WO2025209010A1

WO2025209010A1 - Methods and apparatuses of an artificial intelligence (ai) based prediction for layer 1/layer 2 (l1/l2) triggered mobility (ltm)

Info

Publication number: WO2025209010A1
Application number: PCT/CN2025/074783
Authority: WO
Inventors: Lianhai WU; Le Yan; Ran YUE
Original assignee: Lenovo Beijing Ltd
Current assignee: Lenovo Beijing Ltd
Priority date: 2025-01-24
Filing date: 2025-01-24
Publication date: 2025-10-09
Anticipated expiration: 2027-07-24

Abstract

Various aspects of the present application relate to methods and apparatuses of an artificial intelligence (AI) based prediction for layer 1/layer 2 (L1/L2) triggered mobility (LTM), for example, an AI based prediction for a layer-1 (L1) beam measurement result and/or an L1 event. According to an embodiment of the present application, a user equipment (UE) includes at least one memory and at least one processor coupled to the at least one memory and configured to cause the UE to: transmit capability information of the UE associated with an AI based prediction of at least one of an L1 beam measurement result or an L1 event; receive a configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event; and perform the AI based prediction based on the configuration.

Description

METHODS AND APPARATUSES OF AN ARTIFICIAL INTELLIGENCE (AI) BASED PREDICTION FOR LAYER 1/LAYER 2 (L1/L2) TRIGGERED MOBILITY (LTM)

TECHNICAL FIELD

The present application relates to wireless communications, and more specifically to methods and apparatuses of an artificial intelligence (AI) based prediction for layer 1/layer 2 (L1/L2) triggered mobility (LTM) , for example, an AI based prediction for a layer-1 (L1) beam measurement result and/or an L1 event.

BACKGROUND

A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE) , or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g. time-domain resources (e.g. symbols, slots, subframes, frames, or the like) or frequency-domain resources (e.g. subcarriers, carriers, or the like) . Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g. sixth generation (6G) ) .

SUMMARY

An article "a" before an element is unrestricted and understood to refer to "at least one" of those elements or "one or more" of those elements. The terms "a, " "at least one, " "one or more, " and "at least one of one or more" may be interchangeable. As used herein, including in the claims, "or" as used in a list of items (e.g. a list of items prefaced by a phrase such as "at least one of" or "one or more of" or "one or both of" ) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C) . Also, as used herein, the phrase "based on" shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as "based on condition A" may be based on both a condition A and a condition B without departing from the scope of the present application. In other words, as used herein, the phrase "based on" shall be construed in the same manner as the phrase "based at least in part on. Further, as used herein, including in the claims, a "set" may include one or more elements.

Some implementations of the present application provide a user equipment (UE) . The UE includes at least one memory; and at least one processor coupled to the at least one memory and configured to cause the UE to: transmit capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; receive a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event; and perform the AI based prediction based on the first configuration.

In some implementations of the UE described herein, the capability information indicates at least one of the following: the UE supporting an L1 beam measurement result prediction; the UE supporting the L1 beam measurement result prediction based on a spatial domain measurement; the UE supporting the L1 beam measurement result prediction based on a temporal domain measurement; the UE supporting a direct L1 event prediction; the UE supporting an indirect L1 event prediction; the UE supporting both the direct L1 event prediction and indirect L1 event prediction; the UE supporting an L1 event prediction based on the spatial domain measurement; or the UE supporting the L1 event prediction based on the temporal domain measurement.

In some implementations of the UE described herein, if the first configuration is for the L1 beam measurement result, the first configuration includes at least one of the following: information of a first prediction time window; information of a first reference signal (RS) resource for a cell of the UE; information indicating a spatial domain measurement for the cell; information indicating a temporal domain measurement for the cell; information indicating a first type of temporal domain measurement prediction for the cell; or information indicating a second type of temporal domain measurement prediction for the cell, wherein the cell is a serving cell or a set of candidate cells of the UE.

In some implementations of the UE described herein, to perform the AI based prediction for the L1 beam measurement result, the at least one processor is configured to cause the UE to perform a measurement on the first RS resource and predict the L1 beam measurement result within the first prediction time window, and wherein the L1 beam measurement result is predicted based on: one or more historical beam measurement results of the serving cell or the set of candidate cells; or one or more current actual beam measurement results of the serving cell or the set of candidate cells.

In some implementations of the UE described herein, the at least one processor is configured to cause the UE to transmit a first report of prediction results after completing the AI based prediction for the L1 beam measurement result, and the first report includes information indicating at least one of the following: the L1 beam measurement result predicted by the AI based prediction; a reference signal (RS) type used for predicting the L1 beam measurement result; whether the L1 beam measurement result is predicted based on a spatial domain measurement or a temporal domain measurement for a cell of the UE; whether the L1 beam measurement result is predicted based on a historical beam measurement result or a current actual beam measurement result for the cell; or whether the L1 beam measurement result is predicted based on a first type of temporal domain measurement prediction or a second type of temporal domain measurement prediction for the cell.

In some implementations of the UE described herein, the L1 event includes at least one of the following: a first event that a current beam of a serving cell of the UE becomes worse than a first threshold, wherein the current beam is a beam corresponding to a transmission configuration indicator (TCI) state indicated by the serving cell; a second event that any beam of a candidate cell becomes an amount of offset better than the current beam of the serving cell; a third event that any beam of the candidate cell becomes better than a second threshold; or a fourth event that the current beam of the serving cell becomes worse than a third threshold and any beam of the candidate cell becomes better than a fourth threshold.

In some implementations of the UE described herein, if the first configuration is for the L1 event, the first configuration includes at least one of the following: information of a second prediction time window; information of a second reference signal (RS) resource for a cell of the UE; time to trigger (TTT) associated with the L1 event; or information indicating that a predicted L1 beam measurement result which is used to predict the L1 event is predicted based on: a spatial domain measurement for the cell; a temporal domain measurement for the cell; a first type of temporal domain measurement prediction for the cell; or a second type of temporal domain measurement prediction for the cell, wherein the cell is a serving cell or a set of candidate cells of the UE.

In some implementations of the UE described herein, to perform the AI based prediction for the L1 event, the at least one processor is configured to cause the UE to predict whether the L1 event is satisfied by adopting a direct L1 event prediction or an indirect L1 event prediction based on the first configuration.

In some implementations of the UE described herein, the L1 event is predicated as satisfied if the L1 event is considered as satisfied during a time duration.

In some implementations of the UE described herein, if the L1 event is predicted based on both L1 beam measurement results of the serving cell and the set of candidate cells, the at least one processor is configured to cause the UE to determine at least one of the following when predicting whether the L1 event is satisfied: whether a same type of RSs or different types of RSs are used for predicting the L1 beam measurement results of the serving cell and the set of candidate cells; or which type of RSs are used for predicting the L1 beam measurement results of the serving cell and the set of candidate cells.

In some implementations of the UE described herein, by adopting the direct L1 event prediction, the at least one processor is configured to cause the UE to predict occurrence probability of the L1 event within the second prediction time window; and by adopting the indirect L1 event prediction, the at least one processor is configured to cause the UE to predict expected occurrence time of the L1 event within the second prediction time window based on an L1 measurement result, wherein the L1 measurement result is predicted by performing the AI based prediction based on current data, and wherein the current data includes at least one of the following: current actual reference signal received power (RSRP) of the serving cell; or current actual RSRP of the set of candidate cells.

In some implementations of the UE described herein, to adopt the indirect L1 event prediction, the at least one processor is configured to cause the UE to select one of the following as a serving beam of a serving cell at a future time instant within the second prediction time window to be used for predicting the L1 event: any beam of the serving cell; a beam configured by a network equipment (NE) ; or a current beam of the serving cell, wherein the current beam is a beam corresponding to a transmission configuration indicator (TCI) state indicated by the serving cell.

In some implementations of the UE described herein, the current beam of the serving cell is selected as the serving beam of the serving cell at the future time instant, if no additional RS of the serving cell is configured to the UE.

In some implementations of the UE described herein, the at least one processor is configured to cause the UE to receive information indicating to predict the L1 event via the direct L1 event prediction or the indirect L1 event prediction.

In some implementations of the UE described herein, if the L1 event is predicted based on an L1 beam measurement result of the serving cell or one candidate cell of the set of candidate cells, the at least one processor is configured to cause the UE to: if a third RS resource is configured for an indirect prediction, predict the L1 event based on the third RS resource via the indirect L1 event prediction; or if the third RS resource is not configured, predict the L1 event via the direct L1 event prediction.

In some implementations of the UE described herein, the at least one processor is configured to cause the UE to: receive information requesting predicted reference signal received power (RSRP) for a beam from a network equipment (NE) ; and predict the L1 event via the indirect L1 event prediction.

In some implementations of the UE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, the at least one processor is configured to cause the UE to: if a fourth RS resource is configured for an indirect prediction for both the serving cell and the set of candidate cells, predict the L1 event based on the fourth RS resource via the indirect L1 event prediction; or if the fourth RS resource is not configured, predict the L1 event via the direct L1 event prediction.

In some implementations of the UE described herein, at least one of the first RS resource, the second RS resource, the third RS resource or the fourth RS resource carries at least one of the following: a synchronization signal block (SSB) ; a channel state information-reference signal (CSI-RS) ; a phase-tracking reference signal (PT-RS) ; a positioning reference signal (PRS) ; or a demodulation reference signal (DM-RS) .

In some implementations of the UE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, and if different RS types for predicting the first L1 beam measurement result and the second L1 beam measurement result are not allowed for the AI based prediction of the L1 event: if a same RS type is configured for predicting both the first L1 beam measurement result of the serving cell and the second L1 beam measurement result of the set of candidate cells, the L1 event is predicted based on the same RS type via the indirect L1 event prediction; or if the same RS type is not configured, the L1 event is predicted via the direct L1 event prediction.

In some implementations of the UE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, and if different prediction types for L1 measurement are not allowed for the first L1 beam measurement result and the second L1 beam measurement result: the first L1 beam measurement result is predicted based on a current actual beam measurement result of the serving cell; and the second L1 beam measurement result is predicted based on a current actual beam measurement result of the set of candidate cells.

In some implementations of the UE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, and if different domain measurements are not allowed for the first L1 beam measurement result and the second L1 beam measurement result, both the first L1 beam measurement result and the second L1 beam measurement result are predicted based on a single domain measurement, and wherein the single domain measurement is a spatial domain measurement or a temporal domain measurement.

In some implementations of the UE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, and if different temporal domain measurement predictions are not allowed for the first L1 beam measurement result and the second L1 beam measurement result, both the first L1 beam measurement result and the second L1 beam measurement result are predicted based on a same temporal domain measurement prediction, and wherein the same temporal domain measurement prediction is a first type of temporal domain measurement prediction or a second type of temporal domain measurement prediction.

In some implementations of the UE described herein, the first L1 beam measurement result and the second L1 beam measurement result are predicted by performing the AI based prediction in different prediction types or in a single prediction type within the different prediction types, and the different prediction types include: a direct prediction of predicting a beam measurement result based on one or more historical beam measurement results; or an indirect prediction of predicting the beam measurement result based on one or more predicated beam measurement results.

In some implementations of the UE described herein, the at least one processor is configured to cause the UE to receive a second configuration from a network equipment (NE) : if the second configuration provides information related to an indirect prediction for both the serving cell and the candidate cell within the sets of candidate cells, the L1 event is predicted via the indirect L1 event prediction; or if the second configuration provides information related to the indirect prediction to only one of the serving cell or the candidate cell, the L1 event is predicted via the direct L1 event prediction.

In some implementations of the UE described herein, if different RS types for predicting the first L1 beam measurement result of the serving cell and the second L1 beam measurement result of the set of candidate cells are not allowed for the AI based prediction of the L1 event: if a same RS type is configured for predicting both the first L1 beam measurement result of the serving cell and the second L1 beam measurement result of the set of candidate cells, the L1 event is predicted based on the same RS type via the indirect L1 event prediction; or if the same RS type is not configured, the L1 event is predicted via the direct L1 event prediction.

