WO2025165289A1

WO2025165289A1 - Assistance information for machine learning (ml) based beam prediction

Info

Publication number: WO2025165289A1
Application number: PCT/SE2025/050074
Authority: WO
Inventors: Johan AXNÄS; Yufei Blankenship; Marco BELLESCHI; Reem KARAKI; Henrik RYDÉN; Chunhui Li; Jianwei Zhang; Siva Muruganathan
Original assignee: Telefonaktiebolaget LM Ericsson AB
Current assignee: Telefonaktiebolaget LM Ericsson AB
Priority date: 2024-02-02
Filing date: 2025-01-31
Publication date: 2025-08-07
Anticipated expiration: 2026-08-02

Abstract

A method, system and apparatus are disclosed. A UE (22) is provided. The UE (22) configured to: determine at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement where the assistance information comprising at least one of: a probability of a line of sight, LOS, channel being reported by the UE (22); a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE (22); UE rotational speed information; or information associated with receiver beam gain. The UE (22) is configured to transmit the at least one reference signal measurement and the assistance information to the network node (16).

Description

ASSISTANCE INFORMATION FOR MACHINE LEARNING (ML) BASED BEAM PREDICTION

TECHNICAL FIELD

The present disclosure relates to wireless communications, and in particular, to assistance information for machine learning (ML) based beam prediction.

BACKGROUND

The Third Generation Partnership Project (3GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile wireless devices (WD), as well as communication between network nodes and between WDs. The 3GPP is also developing standards for Sixth Generation (6G) wireless communication networks.

One feature of NR, compared to previous generation of wireless networks, is the ability to operate in higher frequencies (e.g., above 10 GHz). The available large transmission bandwidths in these frequency ranges can potentially provide large data rates. However, as carrier frequency increases, both pathloss and penetration loss increase. To maintain the coverage at the same level, highly directional beams may be required to focus the radio transmitter energy in a particular direction on the receiver. However, large radio antenna arrays - at both receiver and transmitter sides - are needed to create such highly direction beams.

To reduce hardware costs, large antenna arrays for high frequencies use timedomain analog beamforming. One aspect of analog beamforming is to share a single radio frequency chain between many (or, potentially, all) of the antenna elements. A limitation of analog beamforming is that it is only possible to transmit radio energy using one beam (in one direction) at a given time.

The above limitation may require the network (NW) and user equipment (UE) to preform beam management procedures to establish and maintain suitable transmitter (Tx) / receiver (Rx) beam-pairs. For example, beam management procedures can be used by a transmitter to sweep a geographic area by transmitting reference signals on different candidate beams, during non-overlapping time intervals, using a predetermined pattern. And by measuring the quality of these reference signals at the receiver side, the best transmit and receive beams can be identified.

NR Beam management procedures

Beam management procedures in NR are defined by a set of L1/L2 procedures that establish and maintain a suitable beam pairs for both transmitting and receiving data. A beam management procedure can include the following sub procedures: beam determination, beam measurements, beam reporting, and beam sweeping.

In case of downlink transmission from the network to the UE, P1/P2/P3 beam management procedures can be performed according to the NR SI technical report to overcome the challenges of establishing and maintaining the beam pairs when, for example, a UE moves or some blockage in the environment requires changing the beams. Although these scenarios are not directly mentioned in specifications, there are relevant procedures defined which enables the realization of these scenarios, examples of such realization are depicted in the corresponding figure of each scenario:

• Pl : The Pl procedure is used to enable UE measurement on different transmission/reception point (TRP) Tx beams to support selection of TRP Tx beams/UE Rx beam(s). During initial access, for example, the network node transmits SS/PBCH block (SSB) beams in different directions to cover the whole cell. The UE measures signal quality on corresponding SSB signals to detect and select an appropriate SSB beam, this is shown in FIG. 1. Random access is then transmitted on the RACH resources indicated by the selected SSB. The corresponding beam will be used by both the UE and the network to communicate until connected mode beam management is active. The network infers which SSB beam was chosen by the UE without any explicit signalling. o For beamforming at Transmission Reception Point (TRP), it typically includes an intra/inter-TRP Tx beam sweep from a set of different beams. For beamforming at UE, it typically includes a UE Rx beam sweep from a set of different beams.

• P2: The P2 procedure is used to enable UE measurement on different TRP Tx beams to possibly change inter/intra-TRP Tx beam(s). The network can use the SSB beam as an indication of which (narrow) CSI-RS beams to try. That is, the selected SSB beam can be used to define a candidate set of narrow CSI-RS beams for beam management. Once CSI-RS is transmitted, the UE measures the RSRP, and reports the result to the network. If the network receives a CSI-RSRP report from the UE where a new CSI-RS beam is better than the old one used to transmit PDCCH/PDSCH, the network updates the serving beam for the UE accordingly, and possibly also modifies the candidate set of CSI-RS beams. The network can also instruct the UE to perform measurements on SSBs. If the network receives a report from the UE where a new SSB beam is better than the previous best SSB beam, a corresponding update of the candidate set of CSI-RS beams for the UE may be motivated. o P2 procedure is performed on a possibly smaller set of beams for beam refinement than in Pl . Note that P2 can be a special case of Pl . For example, in connected mode, the network node configures the UE with different CSI-RSs and transmits each CSI-RS on the corresponding beam. UE then measures the quality of each CSI-RS beam on its current RX beam and sends feedback about the quality of the measured beams. Thereafter, based on this feedback, the network node will decide and possibly indicate to the UE which beam will be used in future transmissions, as shown in FIG. 2.

• P3 : is used to enable UE measurement on the same TRP Tx beam to change UE Rx beam in the case UE uses beamforming. Once in connected mode, the UE is configured with a set of reference signals. Based on measurements, the UE determines which Rx beam is suitable to receive each reference signal in the set. The network then indicates which reference signals are associated with the beam that will be used to transmit PDCCH/PDSCH, and the UE uses this information to adjust its Rx beam when receiving PDCCH/PDSCH. o In connected mode, P3 can be used by the UE to find the best Rx beam for the corresponding Tx beam. In this case, the network node keeps one CSI- RS Tx beam at a time, and UE performs the sweeping and measurements on its own Rx beams for that specific Tx beam. UE then finds the best corresponding Rx beam based on the measurements and will use it in future for reception when the network node indicates the use of that Tx beam.

FIG. 3 is a diagram of UE Rx beam selection for corresponding CSI-RS Tx beam in DL according to the P3 scenario.

Beam measurement and reporting in NR For beam management, a UE can be configured to report RSRP or/and SINR for each one of up to four beams, either on CSI-RS or SSB. UE measurement reports can be sent either over PUCCH or PUSCH to the network node, e.g., gNB.

Reference signal configurations in NR

CSI-RS:

A CSI-RS is transmitted over each transmit (Tx) antenna port at the network node and for different antenna ports. The CSI-RS is multiplexed in time, frequency, and code domain such that the channel between each Tx antenna port at the network node and each receive antenna port at a UE can be measured by the UE. The time-frequency resource used for transmitting CSI-RS is referred to as a CSI-RS resource.

In NR, the CSI-RS for beam management is defined as a 1- or 2-port CSI-RS resource in a CSI-RS resource set where the filed repetition is present. The following three types of CSI-RS transmissions are supported:

• Periodic CSI-RS: CSI-RS is transmitted periodically in certain slots. This CSI-RS transmission is semi-statically configured using RRC signaling with parameters such as CSI-RS resource, periodicity, and slot offset.

• Semi -Persistent CSI-RS: Similar to periodic CSI-RS, resources for semi-persistent CSI-RS transmissions are semi-statically configured using RRC signaling with parameters such as periodicity and slot offset. However, unlike periodic CSI-RS, dynamic signaling is needed to activate and deactivate the CSI-RS transmission.

• Aperiodic CSI-RS: This is a one-shot CSI-RS transmission that can happen in any slot. Here, one-shot means that CSI-RS transmission only happens once per trigger. The CSI-RS resources (i.e., the RE locations which consist of subcarrier locations and OFDM symbol locations) for aperiodic CSI-RS are semi-statically configured. The transmission of aperiodic CSI-RS is triggered by dynamic signaling through PDCCH using the CSI request field in UL DCI, in the same DCI where the UL resources for the measurement report are scheduled. Multiple aperiodic CSI-RS resources can be included in a CSI-RS resource set and the triggering of aperiodic CSI-RS is on a resource set basis.

SSB:

In NR, an SSB consists of a pair of synchronization signals (SSs), physical broadcast channel (PBCH), and DMRS for PBCH. An SSB is mapped to 4 consecutive OFDM symbols in the time domain and 240 contiguous subcarriers (20 RBs) in the frequency domain. NR supports beamforming and beam-sweeping for SSB transmission, by enabling a cell to transmit multiple SSBs in different narrow-beams multiplexed in time. The transmission of these SSBs is confined to a half frame time interval (5 ms). It is also possible to configure a cell to transmit multiple SSBs in a single wide-beam with multiple repetitions. The design of beamforming parameters for each of the SSBs within a half frame is up to network implementation. The SSBs within a half frame are broadcasted periodically from each cell. The periodicity of the half frames with SS/PBCH blocks is referred to as SSB periodicity, which is indicated by SIB1.

The maximum number of SSBs within a half frame, denoted by L, depends on the frequency band, and the time locations for these L candidate SSBs within a half frame depends on the SCS of the SSBs. The L candidate SSBs within a half frame are indexed in an ascending order in time from 0 to L-l. By successfully detecting PBCH and its associated DMRS, a UE knows the SSB index. A cell does not necessarily transmit SS/PBCH blocks in all L candidate locations in a half frame, and the resource of the unused candidate positions can be used for the transmission of data or control signaling instead. It is up to network implementation to decide which candidate time locations to select for SSB transmission within a half frame, and which beam to use for each SSB transmission.

Measurement resource configurations in NR

A UE can be configured with the following:

N>1 CSI reporting settings (CSI-ReportConfig) and

M>1 resource settings (CSI-ResourceConfig).

Each CSI reporting setting is linked to one or more resource setting for channel and/or interference measurement. The CSI framework is modular in the sense that several CSI reporting settings may be associated with the same Resource Setting.

The measurement resource configurations for beam management are provided to the UE by RRC information element (IE) (CSI-ResourceConfigs). One CSI- ResourceConfig contains several NZP-CSI-RS-ResourceSets and/or CSI-SSB- ResourceSets.

A UE can be configured to measure CSI-RSs using the RRC IE NZP-CSI-RS- ResourceSet. A NZP CSI-RS resource set contains the configurations of Ks >1 CSI-RS resources. Each CSI-RS resource configuration resource includes at least the following:

- mapping to REs,

- the number of antenna ports, and - time-domain behavior.

