Method for space beam prediction on wireless device side

Abstract

A wireless device (WD) is described. The WD is configured to: receive a downlink (DL) RS configuration for configuring two or more sets of reference signal resources; receiving a CSI report configuration and a first message, the first message requesting a WD to measure a subset of DL RSs in the first set of DL RSs associated with the beams of the first set; and performing a measurement on a subset of the DL RSs in the second set of DL RSs. The WD is further configured to perform one or more actions associated with an artificial intelligence model using at least measurements of a subset of DL RSs of the second set of DL RSs; predicting one or more DL RSs from the first set of DL RSs based in part on the one or more actions; and transmitting information on the predicted one or more RSs.

Description

Technical Field

[0001] The present disclosure relates to wireless communications, and in particular to prediction of beams between a fixed set of beams ("F beams"). Background Art

[0002] The 3rd Generation Partnership Project (3GPP) has developed and is developing standards for fourth generation (4G) (also known as Long Term Evolution (LTE)) and fifth generation (5G) (also known as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communications between network nodes (such as base stations) and mobile wireless devices (WDs), as well as communications between network nodes and between wireless devices. Sixth generation (6G) wireless communication systems are also under development. Beam management Beam Management Process

[0003] In frequency range 2 (FR2), multiple radio frequency (RF) beams may be used to transmit and receive signals at network nodes and wireless devices. For each downlink (DL) beam from a network node, there is typically an associated best wireless device receive (Rx) beam for receiving signals from the DL beam. The DL beam and the associated wireless device Rx beam form a beam pair. The beam pair may be identified by a so-called beam management process in New Radio (NR).

[0004] A DL beam is (usually) identified by an associated DL Reference Signal (RS) sent in that beam. The RS may be sent periodically, semi-persistently, or aperiodically. The DL RS used for this purpose may be a Synchronization Signal (SS) and a Physical Broadcast Channel (PBCH) Block (SSB) or a Channel State Information RS (CSI-RS). By measuring all DL RSs, the wireless device may determine and report to the network node the best DL beam for DL ​​transmission. The network node may then send a burst of DL-RS in the reported best DL beam to let the wireless device evaluate the candidate wireless device Rx beams.

[0005] Although not explicitly stated in the 3GPP NR specification, beam management has been divided into three processes, which are Figure 1 An example is shown schematically:

[0006] P-1 process: The goal is to find the rough direction of the wireless device using a wide network node transmit (TX) beam covering the entire angular sector.

[0007] P-2 process: The purpose is to refine the network node TX beam by performing a new beam search around the coarse direction found in P1.

[0008] P-3 process: used for radios with analog beamforming to let them find the appropriate radio RX beam.

[0009] The P-1 process is expected to utilize beams with relatively large beamwidths, and where beam RSs are sent periodically and shared among all wireless devices of the cell (cell-specific RS transmission). Typically, the RSs used for the P-1 process are periodic channel state information reference signals (CSI-RS) or synchronization signal blocks (SSBs). The wireless device then reports the N best beams and their corresponding reference signal strength indicator (RSRP) values ​​to the network node.

[0010] The P-2 process is expected to use aperiodic / or semi-persistent CSI-RS transmitted in narrow beams around the coarse direction found in the P- 1 process. These RSs are configured in a wireless device specific manner (not shared by many wireless devices).

[0011] The P-3 process is expected to use aperiodic or semi-persistent CSI-RS that is transmitted repeatedly in a narrow network node beam. An alternative approach is to let the wireless device determine the appropriate wireless device RX beam based on periodic SSB transmissions. Since each SSB consists of four optical frequency division multiplexing (OFDM) symbols, up to four wireless device RX beams can be evaluated during each SSB burst transmission. One benefit of using SSB instead of CSI-RS is that the additional overhead of CSI-RS transmission is not required. Beam pointing

[0012] In NR, several signals can be sent from different antenna ports of the same network node. These signals can have the same large-scale characteristics, such as Doppler shift / spread, average delay spread or average delay. These antenna ports are thus called quasi-co-located (QCL).

[0013] If the wireless device knows that both antenna ports are QCL with respect to a certain parameter (eg, Doppler spread), the wireless device may estimate the parameter based on one of the antenna ports and apply the estimate to receiving the signal on the other antenna port.

[0014] For example, there may be a QCL relationship between the CSI-RS for Tracking RS (TRS) and the Physical Downlink Shared Channel (PDSCH) Demodulation Reference Signal (DMRS). When a wireless device receives the PDSCH DMRS, it can use the measurements already made on the Timing Reference Signal (TRS) to assist in DMRS reception.

[0015] Information about what assumptions can be made about QCL is signaled from the network to the wireless device. In NR, four types of QCL relationships between the transmit source RS and the transmit target RS are defined:

[0016] Type A: {Doppler shift, Doppler spread, average delay, delay spread}

[0017] Type B: {Doppler shift, Doppler spread}

[0018] Type C: {average delay, Doppler shift}

[0019] Type D: {spatial Rx parameters}

[0020] QCL Type D was introduced in NR to facilitate beam management with analog beamforming and is referred to as spatial QCL. Currently there is no strict definition of spatial QCL, but it is understood that if two transmit antenna ports are spatially QCL, the wireless device can use the same Rx beam to receive them. This helps wireless devices that use analog beamforming to receive signals, because the wireless device needs to adjust its RX beam in a certain direction before receiving a specific signal. If the wireless device knows that the signal is spatially QCL with some other signal it received earlier, it can safely use the same RX beam to receive the signal.

[0021] In NR, the spatial QCL relationship of DL or UL signals / channels can be indicated to the wireless device by using "beam indication". "Beam indication" is used to help the wireless device find a suitable RX beam for DL ​​reception and / or a suitable TX beam for UL transmission. In NR, the "beam indication" of DL is communicated to the wireless device by indicating the transmission configuration indicator (TCI) state to the wireless device, while in UL, the "beam indication" can be communicated by indicating the DL-RS or UL-RS as a spatial relationship (in NR Rel-15 / 16, i.e. 3GPP Rel-15 / 16) or TCI state (in 3GPP NR Rel-17). Beam management using unified TCI framework

[0022] In NR, downlink beam management is performed by conveying the spatial QCL (“Type D”) assumption to the wireless device through the TCI state.

[0023] In 3GPP NR Rel-15 or Rel-16:

[0024] -For Physical Downlink Control Channel (PDCCH): The network (NW) and / or network node configures a set of PDCCH TCI states for the wireless device through Radio Resource Control (RRC), and then activates one TCI state for each Control Resource Set (CORESET) using Medium Access Control (MAC) Control Element (CE).

[0025] -For Physical Downlink Shared Channel (PDSCH): NW and / or network node configures a set of PDSCH TCI states for wireless devices through RRC, and then activates up to 8 TCI states through MAC CE. After activation, NW and / or network node uses the TCI field in the downlink control information (DCI) to dynamically indicate one of these activated TCI states when scheduling PDSCH.

[0026] Such a framework allows the network great flexibility to instruct wireless devices to receive signals from different spatial directions in DL at the cost of large signaling overhead and slow beam switching. These limitations are particularly significant and expensive when considering wireless device mobility. An example is that beam updates using DCI can only be performed for PDSCH, and MAC-CE and / or RRC are required to update beams for other reference signals / channels, resulting in additional overhead and latency.

[0027] Furthermore, in most cases, the network transmits to and receives from the wireless device in the same direction for both data and control. Therefore, using separate frameworks (TCI state corresponding spatial relationships) for different channels / signals complicates implementation.

[0028] In 3GPP Rel-17, a common beam framework for beam management was introduced in FR2, where a common beam represented by a TCI state can be activated / indicated to a wireless device, and the common beam is applicable to multiple channels / signals, such as PDCCH and PDSCH. The common beam framework is also called a unified TCI state framework.

[0029] The new framework can be configured by RRC in one or two modes of operation (i.e., "joint DL / UL TCI" or "separate DL / UL TCI"). For "joint DL / UL TCI", one common joint TCI state is used for both DL and UL signals / channels. For "separate DL / UL TCI", one common DL-only TCI state is used for DL ​​channels / signals, and one common UL-only TCI state is used for UL signals / channels.

[0030] The unified TCI state may be updated in a similar manner to the TCI state update for PDSCH in Rel-15 / 16, i.e., with one of two alternatives:

[0031] Two stages: RRC signaling is used to configure multiple unified TCI states in the high-level parameter PDSCH-config, and MAC-CE is used to activate one of the unified TCI states.

[0032] Phase 3: RRC signaling is used to configure multiple unified TCI states in PDSCH-config, MAC-CE is used to activate up to 8 unified TCI states, and the 3-bit TCI state bit field in DCI is used to indicate one of the activated unified TCI states.

[0033] An activated or indicated unified TCI state will be used in subsequent PDCCH and PDSCH transmissions until a new unified TCI state is activated or indicated.

[0034] Existing DCI formats 1 and 1_2 are reused for beam indication both with and without DL allocations. For DCI formats 1 and 1_2 with DL allocations, an acknowledgement / negative acknowledgement (ACK / NACK) of the PDSCH can be used as an indication of successful reception of the beam indication. For DCI formats 1 and 1_2 without DL allocations, a new ACK / NACK mechanism similar to the SPS PDSCH release with type 1 and type 2 hybrid automatic repeat request acknowledgement (HARQ-ACK) codebooks is used, where the wireless device reports an acknowledgement (ACK) upon successful reception of the beam indication DCI.