In some implementations of the UE described herein, the at least one processor is configured to cause the UE to transmit a second report of prediction results after completing the AI based prediction for the L1 event, and the second report includes at least one of the following: information indicating whether the L1 event occurs within the second prediction time window; information indicating whether the L1 event is predicted via the direct L1 event prediction or the indirect L1 event prediction; or information indicating that a predicted L1 beam measurement result used to predict the L1 event is predicted based on: a spatial domain measurement for the cell; a temporal domain measurement for the cell; a first type of temporal domain measurement prediction for the cell; or a second type of temporal domain measurement prediction for the cell.

In some implementations of the UE described herein, by adopting the first type of temporal domain measurement prediction, the at least one processor is configured to cause the UE to predict an L1 measurement result for a first beam of the cell in a prediction time window based on same or different beam measurement results in an observation time window of the first beam; and by adopting the second type of temporal domain measurement prediction, the at least one processor is configured to cause the UE to predict a sub-set of beam measurement instants in the temporal domain of the first beam.

In some implementations of the UE described herein, at least one of the first report or the second report is transmitted via radio resource control (RRC) singling or a medium access control (MAC) control elements (CE) .

Some implementations of the present application provide a processor for wireless communication, comprising at least one controller coupled with at least one memory and configured to cause the processor to: transmit capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; receive a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event; and perform the AI based prediction based on the first configuration.

Some implementations of the present application provide a method performed by a user equipment (UE) . The method includes: transmitting capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; receiving a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event; and performing the AI based prediction based on the first configuration.

Some implementations of the present application provide a network equipment (NE) . The NE includes at least one memory; and at least one processor coupled to the at least one memory and configured to cause the NE to: receive, from a user equipment (UE) , capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; and transmit, to the UE, a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event.

In some implementations of the NE described herein, the capability information indicates at least one of the following: the UE supporting an L1 beam measurement result prediction; the UE supporting the L1 beam measurement result prediction based on a spatial domain measurement; the UE supporting the L1 beam measurement result prediction based on a temporal domain measurement; the UE supporting a direct L1 event prediction; the UE supporting an indirect L1 event prediction; the UE supporting both the direct L1 event prediction and indirect L1 event prediction; the UE supporting an L1 event prediction based on the spatial domain measurement; or the UE supporting the L1 event prediction based on the temporal domain measurement.

In some implementations of the NE described herein, if the first configuration is for the L1 beam measurement result, the first configuration includes at least one of the following: information of a first prediction time window; information of a first reference signal (RS) resource for a cell of the UE; information indicating a spatial domain measurement for the cell; information indicating a temporal domain measurement for the cell; information indicating a first type of temporal domain measurement prediction for the cell; or information indicating a second type of temporal domain measurement prediction for the cell, wherein the cell is a serving cell or a set of candidate cells of the UE.

In some implementations of the NE described herein, the L1 beam measurement result is predicted by the UE within the first prediction time window by performing the AI based prediction based on: one or more historical beam measurement results of the serving cell or the set of candidate cells; or one or more current actual beam measurement results of the serving cell or the set of candidate cells.

In some implementations of the NE described herein, the at least one processor is configured to cause the NE to receive, from the UE, a first report of prediction results of the AI based prediction for the L1 beam measurement result, and the first report includes information indicating at least one of the following: the L1 beam measurement result predicted by the AI based prediction; a reference signal (RS) type used for predicting the L1 beam measurement result; whether the L1 beam measurement result is predicted based on a spatial domain measurement or a temporal domain measurement for a cell of the UE; whether the L1 beam measurement result is predicted based on a historical beam measurement result or a current actual beam measurement result for the cell; or whether the L1 beam measurement result is predicted based on a first type of temporal domain measurement prediction or a second type of temporal domain measurement prediction for the cell.

In some implementations of the NE described herein, the L1 event includes at least one of the following: a first event that a current beam of a serving cell of the UE becomes worse than a first threshold, wherein the current beam is a beam corresponding to a transmission configuration indicator (TCI) state indicated by the serving cell; a second event that any beam of a candidate cell becomes an amount of offset better than the current beam of the serving cell; a third event that any beam of the candidate cell becomes better than a second threshold; or a fourth event that the current beam of the serving cell becomes worse than a third threshold and any beam of the candidate cell becomes better than a fourth threshold.

In some implementations of the NE described herein, if the first configuration is for the L1 event, the first configuration includes at least one of the following: information of a second prediction time window; information of a second reference signal (RS) resource for a cell of the UE; time to trigger (TTT) associated with the L1 event; or information indicating that a predicted L1 beam measurement result which is used to predict the L1 event is predicted based on: a spatial domain measurement for the cell; a temporal domain measurement for the cell; a first type of temporal domain measurement prediction for the cell; or a second type of temporal domain measurement prediction for the cell, wherein the cell is a serving cell or a set of candidate cells of the UE.

In some implementations of the NE described herein, whether the L1 event is satisfied is predicted by the UE by adopting a direct L1 event prediction or an indirect L1 event prediction via the AI based prediction based on the first configuration.

In some implementations of the NE described herein, the L1 event is predicated as satisfied if the L1 event is considered as satisfied during a time duration.

In some implementations of the NE described herein, by adopting the direct L1 event prediction, occurrence probability of the L1 event is predicted within the second prediction time window; and by adopting the indirect L1 event prediction, expected occurrence time of the L1 event is predicted within the second prediction time window based on an L1 measurement result, wherein the L1 measurement result is predicted by performing the AI based prediction based on current data, and wherein the current data includes at least one of the following: current actual reference signal received power (RSRP) of the serving cell; or current actual RSRP of the set of candidate cells.

In some implementations of the NE described herein, one of the following is selected as a serving beam of a serving cell at a future time instant within the second prediction time window to be used for predicting the L1 event by adopting the indirect L1 event prediction: any beam of the serving cell; a beam configured by a network equipment (NE) ; or a current beam of the serving cell, wherein the current beam is a beam corresponding to a transmission configuration indicator (TCI) state indicated by the serving cell.

In some implementations of the NE described herein, the current beam of the serving cell is selected as the serving beam of the serving cell at the future time instant, if no additional RS of the serving cell is configured to the UE.

In some implementations of the NE described herein, the at least one processor is configured to cause the NE to transmit, to the UE, information indicating to predict the L1 event via the direct L1 event prediction or the indirect L1 event prediction.

In some implementations of the NE described herein, if the L1 event is predicted based on an L1 beam measurement result of the serving cell or one candidate cell of the set of candidate cells: if a third RS resource is configured by the NE for an indirect prediction, the L1 event is predicted based on the third RS resource via the indirect L1 event prediction; or if the third RS resource is not configured, the L1 event is predicted via the direct L1 event prediction.

In some implementations of the NE described herein, the at least one processor is configured to cause the NE to transmit, to the UE, information requesting predicted reference signal received power (RSRP) for a beam, and wherein the L1 event is predicted via the indirect L1 event prediction.

In some implementations of the NE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells: if a fourth RS resource is configured for an indirect prediction by the NE for both the serving cell and the set of candidate cells, the L1 event is predicted based on the fourth RS resource via the indirect L1 event prediction; or if the fourth RS resource is not configured, the L1 event is predicted via the direct L1 event prediction.

In some implementations of the NE described herein, at least one of the first RS resource, the second RS resource, the third RS resource or the fourth RS resource carries at least one of the following: a synchronization signal block (SSB) ; a channel state information-reference signal (CSI-RS) ; a phase-tracking reference signal (PT-RS) ; a positioning reference signal (PRS) ; or a demodulation reference signal (DM-RS) .

In some implementations of the NE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, and if different RS types for predicting the first L1 beam measurement result and the second L1 beam measurement result are not allowed for the AI based prediction of the L1 event: if a same RS type is configured by the NE for predicting both the first L1 beam measurement result of the serving cell and the second L1 beam measurement result of the set of candidate cells, the L1 event is predicted based on the same RS type via the indirect L1 event prediction; or if the same RS type is not configured, the L1 event is predicted via the direct L1 event prediction.

In some implementations of the NE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, and if different prediction types for L1 measurement are not allowed for the first L1 beam measurement result and the second L1 beam measurement result: the first L1 beam measurement result is predicted based on a current actual beam measurement result of the serving cell; and the second L1 beam measurement result is predicted based on a current actual beam measurement result of the set of candidate cells.

In some implementations of the NE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, and if different domain measurements are not allowed for the first L1 beam measurement result and the second L1 beam measurement result, both the first L1 beam measurement result and the second L1 beam measurement result are predicted based on a single domain measurement, and wherein the single domain measurement is a spatial domain measurement or a temporal domain measurement.

In some implementations of the NE described herein, if the L1 event is predicted based on both a first L1 beam measurement result of the serving cell and a second L1 beam measurement result of a candidate cell of the set of candidate cells, and if different temporal domain measurement predictions are not allowed for the first L1 beam measurement result and the second L1 beam measurement result, both the first L1 beam measurement result and the second L1 beam measurement result are predicted based on a same temporal domain measurement prediction, and wherein the same temporal domain measurement prediction is a first type of temporal domain measurement prediction or a second type of temporal domain measurement prediction.

In some implementations of the NE described herein, the first L1 beam measurement result and the second L1 beam measurement result are predicted by performing the AI based prediction in different prediction types or in a single prediction type within the different prediction types, and the different prediction types include: a direct prediction of predicting a beam measurement result based on one or more historical beam measurement results; or an indirect prediction of predicting the beam measurement result based on one or more predicated beam measurement results.

In some implementations of the NE described herein, the at least one processor is configured to cause the NE to transmit a second configuration to the UE: if the second configuration provides information related to an indirect prediction for both the serving cell and the candidate cell within the sets of candidate cells, the L1 event is predicted via the indirect L1 event prediction; or if the second configuration provides information related to the indirect prediction to only one of the serving cell or the candidate cell, the L1 event is predicted via the direct L1 event prediction.

In some implementations of the NE described herein, if different RS types for predicting the first L1 beam measurement result and the second L1 beam measurement result are not allowed for the AI based prediction of the L1 event: if a same RS type is configured for predicting both the first L1 beam measurement result of the serving cell and the second L1 beam measurement result of the set of candidate cells, the L1 event is predicted based on the same RS type via the indirect L1 event prediction; or if the same RS type is not configured, the L1 event is predicted via the direct L1 event prediction.

In some implementations of the NE described herein, the at least one processor is configured to cause the NE to receive, from the UE, a second report of prediction results after completing the AI based prediction for the L1 event, and the second report includes at least one of the following: information indicating whether the L1 event occurs within the second prediction time window; information indicating whether the L1 event is predicted via the direct L1 event prediction or the indirect L1 event prediction; or information indicating that a predicted L1 beam measurement result used to predict the L1 event is predicted based on: a spatial domain measurement for the cell; a temporal domain measurement for the cell; a first type of temporal domain measurement prediction for the cell; or a second type of temporal domain measurement prediction for the cell.

In some implementations of the NE described herein, by adopting the first type of temporal domain measurement prediction, an L1 measurement result for a first beam of the cell is predicted by the UE in a prediction time window based on same or different beam measurement results in an observation time window of the first beam; and by adopting the second type of temporal domain measurement prediction, a sub-set of beam measurement instants is predicted by the UE in the temporal domain of the first beam.

In some implementations of the NE described herein, at least one of the first report or the second report is transmitted via radio resource control (RRC) singling or a medium access control (MAC) control elements (CE) .

Some implementations of the present application provide a processor for wireless communication, comprising at least one controller coupled with at least one memory and configured to cause the processor to: receive, from a user equipment (UE) , capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; and transmit, to the UE, a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event.