Up to 64 CSI-RS resources can be grouped together in a NZP-CSI-RS- ResourceSet.

A UE can be configured to measure SSBs using the RRC IE CSI-SSB- ResourceSet. Resource sets comprising SSB resources are defined in a similar manner to the CSI-RS resources defined above.

In the case of aperiodic CSI-RS and/or aperiodic CSI reporting, the network node configures the UE with S_c CSI triggering states. Each triggering state contains the aperiodic CSI report setting to be triggered along with the associated aperiodic CSI-RS resource sets.

Periodic and semi-persistent resource settings can only comprise a single resource set (i.e., S=l). Aperiodic resource settings can have many resources sets (S>=1), because one out of the S resource sets defined in the resource setting is indicated by the aperiodic triggering state that triggers a CSI report.

Measurement Reporting

Three types of CSI reporting are supported in NR as follows:

• Periodic CSI Reporting on PUCCH: CSI is reported periodically by a UE. Parameters such as periodicity and slot offset are configured semi-statically by higher layer RRC signaling from the network node to the UE

• Semi -Persistent CSI Reporting on PUSCH or PUCCH: similar to periodic CSI reporting, semi-persistent CSI reporting has a periodicity and slot offset which may be semi-statically configured. However, a dynamic trigger from network node to UE may be needed to allow the UE to begin semi-persistent CSI reporting. A dynamic trigger from network node to UE is needed to request the UE to stop the semi-persistent CSI reporting.

• Aperiodic CSI Reporting on PUSCH: This type of CSI reporting involves a singleshot (i.e., one time) CSI report by a UE which is dynamically triggered by the network node using DCI. Some of the parameters related to the configuration of the aperiodic CSI report is semi-statically configured by RRC but the triggering is dynamic.

In each CSI reporting setting, the content and time-domain behavior of the report is defined, along with the linkage to the associated Resource Settings.

The CSI-ReportConfig IE comprises the following configurations:

• reportConfigType o Defines the time-domain behavior (periodic CSI reporting, semi- persistent CSI reporting, or aperiodic CSI reporting) along with the periodicity and slot offset of the report for periodic CSI reporting.

• reportQuantity o Defines the reported CSI parameters — the CSI content; for example, the PMI, CQI, RI, LI (layer indicator), CRI (CSI-RS resource index) and Ll-RSRP. Only certain combinations are possible; for example, ‘cri-RI-PMI-CQI’ is one possible value and ‘cri-RSRP’ is another) and each value of reportQuantity could be said to correspond to a certain CSI mode.

• codebookConfig o Defines the codebook used for PMI reporting, along with possible codebook subset restriction (CBSR). NR supported the following two types of PMI codebooks: Type I CSI and Type II CSI. Additionally, the Type I and Type II codebooks each have two different variants: regular and port selection.

• reportFrequencyConfiguration o Define the frequency granularity of PMI and CQI (wideband or subband), if reported, along with the CSI reporting band, which is a subset of subbands of the bandwidth part (BWP) which the CSI corresponds to

• Measurement restriction in the time domain (ON/OFF) for channel and interference respectively

For beam management, a UE can be configured to report Ll-RSRP for up to four different CSI-RS/SSB resource indicators. The reported RSRP value corresponding to the first (best) CRI/SSBRI requires 7 bits, using absolute values, while the others require 4 bits using encoding relative to the first. In NR release 16, the report of Ll-SINR for beam management has already been supported.

Agreements in 3GPP

During the 3 GPP meeting RANl#109-e it was agreed to study AI/ML based spatial beam prediction, one aspect of which is as follows: Predict the “best” beam (or beams) from a Set A of beams using measurement results from another Set B of beams. Set A and Set B of beams have not been defined yet (left for future study); however, the following two examples illustrate some scenarios that will likely be studied in Release 18:

- SetB is a subset of a Set A. For example, Set A is a set of 8 SSB/CSI-RS beams shown in FIG. 4 (both white and black circles). The UE measures Set B (the 4 beams indicated by dark circles). The AI/ML model should predict the best beam (or beams) in Set A using only measurements from Set B.

- Set A and Set B correspond to two different sets of beams. For example, Set A is a set of 30 narrow CSI-RS beams, and Set B is a set of 8 wide SSB beams as shown in FIG. 5. The UE measures beams in Set B and the AI/ML model should predict the best beam(s) from Set A.

The spatial beam prediction can be performed in the network node or the UE - the study item will cover both scenarios.

During the 3 GPP meeting RAN1#110, it was agreed to study AI/ML model training both at the network and UE side. Which side that performs the training is expected to impact how data collection is performed, where another agreement is to study the aspect of data collection for beam management. Moreover, it was agreed to study the aspect of model monitoring and the standard impact on AI/ML model inference (e.g., reporting of predicted values).

3GPP study item technical report (TR)

3GPP TR 38.843 regarding performance monitoring is described below.

Performance monitoring:

For the performance monitoring of BM-Casel and BM-Case2:

Performance metric(s) with the following alternatives:

Alt.l : Beam prediction accuracy related KPIs, e.g., Top-K/1 beam prediction accuracy

Alt.2: Link quality related KPIs, e.g., throughput, Ll-RSRP, Ll- SINR, hypothetical BLER

Alt.3 : Performance metric based on input/output data distribution of AI/ML

Alt.4: The Ll-RSRP difference evaluated by comparing measured RSRP and predicted RSRP

Benchmark/reference for the performance comparison, including: Alt.1 : The best beam(s) obtained by measuring beams of a set indicated by gNB (e.g., Beams from Set A)

Alt.4: Measurements of the predicted best beam(s) corresponding to model output (e.g., Comparison between actual Ll-RSRP and predicted RSRP of predicted Top-l/K Beams)

Signalling/configuration/measurement/report for model monitoring, e.g., signalling aspects related to assistance information (if supported), Reference signals

For BM-Casel and BM-Case2 with a UE-side AI/ML model:

Typel performance monitoring:

Configuration/Signalling from gNB (e.g., network node) to UE for measurement and/or reporting

UE may have different operations

Optionl : UE sends reporting to network (NW) (e.g., for the calculation of performance metric at NW)

Option2: UE calculates performance metric(s), either reports it to NW or reports an event to NW based on the performance metric(s)

Indication from NW for UE to do LCM operations

Note: At least the performance and reporting overhead of model monitoring mechanism should be considered

Type2 performance monitoring (UE-side performance monitoring):

Indication/request/report from UE to gNB for performance monitoring

Note: The indication/request/report may be not needed in some case(s)

Configuration/Signalling from gNB to UE for performance monitoring measurement and/or reporting

UE calculates performance metric(s), either reports it to NW or reports an event to NW based on the performance metric(s)

If it is for UE-side model monitoring, UE makes decision(s) of model selection/activation/ deactivation/switching/fallback operation

Indication from NW to UE to do LCM operation

UE reporting of beam measurement s) based on a set of beams indicated by gNB

Signalling, e.g., RRC -based, LI -based Note: Performance and UE complexity, power consumption should be considered

Mechanism that facilitates the UE to detect whether the functionality/model is suitable or no longer suitable Table 7.2.3-1 summarizes applicability of various alternatives for performance metric(s) of AI/ML model monitoring for BM-Casel and BM-Case2.

Table 7.2.3-1: Alternatives for Performance metric(s) of AI/ML model monitoring for BM-Case 1 and BM-Case 2 Notel : The above analysis may not give an indication about whether/which metric is supported or specified.

Note2: Monitoring performance of the above alternatives are not addressed in the table.

NW-sided vs UE-sided model

As mentioned above, the AI/ML model for beam prediction can be NW-sided or UE-sided (i.e., executed in the network node or in the UE).

1. If the model is NW-sided, the UE makes RSRP (i.e., layer 1 RSRP or Ll-RSRP) and/or SINR (i.e., layer 1 SINR or Ll-SINR) measurements and reports the measurement results to the NW for input into the AI/ML model.

2. If the model is UE-sided, the UE both makes the measurements and the AI/ML- model-based prediction, and hence no reporting of the measurements is needed except for the final predicted beam(s).

Data collection

A key part of AI/ML-based prediction is data collection. Data collection is performed in several stages of the life-cycle management (LCM). i. First, the model must be trained by collecting measurement data for a large set of UE locations/channel conditions representative for the UE locations/channel conditions that may be encountered during use of the model (i.e., inference). For each UE, preferably all possible narrow Tx beam directions should be swept, i.e., a fairly large set of beams. ii. Second, when using the model for prediction (i.e., inference), measurement data for any UE to predict beams may need to be collected and fed to the AI/ML model. The set of beams to sweep for a UE is here much smaller than during training, since not all narrow beams are swept, only a few wide (or possibly narrow) beams are swept. iii. Finally, measurements are needed to monitor that the model functions well, or otherwise disable it or update it.

For a NW-sided model, all three types of data collection (training, inference, monitoring) follow the same general procedure:

1. The NW transmits some signal (e.g., CSI-RS or SSB) using a set of several different Tx beams on the DL

2. The UE measures the RSRP (or some other quantity, for example, Ll-SINR) of the different transmissions a. The UE here typically does Rx beamforming; this beamforming is, however, an implementation detail that it is up to the UE to decide on.

3. The UE reports the measured RSRP (or other quantity, for example, Ll-SINR ) values to the NW.

However, the measured RSRP (or some other quantity, for example, Ll-SINR) values reported by the UE to the network during a Tx beam sweep may not be enough for training of an NW-sided AI/ML model and accurate beam prediction during inference, since there are many conditions and aspects relevant to beam prediction that are not directly reflected in the RSRP values (or some other quantity, for example, Ll-SINR).

SUMMARY

Some embodiments advantageously provide methods, systems, and apparatuses for assistance information for machine learning (ML) based beam prediction.

One aspect of the present disclosure is that the UE should, during data collection for AI/ML beam prediction, report not only RSRP/RSRQ/SINR, but also additional assistance information to the network. The assistance information can be, for example, whether a beam is likely LOS, which Rx panel the UE used for measurements, whether the UE can hear (e.g., receive signaling from) the network node well in only one direction or in multiple directions, etc., as described herein.

In particular, in some embodiments, the assistance information provided is tied to particular measurements in a set of logged measurements. For example, if the UE is configured to log beam quality in terms of RSRP for a period of time, with reporting of logged data only at the end, the assistance information can be logged alongside the RSRP values (e.g., with time stamps) so that it can be combined with the RSRP measurements on the network side (e.g., network node side).