[0035] For DCI based beam indication, the first timeslot to which the indicated TCI applies is at least Y symbols after the last symbol of the confirmation of the joint or individual DL / UL beam indication. The Y symbols are configured by the network node based on the wireless device capabilities, which are also reported in symbols. The value of Y has not yet been determined and is left to the Radio Access Network 4 (RAN4) to decide. Reference signal Reference signal configuration CSI-RS:

[0036] CSI-RS is transmitted on each transmit (Tx) antenna port at the network node and for different antenna ports. CSI-RS is multiplexed in the time domain, frequency domain, and code domain so that the channel between each Tx antenna port at the network node and each receive antenna port at the wireless device can be measured by the wireless device. The time-frequency resources used to transmit CSI-RS are called CSI-RS resources.

[0037] In NR, CSI-RS for beam management is defined as 1-port or 2-port CSI-RS resources with field duplication in the CSI-RS resource set. The following three types of CSI-RS transmission are supported:

[0038] Periodic CSI-RS: CSI-RS is transmitted periodically in certain time slots. This CSI-RS transmission is semi-statically configured using RRC signaling with parameters such as CSI-RS resource, periodicity, and slot offset.

[0039] Semi-persistent CSI-RS: Similar to periodic CSI-RS, resources for semi-persistent CSI-RS transmission are semi-statically configured using RRC signaling with parameters such as periodicity and slot offset. However, unlike periodic CSI-RS, dynamic signaling is required to activate and deactivate CSI-RS transmission.

[0040] ·Aperiodic CSI-RS: This is a one-time CSI-RS transmission that can occur in any time slot. Here, one-time means that CSI-RS transmission occurs only once per trigger. The CSI-RS resources (i.e., RE positions including subcarrier positions and OFDM symbol positions) used for aperiodic CSI-RS are semi-statically configured. The transmission of aperiodic CSI-RS is triggered by dynamic signaling using the CSI request field in the UL DCI through PDCCH in the same DCI that schedules the UL resources for measurement reporting. Multiple aperiodic CSI-RS resources can be included in a CSI-RS resource set, and the triggering of aperiodic CSI-RS is based on the resource set. SSB:

[0041] In NR, SSB consists of a pair of synchronization signals (SS), physical broadcast channel (PBCH) and DMRS for PBCH. SSB is mapped to 4 consecutive OFDM symbols in the time domain and 240 consecutive subcarriers (20 RBs) in the frequency domain.

[0042] To support beamforming and beam scanning for SSB transmission, in NR, a cell can send multiple SSBs in different narrow beams in a time multiplexed manner. The transmission of these SSBs is limited to a half-frame time interval (5ms). A cell can also be configured to send multiple SSBs in a single wide beam with multiple repetitions. The design of the beamforming parameters for each SSB within a half-frame may depend on the network implementation. The SSBs within a half-frame are broadcast periodically from each cell. The periodicity of a half-frame with SS / PBCH blocks is called the SSB periodicity, which is indicated by SIB1.

[0043] The maximum number of SSBs within a half-frame (represented by L) depends on the frequency band, and the time positions of these L candidate SSBs within the half-frame depend on the SCS of the SSB. The L candidate SSBs within the half-frame are indexed in ascending order in time from 0 to L-1. The wireless device knows the SSB index by successfully detecting the PBCH and its associated DMRS. The cell does not have to send SS / PBCH blocks in all L candidate positions in the half-frame, and the resources of the unused candidate positions can be used instead for the transmission of data or control signaling. It is up to the network implementation to decide which candidate time positions to select for SSB transmission within the half-frame, and which beam to use for each SSB transmission. Measuring resource allocation

[0044] In NR, a wireless device can be configured with N≥1 CSI report settings (i.e., CSI-ReportConfig), M≥1 resource settings (i.e., CSI-ResourceConfig), where each CSI report setting is linked to one or more resource settings for channel and / or interference measurement. The CSI framework is modular, which means that several CSI report settings can be associated with the same resource setting.

[0045] One CSI-ResourceConfig contains several non-zero power (NZP)-CSI-RS-ResourceSets and / or CSI-SSB-ResourceSets.

[0046] The wireless device can be configured to perform measurements on the CSI-RS. Here, the RRC information element (IE) NZP-CSI-RS-ResourceSet is used. The NZP CSI-RS resource set contains the configuration of Ks≥1 CSI-RS resources, where the configuration of each CSI-RS resource includes at least: mapping to RE, number of antenna ports, time domain behavior, etc. Up to 64 CSI-RS resources can be grouped into NZP-CSI-RS-ResourceSet. The wireless device can also be configured to perform measurements on SSB. Here, RRCIE CSI-SSB-ResourceSet is used. The resource set including SSB resources is defined in a similar manner.

[0047] In the case of aperiodic CSI-RS and / or aperiodic CSI reporting, the network node configures the wireless device with S_c CSI triggering states. Each triggering state contains an aperiodic CSI reporting setting to be triggered together with an associated aperiodic CSI-RS resource set.

[0048] Periodic and semi-persistent resource settings may include only a single resource set (i.e., S=1), while for aperiodic resource settings, S>=1. This is because in the aperiodic case, one of the S resource sets included in the resource setting is indicated by an aperiodic trigger state that triggers CSI reporting. Measurement Report

[0049] Three types of CSI reports are supported in NR as follows:

[0050] • Periodic CSI reporting on the Physical Uplink Control Channel (PUCCH): CSI is reported periodically by the wireless device. Parameters such as periodicity and slot offset are semi-statically configured by higher layer RRC signaling from the network node to the wireless device.

[0051] Semi-persistent CSI reporting on Physical Uplink Shared Channel (PUSCH) or PUCCH: Similar to periodic CSI reporting, semi-persistent CSI reporting has a periodicity and slot offset that can be semi-statically configured. However, a dynamic trigger from the network node to the wireless device may be required to allow the wireless device to start semi-persistent CSI reporting. A dynamic trigger from the network node to the wireless device is required to request the wireless device to stop semi-persistent CSI reporting.

[0052] • Aperiodic CSI reporting on PUSCH: This type of CSI reporting involves a single (ie, one time) CSI report by a wireless device that is dynamically triggered by a network node using DCI. Some parameters related to the configuration of aperiodic CSI reporting are semi-statically configured by RRC, but the triggering is dynamic.

[0053] In each CSI report setting, the content and temporal behavior of the report are defined, as well as links to the associated resource settings. The CSI-ReportConfig IE includes the following configurations:

[0054] reportConfigType

[0055] o Defines the time domain behavior, i.e., periodic CSI reporting, semi-persistent CSI reporting, or aperiodic CSI reporting, as well as the reporting periodicity and slot offset for periodic CSI reporting.

[0056] reportQuantity

[0057] o Defines the reported CSI parameters (i.e., CSI content), such as PMI, CQI, RI, LI (layer indicator), CRI (CSI-RS resource index), and L1-RSRP. Only a certain number of combinations are possible (e.g., "cri-RI-PMI-CQI" is one possible value, and "cri-RSRP" is another), and each value of reportQuantity can correspond to a certain CSI mode.

[0058] codebookConfig

[0059] o Defines the codebook used for PMI reporting and possible codebook subset restriction (CBSR). Two "types" of PMI codebooks are defined in NR, Type I CSI and Type I ICSI, each codebook type also has two variants.

[0060] ·reportFrequencyConfiguration

[0061] o Defines the frequency granularity of PMI and CQI (wideband or subband), if reported, and the CSI reporting band, which is a subset of the subband of the bandwidth part (BWP) to which the CSI corresponds.

[0062] Time domain measurement limits (ON / OFF) for channel and interference separately

[0063] For beam management, the wireless device can be configured to report L1-RSRP for up to four different CSI-RS / SSB resource indicators. The reported RSRP value corresponding to the first (best) CSI reference signal resource indicator (CRI) and / or SSB resource indicator (RI) requires 7 bits (using absolute value), while other RSRP values ​​require 4 bits (using coding relative to the first one). In NR Release 16, reporting of L1 signal-to-interference-and-noise ratio (L1-SINR) for beam management is already supported. Beam Prediction

[0064] An example artificial intelligence (AI) / machine learning (ML) model currently being discussed in AI for air interface 3GPP Rel-18 includes predicting channels for beams about specific time-frequency resources. The expected performance of such predictions depends on several different aspects, such as time / frequency variations of the channel due to wireless device mobility or environmental changes. Due to the inherent correlation of channels in time, frequency, and spatial domains, ML models can be trained to exploit such correlations. The spatial domain can include different beams, where the relevant properties depend in part on how network node antennas form different beams and how wireless devices form receiver beams.

[0065] Devices can use this predictive ML model to reduce their beamforming-related measurements. In NR, a device can be requested to measure on a set of SSB beams or / and CSI-RS beams. Fixed devices typically experience less beam quality variation than mobile devices. Therefore, fixed devices can save battery and reduce the number of beam measurements by instead using an ML model to predict beam quality without explicit measurements. This can be achieved, for example, by measuring a subset of the beams and predicting the remaining beams. AI measurements on a subset of beams can be used to predict the best beam, which can reduce measurement time by up to 75%.