Some implementations of the present application provide a method performed by a network equipment (NE) . The method includes: receiving, from a user equipment (UE) , capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; and transmitting, to the UE, a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event.

BRIEF DESCRIPTION OF THE DRAWINGS

Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present application.

Figure 2 illustrates an example of a user equipment (UE) 200 in accordance with aspects of the present application.

Figure 3 illustrates an example of a processor 300 in accordance with aspects of the present application.

Figure 4 illustrates an example of a network equipment (NE) 400 in accordance with aspects of the present application.

Figure 5 illustrates a flowchart of a method performed by a UE in accordance with aspects of the present application.

Figure 6 illustrates a flowchart of a method performed by a NE in accordance with aspects of the present application.

Figure 7 illustrates a schematic diagram of an AI based prediction of an L1 beam measurement result and/or an L1 event in accordance with aspects of the present application.

DETAILED DESCRIPTION

In general, when a UE moves from one cell to another cell, a serving cell change needs to be performed. In the legacy, the serving cell change is triggered by explicit radio resource control (RRC) reconfiguration message (e.g. a handover (HO) command) to trigger the synchronization of a target cell based on Layer-3 (L3) measurements report. It leads to longer latency, larger overhead, and longer interruption time than lower layer-based mobility. Therefore, in 3GPP, Layer 1/layer 2 (L1/L2) triggered mobility (LTM) was approved to change a serving cell via L1/L2 signalling, in order to reduce the latency, overhead and interruption time.

LTM is a procedure in which the serving cell provides LTM candidate cell configuration to UE. Then, a network equipment (e.g. a serving cell or serving BS) receives L1 measurement report (s) from a UE, and on their basis the BS changes UE’s serving cell by a cell switch command signaled via a medium access control (MAC) control element (CE) . The cell switch command indicates an LTM candidate cell configuration ID that the BS previously prepared and provided to the UE through RRC signalling. Then the UE switches to the target cell according to the LTM cell switch command. The LTM can be used to reduce the mobility latency. LTM may also be named as L1/L2 lower layer-Triggered Mobility or the like.

Master cell group (MCG) LTM is a PCell switch procedure that the network triggers via a MAC CE based on L1 measurements. Secondary cell group (SCG) LTM is a PSCell switch procedure that the network triggers via a MAC CE based on L1 measurements.

Currently, the following LTM events based on beam specific quality of a serving cell and candidate cells may be supported as L1 LTM measurement events.
- Event #A for LTM: Beam (s) of a serving cell becomes worse than an absolute
threshold;
- Event #B for LTM: Beam (s) of a candidate cell becomes offset better than beam (s)
of a serving cell;
- Event #C for LTM: Beam (s) of a candidate cell becomes better than an absolute
threshold;
- Event #D for LTM: Beam (s) of a serving cell becomes worse than an absolute
threshold AND Beam (s) of a candidate cell becomes better than another absolute threshold.

For example, solution for E1 (Event #A for LTM: Beam (s) of a serving cell becomes worse than an absolute threshold) is as follows:
(1) Entering condition:
- Option E1-1a: A number m is configured by network. If m =1, it is fixed in the
specification. Namely, the configuration from network is not needed.
- Alternative#1: UE considers the entering condition for this event to be fulfilled
when condition E1-1 is fulfilled for the best beam.
- Alternative#2: UE considers the entering condition for this event to be fulfilled
when condition E1-1 is fulfilled for the mth beam.
- Alternative#3: UE considers the entering condition for this event to be fulfilled
when condition E1-1 is fulfilled based on the average of the m beams.
The m beams could be the best m beams from the serving cell in this option.
- Option E1-1b: A number m and threshold for beam filtering are configured by network.
- UE considers the entering condition for this event to be fulfilled when condition E1-
1 is fulfilled based on the average of the best minimum (m1, m) beams. There are m1 beams of the serving cell meeting the threshold. Ms is the average of minimum (m1, m) beams of the serving cell.
- UE considers the entering condition for this event to be fulfilled when condition E1-
2 is fulfilled based on the average of the best minimum (m1, m) beams. There are m1 beams of the serving cell meeting the threshold. Ms is the average of minimum (m1, m) beams of the serving cell.
Inequality E1-1 (Entering condition)
Mbs + Hys < Thresh
The variables in the formula are defined as follows:
Mbs is the measurement result of the beam of the serving cell.
Hys is the hysteresis parameter for this event.
Thresh is the threshold parameter for this event.

Solution for E2 (Event #B for LTM: Beam (s) of a candidate cell becomes offset better than beam (s) of a serving cell) is as follows:
(1) Entry condition:
- Option E2-1a: A number m is configured by network.
- Alternative#1: UE considers the entering condition for this event to be fulfilled
when condition E2-1 is fulfilled for each beam from the best m beams.
- Alternative#2: UE considers the entering condition for this event to be fulfilled
when condition E2-1 is fulfilled based on the average of the best m beams.
- Option E2-1b: A number m and a threshold for beam filtering is configured by network.
- Alternative#1: UE considers the entering condition for this event to be fulfilled
when condition E2-1 is fulfilled for each beam from the best minimum (m1, m2 and m) beams. The number m is configured by network. One threshold is configured by the network to UE. Only the beam which is greater than the threshold can be selected for checking entering condition. There are m1 beams of the serving cell meeting the threshold. There are m2 beams of the serving cell meeting the threshold.
√ For example, if Mn used in E2-1 is the best beam from the neighbour cell, Mp
used in E2-2 is also the best beam from the serving cell. If Mn used in E2-1 is the second-best beam from the neighbour cell, Mp used in E2-2 is also the second-best beam from the serving cell. And so on.
- Alternative#2: UE considers the entering condition for this event to be fulfilled
when condition E2-2 is fulfilled based on the average of beams of serving cell and neighbour cell. There are m1 beams of the serving cell meeting the threshold. There are m2 beams of the neighbour cell meeting the threshold. Mn is the average of minimum (m2, m) beams of neighbour cell. Mp is the average of minimum (m1, m) beams of serving cell.
- Use the SpCell for Mbp, Ofp and Ocp.
Inequality E2-1 (Entering condition)
Mbn + Ofn + Ocn - Hys > Mbp + Ofp + Ocp + Off
The variables in the formula are defined as follows:
Mbn is the measurement result of the beam of the neighbour cell.
Ofn is the measurement object specific offset of the reference signal of the
neighbour cell.
Ocn is the cell specific offset of the neighbour cell.
Mbp is the measurement result of the SpCell.
Ofp is the measurement object specific offset of the SpCell (i.e. offsetMO as
defined within measObjectNR corresponding to the SpCell) .
Ocp is the cell specific offset of the SpCell (i.e. cellIndividualOffset as defined
within measObjectNR corresponding to the SpCell) , and is set to zero if not configured for the SpCell.
Hys is the hysteresis parameter for this event (i.e. hysteresis as defined within
reportConfigNR for this event) .

Solution for E3 (Event #C for LTM: Beam (s) of a candidate cell becomes better than an absolute threshold) is as follows:
(1) Entering condition:
- Option E3-1a: A number m is configured by network. If m =1, it is fixed in the
specification. Namely, the configuration from network is not needed.
- Alternative#1: UE considers the entering condition for this event to be fulfilled
when condition E3-1 is fulfilled for the m beams.
- Alternative#2: UE considers the entering condition for this event to be fulfilled
when condition E3-1 is fulfilled based on the average of the m beams.
The m beams could be the best m beams from the serving cell in this option.
- UE considers the entering condition for this event to be fulfilled when condition E1-
1 is fulfilled based on the average of the best minimum (m1, m) beams. There are m1 beams of the neighbour cell meeting the threshold. Mbs is the average of minimum (m1, m) beams of the neighbour cell.
Inequality E3-1 (Entering condition)
Mbn + Ofn + Ocn - Hys > Thresh
The variables in the formula are defined as follows:
Mbn is the measurement result of the neighbour cell or the measurement result
of serving PSCell (i.e., in case it is configured as candidate PSCell for CondEvent E3 evaluation) for CHO with candidate SCG (s) case.
Ofn is the measurement object specific offset of the neighbour cell (i.e.
offsetMO as defined within measObjectNR corresponding to the neighbour cell) .
Ocn is the measurement object specific offset of the neighbour cell (i.e.
cellIndividualOffset as defined within measObjectNR corresponding to the neighbour cell, or cellIndividualOffset as defined within reportConfigNR) , and set to zero if not configured for the neighbour cell.
Hys is the hysteresis parameter for this event.
Thresh is the threshold parameter for this event.

Solution for E4 (Event #D for LTM: Beam (s) of a serving cell becomes worse than an absolute threshold AND Beam (s) of a candidate cell becomes better than another absolute threshold) is as follows:
(1) Entering condition:
- Option E4-1a: A number m is configured by network. If m =1, it is fixed in the
specification. Namely, the configuration from network is not needed.
- Alternative#1: UE considers the entering condition for this event to be fulfilled
when condition E4-1 is fulfilled for the m beams from the serving cell and E4-2 is fulfilled for the m beams from the neighbour cell.
- Alternative#2: UE considers the entering condition for this event to be fulfilled
when condition E4-1 is fulfilled based on the average of the m beams from the serving cell and condition E4-1 is fulfilled based on the average of the m beams from the neighbour cell.
The m beams could be the best m beams from the serving cell in this option.
- UE considers the entering condition for this event to be fulfilled when condition
E4-3 is fulfilled based on the average of the best minimum (m2, m) beams from serving cell or condition E4-4 is fulfilled based on the average of the best minimum (m1, m) beams from neighbour cell. There are m2 beams of the serving cell meeting the threshold. There are m1 beams of the neighbour cell meeting the threshold. Mbn is the average of minimum (m1, m) beams of the neighbour cell. Mbp is the average of minimum (m2, m) beams of the serving cell.
Inequality E4-1 (Entering condition 1)
Mbp + Hys < Thresh1
Inequality E4-2 (Entering condition 2)
Mbn + Ofn + Ocn - Hys > Thresh2
The variables in the formula are defined as follows:
Mbp is the measurement result of the beam from NR SpCell.
Mbn is the measurement result of the beam of the neighbour cell.
Ofn is the measurement object specific offset of the neighbour cell (i.e.
offsetMO as defined within measObjectNR corresponding to the neighbour cell) .
Ocn is the cell specific offset of the neighbour cell, and set to zero if not
configured for the neighbour cell.
Hys is the hysteresis parameter for this event.
Thresh1 is the threshold parameter for this event.
Thresh2 is the threshold parameter for this event.

In some cases, an LTM configuration includes the beam configuration of both synchronization signal block (SSB) and channel state information reference signal (CSI-RS) in L1 measurement resource configuration.

AI, at least including machine learning (ML) is used to learn and perform certain tasks via training neural networks (NNs) with vast amounts of data, which is successfully applied in computer vison (CV) and nature language processing (NLP) areas. Deep learning, which is a subordinate concept of ML, utilizes multi-layered NNs as an “AI model” (or referred to as AI/ML model or the like) or "AI-based model" (or referred to as AI/ML based model or the like) to learn how to solve problems and/or optimize performance from vast amounts of data. If AI models used on AI-based methods are well trained, the AI-based methods can obtain better performance than the traditional methods. Thus, 3rd generation partnership program (3GPP) has been considering to introduce AI into 3GPP since 2016.

For example, one 3GPP work item is to study AI/ML aided mobility for network triggered layer 3 (L3) -based handover considering AI/ML based measurement result and event prediction, wherein the AI/ML models can be located in the network side and/or UE side. However, there are several issues to be solved, e.g., how to handle or indicate an indirect AI based prediction and a direct AI based prediction for an L1 event, whether the indirect or direct AI based prediction is decided by a network node or UE, whether L1 beam measurement results predicted via an indirect AI based prediction and a direct AI based prediction can be comparable in an AI based L1 event prediction (e.g. in equations of Event #B for LTM and Event #D for LTM) , whether different RS types can be used for both a serving cell and a neighboring cell for an AI based L1 event prediction of Event #B for LTM and Event #D for LTM, which beam for the serving cell can be used for an AI based L1 event prediction, and whether a prediction type (indirect or direct prediction) should be included in a report of prediction results transmitted by UE.