According to one aspect of the present disclosure, a method implemented by a user equipment, UE, that is configured to communicate with a network node is provided. At least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement is determined. The assistance information comprises at least one of: a probability of a line of sight, LOS, channel being reported by the UE; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE; UE rotational speed information; or information associated with receiver beam gain. The at least one reference signal measurement and the assistance information is transmitted to the network node. According to another aspect of the present disclosure, a user equipment, UE, that is configured to communicate with a network node is provided. The UE is configured to: determine at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement where the assistance information comprising at least one of: a probability of a line of sight, LOS, channel being reported by the UE; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE; UE rotational speed information; or information associated with receiver beam gain. The UE is further configured to transmit the at least one reference signal measurement and the assistance information to the network node.

According to another aspect of the present disclosure, a method implemented by a network node that is configured to communicate with a user equipment, UE is provided. At least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement is received where the assistance information comprises at least one of: a probability of a line of sight, LOS, channel being reported by the UE; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE; UE rotational speed information; or information associated with receiver beam gain. At least one action is performed based on the at least one reference signal measurement and the assistance information.

According to another aspect of the present disclosure, a network node that is configured to communicate with a user equipment, UE is provided. The network node is configured to: receive at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement, the assistance information comprising at least one of: a probability of a line of sight, LOS, channel being reported by the UE; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE; UE rotational speed information; or information associated with receiver beam gain. The network node is further configured to perform at least one action based on the at least one reference signal measurement and the assistance information. BRIEF DESCRIPTION OF THE DRAWINGS

A more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:

FIG. 1 is a diagram of an SSB beam selection as part of an initial access procedure according to a Pl scenario;

FIG. 2 is a diagram of a CSI-RS Tx beam selection in the downlink according to a P2 scenario;

FIG. 3 is a diagram of a UE Rx beam selection for the corresponding CSI-RS Tx beam in DL according to P3 scenario;

FIG. 4 is a diagram of an example of a grid-of-beam type radio pattern where set B is a subset of set A;

FIG. 5 is a diagram of an example where set A is a set of narrow beams and set B is a set of wide beams.

FIG. 6 is a schematic diagram of an example network architecture illustrating a communication system connected via an intermediate network to a host computer according to the principles in the present disclosure;

FIG. 7 is a block diagram of a network node and a wireless device according to the principles of the present disclosure;

FIG. 8 is a flowchart of an example process in a network node according to the principles of the present disclosure;

FIG. 9 is a flowchart of another example process in a network node according to the principles of the present disclosure;

FIG. 10 is a flowchart of an example process in a wireless device according to the principles of the present disclosure;

FIG. 11 is a flowchart of another example process in a wireless device according to the principles of the present disclosure;

FIG. 12 is a sequence diagram according to the principles of the present disclosure; and

FIG. 13 is a diagram of channel impulse response according to the principles of the present disclosure. DETAILED DESCRIPTION

Before describing in detail example embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to assistance information for machine learning (ML) based beam prediction. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein. Like numbers refer to like elements throughout the description.

As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate electrical or data communication, which may be accomplished by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling or optical signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate and modifications and variations are possible of achieving the electrical and data communication.

In some embodiments described herein, the term “coupled,” “connected,” and the like, may be used herein to indicate a connection, although not necessarily directly, and may include wired and/or wireless connections.

The term “network node” used herein can be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, base transceiver station (BTS), base station controller (BSC), radio network controller (RNC), g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multi- standard radio (MSR) radio node such as MSR BS, multi-cell/multicast coordination entity (MCE), integrated access and backhaul (IAB) node, relay node, donor node controlling relay, radio access point (AP), transmission points, transmission nodes, Remote Radio Unit (RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), self-organizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also comprise test equipment. The term “radio node” used herein may be used to also denote a wireless device (WD) such as a wireless device (WD) or a radio network node.

In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The UE herein can be any type of wireless device capable of communicating with a network node or another UE over radio signals, such as a wireless device (WD). The UE may also be a radio communication device, target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine communication (M2M), low-cost and/or low-complexity UE, a sensor equipped with UE, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device, etc.

Also, in some embodiments the generic term “radio network node” is used. It can be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, Multi-cell/multicast Coordination Entity (MCE), IAB node, relay node, access point, radio access point, Remote Radio Unit (RRU) Remote Radio Head (RRH).

Note that although terminology from one particular wireless system, such as, for example, 3GPP LTE and/or New Radio (NR), may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.

Note further, that functions described herein as being performed by a wireless device or a network node may be distributed over a plurality of wireless devices and/or network nodes. In other words, it is contemplated that the functions of the network node and wireless device described herein are not limited to performance by a single physical device and, in fact, can be distributed among several physical devices.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

Some embodiments provide assistance information for ML based beam prediction.

Referring again to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 6 a schematic diagram of a communication system 10, according to an embodiment, such as a 3 GPP -type cellular network that may support standards such as LTE and/or NR (5G), which comprises an access network 12, such as a radio access network, and a core network 14. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). Each network node 16a, 16b, 16c is connectable to the core network 14 over a wired or wireless connection 20. A first wireless device (UE) 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second UE 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of UEs 22a, 22b (collectively referred to as UEs 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding network node 16. Note that although only two UEs 22 and three network nodes 16 are shown for convenience, the communication system may include many more UEs 22 and network nodes 16.

Also, it is contemplated that a UE 22 can be in simultaneous communication and/or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a UE 22 can have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, UE 22 can be in communication with an eNB for LTE/E-UTRAN and a gNB for NR/NG-RAN. The intermediate network 30 may be one of, or a combination of more than one of, a public, private or hosted network. The intermediate network 30, if any, may be a backbone network or the Internet. In some embodiments, the intermediate network 30 may comprise two or more sub-networks (not shown).

The communication system of FIG. 6 as a whole enables connectivity between one of the connected UEs 22a, 22b and one or more other entities in system 10. A network node 16 is configured to include a ML unit 32 which is configured to perform one or more network node 16 functions described herein such as with respect to using assistance information for machine learning (ML) based beam prediction. A UE 22 is configured to include an assistance unit 34, which is configured to perform one or more UE 22 functions described herein, such as with respect to assistance information for machine learning (ML) based beam prediction.

Example implementations, in accordance with an embodiment, of the UE 22 and network node 16 discussed in the preceding paragraphs will now be described with reference to FIG. 7. The communication system 10 further includes a network node 16 provided in a communication system 10 and including hardware 58 enabling it to communicate with the UE 22. The hardware 58 may include a communication interface 60 for setting up and maintaining a wired or wireless connection with an interface of a different communication device of the communication system 10, as well as a radio interface 62 for setting up and maintaining at least a wireless connection 64 with a UE 22 located in a coverage area 18 served by the network node 16. The radio interface 62 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and/or one or more RF transceivers. In the embodiment shown, the hardware 58 of the network node 16 further includes processing circuitry 68. The processing circuitry 68 may include a processor 70 and a memory 72. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 68 may comprise integrated circuitry for processing and/or control, e.g., one or more processors and/or processor cores and/or FPGAs (Field Programmable Gate Array) and/or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 70 may be configured to access (e.g., write to and/or read from) the memory 72, which may comprise any kind of volatile and/or nonvolatile memory, e.g., cache and/or buffer memory and/or RAM (Random Access Memory) and/or ROM (Read-Only Memory) and/or optical memory and/or EPROM (Erasable Programmable Read-Only Memory). Thus, the network node 16 further has software 74 stored internally in, for example, memory 72, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the network node 16 via an external connection. The software 74 may be executable by the processing circuitry 68. The processing circuitry 68 may be configured to control any of the methods and/or processes described herein and/or to cause such methods, and/or processes to be performed, e.g., by network node 16. Processor 70 corresponds to one or more processors 70 for performing network node 16 functions described herein. The memory 72 is configured to store data, programmatic software code and/or other information described herein. In some embodiments, the software 74 may include instructions that, when executed by the processor 70 and/or processing circuitry 68, causes the processor 70 and/or processing circuitry 68 to perform the processes described herein with respect to network node 16. For example, processing circuitry 68 of the network node 16 may include ML unit 32 configured to perform one or more network node 16 functions as described herein such as with respect to assistance information for ML based beam prediction.

The communication system 10 further includes the UE 22 already referred to. The UE 22 may have hardware 80 that may include a radio interface 82 configured to set up and maintain a wireless connection 64 with a network node 16 serving a coverage area 18 in which the UE 22 is currently located. The radio interface 82 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and/or one or more RF transceivers.

The hardware 80 of the UE 22 further includes processing circuitry 84. The processing circuitry 84 may include a processor 86 and memory 88. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 84 may comprise integrated circuitry for processing and/or control, e.g., one or more processors and/or processor cores and/or FPGAs (Field Programmable Gate Array) and/or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 86 may be configured to access (e.g., write to and/or read from) memory 88, which may comprise any kind of volatile and/or nonvolatile memory, e.g., cache and/or buffer memory and/or RAM (Random Access Memory) and/or ROM (Read-Only Memory) and/or optical memory and/or EPROM (Erasable Programmable Read-Only Memory).

Thus, the UE 22 may further comprise software 90, which is stored in, for example, memory 88 at the UE 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the UE 22. The software 90 may be executable by the processing circuitry 84. The software 90 may include a client application 92. The client application 92 may be operable to provide a service to a human or non-human user via the UE 22, with the support of the host computer 24. In the host computer 24, an executing host application 50 may communicate with the executing client application 92 via the OTT connection 52 terminating at the UE 22 and the host computer 24. In providing the service to the user, the client application 92 may receive request data from the host application 50 and provide user data in response to the request data. The OTT connection 52 may transfer both the request data and the user data. The client application 92 may interact with the user to generate the user data that it provides.

The processing circuitry 84 may be configured to control any of the methods and/or processes described herein and/or to cause such methods, and/or processes to be performed, e.g., by UE 22. The processor 86 corresponds to one or more processors 86 for performing UE 22 functions described herein. The UE 22 includes memory 88 that is configured to store data, programmatic software code and/or other information described herein. In some embodiments, the software 90 and/or the client application 92 may include instructions that, when executed by the processor 86 and/or processing circuitry 84, causes the processor 86 and/or processing circuitry 84 to perform the processes described herein with respect to UE 22. For example, the processing circuitry 84 of the UE 22 may include an assistance unit 34 configured to perform one or more UE 22 functions as described herein such as with respect to assistance information for ML based beam prediction.

In some embodiments, the inner workings of the network node 16, UE 22, and host computer 24 may be as shown in FIG. 7 and independently, the surrounding network topology may be that of FIG. 6.

The wireless connection 64 between the UE 22 and the network node 16 is in accordance with the teachings of the embodiments described throughout this disclosure. More precisely, the teachings of some of these embodiments may improve the data rate, latency, and/or power consumption and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime, etc.

In some embodiments, the network node 16 is configured to, and/or the network node’s 16 processing circuitry 68 is configured to perform the functions and/or methods described herein for preparing/initiating/maintaining/supporting/ending a transmission to the UE 22, and/or preparing/terminating/maintaining/supporting/ending in receipt of a transmission from the UE 22.