[0066] In one prior art system, a method is described for enabling a wireless device to predict future beam values ​​based on historical values. Based on device data received from measurement reports, the network / network node can learn, for example, which sequences of signal quality measurements (e.g., RSRP measurements) lead to large signal quality degradation events (e.g., Figure 2 For example, the learning process can be implemented by dividing the periodically reported RSRP data into a training window and a prediction window.

[0067] exist Figure 2 In the example shown, both devices move and turn around the same corner. Device 120b, marked by the dashed line, turns around the corner first and experiences a large signal quality drop. The idea is to mitigate the drop in the second device (120a) by learning from the experience of the first device.

[0068] Learning can be performed by feeding the RSRP in t1, ..., tn into a machine learning model (e.g., a neural network) and then learning the RSRP in tn+1, tn+2. After the model is trained, the network can then predict future signal quality values, and the signal quality prediction can then be used to avoid radio link failure or beam failure in the following way: - Initiate inter-frequency switching - Set switch / reselect parameters - Perform candidate beam selection in advance to avoid beam failure -Change device scheduler priorities, such as scheduling devices when signal quality is expected to be good or meet predefined thresholds. 3GPP considerations

[0069] 3GPP has considered studying AI / ML-based spatial beam prediction of beams of set A based on measurement results of beams of set B. The beams of set B may be a subset of the beams of set A, or the beams of set A may consist of different beams than the beams of set B (e.g., set A consists of narrow beams and set B consists of wide beams). Spatial beam prediction may be performed on the network node side or on the wireless device side.

[0070] The first problem is that the amount of CSI measurements that a wireless device is configured to perform, as well as the size of CSI reports, are increasing with each release introducing new features compared to existing systems and / or 3GPP standards.

[0071] In the case of deployments in higher frequencies, such as in 5G NR, the number is even higher because the wireless device is configured to perform measurements on resources (DL RS, e.g., SSB and / or CSI-RS) sent in multiple spatial domain directions (e.g., DL RS sent using spatial domain filters and / or multiple-input multiple-output (MIMO) precoding vectors), which may be referred to as DL beams or beams sent by the network / network node.

[0072] Having to perform more CSI measurements increases wireless device energy consumption, which is the second problem.

[0073] If these measurements are based on DLRS (e.g., CSI-RS for beam measurement) that the network / network node transmits primarily for this purpose and for a specific wireless device, this may increase the overhead of network transmissions and create additional interference when the cell serves more wireless devices, which is the third and fourth problems.

[0074] Additionally, more DL RSs / beams to measure may result in increased delays in performing CSI measurements, which may result in delays in making the CSI measurements available for reporting, which is the fifth problem.

[0075] Longer delays in making CSI measurements available may result in a risk of failures in the connection, such as beam failure detection (BFD) and / or radio link failure (RLF), because the wireless device may attempt to report to the network / network node that the current beam (e.g., the DL RS associated with the currently activated TCI state) has poor quality or that there is a much better beam (e.g., another DL RS associated with another TCI state) available, so that if it takes too long, the network / network node may trigger a beam switching command (e.g., a medium access control (MAC) control element (CE) indicating a new TCI state to be activated) too late, and thus a failure may occur.

[0076] The prediction of beams by the wireless device requires the wireless device to implicitly assume that the network / network node uses a set of F fixed beams (fixed beam mode, pointing direction, power, etc.) (F beams refers to the number of fixed beams), and the wireless device attempts to use measurements to predict which of the F beams is the preferred beam (e.g., highest received SNR) without measuring the associated DL RSs in all F beams. In this way, some problems of existing systems are partially solved. This is one reason why 3GPP discusses the use of AI / ML for spatial domain beam prediction.

[0077] The problem with spatial beam prediction is that the AI / ML model in the wireless device needs to have information about all F beams, such as beam patterns, etc. Otherwise, the ML model cannot predict the preferred beam among the F, because it only measures other / fewer beams. It has been proposed in 3GPP that the network should signal to the wireless device information about all its F beams, for example, the beam radiation pattern of each of its F beams. The disadvantage of this approach is that it takes into account the beam information seen from the transmitter's perspective, but does not take into account the impact of the radio channel (scattering, etc.).

[0078] This is also a problem because beam patterns can be network site specific and subject to individual site adjustments such as cell planning etc. Furthermore, information about the beams being used by network nodes can be proprietary information, which network vendors are unlikely to be willing to share publicly.

[0079] Therefore, there are various problems with existing systems and proposals. Summary of the invention

[0080] Some embodiments advantageously provide methods, systems, and apparatus for predicting a preferred beam among F beams.

[0081] One problem in existing systems is how a wireless device can perform prediction of a preferred beam among F beams based on receiver measurements of fewer or other transmitted network beams, without requiring the network / network node to disclose proprietary information of the F beams it uses.

[0082] According to one or more embodiments of the present disclosure, DL RS opportunities are provided so that the wireless device can intermittently measure all F beams (DL RS of set A). The ML algorithm then obtains the "definition" of all F beams (set A) as input, and in addition, these are defined when the wireless device receives it (unlike existing systems, which use beam radiation patterns, etc. to define the F beams). The ML algorithm also uses measurements of a different set of beams (set B) as input, and set B can be a subset of A. Based on set A (all F beams that are rarely received) and set B (frequently received), the wireless device ML algorithm can frequently perform predictions on preferred beams in set A without frequently measuring all F beams in set A.

[0083] According to one aspect, a wireless device (WD) is described. The WD is configured to communicate with a network node and predict at least a reference signal (RS) associated with the network node. The WD is configured to receive a downlink DL RS configuration for configuring two or more sets of reference signal resources. The DL RS configuration includes a first configuration for a beam of a first set and a second configuration for a beam of a second set. The beam of the second set is a subset of the beam of the first set. The WD is configured to: receive a CSI report configuration associated with the DL reference signal configuration; receive a first message, the first message requesting the WD to measure a DL RS subset in the first set of DL RSs associated with the beam of the first set according to the CSI report configuration; and perform measurements on a DL RS subset in the second set of DL RSs associated with the beam of the second set. The WD is also configured to: perform one or more actions associated with an artificial intelligence model using at least the measurement of the DL RS subset in the second set of DL RSs; predict one or more DL RSs from the first set of DL RSs associated with the beam of the first set based in part on the one or more actions; and send information about the predicted one or more RSs to the network node.

[0084] In some embodiments, the WD is further configured to receive a second message requesting the WD to measure a first set of DL RSs. The first set of DL RSs are transmitted less frequently than the second set of DL RSs.

[0085] In some other embodiments, the WD is further configured to perform collection of data associated with predicted performance of one or more DL RSs from the first set of DL RSs based on measurements of the second set of DL RSs.

[0086] In some embodiments, the WD is also configured to send a capability indication to the network node indicating one or more of: prediction support; support for spatial prediction beam reports for predicting one or both of beams in the first set of beams and reference signals in the first set of RSs; a first maximum number of beams in the first set of beams and one or both of DL RSs in the first set of DL RSs; a second maximum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; a minimum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; machine learning ML model processing capabilities associated with the artificial intelligence model; and prediction performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

[0087] In some other embodiments, the WD is further configured to send a third message to the network node, the third message including uplink UL assistance information. The UL assistance information includes one or more of the following: WD position information; an estimate of one or both of WD speed and WD rotation; information about the WD antenna panel; and information about the WD antenna panel configuration usage.

[0088] In some embodiments, the DL RS configuration includes two CSI-RS resource sets, the two CSI-RS resource sets including: a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; and a second CSI-RS resource set having N CSI-RS resources associated with a beam of the second set.

[0089] In some other embodiments, the second CSI-RS resource set is a subset of the first CSI-RS resource set; the first CSI-RS resource set and the second CSI-RS resource set are linked via an association, wherein the association indicates that the same beam from the network node will be used for the CSI-RS resources when the CSI-RS resources are sent as part of the first CSI-RS resource set and when the CSI-RS resources are sent as part of the second CSI-RS resource set; the association is explicitly configured based on the CSI-RS resource set; and the association is configured by a field in the CSI report configuration.

[0090] In some embodiments, the CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; the association is explicitly configured in one resource setting; it is explicitly indicated that the two CSI-RS resource sets are linked together; the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; the association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; the association of the two CSI-RS resources is explicitly configured in a table; the association of the two CSI-RS resources is dynamically indicated; the first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behaviors.

[0091] In some other embodiments, the DL RS configuration includes a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with a beam of the second set, and one or both of the following: (A) the CSI report configuration indicates the CSI-RS resources in the CSI-RS resource set that the WD is to measure; and (B) the DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD is to measure.

[0092] In some embodiments, the WD is further configured to receive beam assist information indicating a spatial correlation and a quasi-co-sited QCL relationship between one or more beams in the first set of beams, wherein the beam assist information can be used as an input to the artificial intelligence model.

[0093] In some other embodiments, the WD is further configured to: predict one or more sets of beams from the first set of beams based in part on the one or more actions; and send information about the predicted one or more sets of beams to the network node.

[0094] In some embodiments, the one or more actions include one or more of: training the artificial model; retraining the artificial model; and updating the artificial model.