At least considering these issues, various aspects of the present disclosure propose that UE may report, to the network side (e.g., gNB) , UE capability information on an AI based prediction of an L1 beam measurement result and/or an L1 event. Based on the received UE capability information, the network side may configure one or more of an L1 beam measurement result prediction or an L1 event prediction for UE and transmit to UE the configuration information. Based on the received configuration information, UE may perform one or more of the L1 beam measurement result prediction or the L1 event prediction. UE may report one or more prediction results to the network side. Accordingly, the network side may receive the reported one or more prediction results.

In the present application, an AI based L1 beam measurement result prediction may also be named as an AI based prediction of an L1 beam measurement result. An AI based L1 event prediction may also be named as an AI based prediction of an L1 event.

More details of the embodiments of the present application will be illustrated in the following text in combination with the appended drawings.

Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present application. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G-Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA) , frequency division multiple access (FDMA) , or code division multiple access (CDMA) , etc.

The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN) , a NodeB, an eNodeB (eNB) , a next-generation NodeB (gNB) , or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g. receive signaling, transmit signaling) over a Uu interface.

An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g. voice, video, packet data, messaging, broadcast, etc. ) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN) . In some implementations, different geographic coverage areas associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.

The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (IoT) device, an Internet-of-Everything (IoE) device, or machine-type communication (MTC) device, among other examples.

A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.

An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g. S1, N2, or network interface) . In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g. via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC) . An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs) .

The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC) , or a 5G core (5GC) , which may include a control plane entity that manages access and mobility (e.g. a mobility management entity (MME) , an access and mobility management functions (AMF) ) and a user plane entity that routes packets or interconnects to external networks (e.g. a serving gateway (S-GW) , a Packet Data Network (PDN) gateway (P-GW) , or a user plane function (UPF) ) . In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g. data bearers, signal bearers, etc. ) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.

The CN 106 may communicate with a packet data network over one or more backhaul links (e.g. via an S1, N2, or another network interface) . The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g. a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g. control information, data, and the like) between the UE 104 and the application server using the established session (e.g. the established PDU session) . The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g. one or more network functions of the CN 106) .

In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g. time resources (e.g. symbols, slots, subframes, frames, or the like) or frequency resources (e.g. subcarriers, carriers) ) to perform various operations (e.g. wireless communications) . In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures) . The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.

One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g. μ=0) may be associated with a first subcarrier spacing (e.g. 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g. μ=0) associated with the first subcarrier spacing (e.g. 15 kHz) may utilize one slot per subframe. A second numerology (e.g. μ=1) may be associated with a second subcarrier spacing (e.g. 30 kHz) and a normal cyclic prefix. A third numerology (e.g. μ=2) may be associated with a third subcarrier spacing (e.g. 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g. μ=3) may be associated with a fourth subcarrier spacing (e.g. 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g. μ=4) may be associated with a fifth subcarrier spacing (e.g. 240 kHz) and a normal cyclic prefix.

A time interval of a resource (e.g. a communication resource) may be organized according to frames (also referred to as radio frames) . Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

Additionally or alternatively, a time interval of a resource (e.g. a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g. quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., μ=0, μ=1, μ=2, μ=3, μ=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g. quantity) of symbols (e.g. OFDM symbols) . In some implementations, the number (e.g. quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g. applicable for 60 kHz subcarrier spacing) , a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g. μ=0) associated with a first subcarrier spacing (e.g. 15 kHz) may be used interchangeably between subframes and slots.

In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz –7.125 GHz) , FR2 (24.25 GHz –52.6 GHz) , FR3 (7.125 GHz –24.25 GHz) , FR4 (52.6 GHz –114.25 GHz) , FR4a or FR4-1 (52.6 GHz –71 GHz) , and FR5 (114.25 GHz –300 GHz) . In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g. control information, data) . In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

FR1 may be associated with one or multiple numerologies (e.g. at least three numerologies) . For example, FR1 may be associated with a first numerology (e.g. μ=0) , which includes 15 kHz subcarrier spacing; a second numerology (e.g. μ=1) , which includes 30 kHz subcarrier spacing; and a third numerology (e.g. μ=2) , which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g. at least 2 numerologies) . For example, FR2 may be associated with a third numerology (e.g. μ=2) , which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g. μ=3) , which includes 120 kHz subcarrier spacing.

Figure 2 illustrates an example of a UE 200 in accordance with aspects of the present application. The UE 200 may include a processor 202, a memory 204, a controller 206, and a transceiver 208. The processor 202, the memory 204, the controller 206, or the transceiver 208, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present application as described herein. These components may be coupled (e.g. operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

The processor 202, the memory 204, the controller 206, or the transceiver 208, or various combinations or components thereof may be implemented in hardware (e.g. circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present application.

The processor 202 may include an intelligent hardware device (e.g. a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 202 may be configured to operate the memory 204. In some other implementations, the memory 204 may be integrated into the processor 202. The processor 202 may be configured to execute computer-readable instructions stored in the memory 204 to cause the UE 200 to perform various functions of the present application.

The memory 204 may include volatile or non-volatile memory. The memory 204 may store computer-readable, computer-executable code including instructions when executed by the processor 202 cause the UE 200 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 204 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

In some implementations, the processor 202 and the memory 204 coupled with the processor 202 may be configured to cause the UE 200 to perform one or more of the functions described herein (e.g. executing, by the processor 202, instructions stored in the memory 204) . For example, the processor 202 may support wireless communication at the UE 200 in accordance with examples as disclosed with respect to Figure 5. The UE 200 may be configured to support: a means for transmitting capability information of the UE associated with an AI based prediction of at least one of an L1 beam measurement result or an L1 event; a means for receiving a configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event; and a means for performing the AI based prediction based on the configuration.

The controller 206 may manage input and output signals for the UE 200. The controller 206 may also manage peripherals not integrated into the UE 200. In some implementations, the controller 206 may utilize an operating system such as or other operating systems. In some implementations, the controller 206 may be implemented as part of the processor 202.

In some implementations, the UE 200 may include at least one transceiver 208. In some other implementations, the UE 200 may have more than one transceiver 208. The transceiver 208 may represent a wireless transceiver. The transceiver 208 may include one or more receiver chains 210, one or more transmitter chains 212, or a combination thereof. The means for receiving abovementioned in the processor 202 or the means for transmitting in the processor 202 may be implemented via at least one transceiver 208.

A receiver chain 210 may be configured to receive signals (e.g. control information, data, packets) over a wireless medium. For example, the receiver chain 210 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 210 may include at least one amplifier (e.g. a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 210 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 210 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

A transmitter chain 212 may be configured to generate and transmit signals (e.g. control information, data, packets) . The transmitter chain 212 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 212 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 212 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

Figure 3 illustrates an example of a processor 300 in accordance with aspects of the present application. The processor 300 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 300 may include a controller 302 configured to perform various operations in accordance with examples as described herein. The processor 300 may optionally include at least one memory 304, which may be, for example, an L1/L2/L3 cache. Additionally, or alternatively, the processor 300 may optionally include one or more arithmetic-logic units (ALUs) 306. One or more of these components may be in electronic communication or otherwise coupled (e.g. operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g. buses) .

The processor 300 may be a processor chipset and include a protocol stack (e.g. a software stack) executed by the processor chipset to perform various operations (e.g. receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g. memory local to or included in the processor chipset (e.g. the processor 300) or other memory (e.g. random access memory (RAM) , read-only memory (ROM) , dynamic RAM (DRAM) , synchronous dynamic RAM (SDRAM) , static RAM (SRAM) , ferroelectric RAM (FeRAM) , magnetic RAM (MRAM) , resistive RAM (RRAM) , flash memory, phase change memory (PCM) , and others) .

The controller 302 may be configured to manage and coordinate various operations (e.g. signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 300 to cause the processor 300 to support various operations in accordance with examples as described herein. For example, the controller 302 may operate as a control unit of the processor 300, generating control signals that manage the operation of various components of the processor 300. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.

The controller 302 may be configured to fetch (e.g. obtain, retrieve, receive) instructions from the memory 304 and determine subsequent instruction (s) to be executed to cause the processor 300 to support various operations in accordance with examples as described herein. The controller 302 may be configured to track memory address of instructions associated with the memory 304. The controller 302 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 302 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 300 to cause the processor 300 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 302 may be configured to manage flow of data within the processor 300. The controller 302 may be configured to control transfer of data between registers, arithmetic logic units (ALUs) , and other functional units of the processor 300.

The memory 304 may include one or more caches (e.g. memory local to or included in the processor 300 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 304 may reside within or on a processor chipset (e.g. local to the processor 300) . In some other implementations, the memory 304 may reside external to the processor chipset (e.g. remote to the processor 300) .

The memory 304 may store computer-readable, computer-executable code including instructions that, when executed by the processor 300, cause the processor 300 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 302 and/or the processor 300 may be configured to execute computer-readable instructions stored in the memory 304 to cause the processor 300 to perform various functions. For example, the processor 300 and/or the controller 302 may be coupled with or to the memory 304, the processor 300, the controller 302, and the memory 304 may be configured to perform various functions described herein. In some examples, the processor 300 may include multiple processors and the memory 304 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.

The one or more ALUs 306 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 306 may reside within or on a processor chipset (e.g. the processor 300) . In some other implementations, the one or more ALUs 306 may reside external to the processor chipset (e.g. the processor 300) . One or more ALUs 306 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 306 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 306 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 306 may support logical operations such as AND, OR, exclusive-OR (XOR) , not-OR (NOR) , and not-AND (NAND) , enabling the one or more ALUs 306 to handle conditional operations, comparisons, and bitwise operations.

The processor 300 may support wireless communication in accordance with examples as disclosed herein.

In some implementations, the processor 300 may be configured to support means for performing operations of a UE as described with respect to Figure 5. The processor 300 may be configured to or operable to support: a means for transmitting capability information of the UE associated with an AI based prediction of at least one of an L1 beam measurement result or an L1 event; a means for receiving a configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event; and a means for performing the AI based prediction based on the configuration.

In some implementations, the processor 300 may be configured to support means for performing operations of a NE as described with respect to Figure 6. The processor 300 may be configured to or operable to support: a means for receiving, from a UE, capability information of the UE associated with an AI based prediction of at least one of an L1 beam measurement result or an L1 event; and a means for transmitting, to the UE, a configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event.

It should be appreciated by persons skilled in the art that the components in exemplary processor 300 may be changed, for example, some of the components in exemplary processor 300 may be omitted or modified or new component (s) may be added to exemplary processor 300, without departing from the spirit and scope of the application. For example, in some embodiments, the processor 300 may not include the ALUs 306.

Figure 4 illustrates an example of a NE 400 in accordance with aspects of the present application. The NE 400 may include a processor 402, a memory 404, a controller 406, and a transceiver 408. The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present application as described herein. These components may be coupled (e.g. operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations or components thereof may be implemented in hardware (e.g. circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present application.

The processor 402 may include an intelligent hardware device (e.g. a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 402 may be configured to operate the memory 404. In some other implementations, the memory 404 may be integrated into the processor 402. The processor 402 may be configured to execute computer-readable instructions stored in the memory 404 to cause the NE 400 to perform various functions of the present application.

The memory 404 may include volatile or non-volatile memory. The memory 404 may store computer-readable, computer-executable code including instructions when executed by the processor 402 cause the NE 400 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 404 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

In some implementations, the processor 402 and the memory 404 coupled with the processor 402 may be configured to cause the NE 400 to perform one or more of the functions described herein (e.g. executing, by the processor 402, instructions stored in the memory 404) . For example, the processor 402 may support wireless communication at the NE 400 in accordance with examples as disclosed herein.