In some embodiments, the UE 22 is configured to, and/or comprises a radio interface 82 and/or processing circuitry 84 configured to perform the functions and/or methods described herein for preparing/initiating/maintaining/supporting/ending a transmission to the network node 16, and/or preparing/terminating/maintaining/supporting/ending in receipt of a transmission from the network node 16. Although FIGS. 6 and 7 show various “units” such as ML unit 32, and assistance unit 34 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry.

FIG. 8 is a flowchart of an example process in a network node 16 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 68 (including the machine learning (ML) unit 32), processor 70, radio interface 62 and/or communication interface 60. Network node 16 is configured to receive (Block SI 00) at least one reference signal measurement and assistance information, where the assistance information comprises at least one of: a probability of a line of sight, LOS, channel, a decorrelation rate of measurements, a variation of a strongest beam of a plurality of measured beams, a number of different beam directions, channel impulse response information, an interference level, UE rotational speed information, or information associated with receiver beam gain, as described herein. Network node 16 is configured to perform (Block SI 02) machine learning, ML, based beam prediction based on the at least one reference signal measurement and assistance information, as described herein.

According to one or more embodiments, a type of the assistance information received is based on a type of the at least one reference signal measurement.

According to one or more embodiments, the network node 16 is further configured to: transmit a plurality of assistance information configuration, or indicate one of the plurality of assistance information configurations for the UE to implement.

According to one or more embodiments, the assistance information is received one of: in an additional field in a UCI RSRP report, with the at least one reference signal measurement in one of RRC or MAC signaling, or separate from the at least one reference signal measurement in one of RRC or MAC signaling.

According to one or more embodiments, the network node 16 is further configured to receive an indication of at least one receiver beam width associated with the interference level, where the ML based beam prediction is based at least on the at least one receiver beam width.

According to one or more embodiments, the network node 16 is further configured to receive an indication of a confidence level, the confidence level being associated with the assistance information, and the ML based beam prediction being based at least on the confidence level.

According to one or more embodiments, the network node 16 is further configured to communicate with the UE 22 according to at least one beam associated with the ML based beam prediction.

FIG. 9 is a flowchart of another example process in a network node 16 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 68 (including the machine learning (ML) unit 32), processor 70, radio interface 62 and/or communication interface 60. Network node 16 is configured to receive (Block SI 04) at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement, where the assistance information comprises at least one of: a probability of a line of sight, LOS, channel being reported by the UE; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE; UE rotational speed information; or information associated with receiver beam gain. Network node 16 is configured to perform (Block SI 06) at least one action based on the at least one reference signal measurement and the assistance information

According to one or more embodiments, the at least one action comprises training a machine learning, ML, model, for performing beam prediction, using at least a portion of one or more of the at least one reference signal measurement and assistance information.

According to one or more embodiments, the network node is further configured to determine whether to use a portion or all of one or more of the at least one reference signal measurement and assistance information for training the ML model based on channel condition of the UE. According to one or more embodiments, the at least one action comprises performing beam prediction using a machine learning, ML, model that has been trained using the at least one reference signal measurement and assistance information.

According to one or more embodiments, the assistance information is associated with one or more of: a reference signal measurement occasion associated with a beam; a set of reference signal measurements occasions associate with one of a single beam or a plurality of beams; a time interval during which the at least one reference signal was measured; a channel state information-reference signal, CSLRS, resource set identifier or a resource identifier where the at least one reference signal measurement is performed; a synchronization signal block, SSB, index where the at least one reference signal measurement is performed; and a measurement configuration.

According to one or more embodiments, different received reference signal measurements or group measurements are associated with one or both of: at least one same type of assistance information; and at least one different type of assistance information.

According to one or more embodiments, the network node is further configured to transmit, to the UE and via radio resource control, RRC, signaling, at least one configuration for generating assistance information.

According to one or more embodiments, the network node is further configured to transmit, to the UE and via downlink control information, DCI, or a medium access control, MAC, control element, an indication of one of the at least one configuration to use for generating assistance information.

According to one or more embodiments, the assistance information is one or more of: included in a field in a uplink control information, UCI, reference signal received power, RSRP report; sent with RSRP values in radio resource control, RRC, signaling or medium access control, MAC, control element signaling; and sent separately from RSRP values in RRC signaling or MAC control element signaling.

According to one or more embodiments, the network node is further configured to receive beam information related to at least one receiver beam width of the UE, where the beam information is provided in addition to the information associated with receiver beam gain.

According to one or more embodiments, the network node is further configured to receive an indication of at least one confidence level associated with the assistance information. According to one or more embodiments, the at least one confidence level corresponds to one of: an estimated variance in the assistance information; an overall confidence level per type of assistance information; a plurality of confidence levels where each confidence level is associated with a respective assistance information value of the assistance information.

According to one or more embodiments, the assistance information comprises one or more of the following types of assistance information: estimated delay spread; index of panel used; index of beam used; index of beam group used; UE location at time when the at least one reference signal measurement was performed; mobility state of the UE; absolute speed; time interval under which the at least one reference signal measurement was taken; receiver panel used to perform the at least one reference signal measurement; and estimated angle of arrival.

FIG. 10 is a flowchart of an example process in a UE 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of UE 22 such as by one or more of processing circuitry 84 (including the assistance unit 34), processor 86, radio interface 82 and/or communication interface 60. UE 22 is configured to perform (Block SI 08) at least one reference signal measurement, as described herein. UE 22 is configured to determine (Block SI 10) assistance information different from the at least one reference signal measurement, where the assistance information comprises at least one of: a probability of a line of sight, LOS, channel, a decorrelation rate of measurements, a variation of a strongest beam of a plurality of measured beams, a number of different beam directions, channel impulse response information, an interference level, UE rotational speed information, or information associated with receiver beam gain, as described herein. UE 22 is configured to indicate (Block SI 12) the at least one reference signal measurement and the assistance information to the network node 16 for use in machine learning, ML, based beam prediction.

According to one or more embodiments, a type of the assistance information determined is based on a type of the at least one reference signal measurement.

According to one or more embodiments, the UE 22 is further configured to: receive a plurality of assistance information configuration, or receive an indication that indicates one of the plurality of assistance information configurations to implement.

According to one or more embodiments, the assistance information is indicated one of: in an additional field in a UCI RSRP report, with the at least one reference signal measurement in one of RRC or MAC signaling, or separate from the at least one reference signal measurement in one of RRC or MAC signaling.

According to one or more embodiments, the UE 22 is further configured to indicate at least one receiver beam width associated with the interference level.

According to one or more embodiments, the UE 22 is further configured to: determine a confidence level associated with the assistance information, and indicate the confidence level to the network node 16.

According to one or more embodiments, the UE 22 is further configured to communicate with the network node 16 according to at least one beam associated with the ML based beam prediction.

FIG. 11 is a flowchart of another example process in a UE 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of UE 22 such as by one or more of processing circuitry 84 (including the assistance unit 34), processor 86, radio interface 82 and/or communication interface 60. UE 22 is configured to determine (Block SI 14) at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement where the assistance information comprises at least one of: a probability of a line of sight, LOS, channel being reported by the UE; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE; UE rotational speed information; or information associated with receiver beam gain, as described herein. UE 22 is further configured to transmit (Block SI 16) the at least one reference signal measurement and the assistance information to the network node, as described herein.

According to one or more embodiments, at least a portion of one or more of the at least one reference signal measurement and assistance information is usable by the network node for training a machine learning, ML, model.

According to one or more embodiments, at least a portion of one or more of the at least one reference signal measurement and assistance information is usable by the network node for performing beam prediction using the ML model that has been trained using at least the portion of one or more of the at least one reference signal measurement and assistance information.

According to one or more embodiments, the assistance information is associated with one or more of: a reference signal measurement occasion associated with a beam; a set of reference signal measurements occasions associate with one of a single beam or a plurality of beams; a time interval during which the at least one reference signal was measured; a channel state information-reference signal, CSI-RS, resource set identifier or a resource identifier where the at least one reference signal measurement is performed; a synchronization signal block, SSB, index where the at least one reference signal measurement is performed; and a measurement configuration.

According to one or more embodiments, the UE is further configured to receive, via radio resource control, RRC, signaling, at least one configuration for generating assistance information.

According to one or more embodiments, the UE is further configured to receive, via downlink control information, DCI, or a medium access control, MAC, control element, an indication of one of the at least one configuration to use for determining assistance information.

According to one or more embodiments, the UE is further configured to transmit beam information related to at least one receiver beam width of the UE, the beam information being provided in addition to the information associated with receiver beam gain.

According to one or more embodiments, the UE is further configured to determine at least one confidence level associated with the assistance information, and indicate the at least one confidence level to the network node.

According to one or more embodiments, the at least one confidence level corresponds to one of: an estimated variance in the assistance information; an overall confidence level per type of assistance information; and a plurality of confidence levels where each confidence level is associated with a respective assistance information value of the assistance information. According to one or more embodiments, the assistance information comprises one or more of the following types of assistance information: estimated delay spread; index of panel used; index of beam used; index of beam group used; UE location at time when the at least one reference signal measurement was performed; mobility state of the UE; absolute speed; time interval under which the at least one reference signal measurement was taken; receiver panel used to perform at least one reference signal measurement; and estimated angle of arrival.

Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for assistance information for ML based beam prediction.

Some embodiments provide assistance information for ML based beam prediction. One or more network node 16 functions described below may be performed by one or more of processing circuitry 68, processor 70, ML unit 32, communication interface 60, radio interface 62, etc. One or more UE 22 functions described below may be performed by one or more of processing circuitry 84, processor 86, assistance unit 34, radio interface 82, etc.

FIG. 12 is a flow diagram of an example process according to some embodiments of the present disclosure. At step 100, capabilities of reporting assistance information with RSRP measurements are transmitted and/or indicated to network node 16, as described herein. At step 110, configuration of assistance information to report is provided to the UE 22, as described herein. At step 120, network node 16 may optionally signal a trigger of specific assistance information, based on the configuration, as described herein. At step 130, the UE reports RSRP measurements along with assistance information, as described herein.

Overall Aspect(s)

One aspect of the present disclosure is that the UE 22 should, during data collection for AI/ML beam prediction, report not only RSRP (or RSRP type information), but also additional assistance information to the network node 16 or network (NW). The assistance information can, e.g., be UE 22 speed (linear and/or rotational), whether a beam is likely LOS (e.g., probability of LOS), which Rx panel the UE used for measurements, whether the UE can hear (e.g., receive signaling above one or more threshold(s)) the network node 16 (e.g., gNB and/or TRP) well in only one direction or in multiple directions, how may UE panels with which the UE can hear the network node 16 (e.g., gNB or TRP), etc..