[0095] According to another aspect, a method in a wireless device (WD) is described. The WD is configured to communicate with a network node and predict at least a reference signal (RS) associated with the network node. The method includes a downlink DL RS configuration for configuring two or more sets of reference signal resources. The DL RS configuration includes a first configuration for a beam of a first set and a second configuration for a beam of a second set. The beam of the second set is a subset of the beam of the first set. The method also includes: receiving a CSI report configuration associated with the DL reference signal configuration; receiving a first message, the first message requesting the WD to measure a DL RS subset in the first set of DL RSs associated with the beam of the first set according to the CSI report configuration; and measuring a DL RS subset in the second set of DL RSs associated with the beam of the second set. The method also includes: performing one or more actions associated with an artificial intelligence model using at least a measurement of a DL RS subset in the DL RS of the second set; predicting one or more DL RSs from the DL RS of the first set associated with the beam of the first set based in part on the one or more actions; and sending information about the predicted one or more RSs to the network node.

[0096] In some embodiments, the method further includes receiving a second message requesting the WD to measure a first set of DL RSs, the first set of DL RSs being transmitted less frequently than the second set of DL RSs.

[0097] In some other embodiments, the method further includes performing collection of data associated with predicted performance of one or more DL RSs from the first set of DL RSs based on measurements of the second set of DL RSs.

[0098] In some embodiments, the method further includes sending a capability indication to the network node indicating one or more of: prediction support; support for spatial prediction beam reporting for predicting one or both of beams in the first set of beams and reference signals in the first set of RSs; a first maximum number of beams in the first set of beams and one or both of DL RSs in the first set of DL RSs; a second maximum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; a minimum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; machine learning ML model processing capabilities associated with the artificial intelligence model; and prediction performance for one or more combinations of the first set of DL RSs and the second set of DL RSs. In some other embodiments, the method further includes sending a third message to the network node, the third message including uplink UL assistance information, the UL assistance information including one or more of: WD position information; estimates of one or both of WD speed and WD rotation; information about WD antenna panels; and information about WD antenna panel configuration usage.

[0099] In some embodiments, the DL RS configuration includes two CSI-RS resource sets, the two CSI-RS resource sets including: a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; and a second CSI-RS resource set having N CSI-RS resources associated with a beam of the second set.

[0100] In some other embodiments, the second CSI-RS resource set is a subset of the first CSI-RS resource set; the first CSI-RS resource set and the second CSI-RS resource set are linked via an association, wherein the association indicates that the same beam from the network node will be used for the CSI-RS resources when the CSI-RS resources are sent as part of the first CSI-RS resource set and when the CSI-RS resources are sent as part of the second CSI-RS resource set; the association is explicitly configured based on the CSI-RS resource set; and the association is configured by a field in the CSI report configuration.

[0101] In some embodiments, the CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; the association is explicitly configured in one resource setting; it is explicitly indicated that the two CSI-RS resource sets are linked together; the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; the association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; the association of the two CSI-RS resources is explicitly configured in a table; the association of the two CSI-RS resources is dynamically indicated; the first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behaviors.

[0102] In some other embodiments, the DL RS configuration includes a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with a beam of the second set, and one or both of the following: (A) the CSI report configuration indicates the CSI-RS resources in the CSI-RS resource set that the WD is to measure; and (B) the DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD is to measure.

[0103] In some embodiments, the method further includes receiving beam-assistance information indicating a spatial correlation and a quasi-co-sited QCL relationship between one or more beams in the first set of beams, the beam-assistance information being capable of being used as an input to the artificial intelligence model.

[0104] In some other embodiments, the method further includes: predicting one or more sets of beams from the first set of beams based in part on the one or more actions; and sending information about the predicted one or more sets of beams to the network node.

[0105] In some embodiments, the one or more actions include one or more of: training the artificial model; retraining the artificial model; and updating the artificial model.

[0106] According to one aspect, a network node is described. The network node is configured to communicate with a wireless device (WD), which is configured to predict at least a reference signal (RS) associated with the network node. The network node is configured to send a downlink DL RS configuration for configuring two or more sets of reference signal resources. The DL RS configuration includes a first configuration for a beam of a first set and a second configuration for a beam of a second set. The beam of the second set is a subset of the beam of the first set. The network node is also configured to: send a CSI report configuration associated with the DL reference signal configuration; and send a first message, the first message requesting the WD to measure a DL RS subset in the DL RS of the first set associated with the beam of the first set according to the CSI report configuration. The WD is also configured to: receive information about one or more RSs from the WD, the one or more RSs being predicted from the DL RS of the first set associated with the beam of the first set based in part on one or more WD actions. One or more WD actions are associated with an artificial intelligence model and are performed using at least a measurement of a DL RS subset in the DL RS of the second set. One or more network node actions are performed based on the information regarding the one or more RSs predicted from the first set of DL RSs.

[0107] In some embodiments, the network node is further configured to send a second message requesting the WD to measure a first set of DL RSs, wherein the first set of DL RSs are transmitted less frequently than the second set of DL RSs.

[0108] In some other embodiments, the network node is further configured to receive a capability indication from the WD. The capability indication indicates one or more of: prediction support; support for spatial prediction beam reporting for predicting one or both of a beam in the first set of beams and a reference signal in the first set of RSs; a first maximum number of beams in the first set of beams and one or both of DL RSs in the first set of DL RSs; a second maximum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; a minimum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; a machine learning ML model processing capability associated with the artificial intelligence model; and prediction performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

[0109] In some embodiments, the network node is further configured to send a third message to the network node, the third message including uplink UL assistance information. The UL assistance information includes one or more of the following. The UL assistance information includes one or more of the following: WD position information, an estimate of one or both of WD speed and WD rotation, information about the WD antenna panel, and information about the use of the WD antenna panel configuration.

[0110] In some other embodiments, two CSI-RS resource sets are included. The two CSI-RS resource sets include a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set, and a second CSI-RS resource set having N CSI-RS resources associated with a beam of the second set.

[0111] In some embodiments, the second CSI-RS resource set is a subset of the first CSI-RS resource set; the first CSI-RS resource set and the second CSI-RS resource set are linked via an association, wherein the association indicates that the same beam from the network node will be used for the CSI-RS resources when the CSI-RS resources are sent as part of the first CSI-RS resource set and when the CSI-RS resources are sent as part of the second CSI-RS resource set; the association is explicitly configured based on the CSI-RS resource set; and the association is configured by a field in the CSI report configuration.

[0112] In some other embodiments, one or more of the following: (A) the CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; (B) the association is explicitly configured in one resource setting; (C) it is explicitly indicated that the two CSI-RS resource sets are linked together; (D) the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; (E) the association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; (F) the association of the two CSI-RS resources is explicitly configured in a table; (G) the association of the two CSI-RS resources is dynamically indicated; and (H) the first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behavior.

[0113] In some embodiments, the DL RS configuration includes a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with a beam of the second set; and one or both of the following: (A) the CSI report configuration indicates the CSI-RS resources in the CSI-RS resource set that the WD is to measure; and (B) the DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD is to measure.

[0114] In some other embodiments, the network node is further configured to send beam assistance information indicating a spatial correlation and a quasi-co-site QCL relationship between one or more beams in the first set of beams, and the beam assistance information can be used as an input to the artificial intelligence model.

[0115] In some embodiments, the network node is further configured to receive information about the predicted one or more sets of beams from the WD.

[0116] In some other embodiments, the one or more network node actions include sending signaling using one or more beams corresponding to the information about the predicted one or more sets of beams.

[0117] According to another aspect, a method in a network node is described. The network node is configured to communicate with a wireless device (WD) configured to predict at least a reference signal (RS) associated with the network node. The method includes sending (S158) a downlink DL RS configuration for configuring two or more sets of reference signal resources. The DL RS configuration includes a first configuration for a beam of a first set and a second configuration for a beam of a second set. The beam of the second set is a subset of the beam of the first set. The method also includes: sending a CSI report configuration associated with the DL reference signal configuration; and sending a first message, the first message requesting the WD to measure a DL RS subset in the DL RS of the first set associated with the beam of the first set according to the CSI report configuration. The method also includes receiving (S164) information about one or more RSs from the WD, the one or more RSs being predicted from the DL RS of the first set associated with the beam of the first set based in part on one or more WD actions, the one or more WD actions being associated with an artificial intelligence model and being performed using at least a measurement of a DL RS subset in the DL RS of the second set. One or more WD actions are associated with the artificial intelligence model and are performed using at least measurements of a subset of DL RSs in the second set of DL RSs. One or more network node actions are performed based on information about one or more RSs predicted from the DL RSs of the first set.

[0118] In some embodiments, the method further includes sending a second message requesting the WD to measure a first set of DL RSs, wherein the first set of DL RSs are transmitted less frequently than the second set of DL RSs.

[0119] In some other embodiments, the method further includes receiving a capability indication from the WD. The capability indication indicates one or more of: prediction support; support for spatial prediction beam reporting for predicting one or both of beams in the first set of beams and reference signals in the first set of RSs; a first maximum number of beams in the first set of beams and one or both of DL RSs in the first set of DL RSs; a second maximum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; a minimum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; a machine learning ML model processing capability associated with the artificial intelligence model; and prediction performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

[0120] In some embodiments, the method further includes sending a third message to the network node, the third message including uplink UL assistance information. The UL assistance information includes one or more of the following: WD position information, an estimate of one or both of WD speed and WD rotation, information about the WD antenna panel, and information about the WD antenna panel configuration usage.

[0121] In some other embodiments, the DL RS configuration includes two CSI-RS resource sets. The two CSI-RS resource sets include a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set, and a second CSI-RS resource set having N CSI-RS resources associated with a beam of the second set.