For example, the NE 400 may be configured to support means for performing the operations as described with respect to Figure 6. The NE 400 may be configured to support: a means for receiving, from a UE, capability information of the UE associated with an AI based prediction of at least one of an L1 beam measurement result or an L1 event; and a means for transmitting, to the UE, a configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event.

The controller 406 may manage input and output signals for the NE 400. The controller 406 may also manage peripherals not integrated into the NE 400. In some implementations, the controller 406 may utilize an operating system such as or other operating systems. In some implementations, the controller 406 may be implemented as part of the processor 402.

In some implementations, the NE 400 may include at least one transceiver 408. In some other implementations, the NE 400 may have more than one transceiver 408. The transceiver 408 may represent a wireless transceiver. The transceiver 408 may include one or more receiver chains 410, one or more transmitter chains 412, or a combination thereof. The means for receiving or the means for transmitting abovementioned in the processor 402 may be implemented via at least one transceiver 408.

A receiver chain 410 may be configured to receive signals (e.g. control information, data, packets) over a wireless medium. For example, the receiver chain 410 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 410 may include at least one amplifier (e.g. a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 410 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 410 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

A transmitter chain 412 may be configured to generate and transmit signals (e.g. control information, data, packets) . The transmitter chain 412 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 412 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 412 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

It should be appreciated by persons skilled in the art that the components in exemplary NE 400 may be changed, for example, some of the components in exemplary NE 400 may be omitted or modified or new component (s) may be added to exemplary NE 400, without departing from the spirit and scope of the application. For example, in some embodiments, the NE 400 may not include the controller 406.

Figure 5 illustrates a flowchart of a method performed by a UE in accordance with aspects of the present application. In some implementations, the UE may execute a set of instructions to control the function elements of the UE to perform the described functions. In some implementations, aspects of operations 502, 504 and 506 may be performed by UE 200 as described with reference to Figure 2. Specific examples are described in the embodiments of Figure 7 as follows.

At 502, the method may include transmitting, by a UE, capability information of the UE associated with an AI based prediction of at least one of an L1 beam measurement result or an L1 event. In some implementations, the capability information indicates at least one of the following:
(1) the UE supporting an L1 beam measurement result prediction;
(2) the UE supporting an L1 beam measurement result prediction based on a spatial domain
measurement;
(3) the UE supporting an L1 beam measurement result prediction based on a temporal
domain measurement;
(4) the UE supporting a direct L1 event prediction;
(5) the UE supporting an indirect L1 event prediction;
(6) the UE supporting both a direct L1 event prediction and an indirect L1 event prediction;
(7) the UE supporting an L1 event prediction based on a spatial domain measurement; or
(8) the UE supporting an L1 event prediction based on a temporal domain measurement.

At 504, the method may include receiving, by the UE, a configuration (denoted as a first configuration) related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event. At 506, the method may include performing the AI based prediction by the UE based on the first configuration.

In some implementations, if the first configuration is for the L1 beam measurement result, the first configuration includes at least one of the following:
(1) Information of a prediction time window (denoted as a first prediction time window)
which is related to the AI based prediction of the L1 beam measurement result.
(2) Information of an RS resource (denoted as a first RS resource) for a cell of the UE. The
cell may be a serving cell or a set of candidate cells of the UE. For instance, the first RS resource may carry at least one of: SSB; CSI-RS; PT-RS; PRS; or DM-RS.
(3) Information (e.g. an indication) indicating a spatial domain measurement for the cell.
(4) Information (e.g. an indication) indicating a temporal domain measurement for the cell.
(5) If it is the temporal domain measurement for the cell:
a) information (e.g. an indication) indicating a type (denoted as a first type) of temporal
domain measurement prediction for the cell. For example, the first type is type A of intra-frequency intra-cell temporal domain prediction that is done by predicting beam measurement result (s) in a prediction time window based on (same or different) beam measurement results in an observation window of the same cell.
b) Information (e.g. an indication) indicating another type (denoted as a second type)
of temporal domain measurement prediction for the cell. For example, the second type is type B of intra-frequency intra-cell temporal domain prediction that is done by predicting sub-set beam measurement instants in a temporal domain of the same cell. Regarding type B of temporal domain prediction, the inputs are historical beam measurement values, and the outputs are values at subsequent time instants that beam measurement is skipped, i.e., the prediction is always after the beam measurement and is at future time instant (s) .

In some implementations, the UE may perform a measurement on the first RS resource and predict the L1 beam measurement result within the first prediction time window. In some cases, the L1 beam measurement result is predicted based on one or more historical beam measurement results of the serving cell or the set of candidate cells (which may be named as a direct prediction for L1 measurement) . In some other cases, the L1 beam measurement result is predicted based on one or more current actual beam measurement results of the serving cell or the set of candidate cells (which may be named as an indirect prediction for L1 measurement) .

In some implementations, the UE may transmit a report (denoted as a first report) of prediction results after completing the AI based prediction for the L1 beam measurement result. The first report may be transmitted via RRC singling or a MAC CE, e.g. to the NE. For instance, the first report includes information indicating at least one of the following:
(1) the L1 beam measurement result predicted by the AI based prediction;
(2) an RS type used for predicting the L1 beam measurement result;
(3) whether the L1 beam measurement result is predicted based on a spatial domain
measurement or a temporal domain measurement for a cell of the UE;
(4) whether the L1 beam measurement result is predicted based on: a historical beam
measurement result (i.e. via the direct prediction for L1 measurement) for the cell, or a current actual beam measurement result (i.e. via the indirect prediction for L1 measurement) for the cell; or
(5) if it is the temporal domain measurement for the cell, whether the L1 beam measurement
result is predicted based on: the first type (e.g. type A) or the second type (e.g. type B) of temporal domain measurement prediction for the cell.

In some implementations, the L1 event includes at least one of the following:
(1) an event that a current beam of a serving cell of the UE becomes worse than a threshold,
e.g., Event #A for LTM. The current beam is a beam corresponding to a TCI state indicated by the serving cell;
(2) an event that any beam of a candidate cell becomes an amount of offset better than the
current beam of the serving cell, e.g., Event #B for LTM;
(3) an event that any beam of the candidate cell becomes better than a threshold, e.g., Event
#C for LTM; or
(4) an event that the current beam of the serving cell becomes worse than one threshold and
any beam of the candidate cell becomes better than another threshold, e.g., Event #D for LTM.

In some implementations, if the first configuration is for the L1 event, the first configuration includes at least one of the following:
(1) information of a prediction time window (denoted as a second prediction time window)
which is related to the AI based prediction of the L1 event;
(2) information of an RS resource (denoted as a second RS resource) for a cell of the UE;
e.g. the cell is a serving cell or a set of candidate cells of the UE; for instance, the second RS resource may carry at least one of: SSB; CSI-RS; PT-RS; PRS; or DM-RS;
(3) TTT associated with the L1 event; or
(4) information (e.g. an indication) indicating that a predicted L1 beam measurement result
(which is to be used to predict the L1 event) is predicted based on:
a) a spatial domain measurement for the cell;
b) a temporal domain measurement for the cell;
c) the first type (i.e. type A) of temporal domain measurement prediction for the cell;
or
d) the second type (i.e. type B) of temporal domain measurement prediction for the cell.

In some implementations, the UE may predict whether the L1 event is satisfied by adopting "a direct L1 event prediction" or "an indirect L1 event prediction" based on the first configuration. In some embodiments, the L1 event is predicated as satisfied, if the L1 event is considered as satisfied during a time duration (e.g. TTT associated with the L1 event) .

In some implementations, if the L1 event is predicted based on both L1 beam measurement results of the serving cell and the set of candidate cells, when predicting whether the L1 event is satisfied, the UE may determine at least one of: (1) whether a same type of RSs or different types of RSs are used for predicting the L1 beam measurement results of the serving cell and the set of candidate cells; or (2) which type of RSs are used for predicting the L1 beam measurement results of the serving cell and the set of candidate cells.

In some cases, by adopting the direct L1 event prediction, the UE may predict occurrence probability of the L1 event within the second prediction time window, e.g. based on historical data. The historical data may include occurrence time of the L1 event in historical time.

In some other cases, by adopting the indirect L1 event prediction, the UE may predict expected occurrence time of the L1 event within the second prediction time window based on an L1 measurement result, and the L1 measurement result is predicted by performing the AI based prediction based on current data. The current data may include current actual RSRP of the serving cell and/or current actual RSRP of the set of candidate cells.

In some implementations, to adopt the indirect L1 event prediction, the UE may select or determine one of the following, as a serving beam of a serving cell at a future time instant (e.g. after 200 ms) within the second prediction time window to be used for predicting the L1 event:
(1) any beam of the serving cell, e.g. a predicted best beam of the serving cell;
(2) a beam configured by a NE, e.g. a list of beams is configured by a NE; or
(3) a current beam of the serving cell. The current beam is a beam corresponding to a TCI
state indicated by the serving cell. For example, if no additional RS of the serving cell is configured to the UE, the current beam of the serving cell may be selected as the serving beam of the serving cell at the future time instant (to be used for predicting the L1 event) .

In some implementations, the UE may receive information (e.g. an explicit indication) indicating to predict the L1 event via the direct L1 event prediction or the indirect L1 event prediction, e.g. from the NE.

In some other implementations, if the L1 event is predicted based on an L1 beam measurement result of the serving cell or one candidate cell of the set of candidate cells (e.g. in case that the L1 event is Event #A for LTM or Event #C for LTM) , if an RS resource (denoted as a third RS resource) is configured for an indirect prediction, the UE may predict the L1 event (e.g. whether Event #A for LTM or Event #C for LTM is satisfied) based on the third RS resource via the indirect L1 event prediction. If the third RS resource is not configured, the UE may predict the L1 event via the direct L1 event prediction. For instance, the third RS resource may carry at least one of: SSB; CSI-RS; PT-RS; PRS; or DM-RS.

In some implementations, the UE may receive information requesting predicted RSRP for a beam from the NE, and then predict the L1 event via the indirect L1 event prediction. The information requesting the predicted RSRP may be deemed as an implicit indication indicating the UE to predict the L1 event via the indirect L1 event prediction.

In some other implementations, if the L1 event is predicted based on both "an L1 beam measurement result (denoted as a first L1 beam measurement result) of the serving cell" and "an L1 beam measurement result (denoted as a second L1 beam measurement result) of a candidate cell of the set of candidate cells" (e.g. in case that the L1 event is Event #B for LTM or Event #D for LTM) , if an RS resource (denoted as a fourth RS resource) is configured for an indirect prediction for both the serving cell and the set of candidate cells (e.g. the RS resource is configured for an indirect L1 event prediction or configured for an indirect prediction for L1 measurement for the first and second L1 beam measurement results) , the UE may predict the L1 event (e.g. whether Event #B for LTM or Event #D for LTM is satisfied) based on the fourth RS resource via an indirect L1 event prediction. If the fourth RS resource is not configured, the UE may predict the L1 event via the direct L1 event prediction. For instance, the fourth RS resource may carry at least one of: SSB; CSI-RS; PT-RS;PRS; or DM-RS.

In some implementations, if the L1 event is predicted based on both the first and second L1 beam measurement results (e.g. in case that the L1 event is Event #B for LTM or Event #D for LTM) , and if different RS types for predicting the first and second L1 beam measurement results are not allowed for the AI based prediction of the L1 event:
(1) If a same RS type is configured for predicting both the first and second L1 beam
measurement results, the L1 event may be predicted based on the same RS type via the indirect L1 event prediction. The configured same RS type may be deemed as an implicit indication indicating the UE to predict the L1 event via the indirect L1 event prediction.
(2) If the same RS type is not configured, the L1 event may be predicted via the direct L1
event prediction.