The assistance information can help the performance of a network-sided AI/ML model, in different ways depending on the type of assistance information, as described herien.

In particular, in some embodiments, the assistance information provided is tied to particular measurements in a set of logged measurements. For example, if the UE 22 is configured to log beam quality in terms of RSRP for a period of time, with reporting of logged data only at the end, the assistance information can be logged alongside the RSRP values (e.g., with time stamps) so that it can be combined with the RSRP measurements on the network side (e.g., network node 16 side).

Embodiments on types of assistance information

Type of assistance information: Probability of LOS (and/or probability of indoor /outdoor UE 22)

In one embodiment, the UE 22 reports as assistance information of a probability of LOS. The probability could be, e.g., a single number representing the probability that at least one reported beam is LOS, a single number representing some average probability for the reported beams to be LOS (e.g., if two beams are reported, and one beam is LOS with probability p l and the other with probability p_2, then p_aver=(p_l+p_2 )/2 could be reported), or multiple numbers representing LOS probabilities for individual beams. In the last case, there could be one value for each reported beam, or for just a subset of the reported beams, e.g., the N strongest reported beams.

In another embodiment, the UE 22 reports a probability of LOS with its corresponding confidence level as assistance information. For example, an indoor UE is existing a building to enter an outdoor scenario where the probability of LOS is with high confidence. For example, two additional bits could be used to indicate the confidence level, i.e., 00 means the probability of LOS with the confidence level between [0,50%], 01 means the probability of LOS with the confidence level between [50,70%], 10 means the probability of LOS with the confidence level between [70,90%], 11 means the probability of LOS with the confidence level between [90,100%].

Each reported probability (e.g., probability of LOS) could have to be rounded and/or approximated to be representable by a small number of bits. For example, the LOS/NLOS probability indicator is a soft value ranging from integer 0 to 10, with integer 'O' indicating likelihood of 0.0, and integer TO' indicating likelihood of 1.0. In the extreme case, the probability could be rounded to just a single bit (i.e., hard value indicator), 0 or 1. It is to be understood that different rounding methods may be used, not necessarily symmetric or regular. Furthermore, in a variant embodiment, not probabilities but rather some function of a probability is reported.

There are several reasons it could be valuable for the network (and/or network node 16) to know whether a beam is LOS. First of all, LOS conditions could be fed as additional input into the ML model both during training and inference. Second, the information could be used to select between different ML models, one for non-LOS UEs 22 and one for LOS UEs 22 (both during training and inference). Third, if it is a LOS beam, the network (and/or network node 16) knows in which direction relative to the network the UE 22 is located, and that the beam RSRP will not likely be much affected by Rayleigh fading. This can facilitate predicting the time dependence of the RSRP of the beam.

In one embodiment, the UE 22 specifically reports probability of it being indoor or outdoor. The UE 22 can estimate this based on a number of methods, e.g., by comparing signal strength (RSRP) and propagation delay to base stations. For the network node 16, it may be useful to know whether the UE is indoor or outdoor, since it may help “fingerprinting” the location of the UE, and hence determine optimal beam direction.

Type of assistance information: How fast the channel(s) change

In another embodiment, the UE 22 provides information about how fast the channel changes, e.g., in terms of the channel decoherence time (i.e., a measure of how correlated the channel is between two time instances) or in terms of time-domain channel property (TDCP) reporting/quantities. Similar to LOS probability, channel change can be reported as a single number or one number per beam, etc. This time can be reported as the channel decoherence time experienced for an entire beam sweep across multiple beams, or as the decoherence time across consecutive channel quality measurements performed at different point in time of the same beam.

In another embodiment, the UE 22 reports the information about how fast the channel changes with its corresponding confidence level as assistance information. For example, an outdoor UE 223 with LOS is walking into a location from a subway station where the channel condition will be worse and the channel might totally decorrelated, which means the information about the channel decoherence time is with high confidence. For example, two additional bits could be used to indicate the confidence level, i.e., 00 means the information about the channel decoherence time with the confidence level between [0,50%], 01 means the information about the channel decoherence time with the confidence level between [50,70%], 10 means the information about the channel decoherence time with the confidence level between [70,90%], 11 means the information about the channel decoherence time with the confidence level between [90,100%].

Knowledge about the channel changes may be valuable for the network/network node 16, since it indicates how much trust the network/network node 16 can have for the relative RSRP values at different point(s) in time. For example, suppose the network during training data collection sweeps all Set A beams in order to find out or determine which beam is the strongest. Since Set A may be very large, this sweep may take a long time, and the channel may change during this time. This means that if the network node 16 receives a large RSRP value for some beam X in the beginning in the sweep, and a somewhat smaller RSRP value for some beam Y close to the end, it does not necessarily mean that the beam X is better, since the channel might have changed during the sweep, and the beam Y may be the better one. The network node 16 should ignore, or assign less weight in the training, to this sweep. Moreover, it may be valuable for the network node 16 to know for each individual beam how fast the channel changes. For example, if most beams have rapidly changing channels, but beam X and Y are much stronger than all those beams and have stable channels, the network might safely use the sweep in training, since the strongest beam can still be reliably determined (as X or Y), in spite of the channels on average being far from stable.

Type of assistance information: Variation/fluctuation of the Strongest beam(s)

In NR before Rel-19, the RSRP reported by UE 22 can be configured to be based on RSRP measurements over one DL RS measurement occasion or to be based on average value over multiple measurements within certain time window or certain number of measurement occasions. In one embodiment, the UE 22 can be configured to report RSRP over a larger time window or larger number of measurement occasions than legacy and include in report the assistance information reflects the change of RSRP(s) or the change of strongest beam within a time window. The information for the change of RSRP or the change of strongest beam comprises at least one of the following:

• number of measurement occasions as the strongest beam within a time window

• Ratio of number of times a beam being detected as strongest beam over number of times of measurements being performed for same beam within a time window

• Variance or standard deviation of RSRP associated with the strongest beam within a time window. In one embodiment, the strongest beam can be extended to N strongest beam(s), where N is of value 1,2,3,... up to a predefined value that is smaller than number of strongest beams UE 22 can support. For basic UE 22 feature N is i . Another typical value for N is 2. When N=2 is configured, the UE 22 reports the number of times a selected beam is detected as strongest beam and the second strongest beam within a time window; or the UE 22 reports a ratio for each order of strongest beam, i.e., the ratio as the first and the ratio as the second strongest beam; or the variance or standard deviation associated with the first strongest beam and second strongest beam.

In one embodiment, UE 22 indicates in UE capability signaling X as the number of strongest beams it can support with variation/fluctuation information, and network node 16 configures Y as the number of strongest beams it requires the UE 22 to report, where the Y is smaller than or equal to X.

Here the time window can be the measurement or monitoring window/period for the beams associated with DL RS, e.g., SSB or CSI-RS.

Type of assistance information: Number of different directions/beams

In some further embodiments, the UE 22 reports more complex channel properties, e.g., the number of different distinct directions in which it can hear the network node 16 Tx beam well. For example, if the UE 22 measures a large (e.g., above a threshold or relative to other measurements) RSRP in one direction and a large RSRP direction in another direction, but low/poor RSRP in intermediate directions, it may classify the channel as multipath and report that to the network or network node 16. This may be particularly easy to do in case the UE 22 has multiple Rx chains for measuring in multiple directions (i.e., multiple beams) simultaneously. The network or network node 16 may use knowledge about multipath to further characterize the environment/location the UE 22 is in and serve as a sort of (simple) fingerprinting that may help beam prediction.

Type of assistance information: Detailed channel impulse response information

In some further embodiments, the UE 22 reports the complex channel properties by reporting the channel itself. For example, the UE 22 can report information of its channel impulse response (CIR), or power delay profile (PDP) or delay profile (DP). The UE 22 can for example be configured to report information for several channel paths, for example report the x strongest or earliest detected taps (that are assumed not to be a noise tap). The reported information can include: (a) for CIR: timing info of the detected paths, magnitude and phase of each detected path; or (b) for PDP: timing info of the detected paths, per-path power of each detected path; or (c) timing info only of each detected path. The channel taps can be reported in one embodiment relative to another beam indicated by the NW/network node 16 or UE 22. Note that support for multipath reporting was introduced as “ AdditionalPath” in LTE Positioning Protocol (LPP) for LTE and NR, 3GPP TS 36.355 and 3GPP TS 37.355.

This can be used by the NW or network node 16 to estimate the delay-spread, NLOS probability and other information to be used as model input. Note that in this scenario, the NW/network node 16 can learn how to process the CIR and then instruct the UE 22 to use such processing in the inference phase. The NW/network node 16 can also learn which beams that are enhancing the LoS path by comparing different CIR for several beams as shown in FIG. 13.

Type of assistance information: Interference level

In some embodiments, the assistance information comprises information about interference experienced by the UE 22. Such information can be valuable to the network for one or more reasons. For example, if there is strong interference, the RSPR reported by the UE 22 may be less accurate, and should be given less weight in ML model training. Furthermore, the predicted beam will likely ultimately be used to transmit data to the UE 22, which can be made more reliably if there is little interference; a weaker beam with little interference may be better choice than a strong beam with very strong interference. Having knowledge about the interference can hence help the network or network node 16 select the best beam, e.g., by feeding it as extra information to the ML model during training as well as inference.

Type of assistance information: UE Rx beam gain

Different UE beams may have different gain, and hence the relative RSRPs between different beams may depend not only on their directions, but also their relative gain. In particular, a wide Rx beam typically results in lower Rx gain than a narrow beam, and hence will lead to reporting a lower RSRP being reported than if a narrow beam pointing in the same direction. If the network/network node 16 does not know the relative gain of different UE Rx beams, this will effectively be an uncertainty in the reported RSRP values, and will make training and inference harder.

In order to mitigate this effect, the UE 22 may report information related to the relative gain of different beams. One example of such information could be the beam width, e.g. in terms of half-power beam width (in each of two dimensions, or in terms of solid angle).

Type of assistance information: UE rotational speed As discussed above, it may be valuable for the network/network node 16 to know how fast the channel changes. One particular factor that can have a large impact on how fast the channel changes is the UE rotational speed. Hence, UE 22 may report assistance information directly related to its rotational speed, e.g., number(s) representing the rotational speed (approximately) in degrees or radians per second.

Type of assistance information: UE beam width

For a given rotational speed, how fast the channel changes may depend on the UE beam width. Hence, it could be valuable to let the UE 22 inform the network/network node 16 about its beam width before providing assistance information in terms of rotational speed. If the beam widths can be seen as constant, such information could be provided as a UE capability, distinct from RSRP reporting.