[0122] In some embodiments, the second CSI-RS resource set is a subset of the first CSI-RS resource set; the first CSI-RS resource set and the second CSI-RS resource set are linked via an association, wherein the link indicates that the same beam from the network node will be used for the CSI-RS resources when the CSI-RS resources are sent as part of the first CSI-RS resource set and when the CSI-RS resources are sent as part of the second CSI-RS resource set; the association is explicitly configured based on the CSI-RS resource set; and the association is configured by a field in the CSI report configuration.

[0123] In some other embodiments, one or more of the following: (A) the CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; (B) the association is explicitly configured in one resource setting; (C) it is explicitly indicated that the two CSI-RS resource sets are linked together; (D) the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; (E) the association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; (F) the association of the two CSI-RS resources is explicitly configured in a table; (G) the association of the two CSI-RS resources is dynamically indicated; and (H) the first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behavior.

[0124] In some embodiments, the DL RS configuration includes a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with a beam of the second set, and one or both of the following: (A) the CSI report configuration indicates the CSI-RS resources in the CSI-RS resource set that the WD is to measure; and (B) the DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD is to measure.

[0125] In some other embodiments, the method further includes sending beam assistance information indicating a spatial correlation and a quasi-co-located QCL relationship between one or more beams in the first set of beams, the beam assistance information being capable of being used as an input to an artificial intelligence model.

[0126] In some embodiments, the method further comprises receiving information about the predicted one or more sets of beams from the WD.

[0127] In some other embodiments, the one or more network node actions include sending signaling using one or more beams corresponding to the information about the predicted one or more sets of beams. BRIEF DESCRIPTION OF THE DRAWINGS

[0128] A more complete understanding of the present embodiments and the attendant advantages and features will be more readily appreciated by reference to the following detailed description considered in conjunction with the accompanying drawings, in which:

[0129] Figure 1 is a schematic diagram of the beam management process;

[0130] Figure 2 is a schematic diagram depicting two devices moving / turning around a corner;

[0131] Figure 3 is a schematic diagram illustrating an example network architecture of a communication system connected to a host computer via an intermediate network according to the principles of the present disclosure;

[0132] Figure 4 is a block diagram of a host computer communicating with a wireless device via a network node over an at least partially wireless connection according to some embodiments of the present disclosure;

[0133] Figure 5 is a flow chart illustrating an example method for executing a client application at a wireless device implemented in a communication system including a host computer, a network node, and a wireless device according to some embodiments of the present disclosure;

[0134] Figure 6 is a flow chart illustrating an example method for receiving user data at a wireless device implemented in a communication system including a host computer, a network node, and a wireless device according to some embodiments of the present disclosure;

[0135] Figure 7 is a flow chart illustrating an example method implemented in a communication system including a host computer, a network node, and a wireless device for receiving user data at a host computer from a wireless device according to some embodiments of the present disclosure;

[0136] Figure 8 is a flow chart illustrating an example method for receiving user data at a host computer implemented in a communication system including a host computer, a network node, and a wireless device according to some embodiments of the present disclosure;

[0137] Fig. 9 is a flow chart of an example process in a network node according to some embodiments of the present disclosure;

[0138] Fig.10 is a flow chart of an example process in a wireless device according to some embodiments of the present disclosure;

[0139] Fig.11 is a flow chart of an example process in a network node according to some embodiments of the present disclosure;

[0140] Fig.12 is a flow chart of an example process in a wireless device according to some embodiments of the present disclosure;

[0141] Fig.13 is a diagram of an example configuration of a collection of resources according to some embodiments of the present disclosure;

[0142] Fig.14 is a diagram of another example configuration of a resource collection according to some embodiments of the present disclosure;

[0143] Fig.15 is a diagram of an example configuration of a first set of beams and a second set of beams, wherein the second set is a subset of the first set, according to some embodiments of the present disclosure;

[0144] Fig.16 is a diagram of an example of measurements performed on a first set of beams and a subset thereof according to some embodiments of the present disclosure;

[0145] Fig.17 is a diagram of an example of an AI / ML model using RSRP measurement according to some embodiments of the present disclosure; and

[0146] Fig.18 is a flow chart of an example process according to the present disclosure. DETAILED DESCRIPTION

[0147] Before describing the example embodiments in detail, it is noted that the embodiments reside primarily in a combination of apparatus components and processing steps related to prediction of a preferred beam among F beams. Therefore, components are appropriately represented by conventional symbols in the drawings, and only those specific details relevant to understanding the embodiments are shown so as not to obscure the disclosure with details that would be obvious to one of ordinary skill in the art having the benefit of the description herein. Like reference numerals represent like elements throughout the specification.

[0148] As used herein, relational terms such as "first" and "second", "top" and "bottom", etc. 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 terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the concepts described herein. As used herein, the singular forms "a", "an", and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It will be further understood that the terms "include" and / or "comprises" when used herein specify the presence of the features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0149] In the embodiments described herein, the connection terms "in communication with..." and the like may be used to indicate electrical or data communication, which may be achieved, for example, by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling, or optical signaling. Those of ordinary skill in the art will appreciate that multiple components may interoperate, and modifications and variations may achieve electrical and data communication.

[0150] In some embodiments described herein, the terms "coupled," "connected," and the like may be used herein to indicate a connection, but not necessarily a direct connection, and may include wired and / or wireless connections.

[0151] The term "network node" used in this document can be any type of network node included in a radio network, which can further include a base station (BS), a radio base station, a base transceiver station (BTS), a base station controller (BSC), a radio network controller (RNC), a gNodeB (gNB), an evolved NodeB (eNB or eNodeB), a NodeB, a multi-standard radio (MSR) radio node (such as an MSR BS), a multi-cell / multicast coordination entity (MCE), an integrated access and backhaul (IAB) node, a relay node, a donor node controlled relay, a radio access point (AP), a transmission point, a transmission node, a remote radio unit (RRU) remote radio head (RRH), a core network node (e.g., a mobility management entity (MME), a self-organizing network (SON) node, a coordination node, a positioning node, an MDT node, etc.), an external node (e.g., a third-party node, a node outside the current network), a node in a distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. As used herein, the term "radio node" may also be used to denote a wireless device (WD), such as a wireless device (WD) or a radio network node.

[0152] In some embodiments, non-limiting terms wireless device (WD) or user equipment (UE) are used interchangeably. WD herein can be any type of wireless device capable of communicating with a network node or another WD via a radio signal (such as a wireless device (WD)). WD can also be a radio communication device, a target device, a device-to-device (D2D) WD, a machine type WD or a WD capable of machine-to-machine communication (M2M), a low-cost and / or low-complexity WD, a sensor equipped with a WD, a tablet computer, a mobile terminal, a smart phone, a laptop embedded device (LEE), a laptop mounted device (LME), a USB dongle, a customer premises equipment (CPE), an Internet of Things (IoT) device, or a narrowband IoT (NB-IOT) device, etc.

[0153] In addition, in some embodiments, the general term "radio network node" is used. It can be any type of radio network node, which can include any one of a base station, a radio base station, a base transceiver station, a base station controller, a network controller, an RNC, an evolved Node B (eNB), a Node B, a gNB, a multi-cell / multicast coordination entity (MCE), an IAB node, a relay node, an access point, a radio access point, a remote radio unit (RRU), and a remote radio head (RRH).

[0154] Note that while terminology from one particular wireless system such as 3GPP LTE and / or New Radio (NR) may be used in the present disclosure, this should not be viewed as limiting the scope of the present disclosure to only the aforementioned systems. Other wireless systems, including but not limited to Wideband 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 utilizing the ideas covered in the present disclosure.

[0155] It is also noted that the functions described herein as being performed by a wireless device or network node may be distributed across multiple wireless devices and / or network nodes. In other words, it is contemplated that the functions of the network nodes and wireless devices described herein are not limited to being performed by a single physical device and may in fact be distributed across several physical devices.

[0156] In some embodiments, a general descriptive element of the form "one of A and B" corresponds to A or B. In some embodiments, at least one of A and B corresponds to A, B, or AB, or corresponds to one or more of A and B. In some embodiments, at least one of A, B, and C corresponds to one or more of A, B, and C, and / or A, B, C, or a combination thereof.

[0157] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present disclosure belongs. It should also be understood that the terms used herein should be interpreted as having a meaning 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 explicitly defined herein.

[0158] Some embodiments provide for prediction of a preferred beam among F beams. Some advantages according to various embodiments of the present disclosure include implementing spatial beam prediction for 5G Advanced and / or 6G on the wireless device side using an AI / ML-based approach, which can be used to reduce DL-RS overhead during the beam management process and reduce measurement complexity for the wireless device. Another advantage can be that network vendors avoid disclosing proprietary implementation details of antennas or beams used (such as beam radiation patterns).

[0159] Referring again to the drawings, wherein like elements are represented by like reference numerals, Figure 1, a schematic diagram of a communication system 10 according to an embodiment is shown, such as a 3GPP-type cellular network that can support standards such as LTE and / or NR (5G), which includes an access network 12 such as a radio access network, and a core network 14. The access network 12 includes a plurality of network nodes 16a, 16b, 16c (collectively referred to as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each of which defines a corresponding coverage area 18a, 18b, 18c (collectively referred to as coverage area 18). Each network node 16a, 16b, 16c can be connected to the core network 14 via a wired or wireless connection 20. A first wireless device (WD) 22a located in the coverage area 18a is configured to be wirelessly connected to the corresponding network node 16a or to be paged by the corresponding network node 16a. A second WD 22b in the coverage area 18b can be wirelessly connected to the corresponding network node 16b. Although multiple WDs 22a, 22b (collectively referred to as wireless devices 22) are shown in this example, the disclosed embodiments are equally applicable to situations where there is only one WD in the coverage area or only one WD is connected to the corresponding network node 16. Note that although only two WDs 22 and three network nodes 16 are shown for convenience, the communication system may include more WDs 22 and network nodes 16.