In some implementations, if the L1 event is predicted based on both the first and second L1 beam measurement results (e.g. the L1 event is Event #B for LTM or Event #D for LTM) , and if different prediction types for L1 measurement are not allowed for the first and second L1 beam measurement results, the first L1 beam measurement result may be predicted based on a current actual beam measurement result of the serving cell, and the second L1 beam measurement result may be predicted based on a current actual beam measurement result of the set of candidate cells. That is, both the first and second L1 beam measurement results are predicted by adopting the indirect prediction for L1 measurement.

In some implementations, if the L1 event is predicted based on both the first and second L1 beam measurement results (e.g. the L1 event is Event #B for LTM or Event #D for LTM) , and if different domain measurements are not allowed for the first and second L1 beam measurement results, both the first and second L1 beam measurement results are predicted based on a single domain measurement, e.g. a spatial domain measurement or a temporal domain measurement.

In some implementations, if the L1 event is predicted based on both the first and second L1 beam measurement results (e.g. the L1 event is Event #B for LTM or Event #D for LTM) , and if different temporal domain measurement predictions are not allowed for the first and second L1 beam measurement results, both the first and second L1 beam measurement results are predicted based on a same temporal domain measurement prediction, e.g. the first type (e.g. Type A) or the second type (e.g. Type B) of temporal domain measurement prediction.

In some implementations, the first and second L1 beam measurement results are predicted by performing the AI based prediction in two different prediction types or in a single prediction type. For example, the prediction types include: (1) a direct prediction of predicting a beam measurement result based on one or more historical beam measurement results (i.e. the direct prediction for L1 measurement) ; or (2) an indirect prediction of predicting the beam measurement result based on one or more predicated beam measurement results (i.e. the indirect prediction for L1 measurement) .

In some implementations, the UE may receive a configuration (denoted as a second configuration) from a NE (e.g. the L1 event is Event #B for LTM or Event #D for LTM) . If the second configuration provides information related to an indirect prediction for both the serving cell and a candidate cell within the sets of candidate cells (e.g. the information indicates an indirect L1 event prediction or indicates that both the first and second L1 beam measurement results are predicted by adopting an indirect prediction for L1 measurement) , the L1 event (e.g. Event #B for LTM or Event #D for LTM) is predicted via the indirect L1 event prediction. If the second configuration provides information related to the indirect prediction to only one of the serving cell or the candidate cell (e.g. the information indicates a direct L1 event prediction or indicates that only one of the first and second L1 beam measurement results is predicted by adopting an indirect prediction for L1 measurement) , the L1 event is predicted via the direct L1 event prediction.

In some implementations, if different RS types for predicting the first and second L1 beam measurement results are not allowed for the AI based prediction of the L1 event (e.g. Event #B for LTM or Event #D for LTM) , if a same RS type is configured for predicting both the first and second L1 beam measurement results, the L1 event is predicted based on the same RS type via the indirect L1 event prediction. If the same RS type is not configured, the L1 event is predicted via the direct L1 event prediction.

In some implementations, the UE may transmit a report (denoted as a second report) of prediction results after completing the AI based prediction for the L1 event. The second report may be transmitted via RRC singling or a MAC CE, e.g. to the NE. For example, the second report includes at least one of the following:
(1) information indicating whether the L1 event occurs within the second prediction time
window;
(2) information indicating whether the L1 event is predicted via the direct L1 event prediction
or the indirect L1 event prediction; or
(3) information indicating that a predicted L1 beam measurement result (that is used to
predict the L1 event) is predicted based on: 1) a spatial domain measurement for the cell; 2) a temporal domain measurement for the cell; 3) the first type (e.g. type A) of temporal domain measurement prediction for the cell; or 4) the second type (e.g. type B) of temporal domain measurement prediction for the cell.

In some embodiments, by adopting the first type (e.g. type A) of temporal domain measurement prediction, the UE may predict an L1 measurement result for a beam (denoted as a first beam) of the cell in a prediction time window based on same or different beam measurement results in an observation time window of the first beam. In some other embodiments, by adopting the second type (e.g. type B) of temporal domain measurement prediction, the UE may predict a sub-set of beam measurement instants in the temporal domain of the first beam.

It should be noted that the method described in Figure 5 describes possible implementations, and that the operations and the steps may be rearranged or otherwise eliminated or modified and that other implementations are possible, without departing from the spirit and scope of the application.

Figure 6 illustrates a flowchart of a method performed by a NE in accordance with aspects of the present application. In some implementations, the NE may be a BS (e.g. gNB) , and may execute a set of instructions to control the function elements of the BS to perform the described functions. In some implementations, aspects of operations 602 and 604 may be performed by NE 400 as described with reference to Figure 4. Specific examples are described in the embodiments of Figure 7 as follows.

At 602, the method may include receiving, by a NE from a UE, capability information of the UE associated with an AI based prediction of at least one of an L1 beam measurement result or an L1 event. The capability information received at 602 may include the same or similar elements as those in the capability information transmitted at 502 in Figure 5. In some implementations, the L1 event may include the same or similar elements as those in the L1 event as described in the embodiments of Figure 5, e.g. Event #A for LTM, Event #B for LTM, Event #C for LTM and/or Event #D for LTM.

At 604, the method may include transmitting, by the NE to the UE, a configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event. The configuration transmitted at 604 may include the same or similar elements as those in the first configuration received at 504 in Figure 5. In some embodiments, the configuration is for the L1 beam measurement result and includes the corresponding configuration information as described in the embodiments of Figure 5. In some other embodiments, the configuration is for the L1 event and includes the corresponding configuration information as described in the embodiments of Figure 5.

In some implementations, the NE may receive, from the UE, a report of prediction results of the AI based prediction for the L1 beam measurement result, e.g. via RRC singling or a MAC CE. This report may include the same or similar elements as those in the first report as described in the embodiments of Figure 5.

In some implementations, the NE may transmit, to the UE, information (e.g. an explicit indication) indicating to predict the L1 event via a direct L1 event prediction or an indirect L1 event prediction. By adopting the direct L1 event prediction, occurrence probability of the L1 event within a prediction time window (e.g. the second prediction time window) may be predicted by the UE, e.g. based on historical data (which may include occurrence time of the L1 event in historical time) . By adopting the indirect L1 event prediction, expected occurrence time of the L1 event within the prediction time window may be predicted by the UE based on an L1 measurement result (which is predicted by performing the AI based prediction based on current data, e.g. current actual RSRP of the serving cell and/or current actual RSRP of the set of candidate cells) .

In some implementations, the NE may transmit, to the UE, information requesting predicted RSRP for a beam. Then, the L1 event is predicted by the UE via the indirect L1 event prediction.

In some implementations, the NE may transmit another configuration to the UE. Such configuration may include the same or similar elements as those in the second configuration as described in the embodiments of Figure 5. For example, if the another configuration provides information related to an indirect prediction for both a serving cell and a candidate cell within a sets of candidate cells of the UE, the L1 event is predicted via an indirect L1 event prediction. If the another configuration provides information related to an indirect prediction to only one of the serving cell or the candidate cell, the L1 event is predicted via a direct L1 event prediction.

In some implementations, the NE may receive, from the UE, a report of prediction results after completing the AI based prediction for the L1 event, e.g. via RRC singling or a MAC CE. This report may include the same or similar elements as those in the second report as described in the embodiments of Figure 5.

It should be noted that the method described in Figure 6 describes possible implementations, and that the operations and the steps may be rearranged or otherwise eliminated or modified and that other implementations are possible, without departing from the spirit and scope of the application.

Figure 7 illustrates a schematic diagram of an AI based prediction of an L1 beam measurement result and/or an L1 event in accordance with aspects of the present application. Details described in all other embodiments of the present application are applicable for the embodiments shown in Figure 7. Following text describes different embodiments of Figure 7 in different cases, i.e. Embodiment 1, Embodiment 2 and Embodiment 3.

Embodiment 1

In Embodiment 1, the same prediction type may be used for a serving cell and a candidate cell (e.g. a neighbor cell) .

At 701, a UE accesses a NE (e.g. the serving gNB) via MCG only or Dual-connectivity (DC) including MCG and SCG. Namely, the UE accesses a MN and a SN (which are included in the NE shown in Figure 7) via DC.

In some embodiments of 701, the UE may report the UE capability information to the NE if receiving the enquiry from the NE. For example, the UE may report at least one of the following UE capability information:
(1) An indication to indicate that the UE supports an L1 beam measurement result prediction.
(2) An indication to indicate that the UE supports an L1 beam measurement result prediction
based on a spatial domain measurement prediction.
(3) An indication to indicate that the UE supports an L1 beam measurement result prediction
based on a temporal domain measurement prediction.
(4) An indication to indicate that the UE supports an indirect L1 event prediction.
(5) An indication to indicate that the UE supports a direct L1 event prediction.
(6) An indication to indicate that the UE supports both the indirect and direct L1 event
predictions.
(7) An indication to indicate that the UE supports an L1 event prediction based on a spatial
domain measurement.
(8) An indication to indicate that the UE supports an L1 event prediction based on a temporal
domain measurement.

At 702, the NE transmits a configuration related to an AI based prediction of an L1 beam measurement result and/or an L1 event to the UE.

In some embodiments of an L1 measurement prediction for a beam, the serving gNB may configure the UE to predict an L1 beam measurement result. For example, the UE can directly predict beam level results (e.g. one or more L1 beam measurement results) based on beam level results (e.g. one or more L1 historical beam measurement results) . Both a spatial domain measurement prediction and a temporal domain measurement prediction can be supported in such embodiments. Regarding the temporal domain measurement prediction, the UE can predict the beam measurement results at a future time instant, e.g. after 200 ms, based on the current beam measurement results.

Some embodiment refer to following two types of temporal domain predictions:
(1) type A temporal domain prediction: an intra-frequency intra-cell temporal domain
prediction is done by predicting beam measurement result (s) in a prediction time window based on (same or different) beam measurement results in an observation window of the same cell; and
(2) type B temporal domain prediction: an intra-frequency intra-cell temporal domain
prediction is done by predicting a sub-set of beam measurement instants in the temporal domain of the same cell.
- Regarding type B temporal domain prediction, the inputs are historical beam
measurement values (or results) , and the outputs are values at subsequent time instant (s) that the beam measurement is skipped, i.e., the type B temporal domain prediction is always after the beam measurement and is at future time instant (s) .

In some embodiments, an intra-frequency intra-cell spatial domain prediction is done by measuring a sub-set of configured SSBs as inputs to an AI model, to predict an L1 beam measurement result for every time instant of the same cell.

In some embodiments, the configuration related to the L1 beam measurement prediction (that is transmitted at 702) may include at least one of: a prediction time window (e.g. a first prediction time window) , an RS resource (e.g. a first RS resource) (which may be SSB, CSI-RS, PT-RS, PRS, or DM-RS or the like) for a certain cell (e.g. a serving cell and/or a neighbor cell) , an indication of a spatial domain measurement for the cell, an indication of a temporal domain measurement prediction for the cell, an indication of type A temporal domain prediction for the cell, or an indication of type B temporal domain prediction for the cell. In some embodiments, the UE may perform a measurement on the configured RS resource and predict the L1 beam measurement result within the configured prediction time window (e.g. at 703) . For instance, the UE may perform an L1 beam measurement result prediction for one or more candidate cells (e.g. at 703) .

An L1 event prediction may also be named as an LTM event prediction or the like. In some embodiments, the L1 event includes at least one of the following:
- Event #A for LTM: Beam (s) of a serving cell becomes worse than an absolute
threshold;
- Event #B for LTM: Beam (s) of a candidate cell becomes offset better than beam (s)
of a serving cell;
- Event #C for LTM: Beam (s) of a candidate cell becomes better than an absolute
threshold;
- Event #D for LTM: Beam (s) of a serving cell becomes worse than an absolute
threshold AND Beam (s) of a candidate cell becomes better than another absolute threshold.