Type of assistance information: Mobility state

In one embodiment, the UE 22 reports as part of the assistance information an indication of the mobility state associated to the performed channel quality measurement. The mobility state can be represented as a flag such as Tow mobility’, ‘medium mobility’, ‘high mobility’, where each of these flags may be associated to a specific range of speeds. The specific range of speeds, e.g., expressed in km/h, for one mobility state may be indicated by the network, or specified in a standardized specification. In another method, the mobility state flag is associated with a specific range (configured by the network or specified) of the number of handovers and/or cell reselections performed by the UE 22 during a certain time interval.

In another embodiment, the mobility state is represented by the specific UE speed, e.g., expressed in km/h.

Embodiments on association with beams

Although assistance information in terms of channel conditions (e.g., UE speed) may be valuable to the network separately, it may become more valuable if associated with particular measurements or set of measurements.

In one embodiment, the assistance information is therefore associated with specific reported measurements. In particular, an index indicating the used Rx panel may be provided for each reported measurement value (e.g., RSRP), similar to the way Capabilityindex (max number of corresponding UL beams) can be reported for each reported RSRP in, e.g., Rel-18. In order to reduce overhead, there may be a way of indicating (or it may be specified in the specifications) that the same Rx panel index applies to all measurements in one report (e.g., one UCI). In another embodiment, some of the assistance information may not change for consecutively performed channel quality measurements. For example, the RX panel adopted for multiple channel quality measurements associated to the same beam or to multiple different beams may be the same. Similarly, the speed may remain constant across different performed channel quality measurements. In such cases, the UE 22 reports one value of the concerned specific assistance information for multiple channel quality measurement reports of one or multiple beams.

Embodiments on UE assistance information on UE 22's preference

The UE 22 can send assistance information on UE 22's preference related to DL MIMO configuration, UL MIMO configuration, DL and UL bandwidth reduction, reduction of maximum number of component carriers (CC), DRX preference, power saving preference, etc. Such assistance information is taken into account in the life cycle management of the AI/ML model for beam management. For example, upon reception of the UE assistance information, Set A and Set B beams can be reconfigured by the network node 16 to take into account the DL/UL MIMO configuration (for example, MIMO layer reduction, preferred max number of MIMO layers), DL/UL bandwidth reduction, and/or reduction of CCs. In another example, if the UE assistance information indicates the UE 22’s preference of power saving, Set B can be reconfigured to a smaller number of beams, thus reducing the amount of UE 22’s active time in each DRX cycle, and achieving UE power saving.

Embodiments to reduce reporting overhead

In some cases, the conditions at which the UE 22 is performing the measurements do not change for some time. In this case, there would be redundancy in reporting assistance information for both training and inference. This may be a concern if, for example, this assistance information is sent on UCI during inference. To reduce this redundancy, the following one or more alternatives can be used:

Alternative 1 : during inference the UE 22 indicates the assistance information only when there is a significant change as compared to the last indicated assistance information. In this case, if information is sent on UCI, the UCI size will be dynamic depending on the need to provide an update to the assistance information. For instance, one part of the CSI report with a fixed size can indicate if there is additional assistance information indicated in the second part of the CSI report. For instance, to report information about the mobility start of the UE 22, the UE 22 indicates in CSI part 1, that assistance information indication is present in part 2, i.e., mobility indication flag = 1. It can also be a bitmap indication for all beams or per beam where each bit corresponds to a measurement condition. Upon reporting, as long as the mobility state does not change, the mobility indication flag is set to 0, and therefore no information corresponding to the mobility start is included in the second part of the CSI.

As another variation, the UE 22 may indicate via dynamic signaling (e.g., UCI) a request to indicate a change in the assistance information (e.g., 1 bit flag). After receiving this indication, the network/network node 16 requests the UE 22 to send the updated information using dedicated signaling, e.g., the UE 22 receives a DCI that schedules the UE 22 to send the information using an RRC message.

Alternative 2: In this alternative embodiment, the UE 22 sends assistance information via a size-varying MAC CE. In the size varying MAC CE, specific fields are included to indicate if a specific type of assistance information is included in the MAC CE or not.

• In one example, one field may be included in the MAC CE to indicate if ‘Probability of LOS’ is reported in the MAC CE. If the field is set to a first value (e.g., ‘ 1’), then ‘Probability of LOS’ is reported as part of the MAC CE. If the field is set to a second value (e.g., ‘0’), then ‘Probability of LOS’ is not reported as part of the MAC CE.

• In a second example, one field may be included in the MAC CE to indicate if ‘How fast channel changes’ is reported in the MAC CE. If the field is set to a first value (e.g., ‘ 1’), then ‘How fast channel changes’ is reported as part of the MAC CE. If the field is set to a second value (e.g., ‘0’), then ‘How fast channel changes’ is not reported as part of the MAC CE.

• In a third example, one field may be included in the MAC CE to indicate if ‘Number of clearly different directions/beams’ is reported in the MAC CE. If the field is set to a first value (e.g., ‘ 1’), then ‘Number of clearly different directions/beams’ is reported as part of the MAC CE. If the field is set to a second value (e.g., ‘0’), then ‘Number of clearly different directions/beams’ is not reported as part of the MAC CE.

• In a fourth example, one field may be included in the MAC CE to indicate if ‘Detailed channel impulse response information’ is reported in the MAC CE. If the field is set to a first value (e.g., ‘ 1’), then ‘Detailed channel impulse response information’ is reported as part of the MAC CE. If the field is set to a second value (e.g., ‘0’), then ‘Detailed channel impulse response information’ is not reported as part of the MAC CE.

• In a fifth example, one field may be included in the MAC CE to indicate if ‘Interference level’ is reported in the MAC CE. If the field is set to a first value (e.g., ‘ 1’), then ‘Interference level’ is reported as part of the MAC CE. If the field is set to a second value (e.g., ‘0’), then ‘Interference level’ is not reported as part of the MAC CE.

• In a sixth example, one field may be included in the MAC CE to indicate if ‘UE Rx beam gain’ is reported in the MAC CE. If the field is set to a first value (e.g.,

‘ 1 ’), then ‘UE Rx beam gain’ is reported as part of the MAC CE. If the field is set to a second value (e.g., ‘0’), then ‘UE Rx beam gain’ is not reported as part of the MAC CE.

Note that Alternative 2 is not limited to the above assistance information types. They are equally valid for other assistance information types described herein. Also, fields may be included for one or more of the assistance information types described herein. The assistance information flag(s) and assistance information (if they are indicated to be present by the respective flag(s)) may be sent together with measurement results in the MAC CE in one embodiment. In another embodiment, assistance information flag(s) and assistance information (if they are indicated to be present by the respective flag(s)) may be sent separately from measurement results in a separate MAC CE in another embodiment.

Alternative 3: the network or network node 16 might have multiple “condition(s)- specific” models trained for different measurement conditions or have one model that is trained to generalize over different measurement conditions by having those conditions part of the input of the model. Those conditions can be either known to the network/network node 16 or obtained via the assistance information from the UE 22. To reduce the overhead of obtaining detailed assistance information about the UE 22 conditions, the NW/network node 16 can define a set of scenarios that map to the one or combinations of the conditions that are believed to have an impact on training and inference consistency. In other words, conditions are encoded together and signaled jointly. For instance, scenario 1 {low mobility, multi-path channel conditions, low interference}, scenario 2 {high mobility, low inference}, scenario 3 { fixed beam panel not guaranteed }, or scenario 4 {high inference}.

Embodiments on a confidence level Some of the types of assistance information described herein may be difficult to measure or estimate accurately. It may then be valuable for the network/network node 16 to know how certain/accurate the reported assistance information is. The UE 22 may, therefore, indicate a confidence level, i.e., estimated accuracy/certainty of the assistance information. The confidence level may be reported in one or more of the following ways:

• together with the assistance information (e.g., in the same UCI report), o per assistance information value, o per group of assistance information values, o per type(s) of assistance information value, and/or o as an overall confidence level applicable to all types of assistance information

• and/or separated from the assistance information, e.g., o as part of UE capability, and/or o via RRC signaling, o via MAC CE.

In the latter case, the confidence level may, e.g., be per type(s) of assistance information value, and/or as an overall confidence level applicable to all types of assistance information.

If the confidence level is reported in multiple ways, e.g., both per assistance information value and as an overall value, there may be rules for how the reported confidence information values should be combined to form a total confidence level.

Hence, in one or more embodiments, one or more types of assistance information may be provided by the UE, as described herein and below.

1. A UE reports channel quality measurements (e.g. RSRP) and additionally report assistance information related to those channel quality measurements, where the assistance information at least comprises one or more of the following types: a. estimated probability of LOS channel (possibly rounded, e.g., to just 0 or 1), and/or the corresponding confidence level i. and/or estimated probability of UE being indoor/outdoor, or probability of transitioning between indoor and outdoor b. how fast measurements become “decorrelated” (e g., no longer make sense to combine as part of single sweep in the network node 16) and/or the corresponding confidence level, i. e.g., quantities based on channel decoherence time, or TDCP c. Variation/fluctuation of strongest beam: number of times or probability ratio that the beam is detected as the strongest beam within a time window, e.g., measurement/monitoring window/period d. how many different directions/beams the UE hears (e.g., received above a predefined threshold) the one or more serving and/or neighboring cells (CSI-RS/SSB) in, or e. detailed channel impulse response information, for example, the pathbased reporting introduced for positioning f. interference level experienced during the channel quality measurements (possibly in terms of RSRQ or SINR), wherein the interference level is reported for one or more of the serving cells or neighboring cells g. UE rotational speed during or around the measurement h. information related to Rx beam gain, e.g., Rx beam width [Types association with beam quality measurements] Any preceding embodiment, a. where one or more of the assistance info is associated with one or more of i. one particular RSRP (can also comprise SINR or RSRQ) measurement occasion associated with one beam, ii. a set of RSRP measurement occasions associated with the same beam or to different beams, iii. a time interval, iv. certain CSI-RS resource set ID or resource ID where the measurement is performed, v. certain SSB Index where the measurement is performed, vi. certain measurement configuration, b. where different reported measurement or group of measurements i. are associated with the same type(s) of assistance information ii. may be associated with different type(s) of assistance information, e.g., no assistance information at all for some measurements (e.g. detailed channel impulse response may be provided for strong beams but not for weak beams) [How network/network node 16 signals/configures associations] Any embodiment, where the network node 16 one or more of: a. configures the UE 22 using RRC b. configures a set of different assistance information sets using RRC, and later indicates in DCI and/or MAC CE which assistance information set to use, where one assistance information set may, e.g., consist of one or more types of assistance information, possibly combined with one or more association types (and related parameters)

4. [How assistance info and its beam associations are signaled/communicated by the UE 22] Any embodiment, where one or more of a. the assistance information is an additional field in a UCI RSRP report, either one field per UCI or one field per RSRP value (i.e. beam) b. the assistance info is sent along with RSRP values in RRC signaling c. the assistance info is sent separate from RSRP values in RRC signaling (but still with some association to RSRP measurements) d. the assistance info is sent along with RSRP values in MAC-CE e. the assistance info is sent separate from RSRP values in MAC-CE (but still with some association to RSRP measurements)

5. [UE beam width] Embodiment If, where the UE 22 additionally provides the network information related to its Rx beam widths.