[0160] In addition, it is contemplated that the WD 22 may communicate simultaneously and / or be configured to communicate with more than one network node 16 and more than one type of network node 16, respectively. For example, the WD 22 may have dual connectivity with a network node 16 supporting LTE and the same or different network nodes 16 supporting NR. As an example, the WD 22 may communicate with an eNB for LTE / E-UTRAN and a gNB for NR / NG-RAN.

[0161] The communication system 10 itself can be connected to a host computer 24, which can be embodied in the hardware and / or software of a stand-alone networking server, a cloud-implemented server, a distributed server, or as a processing resource in a server farm. The host computer 24 can be under the ownership or control of a service provider, or can be operated by or on behalf of the service provider. The connections 26 and 28 between the communication system 10 and the host computer 24 can extend directly from the core network 14 to the host computer 24, or can extend via an optional intermediate network 30. The intermediate network 30 can be a combination of one or more of a public network, a private network, or a managed network. The intermediate network 30 (if any) can be a backbone network or the Internet. In some embodiments, the intermediate network 30 can include two or more subnetworks (not shown).

[0162] Figure 1The communication system as a whole implements a connection between one of the connected WDs 22a, 22b and the host computer 24. The connection can be described as an over-the-top (OTT) connection. The host computer 24 and the connected WDs 22a, 22b are configured to communicate data and / or signaling via an OTT connection using the access network 12, the core network 14, any intermediate network 30, and possible additional infrastructure (not shown) as intermediaries. The OTT connection can be transparent in the sense that at least some of the participating communication devices through which the OTT connection passes do not know the routes of the uplink and downlink communications. For example, the network node 16 may not or need not be informed of the past routes of incoming downlink communications, where data originating from the host computer 24 will be forwarded (e.g., switched) to the connected WD 22a. Similarly, the network node 16 does not need to know the future routes of outgoing uplink communications initiated from the WD 22a to the host computer 24.

[0163] The network node 16 is configured to include a configuration unit 32 configured to perform one or more network node 16 functions described herein, including functions related to prediction of a preferred beam in a set of F beams. The wireless device 22 is configured to include a determination unit 34 configured to perform one or more network node 16 functions described herein, including functions related to prediction of a preferred beam in a set of F beams.

[0164] According to the embodiment, reference will now be made to Figure 4 10 to describe an example implementation of the WD 22, network node 16, and host computer 24 discussed in the preceding paragraphs. In the communication system 10, the host computer 24 includes hardware (HW) 38, which includes a communication interface 40, which is configured to establish and maintain a wired or wireless connection with an interface of different communication devices of the communication system 10. The host computer 24 also includes a processing circuit 42, which may have storage and / or processing capabilities. The processing circuit 42 may include a processor 44 and a memory 46. In particular, in addition to or in place of a processor, such as a central processing unit and a memory, the processing circuit 42 may include an integrated circuit for processing and / or control, for example, one or more processors and / or processor cores and / or an FPGA (field programmable gate array) and / or an ASIC (application-specific integrated circuit) suitable for executing instructions. The processor 44 may be configured to access (e.g., write to and / or read from) a memory 46, which may include any kind of volatile and / or non-volatile memory, such as 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).

[0165] Processing circuitry 42 may be configured to control any of the methods and / or processes described herein and / or cause such methods and / or processes to be performed, for example, by host computer 24. Processor 44 corresponds to one or more processors 44 for performing the functions of host computer 24 described herein. Host computer 24 includes memory 46 configured to store data, programming software code, and / or other information described herein. In some embodiments, software 48 and / or host application 50 may include instructions that, when executed by processor 44 and / or processing circuitry 42, cause processor 44 and / or processing circuitry 42 to perform the processes described herein with respect to host computer 24. The instructions may be software associated with host computer 24.

[0166] The software 48 may be executed by the processing circuit 42. The software 48 includes a host application 50. The host application 50 is operable to provide services to a remote user, such as a WD 22 connected via an OTT connection 52 terminated at the WD 22 and the host computer 24. When providing services to the remote user, the host application 50 may provide user data transmitted using the OTT connection 52. "User data" may be data and information described herein as implementing the described functions. In one embodiment, the host computer 24 may be configured to provide control and functionality to the service provider, and may be operated by or on behalf of the service provider. The processing circuit 42 of the host computer 24 may enable the host computer 24 to observe, monitor, control, send to and / or receive from the network node 16 and / or the wireless device 22. The processing circuit 42 of the host computer 24 may include a control unit 54, which is configured to enable the service provider to observe, monitor, control, send to and / or receive from the network node 16 and / or the wireless device 22.

[0167] The communication system 10 also includes a network node 16, which is arranged in the communication system 10 and includes hardware 58 that enables it to communicate with the host computer 24 and with the WD 22. The hardware 58 may include a communication interface 60 for establishing and maintaining a wired or wireless connection to the interface of different communication devices of the communication system 10, and a radio interface 62 for establishing and maintaining at least a wireless connection 64 with the WD 22 located in the 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. The communication interface 60 may be configured to facilitate a connection 66 to the host computer 24. The connection 66 may be direct, or it may be through the core network 14 of the communication system 10 and / or through one or more intermediate networks 30 external to the communication system 10.

[0168] In the illustrated embodiment, the hardware 58 of the network node 16 also includes a processing circuit 68. The processing circuit 68 may include a processor 70 and a memory 72. In particular, in addition to or in place of a processor (such as a central processing unit) and a memory, the processing circuit 68 may include an integrated circuit for processing and / or control, for example, one or more processors and / or processor cores and / or an FPGA (field programmable gate array) and / or an ASIC (application-specific integrated circuit) 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 include any kind of volatile and / or non-volatile memory, for example, a cache and / or buffer memory and / or a RAM (random access memory) and / or a ROM (read-only memory) and / or an optical memory and / or an EPROM (erasable programmable read-only memory).

[0169] Thus, the network node 16 also has software 74 stored internally, for example, in the memory 72, or stored in an external memory (e.g., a database, a storage array, a network storage device, etc.) accessible by the network node 16 via an external connection. The software 74 may be executed by the processing circuit 68. The processing circuit 68 may be configured to control any of the methods and / or processes described herein and / or cause such methods and / or processes to be performed, for example, by the network node 16. The processor 70 corresponds to one or more processors 70 for performing the network node 16 functions described herein. The memory 72 is configured to store data, programming 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 the processing circuit 68, cause the processor 70 and / or the processing circuit 68 to perform the processes described herein with respect to the network node 16. For example, the processing circuit 68 of the network node 16 may include a configuration unit 32 configured to perform one or more network node 16 functions described herein, including functions related to the prediction of a preferred beam among a set of F beams.

[0170] The communication system 10 also includes the already mentioned WD 22. The WD 22 may have hardware 80, which may include a radio interface 82 configured to establish and maintain a wireless connection 64 with a network node 16 serving the coverage area 18 in which the WD 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.

[0171] The hardware 80 of the WD 22 also includes a processing circuit 84. The processing circuit 84 may include a processor 86 and a memory 88. In particular, in addition to or in place of a processor (such as a central processing unit) and a memory, the processing circuit 84 may include an integrated circuit for processing and / or control, for example, one or more processors and / or processor cores and / or an FPGA (field programmable gate array) and / or an ASIC (application-specific integrated circuit) adapted to execute instructions. The processor 86 may be configured to access (e.g., write to and / or read from) a memory 88, which may include any kind of volatile and / or non-volatile memory, for example, a cache and / or buffer memory and / or a RAM (random access memory) and / or a ROM (read-only memory) and / or an optical memory and / or an EPROM (erasable programmable read-only memory).

[0172] Therefore, WD 22 may also include software 90, which is stored in a memory 88 at, for example, WD 22, or in an external memory (e.g., a database, a storage array, a network storage device, etc.) accessible to WD 22. Software 90 may be executed by processing circuit 84. Software 90 may include client applications 92. Client application 92 may be operable to provide services to human or non-human users via WD 22 with the support of host computer 24. In host computer 24, the executing host application 50 may communicate with the executing client application 92 via an OTT connection 52 terminated at WD 22 and host computer 24. When providing services to users, client application 92 may receive request data from host application 50 and provide user data in response to the request data. OTT connection 52 may transmit both request data and user data. Client application 92 may interact with the user to generate the user data it provides.

[0173] The processing circuit 84 may be configured to control any of the methods and / or processes described herein and / or cause such methods and / or processes to be performed, for example, by the WD 22. The processor 86 corresponds to one or more processors 86 for performing the WD 22 functions described herein. The WD 22 includes a memory 88 configured to store data, programming 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 the processing circuit 84, cause the processor 86 and / or the processing circuit 84 to perform the processes described herein with respect to the WD 22. For example, the processing circuit 84 of the wireless device 22 may include a determination unit 34, which is configured to perform one or more network node 16 functions described herein, including functions related to the prediction of a preferred beam among a set of F beams.

