodiment in a particular category may also be used in a corresponding manner in an example embodiment of any other category.

[0166] ABBREVIATIONS

[0167] 3 GPP 3 rd Generation Partnership Proj ect

[0168] BLER Block Error Rate

[0169] CNN Convolutional Neural Network

[0170] CSI Channel Status Information

[0171] CU Central Unit DU Distributed Unit gNB gNodeB

[0172] LI PHY layer

[0173] L2 MAC layer

[0174] L3 RRC layer

[0175] LSTM Long Short-Term Memory

[0176] LTM Lower-Layer-Triggered Mobility MAC Medium Access Control ML Machine Learning

[0177] MSE Mean Squared Error

[0178] NR New Radio

[0179] PCI Physical Cell Identifier

[0180] PHY Physical

[0181] RAN Radio Access Network

[0182] RNN Recurrent Neural Network

[0183] RRC Radio Resource Control

[0184] RRM Radio Resource Management RS Reference Signal

[0185] RSRP Reference Signal Received Power RSRQ Reference Signal Received Quality RS SI Received Signal Strength Indicator SINR Signal-to-Interference-plus-Noise Ratio SSB Synchronization Signal Block TRP T ransmission and Reception Point

[0186] UE User Equipment

Claims

C l a i m s1) A user equipment comprising at least one processor and at least one memory, the at least one memory storing instructions that, when executed by the at least one processor, cause the user equipment to perform at least the following: receiving configuration information from a radio node of a radio access network; obtaining, for one or more points in time and for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell of the radio access network, a predicted value of at least one signal condition parameter; obtaining a first selection of the one or more beams of the serving cell and / or a second selection of the one or more beams of the at least one candidate target cell; transmitting beam selection information to the radio node, wherein the beam selection information is indicative of the first and / or second selection of beams.2) The user equipment according to claim 1, the at least one memory further storing instructions that, when executed by the at least one processor, cause the user equipment to perform at least one of the following: transmitting monitoring request information to the radio node; receiving monitoring request acknowledge information from the radio node; obtaining, at least for one of the one or more points in time and at least for the first and / or second selection of beams, a measured value of the at least one signal condition parameter; determining, based on the predicted and measured values of the at least one signal condition parameter and based on the configuration information, whether or not a first prediction validation condition is fulfilled; based on the first prediction validation condition being fulfilled, transmitting monitoring output information to the radio node.3) The user equipment according to claim 2, wherein the configuration information comprises at least one of the following: a first time information indicative of the one or more points in time for which the predicted value of the at least one signal condition parameter is to be obtained for the one or more beams of the serving cell and / or the one or more beams of the at least one candidate target cell;a second time information indicative of the at least one point in time for which the measured value of the at least one signal condition parameter is to be obtained for at least the first and / or second selection of beams; at least one prediction validation condition parameter based on which it is to be determined whether or not the first prediction validation condition is fulfilled.4) The user equipment according to claim 3, wherein the first time information is a number of time steps of a predefined step width; and / or wherein the second time information is a prediction validation measurement interval; and / or wherein the at least one prediction validation condition parameter is a prediction error threshold and / or a prediction error offset.5) The user equipment according to one of claims 1 to 4, wherein obtaining the predicted value of the at least one signal condition parameter and / or obtaining the first and / or second selection of beams is carried out using a neural network.6) The user equipment according to claim 5, wherein the neural network is at least one of the following: a long short-term memory (LSTM) neural network; a recurrent neural network (RNN); a convolutional neural network (CNN); a transformer.7) The user equipment according to one of claims 1 to 6, wherein obtaining the predicted value of the at least one signal condition parameter is based on at least one of the following: a current value of at least one signal condition parameter for the one or more beams of the serving cell and / or the one or more beams of the at least one candidate target cell; a window length associated with the respective one or more beams; a beam identifier associated with the respective one or more beams.8) The user equipment according to one of claims 1 to 7, wherein the at least one signal condition parameter is one or more of the following: a received signal strength indicator (RS SI); a reference signal received power (RSRP); a reference signal received quality (RSRQ); a signal-to-interference-plus-noise ratio (SINR); a block error rate (BLER).9) The user equipment according to claim 2, the at least one memory further storing instructions that, when executed by the at least one processor, cause the user equipment to perform at least one of the following: based on the first prediction validation condition being fulfilled, determining, based on the predicted and measured values of the at least one signal condition parameter and based on the configuration information, whether or not at least one further prediction validation condition is fulfilled, wherein the monitoring output information is only transmitted to the radio node based on both the first prediction validation condition and at least one of the at least one further prediction validation condition being fulfilled; based on the first prediction validation condition being not fulfilled, obtaining updated configuration information; based on the first prediction validation condition being not fulfilled, transmitting configuration update request information to the radio node.10) The user equipment according to one of claims 1 to 9, the at least one memory further storing instructions that, when executed by the at least one processor, cause the user equipment to perform at least one of the following: initiating signalling exchange with the radio node; transmitting signalling information to the radio node.11) A method performed by a user equipment, the method comprising at least the following: receiving configuration information from a radio node of a radio access network; obtaining, for one or more points in time and for one or more beams of a serving cell and / or one or more beams of at least one candidate target cell of the radio access network, a predicted value of at least one signal condition parameter; obtaining a first selection of the one or more beams of the serving cell and / or a second selection of the one or more beams of the at least one candidate target cell; transmitting beam selection information to the radio node, wherein the beam selection information is indicative of the first and / or second selection of beams.12) A radio node of a radio access network, the radio node comprising at least one processor and at least one memory, the at least one memory storing instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: transmitting configuration information to a user equipment; receiving beam selection information from the user equipment, wherein the beam selection information is indicative of a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell.13) The radio node according to claim 12, the at least one memory further storing instructions that, when executed by the at least one processor, cause the radio node to perform at least one of the following: receiving monitoring request information from the user equipment; transmitting monitoring request acknowledge information to the user equipment; receiving monitoring output information from the user equipment; processing the beam selection information and / or the monitoring output information; preparing a handover of the user equipment towards at least one candidate target cell.14) The radio node according to claim 12, wherein the configuration information comprises at least one of the following: a first time information indicative of one or more points in time for which a predicted value of at least one signal condition parameter is to be obtained for the one or more beams of the serving cell and / or the one or more beams of the at least one candidate target cell; a second time information indicative of at least one of the one or more points in time for which a measured value of the at least one signal condition parameter is to be obtained for at least the first and / or second selection of beams; at least one prediction validation condition parameter based on which it is to be determined whether or not a first prediction validation condition is fulfilled.15) The radio node according to claim 14, wherein the first time information is a number of time steps of a predefined step width; and / or wherein the second time information is a prediction validation measurement interval; and / or wherein the at least one prediction validation condition parameter is a prediction error threshold and / or a prediction error offset.16) The radio node according to one of clams 12 to 15, the at least one memory further storing instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: receiving configuration update request information from the user equipment.17) The radio node according to one of clams 12 to 16, the at least one memory further storing instructions that, when executed by the at least one processor, cause the radio node to perform at least the following: initiating signalling exchange with the user equipment; receiving signalling information from the user equipment.18) A method performed by a radio node of a radio access network, the method comprising at least the following: transmitting configuration information to a user equipment;receiving beam selection information from the user equipment, wherein the beam selection information is indicative of a first selection of one or more beams of a serving cell and / or a second selection of one or more beams of at least one candidate target cell.

Citation Information

Patent Citations

  • User terminal and radio communication method

    US20190261347A1

  • Measurement method, device, and storage medium

    WO2022127773A1

  • Wireless terminal, radio access network node, and methods therefor

    WO2023079947A1