6. [Confidence level] Any earlier embodiment, where the UE 22 reports confidence level about the assistance information. For example, one or more of a. an estimated variance in the quantity, or the likelihood that the reported quantity is correct (e.g., a number between 0 and 1) b. Either an overall confidence level per type of assistance information, or separate confidence level per reported assistance information value or set of values.

Hence, one or more embodiments described herein provides signaling and association methods. These methods may be associated with a wider range of assistance information type such as, for example,

• estimated delay spread,

• index of panel used,

• index of beam used,

• index of beam group used,

• The UE 22 location at the point in time in which the channel quality measurement was measured • The mobility state, .e.g., in terms of high/medium/low speed, at the point in time in which the channel quality was measured.

• The absolute speed, e.g., in km/h, during which the measurement was taken

• The time interval under which the reported value of RSRP was measured

• The RX panel the UE 22 used to perform the said channel quality measurement

• estimated angle of arrival ( in earth-bounded or UE-local coordinate system), While several of the embodiments mention "RSRP", it should be understood that it could be any other quantity representing beam quality, e.g., RSRQ, SINR, etc.

One or more embodiments described herein provides one or more of the following advantages:

Examples of benefits from the assistance information is that the network (NW) can adapt its handling of the collected data in several different ways, depending on the type of assistance info. Some examples of info type and advantage are listed below:

• If the NW/network node 16 learns that the channel conditions for the UE 22 change quickly, the NW/network node 16 may decide not to feed an entire beam sweep (e.g., complete Set A sweep) to ML model training, but rather use only part of the sweep, or split the sweep into several parts that are fed to training independently.

• If the NW/network node 16 learns about the interference level the UE 22 experiences on different beams, the NW/ network node 16 can take this into account when predicting which beam will be the best for data communication to the UE 22 (e.g., high interference may mean a beam is not good for data transmission even if it has a high RSRP).

Some Examples

Example Al . A network node configured to communicate with a user equipment, UE, the network node configured to, and/or comprising a radio interface and/or comprising processing circuitry configured to: receive at least one reference signal measurement and assistance information, the assistance information comprising at least one of: a probability of a line of sight, LOS, channel; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level;

UE rotational speed information; or information associated with receiver beam gain; and perform machine learning, ML, based beam prediction based on the at least one reference signal measurement and assistance information.

Example A2. The network node of Example Al, wherein a type of the assistance information received is based on a type of the at least one reference signal measurement.

Example A3. The network node of Example Al, wherein the network node is further configured to: transmit a plurality of assistance information configuration; or indicate one of the plurality of assistance information configurations for the LE to implement.

Example A4. The network node of any one of Examples A1-A3, wherein the assistance information is received one of in an additional field in an uplink control information, UCI, reference signal received power, RSRP report; with the at least one reference signal measurement in one of radio resource control, RRC, or medium access control, MAC, signaling; or separate from the at least one reference signal measurement in one of RRC or MAC signaling.

Example A5. The network node of any one of Examples A1-A4, wherein the network node is further configured to receive an indication of at least one receiver beam width associated with the interference level; and the ML based beam prediction being based at least on the at least one receiver beam width.

Example A6. The network node of any one of Examples A1-A5, wherein the network node is further configured to receive an indication of a confidence level, the confidence level being associated with the assistance information; and the ML based beam prediction being based at least on the confidence level.

Example A7. The network node of any one of Examples A1-A6, wherein the network node is further configured to communicate with the LE according to at least one beam associated with the ML based beam prediction.

Example BL A method implemented by a network node, the network node is configured to communicate with a user equipment, LE, the method comprising: receiving at least one reference signal measurement and assistance information, the assistance information comprising at least one of: a probability of a line of sight, LOS, channel; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level;

UE rotational speed information; or information associated with receiver beam gain; and performing machine learning, ML, based beam prediction based on the at least one reference signal measurement and assistance information.

Example B2. The method of Example Bl, wherein a type of the assistance information received is based on a type of the at least one reference signal measurement.

Example B3. The method of Example Bl, further comprising: transmitting a plurality of assistance information configuration; or indicating one of the plurality of assistance information configurations for the UE to implement.

Example B4. The method of any one of Examples B1-B3, wherein the assistance information is received one of: in an additional field in an uplink control information, UCI, reference signal received power, RSRP report; with the at least one reference signal measurement in one of radio resource control, RRC, or medium access control, MAC, signaling; or separate from the at least one reference signal measurement in one of RRC or MAC signaling.

Example B5. The method of any one of Examples B1-B4, further comprising receiving an indication of at least one receiver beam width associated with the interference level; and the ML based beam prediction being based at least on the at least one receiver beam width.

Example B6. The method of any one of Examples B1-B5, further comprising receiving an indication of a confidence level, the confidence level being associated with the assistance information; and the ML based beam prediction being based at least on the confidence level.

Example B7. The method of any one of Examples B1-B6, further comprising communicating with the UE according to at least one beam associated with the ML based beam prediction.

Example CL A user equipment, UE, configured to communicate with a network node, the UE configured to, and/or comprising a radio interface and/or processing circuitry configured to: perform at least one reference signal measurement; determine assistance information different from the at least one reference signal measurement, the assistance information comprising at least one of a probability of a line of sight, LOS, channel; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level;

UE rotational speed information; or information associated with receiver beam gain; and indicate the at least one reference signal measurement and the assistance information to the network node for use in machine learning, ML, based beam prediction.

Example C2. The UE of Example Cl, wherein a type of the assistance information determined is based on a type of the at least one reference signal measurement.

Example C3. The UE of any one of Examples C1-C2, wherein the UE is further configured to: receive a plurality of assistance information configuration; or receive an indication that indicates one of the plurality of assistance information configurations to implement.

Example C4. The UE of any one of Examples C1-C3, wherein the assistance information is indicated one of: in an additional field in a uplink control information, UCI, reference signal received power, RSRP report; with the at least one reference signal measurement in one of radio resource control, RRC, or medium access control, MAC, signaling; or separate from the at least one reference signal measurement in one of RRC or MAC signaling.

Example C5. The UE of any one of Examples C1-C4, wherein the UE is further configured to indicate at least one receiver beam width associated with the interference level.

Example C6. The UE of any one of Examples C1-C5, wherein the UE is further configured to: determine a confidence level associated with the assistance information; and indicate the confidence level to the network node.

Example C7. The UE of any one of Examples C1-C6, wherein the UE is further configured to communicate with the network node according to at least one beam associated with the ML based beam prediction.

Example DI. A method implemented in a user equipment, UE, the UE configured to communicate with a network node, the method comprising performing at least one reference signal measurement; determining assistance information different from the at least one reference signal measurement, the assistance information comprising at least one of: a probability of a line of sight, LOS, channel; a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level;

UE rotational speed information; or information associated with receiver beam gain; and indicating the at least one reference signal measurement and the assistance information to the network node for use in machine learning, ML, based beam prediction.

Example D2. The method of Example DI, wherein a type of the assistance information determined is based on a type of the at least one reference signal measurement.

Example D3. The method of any one of Examples D1-D2, further comprising: receiving a plurality of assistance information configuration; or receiving an indication that indicates one of the plurality of assistance information configurations to implement. Example D4. The method of any one of Examples D1-D3, wherein the assistance information is indicated one of: in an additional field in a uplink control information, UCI, reference signal received power, RSRP report; with the at least one reference signal measurement in one of radio resource control, RRC, or medium access control, MAC, signaling; or separate from the at least one reference signal measurement in one of RRC or MAC signaling.

Example D5. The method of any one of Examples D1-D4, further comprising indicating at least one receiver beam width associated with the interference level.

Example D6. The method of any one of Examples D1-D5, further comprising: determining a confidence level associated with the assistance information; and indicating the confidence level to the network node.

Example D7. The method of any one of Examples D1-D6, further comprising communicating with the network node according to at least one beam associated with the ML based beam prediction.

As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and/or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step, action and/or functionality described herein may be performed by, and/or associated to, a corresponding module, which may be implemented in software and/or firmware and/or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that can be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD-ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.

Some embodiments are described herein with reference to flowchart illustrations and/or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a special purpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer readable memory or storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

It is to be understood that the functions/acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows.

Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, Java® or C++. However, the computer program code for carrying out operations of the disclosure may also be written in conventional procedural programming languages, such as the "C" programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments can be combined in any way and/or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.

Abbreviations that may be used in the preceding description include:

Abbreviation Explanation

Al Artificial intelligence

CSI-RS Channel status information

DCI Downlink control information gNB Base station

MAC Medium access control

ML Machine learning

NW Network

PHY Physical layer

RRC Radio resource control

RS Reference signal

RSRP Reference signal received power

RSRQ Reference signal received quality

Rx Receive, receiving, reception

SINR Signal-to-interference-and-noise ratio

TCI Transmission configuration indication

TDCP Time-domain channel property

Tx Transmit, transmitting, transmission

UE User equipment

It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings without departing from the scope of the following claims.

Claims

CLAIMS:

1. A method implemented by a user equipment, UE (22), that is configured to communicate with a network node (16), the method comprising: determining (SI 14) at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement, the assistance information comprising at least one of: a probability of a line of sight, LOS, channel being reported by the UE (22); a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE (22);

UE rotational speed information; or information associated with receiver beam gain; and transmitting (SI 16) the at least one reference signal measurement and the assistance information to the network node (16).

2. The method of Claim 1, wherein at least a portion of one or more of the at least one reference signal measurement and assistance information is usable by the network node (16) for training a machine learning, ML, model.

3. The method of Claim 2, wherein at least a portion of one or more of the at least one reference signal measurement and assistance information is usable by the network node (16) for performing beam prediction using the ML model that has been trained using at least the portion of one or more of the at least one reference signal measurement and assistance information.

4. The method of any one of Claims 2-3, wherein the assistance information is associated with one or more of: a reference signal measurement occasion associated with a beam; a set of reference signal measurements occasions associate with one of a single beam or a plurality of beams; a time interval during which the at least one reference signal was measured; a channel state information-reference signal, CSI-RS, resource set identifier or a resource identifier where the at least one reference signal measurement is performed; a synchronization signal block, SSB, index where the at least one reference signal measurement is performed; and a measurement configuration.