[0174] In some embodiments, the internal workings of network node 16, WD 22, and host computer 24 may be as follows: Figure 4 As shown and independently, the surrounding network topology can be Figure 3 network topology.

[0175] exist Figure 4 , the OTT connection 52 has been abstractly drawn to illustrate communications between the host computer 24 and the wireless device 22 via the network node 16 without explicitly referencing any intermediate devices and precisely routing messages via those devices. The network infrastructure can determine routes that it can be configured to hide from the WD 22 or from the service provider operating the host computer 24, or both. While the OTT connection 52 is active, the network infrastructure can also take decisions to dynamically change the route (e.g., based on load balancing considerations or reconfiguration of the network).

[0176] The wireless connection 64 between the WD 22 and the network node 16 is in accordance with the teachings of the embodiments described throughout this disclosure. One or more of the various embodiments improves the performance of the OTT service provided to the WD 22 using the OTT connection 52, where the wireless connection 64 can form the last segment. More specifically, the teachings of some of these embodiments can improve data rates, latency, and / or power consumption, and thereby provide benefits such as reduced user waiting time, loose restrictions on file size, better responsiveness, extended battery life, etc.

[0177] In some embodiments, a measurement process may be provided for the purpose of monitoring data rates, delays, and other factors targeted by one or more embodiments. In response to changes in the measurement results, there may also be an optional network function for reconfiguring the OTT connection 52 between the host computer 24 and the WD 22. The measurement process and / or network function for reconfiguring the OTT connection 52 may be implemented in the software 48 of the host computer 24 or in the software 90 of the WD 22 or in both. In an embodiment, a sensor (not shown) may be deployed in or associated with a communication device through which the OTT connection 52 passes; the sensor may participate in the measurement process by supplying the values ​​of the monitored quantities illustrated above, or supplying the values ​​of other physical quantities from which the software 48, 90 can calculate or estimate the monitored quantities. The reconfiguration of the OTT connection 52 may include message formats, retransmission settings, preferred routes, etc.; the reconfiguration does not need to affect the network node 16, and the reconfiguration may be unknown or imperceptible to the network node 16. Some such processes and functions may be known and practiced in the art. In some embodiments, the measurements may involve proprietary WD signaling that facilitates the host computer 24 to measure throughput, propagation time, latency, etc. In some embodiments, the measurements may be achieved because the software 48, 90 uses the OTT connection 52 to cause messages to be sent, particularly empty or "dummy" messages, while it monitors propagation time, errors, etc.

[0178] Thus, in some embodiments, the host computer 24 includes processing circuitry 42 configured to provide user data and a communication interface 40 configured to forward the user data to a cellular network for transmission to the WD 22. In some embodiments, the cellular network also includes a network node 16 having a radio interface 62. In some embodiments, the network node 16 is configured to and / or the processing circuitry 68 of the network node 16 is configured to perform the functions and / or methods described herein for preparing / initiating / maintaining / supporting / terminating transmissions to the WD 22 and / or preparing / terminating / maintaining / supporting / terminating transmissions received from the WD 22.

[0179] In some embodiments, host computer 24 includes processing circuitry 42 and communication interface 40 configured to receive user data originating from a transmission from WD 22 to network node 16. In some embodiments, WD 22 is configured as and / or includes a radio interface 82 and / or processing circuitry 84 configured to perform the functions and / or methods described herein for preparing / initiating / maintaining / supporting / terminating a transmission to network node 16 and / or preparing / terminating / maintaining / supporting / terminating a transmission received from network node 16.

[0180] although Figure 3 and Figure 4Various "units" such as configuration unit 32 and determination unit 34 are shown within respective processors, but 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 circuit. In other words, the unit may be implemented in hardware or in a combination of hardware and software within the processing circuit.

[0181] Figure 5 is a diagram showing a communication system (such as, for example, Figure 3 and Figure 4 The communication system may include a host computer 24, a network node 16, and a WD 22, which may be referenced Figure 4 Those described in the present disclosure. In a first step of the method, the host computer 24 provides user data (box S100). In an optional sub-step of the first step, the host computer 24 provides user data by executing a host application (e.g., host application 50) (box S102). In a second step, the host computer 24 initiates a transmission to the WD 22 carrying the user data (box S104). In an optional third step, in accordance with the teachings of the embodiments described throughout the present disclosure, the network node 16 sends the user data carried in the transmission initiated by the host computer 24 to the WD 22 (box S106). In an optional fourth step, the WD 22 executes a client application associated with the host application 50 executed by the host computer 24, such as, for example, the client application 92 (box S108).

[0182] Figure 6 FIG. 1 is a diagram showing a communication system (such as, for example, Figure 1 The communication system may include a host computer 24, a network node 16, and a WD 22, which may be referenced Figure 3 and Figure 4 Those described. In a first step of the method, the host computer 24 provides user data (box S110). In an optional sub-step (not shown), the host computer 24 provides the user data by executing a host application (e.g., host application 50). In a second step, the host computer 24 initiates a transmission to the WD 22 carrying the user data (box S112). According to the teachings of the embodiments described throughout the present disclosure, the transmission can be transmitted via the network node 16. In an optional third step, the WD 22 receives the user data carried in the transmission (box S114).

[0183] Figure 7 is a diagram showing a communication system (such as, for example, Figure 3The communication system may include a host computer 24, a network node 16, and a WD 22, which may be referenced Figure 3 and Figure 4 Those described. In the optional first step of the method, WD 22 receives input data provided by host computer 24 (box S116). In an optional sub-step of the first step, WD 22 executes client application 92, which provides user data in response to the received input data provided by host computer 24 (box S118). Additionally or alternatively, in an optional second step, WD 22 provides user data (box S120). In an optional sub-step of the second step, WD provides user data by executing a client application (such as client application 92) (box S122). When providing user data, the executed client application 92 may also consider user input received from the user. Regardless of the specific manner of providing user data, WD 22 may initiate transmission of user data to host computer 24 in an optional third sub-step (box S124). In the fourth step of the method, according to the teachings of the embodiments described throughout the present disclosure, host computer 24 receives user data sent from WD 22 (box S126).

[0184] Figure 8 FIG. 1 is a diagram showing a communication system (such as, for example, Figure 3 The communication system may include a host computer 24, a network node 16, and a WD 22, which may be referenced Figure 3 and Figure 4 In an optional first step of the method, in accordance with the teachings of the embodiments described throughout the present disclosure, the network node 16 receives user data from the WD 22 (block S128). In an optional second step, the network node 16 initiates transmission of the received user data to the host computer 24 (block S130). In a third step, the host computer 24 receives the user data carried in the transmission initiated by the network node 16 (block S132).

[0185] Fig. 91 is a flow chart 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 the network node 16, such as by one or more of the processing circuit 68 (including the configuration unit 32), the processor 70, the radio interface 62, and / or the communication interface 60. The network node 16 is configured to send a downlink DL reference signal configuration to a wireless device, the configuration corresponding to at least a first set of reference signal resources and a second set of reference signal resources, wherein the first set and the second set overlap at least partially (block S134). The network node 16 is also configured to communicate with the wireless device according to a preferred reference signal subset of the reference signals of the first set, wherein the preferred reference signal subset is selected based in part on the reference signals of the second set (block S136).

[0186] In at least one embodiment, the reference signal configuration includes at least one of a quasi co-location type D relationship and a spatial transmitter filter. In at least one embodiment, the method further includes sending a trigger on the preferred reference signal subset to cause the wireless device 22 to perform at least one measurement related to the reference signals of the second set.

[0187] Fig.10 is a flow chart of an example process in a wireless device 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of the wireless device 22, such as by one or more of the processing circuit 84 (including the determination unit 34), the processor 86, the radio interface 82, and / or the communication interface 60. The wireless device 22 is configured to receive a downlink DL reference signal configuration, wherein the configuration corresponds to at least a first set of reference signal resources and a second set of reference signal resources, and the first set and the second set overlap at least partially (block S138). The wireless device 22 is also configured to perform at least one measurement of at least one reference signal in the second set (block S140). The wireless device 22 is also configured to determine a preferred reference signal subset among the reference signals of the first set based at least in part on the measurement (block S142).

[0188] In at least one embodiment, the reference signal configuration includes at least one of a quasi co-sited type D relationship and a spatial transmitter filter. In at least one embodiment, the performing of at least one measurement related to the second set of reference signals is in response to receiving a trigger.

[0189] Fig.11is a flowchart of an example process in a wireless device 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of the wireless device 22, such as by one or more of the processing circuit 84 (including the determination unit 34), the processor 86, the radio interface 82, and / or the communication interface 60. The wireless device 22 is configured to receive (block S144) a downlink (DL) RS configuration for configuring two or more sets of reference signal resources. The DL RS configuration includes a first configuration for a beam of a first set and a second configuration for a beam of a second set. The beam of the second set is a subset of the beam of the first set. The wireless device 22 is also configured to receive (block S146) a CSI report configuration associated with the DL reference signal configuration; receive (block S148) a first message requesting the WD 22 to measure a DL RS subset of the first set of DL RSs associated with the beam of the first set according to the CSI report configuration; and perform (block S150) measurement on a DL RS subset of the second set of DL RSs associated with the beam of the second set. The wireless device 22 is also configured to perform (box S152) one or more actions associated with the artificial intelligence model using at least measurements of a subset of DL RSs in the second set of DL RSs; predict (box S154) one or more DL RSs from the first set of DL RSs associated with the first set of beams based in part on the one or more actions; and send (box S156) information about the predicted one or more RSs to the network node 16.