An indirect prediction for L1 event (i.e. an indirect L1 event prediction) is that the L1 event is predicted by an AI model based on an L1 measurement prediction result. For the indirect L1 event prediction, an intermediate output of the AI model (i.e., the output of L1 beam measurement result) may be RSRP of a serving cell or one or more candidate cells of the UE, and a final output of the AI model may be the expected occurrence time of a certain L1 event (e.g. Event #A for LTM, Event #B for LTM, Event #C for LTM, and/or Event #D for LTM) .

A direct prediction for L1 event (i.e. a direct L1 event prediction) is that the L1 event is predicted by an AI model based on historic data. For the direct L1 event prediction, an output of the AI model is the probability of event occurrence within a prediction time window.

In some embodiments, the L1 event prediction may consider TTT. For example, the L1 event (e.g. Event #A for LTM, Event #B for LTM, Event #C for LTM, and/or Event #D for LTM) may be determined as satisfied only if an entering condition is met during the TTT.

In some embodiments, the configuration related to an L1 event prediction (that is transmitted at 702) may include at least one of: a prediction time window (e.g. a second prediction time window) , an RS resource (e.g. a second RS resource) (which may be SSB, CSI-RS, PT-RS, PRS, or DM-RS or the like) for a certain cell (e.g. the serving cell and/or the candidate cell) , TTT, an indication of a spatial domain measurement for the cell, an indication of a temporal domain measurement prediction for the cell, an indication of type A temporal domain prediction for the cell, or an indication of type B temporal domain prediction for the cell, and a list of candidate cells. More details of the configuration related to the L1 event prediction are described in the following texts.

At 703, the UE performs the AI based prediction of the L1 beam measurement results and/or the L1 event. For example, the UE performs the AI based prediction based on an RRC configuration. The UE starts performing the AI based prediction upon reception of the RRC configuration or upon reception of an additional indication.

In some embodiments in Embodiment 1, regarding RS types used by the UE for a serving cell and a candidate cell (e.g. for Event #B for LTM and Event #D for LTM) , different options may be adopted in different embodiments, i.e. Option 1 and Option 2.
(1) Option 1: a same RS type should be used for both the serving cell and the candidate cell
for a prediction of Event #B for LTM and Event #D for LTM. The NE can configure which RS type (e.g. SSB, CSI-RS, PT-RS, PRS, or DM-RS) for the serving cell or the candidate cell to be used for the L1 event prediction.
(2) Option 2: the L1 event prediction can be based on different RS types for the serving cell
and the candidate cell, respectively. In some embodiments, the AI model (of the UE itself) is aware of the different RS types to be used during the L1 event prediction. For example, the AI model can adjust the different RS types for the serving cell and the candidate cell.

In some embodiments of Figure 7, when performing the AI based prediction of Event #A for LTM, Event #B for LTM and/or Event #D for LTM based on actual beam measurement results, a current beam of a serving cell (i.e. a beam corresponding to the indicated TCI state) may be used for an L1 event prediction for the serving cell. However, the current beam is configured by NE, and thus the UE is not aware which beam will be configured as a serving beam of a serving cell at a future time instant, e.g. after a time duration (for example, 200 ms) . Regarding which beam for the serving cell at a future time instant can be used by the UE for the L1 event prediction, different options may be adopted in different embodiments, i.e. Option A, Option B and Option C.
(1) Option A: any beam of the serving cell (e.g. a predicted best one) can be used for the L1
event prediction.
(2) Option B: the NE provides a list of beams for the L1 event prediction when the NE
configures the L1 event prediction.
(3) Option C: a current beam of the serving cell is used for the L1 event prediction.
Optionally, if no additional RS of the serving cell is configured to the UE, the current beam of the serving cell may be used for the L1 event prediction.

In some embodiments of Figure 7, regarding how to handle or indicate an indirect L1 event prediction and a direct L1 event prediction, different options may be adopted in different embodiments, i.e. Option M and Option N.
- Option M (an explicit option) : the NE provides an explicit indication of an indirect L1
event prediction and a direct L1 event prediction to the UE.
- Option N (an implicit option) : the NE provides an implicit indication of an indirect L1
event prediction and a direct L1 event prediction to the UE. There may be following different cases, i.e. Case 1, Case 2, and Case 3.

Case 1: Regarding Event #A for LTM and Event #C for LTM, if an RS resource (e.g. a third RS resource) (which may be SSB, CSI-RS, PT-RS, PRS, or DM-RS or the like) is configured for indirect prediction, the UE should use an indirect L1 event prediction based on the configured RS resource to predict the L1 event. Otherwise, a direct L1 event prediction is used by the UE to predict the L1 event.

Case 2: Regarding Event #B for LTM and Event #D for LTM, if an RS resource (e.g. SSB, CSI-RS, PT-RS, PRS, or DM-RS or the like) related to indirect prediction is configured for both the serving cell and the candidate cell, the UE should use an indirect L1 event prediction based on the configured RS to predict this L1event. Otherwise, the direct L1 event prediction is used by the UE to predict the L1 event.

In some embodiments in Embodiment 1, considering the assumption that different RS types for predicting L1 beam measurement results of the serving cell and the candidate cell is not allowed for Event #B for LTM and Event #D for LTM, if a same RS type is configured for predicting both the L1 beam measurement results of the serving cell and the candidate cell, the indirect L1 event prediction should be used to predict the L1 this event. Otherwise, the direct L1 event prediction is used by the UE to predict the L1 this event.

In some embodiments in Embodiment 1, if different prediction types (the indirect or direct prediction for L1 measurement) for the serving cell and the candidate cell is not allowed for Event #B for LTM and Event #D for LTM, the same indirect prediction for L1 measurement should be used for both the serving cell and the candidate cell.

In some other embodiments in Embodiment 1, if a spatial domain measurement and a temporal domain measurement prediction cannot be used for the serving cell and the candidate cell, respectively, a single prediction (e.g. the spatial or temporal domain measurement prediction) is used for both the serving cell and the candidate cell. It is also possible that it is the UE's implementation to select one or both of the spatial and temporal domain measurement predictions for each cell.

In some additional embodiments in Embodiment 1, if different types of temporal domain measurement prediction (type A or type B) cannot be used for the serving cell and the candidate cell, respectively, the same type of temporal domain measurement prediction (e.g. type A or type B) is used for both the serving cell and the candidate cell. It is also possible that it is the UE's implementation to select one of type A or type B temporal domain measurement prediction for each cell.

Case 3: If the NE configures the UE to report predicted RSRP for a beam, the UE is expected to predict the L1 event using the indirect L1 event prediction. In Case 3, if an RS resource is not configured for an indirect prediction, the UE itself can monitor a SSB resource of the serving cell or the candidate cell.

In some embodiments in Embodiment 1, regarding whether an indirect prediction for L1 measurement and a direct prediction for L1 measurement can be comparable during an L1 event prediction, e.g. for Event #B for LTM and Event #D for LTM, there may be following embodiments.

In some embodiments, a same prediction type (i.e. an indirect or direct prediction for L1 measurement) should be used for both a serving cell and a candidate cell in Event #B for LTM and Event #D for LTM. In the equations of these two L1 events, both the serving cell and the candidate cell are involved.

In an example, if a necessary configuration related to indirect prediction for L1 measurement has been provided for both the serving cell and the candidate cell, an indirect L1 event prediction should be used for the L1 event. If different RS types for predicting L1 beam measurement results of the serving cell and the candidate cell are not allowed, the same RS type for predicting L1 beam measurement results of the serving cell and the candidate cell is needed to be configured for the indirect L1 event prediction. Otherwise, if the same RS type for predicting L1 beam measurement results of both the serving cell and the candidate cell is not configured, the direct L1 event prediction is adopted to predict the L1 event.

In another example, if a necessary configuration related to an indirect prediction for L1 measurement is provided to only one of the serving cell or the candidate cell (e.g. only the serving cell is configured for an RS resource, but the candidate cell is not configured for an RS resource) , the direct prediction is adopted to predict the L1 event.

At 704, when the UE predicts L1 event occurrence (e.g. within the prediction time window) , the UE is triggered to report the predicted results. The UE can transmit a report of prediction results via RRC or MAC CE. The report of prediction results may include at least one of:
(1) an indication indicating whether the L1 event occurs within the prediction time window,
(2) the predicted beam measurement results (e.g. if the indirect prediction for L1
measurement is used) ,
(3) an RS type used for predicting the L1 beam measurement result (e.g. if the indirect
prediction for L1 measurement is used) ,
(4) an indication of an indirect prediction for L1 measurement or a direct prediction for L1
measurement for a cell,
(5) an indication of a spatial domain measurement prediction or a temporal domain
measurement prediction for a cell,
(6) an indication of type A temporal domain prediction or type B temporal domain prediction
for a cell,
(7) an indication indicating an indirect L1 event prediction or a direct L1 event prediction of
this predicted L1 event,
(8) an indication of a spatial domain measurement prediction or a temporal domain
measurement prediction for the L1 event, or
(9) an indication of type A temporal domain prediction or type B temporal domain prediction
for the L1 event.

Embodiment 2

In Embodiment 2, different prediction types are allowed for a serving cell and a candidate cell (e.g. a neighbor cell) .

Operation 701 in Embodiment 2 is the same as operation 701 in Embodiment 1.

Operation 702 in Embodiment 2 is the same as operation 702 in Embodiment 1.

In some embodiments in Embodiment 2, regarding RS types used by the UE for a serving cell and a candidate cell (e.g. for Event #B for LTM and Event #D for LTM) , different options may be adopted in different embodiments, i.e. Option 1 and Option 2 as described in Embodiment 1.

In some embodiments in Embodiment 2, regarding which beam for the serving cell at a future time instant can be used by the UE for the L1 event prediction, different options may be adopted in different embodiments, i.e. Option A, Option B and Option C as described in Embodiment 1.

In some embodiments in Embodiment 2, regarding how to handle or indicate an indirect L1 event prediction and a direct L1 event prediction, different options may be adopted in different embodiments, i.e. Option X and Option Y.
- Option X (an explicit option) : the NE provides an explicit indication of an indirect L1
event prediction and a direct L1 event prediction to the UE.
- Option Y (an implicit option) : the NE provides an implicit indication of an indirect L1
event prediction and a direct L1 event prediction to the UE. There may be following different cases, i.e. Case A, Case B, and Case C.

Case A: Regarding Event #A for LTM and Event #C for LTM, if an RS resource (e.g. a third RS resource) (which may be SSB, CSI-RS, PT-RS, PRS, or DM-RS or the like) is configured for indirect prediction, the UE should use an indirect L1 event prediction based on the configured RS resource to predict the L1 event. Otherwise, a direct L1 event prediction is used by the UE to predict the L1 event.

Case B: Regarding Event #B for LTM and Event #D for LTM, if an RS resource (e.g. SSB, CSI-RS, PT-RS, PRS, or DM-RS or the like) related to indirect prediction is configured for both the serving cell and the candidate cell, the UE should use an indirect L1 event prediction based on the configured RS to predict this L1event. Otherwise, the direct L1 event prediction is used by the UE to predict the L1 event.

In some embodiments in Embodiment 2, considering the assumption that different RS types for predicting L1 beam measurement results of the serving cell and the candidate cell is not allowed for Event #B for LTM and Event #D for LTM, if different RS types are configured for predicting both the L1 beam measurement results of the serving cell and the candidate cell, the direct L1 event prediction should be used to predict the L1 this event.

In some embodiments in Embodiment 2, considering the assumption that different RS types for predicting L1 beam measurement results of the serving cell and the candidate cell are allowed for Event #B for LTM and Event #D for LTM, if different RS types have been configured to the serving cell and the candidate cell, respectively, an indirect prediction for L1 measurement is allowed to be used for the serving cell and the candidate cell on top of the configured RS resource.