5. The method of any one of Claims 2-4, wherein different received reference signal measurements or group measurements are associated with one or both of: at least one same type of assistance information; and at least one different type of assistance information.

6. The method of any one of Claims 1-5, further comprising receiving, via radio resource control, RRC, signaling, at least one configuration for generating assistance information.

7. The method of Claim 6, further comprising receiving, via downlink control information, DCI, or a medium access control, MAC, control element, an indication of one of the at least one configuration to use for determining assistance information.

8. The method of any one of Claims 1-7, wherein the assistance information is one or more of: included in a field in a uplink control information, UCI, reference signal received power, RSRP report; sent with RSRP values in radio resource control, RRC, signaling or medium access control, MAC, control element signaling; and sent separately from RSRP values in RRC signaling or MAC control element signaling.

9. The method of any one of Claims 1-8, further comprising transmitting beam information related to at least one receiver beam width of the UE (22), the beam information being provided in addition to the information associated with receiver beam gain.

10. The method of any one of Claims 1-9, further comprising: determining at least one confidence level associated with the assistance information; and indicating the at least one confidence level to the network node (16).

11. The method of Claim 10, wherein the at least one confidence level corresponds to one of: an estimated variance in the assistance information; an overall confidence level per type of assistance information; and a plurality of confidence levels, each confidence level being associated with a respective assistance information value of the assistance information.

12. The method of any one of Claims 1-11, wherein the assistance information comprises one or more of the following types of assistance information: estimated delay spread; index of panel used; index of beam used; index of beam group used;

UE location at time when the at least one reference signal measurement was performed; mobility state of the UE (22); absolute speed; time interval under which the at least one reference signal measurement was taken; receiver panel used to perform at least one reference signal measurement; and estimated angle of arrival.

13. A user equipment, UE (22), that is configured to communicate with a network node (16), the UE (22) configured to: determine at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement, the assistance information comprising at least one of: a probability of a line of sight, LOS, channel being reported by the UE (22); a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE (22);

UE rotational speed information; or information associated with receiver beam gain; and transmit the at least one reference signal measurement and the assistance information to the network node (16).

14. The UE (22) of Claim 13, wherein at least a portion of one or more of the at least one reference signal measurement and assistance information is usable by the network node for training a machine learning, ML, model.

15. The UE (22) of Claim 14, wherein at least a portion of one or more of the at least one reference signal measurement and assistance information is usable by the network node for performing beam prediction using the ML model that has been trained using at least the portion of one or more of the at least one reference signal measurement and assistance information.

16. The UE (22) of any one of Claims 14-15, wherein the assistance information is associated with one or more of: a reference signal measurement occasion associated with a beam; a set of reference signal measurements occasions associate with one of a single beam or a plurality of beams; a time interval during which the at least one reference signal was measured; a channel state information-reference signal, CSLRS, resource set identifier or a resource identifier where the at least one reference signal measurement is performed; a synchronization signal block, SSB, index where the at least one reference signal measurement is performed; and a measurement configuration.

17. The UE (22) of any one of Claims 14-16, wherein different received reference signal measurements or group measurements are associated with one or both of: at least one same type of assistance information; and at least one different type of assistance information.

18. The UE (22) of any one of Claims 13-17, further comprising receiving, via radio resource control, RRC, signaling, at least one configuration for generating assistance information.

19. The UE (22) of Claim 18, further comprising receiving, via downlink control information, DCI, or a medium access control, MAC, control element, an indication of one of the at least one configuration to use for determining assistance information.

20. The UE (22) of any one of Claims 13-19, wherein the assistance information is one or more of: included in a field in a uplink control information, UCI, reference signal received power, RSRP report; sent with RSRP values in radio resource control, RRC, signaling or medium access control, MAC, control element signaling; and sent separately from RSRP values in RRC signaling or MAC control element signaling.

21. The UE (22) of any one of Claims 13-20, further comprising transmitting beam information related to at least one receiver beam width of the UE (22), the beam information being provided in addition to the information associated with receiver beam gain.

22. The UE (22) of any one of Claims 13-21, further comprising: determining at least one confidence level associated with the assistance information; and indicating the at least one confidence level to the network node (16).

23. The UE (22) of Claim 22, wherein the at least one confidence level corresponds to one of: an estimated variance in the assistance information; an overall confidence level per type of assistance information; and a plurality of confidence levels, each confidence level being associated with a respective assistance information value of the assistance information.

24. The UE (22) of any one of Claims 13-23, wherein the assistance information comprises one or more of the following types of assistance information: estimated delay spread; index of panel used; index of beam used; index of beam group used;

25. A method implemented by a network node (16) that is configured to communicate with a user equipment, UE (22), the method comprising: receiving (SI 04) at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement, the assistance information comprising at least one of: a probability of a line of sight, LOS, channel being reported by the UE (22); a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE (22);

UE rotational speed information; or information associated with receiver beam gain; and performing (SI 06) at least one action based on the at least one reference signal measurement and the assistance information.

26. The method of Claim 25, wherein the at least one action comprises training a machine learning, ML, model, for performing beam prediction, using at least a portion of one or more of the at least one reference signal measurement and assistance information.

27. The method of Claim 26, further comprising determining whether to use a portion or all of one or more of the at least one reference signal measurement and assistance information for training the ML model based on channel condition of the UE (22).

28. The method of any one of Claims 25-27, wherein the at least one action comprises performing beam prediction using a machine learning, ML, model that has been trained using the at least one reference signal measurement and assistance information.

29. The method of any one of Claims 26-28, wherein the assistance information is associated with one or more of: a reference signal measurement occasion associated with a beam; a set of reference signal measurements occasions associate with one of a single beam or a plurality of beams; a time interval during which the at least one reference signal was measured; a channel state information-reference signal, CSLRS, resource set identifier or a resource identifier where the at least one reference signal measurement is performed; a synchronization signal block, SSB, index where the at least one reference signal measurement is performed; and a measurement configuration.

30. The method of any one of Claims 26-29, wherein different received reference signal measurements or group measurements are associated with one or both of: at least one same type of assistance information; and at least one different type of assistance information.

31. The method of any one of Claims 25-30, further comprising transmitting, to the UE (22) and via radio resource control, RRC, signaling, at least one configuration for generating assistance information.

32. The method of Claim 31, further comprising transmitting, to the UE (22) and via downlink control information, DCI, or a medium access control, MAC, control element, an indication of one of the at least one configuration to use for generating assistance information.

33. The method of any one of Claims 25-32, wherein the assistance information is one or more of: included in a field in a uplink control information, UCI, reference signal received power, RSRP, report; sent with RSRP values in radio resource control, RRC, signaling or medium access control, MAC, control element signaling; and sent separately from RSRP values in RRC signaling or MAC control element signaling.

34. The method of any one of Claims 25-33, further comprising receiving beam information related to at least one receiver beam width of the UE (22), the beam information being provided in addition to the information associated with receiver beam gain.

35. The method of any one of Claims 25-34, further comprising receiving an indication of at least one confidence level associated with the assistance information.

36. The method of Claim 35, wherein the at least one confidence level corresponds to one of: an estimated variance in the assistance information; an overall confidence level per type of assistance information; and a plurality of confidence levels, each confidence level being associated with a respective assistance information value of the assistance information.

37. The method of any one of Claims 25-36, wherein the assistance information comprises one or more of the following types of assistance information: estimated delay spread; index of panel used; index of beam used; index of beam group used;

UE location at time when the at least one reference signal measurement was performed; mobility state of the UE (22); absolute speed; time interval under which the at least one reference signal measurement was taken; receiver panel used to perform the at least one reference signal measurement; and estimated angle of arrival.

38. A network node (16) that is configured to communicate with a user equipment, UE (22), the network node (16) configured to: receive at least one reference signal measurement and assistance information that is associated with the at least one reference signal measurement, the assistance information comprising at least one of: a probability of a line of sight, LOS, channel being reported by the UE (22); a decorrelation rate of measurements; a variation of a strongest beam of a plurality of measured beams; a number of different beam directions; channel impulse response information; an interference level experienced by the UE (22);

UE rotational speed information; or information associated with receiver beam gain; and perform at least one action based on the at least one reference signal measurement and the assistance information.

39. The network node (16) of Claim 38, wherein the at least one action comprises training a machine learning, ML, model, for performing beam prediction, using at least a portion of one or more of the at least one reference signal measurement and assistance information.

40. The network node (16) of Claim 39, further comprising determining whether to use a portion or all of one or more of the at least one reference signal measurement and assistance information for training the ML model based on channel condition of the UE (22).

41. The network node (16) of any one of Claims 38-40, wherein the at least one action comprises performing beam prediction using a machine learning, ML, model that has been trained using the at least one reference signal measurement and assistance information.

42. The network node (16) of any one of Claims 39-41, wherein the assistance information is associated with one or more of: a reference signal measurement occasion associated with a beam; a set of reference signal measurements occasions associate with one of a single beam or a plurality of beams; a time interval during which the at least one reference signal was measured; a channel state information-reference signal, CSLRS, resource set identifier or a resource identifier where the at least one reference signal measurement is performed; a synchronization signal block, SSB, index where the at least one reference signal measurement is performed; and a measurement configuration.

43. The network node (16) of any one of Claims 39-42, wherein different received reference signal measurements or group measurements are associated with one or both of: at least one same type of assistance information; and at least one different type of assistance information.

44. The network node (16) of any one of Claims 38-43, further comprising transmitting, to the UE (22) and via radio resource control, RRC, signaling, at least one configuration for generating assistance information.

45. The network node (16) of Claim 44, further comprising transmitting, to the UE (22) and via downlink control information, DCI, or a medium access control, MAC, control element, an indication of one of the at least one configuration to use for generating assistance information.

46. The network node (16) of any one of Claims 38-45, wherein the assistance information is one or more of: included in a field in a uplink control information, UCI, reference signal received power, RSRP report; sent with RSRP values in radio resource control, RRC, signaling or medium access control, MAC, control element signaling; and sent separately from RSRP values in RRC signaling or MAC control element signaling.

47. The network node (16) of any one of Claims 38-46, further comprising receiving beam information related to at least one receiver beam width of the UE (22), the beam information being provided in addition to the information associated with receiver beam gain.

48. The network node (16) of any one of Claims 38-47, further comprising receiving an indication of at least one confidence level associated with the assistance information.

49. The network node (16) of Claim 48, wherein the at least one confidence level corresponds to one of: an estimated variance in the assistance information; an overall confidence level per type of assistance information; and a plurality of confidence levels, each confidence level being associated with a respective assistance information value of the assistance information.

50. The network node (16) of any one of Claims 38-49, wherein the assistance information comprises one or more of the following types of assistance information: estimated delay spread; index of panel used; index of beam used; index of beam group used;