In some other embodiments in Embodiment 2, considering the assumption that different spatial domain and temporal domain measurement predictions for the serving cell and the candidate cell are allowed for Event #B for LTM and Event #D for LTM, if such different predictions have been configured for the serving cell and the candidate cell, respectively, an indirect L1 event prediction is allowed to be used for the serving cell and the candidate cell on top of the configured RS resource. Otherwise, a direct L1 event prediction is used by the UE.

In some additional embodiments in Embodiment 2, considering the assumption that different types of a temporal domain measurement prediction for the serving cell and the candidate cell is allowed for Event #B for LTM and Event #D for LTM, if such different types have been configured for the serving cell and the candidate cell, respectively, an indirect L1 event prediction is allowed to be used to predict this L1 event on top of the configured RS resource. Otherwise, a direct L1 event prediction is used by the UE.

Case C: If the NE configures the UE to report predicted RSRP for a beam, the UE is expected to predict the L1 event using the indirect L1 event prediction. In Case C, if an RS resource is not configured for an indirect prediction, the UE itself can monitor a SSB resource of the serving cell or the candidate cell.

In some embodiments in Embodiment 2, regarding whether an indirect prediction for L1 measurement and a direct prediction for L1 measurement can be comparable during an L1 event prediction, e.g. for Event #B for LTM and Event #D for LTM, there may be following embodiments.

In some embodiments, different prediction types (i.e. an indirect or direct prediction for L1 measurement) is allowed for both the serving cell and the candidate cell in Event #B for LTM and Event #D for LTM. In the equations of these two L1 events, both the serving cell and the candidate cell are involved. In an example, if a necessary configuration related to an indirect prediction for L1 measurement has been provided for both the serving cell and the candidate cell, an indirect L1 event prediction can be used in priority for the L1 event. In another example, if a necessary configuration related to an indirect prediction for L1 measurement is not provided, the direct prediction is adopted to predict the L1 event.

Operation 704 in Embodiment 2 is the same as operation 704 in Embodiment 1.

Embodiment 3

In Embodiment 3, a UE itself selects a prediction type for a serving cell and a candidate cell (e.g. a neighbor cell) .

Operation 701 in Embodiment 3 is the same as operation 701 in Embodiment 1.

Operation 702 in Embodiment 3 is the same as operation 702 in Embodiment 1.

In some embodiments in Embodiment 3, regarding RS types used by the UE for a serving cell and a candidate cell (e.g. for Event #B for LTM and Event #D for LTM) , different options may be adopted in different embodiments, i.e. Option 1 and Option 2 as described in Embodiment 1.

In some embodiments in Embodiment 3, regarding which beam for the serving cell at a future time instant can be used by the UE for the L1 event prediction, different options may be adopted in different embodiments, i.e. Option A, Option B and Option C as described in Embodiment 1.

In some embodiments in Embodiment 3, regarding how to handle or indicate an indirect L1 event prediction and a direct L1 event prediction, different options may be adopted in different embodiments, i.e. Option I and Option II.
- Option I: It is up to the UE to select an indirect L1 event prediction or a direct L1 event
prediction, if a prediction type (the indirect or direct prediction for L1 measurement) should be same for the serving cell and the candidate cell for Event #B for LTM and Event #D for LTM. If a direct L1 event prediction is selected, no predicted RSRP of beams will be reported. The NE can know that the direct L1 event prediction is used, if no predicted RSRP of beams is reported. If the indirect L1 event prediction is selected, the predicted RSRP of beams should be reported.
- Option II: It is up to the UE to select an indirect prediction or a direct prediction for L1
measurement for each cell (the serving cell or the candidate cell) , if different prediction types (the indirect or direct prediction for L1 measurement) are allowed for the serving cell and the candidate cell in Event #B for LTM and Event #D for LTM. If a direct prediction for L1 measurement is selected, no predicted RSRP of beams will be reported. The NE can know that the direct prediction for L1 measurement is used if no predicted RSRP of beams is reported. If the indirect prediction is selected, the predicted RSRP of beams should be reported.

Operation 704 in Embodiment 3 is the same as operation 704 in Embodiment 1.

The description herein is provided to enable a person having ordinary skill in the art to make or use the application. Various modifications to the application will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the application. Thus, the application is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.

Claims

A user equipment (UE) , comprising:

at least one memory; and

at least one processor coupled to the at least one memory and configured to cause the UE to:

transmit capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event;

receive a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event; and

perform the AI based prediction based on the first configuration.
The UE of claim 1, wherein the capability information indicates at least one of the following:

the UE supporting an L1 beam measurement result prediction;

the UE supporting the L1 beam measurement result prediction based on a spatial domain measurement;

the UE supporting the L1 beam measurement result prediction based on a temporal domain measurement;

the UE supporting a direct L1 event prediction;

the UE supporting an indirect L1 event prediction;

the UE supporting both the direct L1 event prediction and indirect L1 event prediction;

the UE supporting an L1 event prediction based on the spatial domain measurement; or

the UE supporting the L1 event prediction based on the temporal domain measurement.
The UE of claim 1, wherein if the first configuration is for the L1 beam measurement result, the first configuration includes at least one of the following:

information of a first prediction time window;

information of a first reference signal (RS) resource for a cell of the UE;

information indicating a spatial domain measurement for the cell;

information indicating a temporal domain measurement for the cell;

information indicating a first type of temporal domain measurement prediction for the cell; or

information indicating a second type of temporal domain measurement prediction for the cell, wherein the cell is a serving cell or a set of candidate cells of the UE.
The UE of claim 3, wherein, to perform the AI based prediction for the L1 beam measurement result, the at least one processor is configured to cause the UE to perform a measurement on the first RS resource and predict the L1 beam measurement result within the first prediction time window, and wherein the L1 beam measurement result is predicted based on:

one or more historical beam measurement results of the serving cell or the set of candidate cells; or

one or more current actual beam measurement results of the serving cell or the set of candidate cells.
The UE of claim 1, wherein the at least one processor is configured to cause the UE to transmit a first report of prediction results after completing the AI based prediction for the L1 beam measurement result, and the first report includes information indicating at least one of the following:

the L1 beam measurement result predicted by the AI based prediction;

a reference signal (RS) type used for predicting the L1 beam measurement result;

whether the L1 beam measurement result is predicted based on a spatial domain measurement or a temporal domain measurement for a cell of the UE;

whether the L1 beam measurement result is predicted based on a historical beam measurement result or a current actual beam measurement result for the cell; or

whether the L1 beam measurement result is predicted based on a first type of temporal domain measurement prediction or a second type of temporal domain measurement prediction for the cell.
The UE of claim 1, wherein the L1 event includes at least one of the following:

a first event that a current beam of a serving cell of the UE becomes worse than a first threshold, wherein the current beam is a beam corresponding to a transmission configuration indicator (TCI) state indicated by the serving cell;

a second event that any beam of a candidate cell becomes an amount of offset better than the current beam of the serving cell;

a third event that any beam of the candidate cell becomes better than a second threshold; or

a fourth event that the current beam of the serving cell becomes worse than a third threshold and any beam of the candidate cell becomes better than a fourth threshold.
The UE of claim 1, wherein if the first configuration is for the L1 event, the first configuration includes at least one of the following:

information of a second prediction time window;

information of a second reference signal (RS) resource for a cell of the UE;

time to trigger (TTT) associated with the L1 event; or

information indicating that a predicted L1 beam measurement result which is used to predict the L1 event is predicted based on:

a spatial domain measurement for the cell;

a temporal domain measurement for the cell;

a first type of temporal domain measurement prediction for the cell; or

a second type of temporal domain measurement prediction for the cell, wherein the cell is a serving cell or a set of candidate cells of the UE.
The UE of claim 7, wherein, to perform the AI based prediction for the L1 event, the at least one processor is configured to cause the UE to predict whether the L1 event is satisfied by adopting a direct L1 event prediction or an indirect L1 event prediction based on the first configuration.
The UE of claim 8, wherein the L1 event is predicated as satisfied if the L1 event is considered as satisfied during a time duration.
The UE of claim 8, wherein, if the L1 event is predicted based on both L1 beam measurement results of the serving cell and the set of candidate cells, the at least one processor is configured to cause the UE to determine at least one of the following when predicting whether the L1 event is satisfied:

whether a same type of RSs or different types of RSs are used for predicting the L1 beam measurement results of the serving cell and the set of candidate cells; or

which type of RSs are used for predicting the L1 beam measurement results of the serving cell and the set of candidate cells.
The UE of claim 8, wherein:

by adopting the direct L1 event prediction, the at least one processor is configured to cause the UE to predict occurrence probability of the L1 event within the second prediction time window; and

by adopting the indirect L1 event prediction, the at least one processor is configured to cause the UE to predict expected occurrence time of the L1 event within the second prediction time window based on an L1 measurement result, wherein the L1 measurement result is predicted by performing the AI based prediction based on current data, and wherein the current data includes at least one of the following:

current actual reference signal received power (RSRP) of the serving cell; or

current actual RSRP of the set of candidate cells.
The UE of claim 8, wherein, to adopt the indirect L1 event prediction, the at least one processor is configured to cause the UE to select one of the following as a serving beam of a serving cell at a future time instant within the second prediction time window to be used for predicting the L1 event:

any beam of the serving cell;

a beam configured by a network equipment (NE) ; or

a current beam of the serving cell, wherein the current beam is a beam corresponding to a transmission configuration indicator (TCI) state indicated by the serving cell.
The UE of claim 12, wherein the current beam of the serving cell is selected as the serving beam of the serving cell at the future time instant, if no additional RS of the serving cell is configured to the UE.
The UE of claim 8, wherein the at least one processor is configured to cause the UE to receive information indicating to predict the L1 event via the direct L1 event prediction or the indirect L1 event prediction.
The UE of claim 8, wherein if the L1 event is predicted based on an L1 beam measurement result of the serving cell or one candidate cell of the set of candidate cells, the at least one processor is configured to cause the UE to:

if a third RS resource is configured for an indirect prediction, predict the L1 event based on the third RS resource via the indirect L1 event prediction; or

if the third RS resource is not configured, predict the L1 event via the direct L1 event prediction.
The UE of claim 8, wherein the at least one processor is configured to cause the UE to transmit a second report of prediction results after completing the AI based prediction for the L1 event, and the second report includes at least one of the following:

information indicating whether the L1 event occurs within the second prediction time window;

information indicating whether the L1 event is predicted via the direct L1 event prediction or the indirect L1 event prediction; or

information indicating that a predicted L1 beam measurement result used to predict the L1 event is predicted based on:

a spatial domain measurement for the cell;

a temporal domain measurement for the cell;

a first type of temporal domain measurement prediction for the cell; or

a second type of temporal domain measurement prediction for the cell.
A network equipment (NE) , comprising:

at least one memory; and

at least one processor coupled to the at least one memory and configured to cause the NE to:

receive, from a user equipment (UE) , capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; and

transmit, to the UE, a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event.
The NE of claim 17, wherein the capability information indicates at least one of the following:

the UE supporting an L1 beam measurement result prediction;

the UE supporting the L1 beam measurement result prediction based on a spatial domain measurement;

the UE supporting the L1 beam measurement result prediction based on a temporal domain measurement;

the UE supporting a direct L1 event prediction;

the UE supporting an indirect L1 event prediction;

the UE supporting both the direct L1 event prediction and indirect L1 event prediction;

the UE supporting an L1 event prediction based on the spatial domain measurement; or

the UE supporting the L1 event prediction based on the temporal domain measurement.
A processor for wireless communication performed by a network equipment (NE) , comprising:

at least one controller coupled with at least one memory and configured to cause the processor to:

receive, from a user equipment (UE) , capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; and

transmit, to the UE, a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event.
A method performed by a network equipment (NE) , comprising:

receiving, from a user equipment (UE) , capability information of the UE associated with an artificial intelligence (AI) based prediction of at least one of a layer-1 (L1) beam measurement result or an L1 event; and

transmitting, to the UE, a first configuration related to the AI based prediction of the at least one of the L1 beam measurement result or the L1 event.