[0190] In some embodiments, the method further includes receiving a second message requesting WD 22 to measure the first set of DL RSs. The first set of DL RSs are transmitted less frequently than the second set of DL RSs.

[0191] In some other embodiments, the method further includes performing collection of data associated with predicted performance of one or more DL RSs from the first set of DL RSs based on measurements of the second set of DL RSs.

[0192] In some embodiments, the method also includes sending a capability indication of one or more of the following to the network node 16: prediction support; support for spatial prediction beam reports for predicting one or both of beams in the first set of beams and reference signals in the first set of RSs; a first maximum number of beams in the first set of beams and one or both of DL RSs in the first set of DLRSs; a second maximum number of beams in the second set of beams and one or both of DL RSs in the second set of DLRSs; a minimum number of beams in the second set of beams and one or both of DL RSs in the second set of DLRSs; machine learning (ML) model processing capabilities associated with the artificial intelligence model; and prediction performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

[0193] In some other embodiments, the method further includes sending a third message including uplink (UL) assistance information to the network node 16. The UL assistance information includes one or more of: WD position information, an estimate of one or both of WD speed and WD rotation, information about the WD antenna panel, and information about the WD antenna panel configuration usage.

[0194] In some embodiments, the DL RS configuration includes two CSI-RS resource sets, the two CSI-RS resource sets include a first CSI-RS resource set and a second CSI-RS resource set, the first CSI-RS resource set has M CSI-RS resources associated with a beam of the first set, and the second CSI-RS resource set has N CSI-RS resources associated with a beam of the second set.

[0195] In some other embodiments, the second CSI-RS resource set is a subset of the first CSI-RS resource set; the first CSI-RS resource set and the second CSI-RS resource set are linked via an association, wherein the association indicates that the same beam from the network node will be used for the CSI-RS resources when the CSI-RS resources are sent as part of the first CSI-RS resource set and when the CSI-RS resources are sent as part of the second CSI-RS resource set; the association is explicitly configured based on the CSI-RS resource set; and the association is configured by a field in the CSI report configuration.

[0196] In some embodiments, the CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; the association is explicitly configured in one resource setting; it is explicitly indicated that the two CSI-RS resource sets are linked together; the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; the association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; the association of the two CSI-RS resources is explicitly configured in a table; the association of the two CSI-RS resources is dynamically indicated; and the first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behaviors.

[0197] In some other embodiments, the DL RS configuration includes a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with a beam of the second set, and one or both of the following: (A) the CSI report configuration indicates the CSI-RS resources in the CSI-RS resource set that WD 22 is to measure; and (B) the DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set that WD 22 is to measure.

[0198] In some embodiments, the method further includes receiving beam-assistance information indicating a spatial correlation and a quasi-co-sited QCL relationship between one or more beams in the first set of beams, the beam-assistance information being capable of being used as an input to the artificial intelligence model.

[0199] In some other embodiments, the method further includes predicting one or more sets of beams from the first set of beams based in part on the one or more actions, and sending information about the predicted one or more sets of beams to the network node 16.

[0200] In some embodiments, the one or more actions include one or more of: training the artificial model, retraining the artificial model, and updating the artificial model.

[0201] Fig.121 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 the network node 16, such as by one or more of the processing circuit 68 (including the configuration unit 32), the processor 70, the radio interface 62, and / or the communication interface 60. The network node 16 is configured to send (block S158) a downlink (DL) RS configuration for configuring two or more sets of reference signal resources. The DL RS configuration includes a first configuration for a beam of a first set and a second configuration for a beam of a second set. The beam of the second set is a subset of the beam of the first set. The network node 16 is also configured to send (block S160) a CSI report configuration associated with the DL reference signal configuration, and to send (block S162) a first message, the first message requesting the WD 22 to measure a DL RS subset in the DL RS of the first set associated with the beam of the first set according to the CSI report configuration. The network node 16 is also configured to receive (box S164) information about one or more RSs from the WD 22, the one or more RSs being predicted from the first set of DL RSs associated with the beams of the first set based in part on the one or more WD actions. The one or more WD actions are associated with the artificial intelligence model and are performed using at least a measurement of a subset of DL RSs in the second set of DL RSs. In addition, the network node 16 is configured to perform (box S166) one or more network node actions based on the information about the one or more RSs predicted from the first set of DL RSs.

[0202] In some embodiments, the method further includes sending a second message requesting the WD 22 to measure the first set of DL RSs, wherein the first set of DL RSs are transmitted less frequently than the second set of DL RSs.

[0203] In some other embodiments, the method further includes receiving a capability indication from WD 22. The capability indication indicates one or more of: prediction support; support for spatial prediction beam reporting for predicting one or both of beams in the first set of beams and reference signals in the first set of RSs; a first maximum number of beams in the first set of beams and one or both of DL RSs in the first set of DL RSs; a second maximum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; a minimum number of beams in the second set of beams and one or both of DL RSs in the second set of DL RSs; a machine learning (ML) model processing capability associated with the artificial intelligence model; and prediction performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

[0204] In some embodiments, the method further includes sending a third message to the network node 16, the third message including uplink UL assistance information. The UL assistance information includes one or more of the following: WD position information, an estimate of one or both of WD speed and WD rotation, information about the WD antenna panel, and information about the WD antenna panel configuration usage.

[0205] In some other embodiments, the DL RS configuration includes two CSI-RS resource sets. The two CSI-RS resource sets include a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set, and a second CSI-RS resource set having N CSI-RS resources associated with a beam of the second set.

[0206] In some embodiments, the second CSI-RS resource set is a subset of the first CSI-RS resource set; the first CSI-RS resource set and the second CSI-RS resource set are linked via an association, wherein the association indicates that the same beam from the network node will be used for the CSI-RS resources when the CSI-RS resources are sent as part of the first CSI-RS resource set and when the CSI-RS resources are sent as part of the second CSI-RS resource set; the association is explicitly configured based on the CSI-RS resource set; and the association is configured by a field in the CSI report configuration.

[0207] In some other embodiments, one or more of the following: (A) the CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; (B) the association is explicitly configured in one resource setting; (C) it is explicitly indicated that the two CSI-RS resource sets are linked together; (D) the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; (E) the association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; (F) the association of the two CSI-RS resources is explicitly configured in a table; (G) the association of the two CSI-RS resources is dynamically indicated; and (H) the first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behavior.

[0208] In some embodiments, the DL RS configuration includes a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with a beam of the second set, and one or both of the following: (A) the CSI report configuration indicates the CSI-RS resources in the CSI-RS resource set that the WD is to measure; and (B) the DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD is to measure.

[0209] In some other embodiments, the method further includes sending beam assistance information indicating a spatial correlation and a quasi-co-located QCL relationship between one or more beams in the first set of beams, the beam assistance information being capable of being used as an input to an artificial intelligence model.

[0210] In some embodiments, the method further includes receiving information from WD 22 regarding the predicted one or more sets of beams.

[0211] In some other embodiments, the one or more network node actions include sending signaling using one or more beams corresponding to the information about the predicted one or more sets of beams.

[0212] Having described the general process flow of the arrangements of the present disclosure and provided examples of hardware and software arrangements for implementing the processes and functions of the present disclosure, the following section provides details and examples of arrangements for predicting preferred beams in a fixed beam ("F-beam") set.

[0213] Some embodiments provide a wireless device configured to make at least one measurement of all available F beams (set A), and these F beams define a "prediction set" of beams, i.e., a predictor based on the set B measurements has an output that maps to one or more of the F beams in set A. One or more network node 16 functions described below may be performed by one or more of the processing circuit 68, the processor 70, the configuration unit 32, etc. General Overview of One or More Embodiments

[0214] The present disclosure describes one or more embodiments on how to perform model training and model inference for AI / ML-based spatial beam prediction on the wireless device 22 side and how to introduce such methods in the 3GPP CSI framework specification.

[0215] More specifically, the present disclosure details a set A of DL RSs and a set B of DL RSs, wherein each DL RS is transmitted by the network node 16 using a certain (fixed by implementation design / cell planning for a given cell) MIMO precoding vector, and thus these DL RSs define a so-called "beam".

[0216] The DL RSs (and their relationships to each other, e.g., QCL) may be configured in a manner that enables the wireless device 22 to use an AI / ML model to reliably predict the "best beam" / DL RS without having to measure all possible (represented as a number F) beams / DL RSs (thus saving beam management overhead), and how the wireless device 22 trains or retrains (updates) an AI / ML model (e.g., an inference function) that predicts set A based on measurements of set B, based on one or more measurements of the configured set B (online training), and CSI measurements of set A. One or more embodiments include the possibility that the network node 16 may also send the resources associated with set A in one or more measurement occasions, so these are used as input to the AI / ML model for data collection and training purposes.

[0217] In at least one embodiment, the wireless device 22 is configured with a first set of DL RS resources associated with set B and DL RS resources associated with set A, wherein the wireless device 22 performs one or more spatial domain predictions (based on CSI measurements of set B) for set A, wherein the spatial domain prediction is performed by a function (AI / ML inference function, AI / ML model). The wireless device 22 performs data collection for training the AI / ML model based on the resources of set B and the transmission timing of set A sent by the network node 16 (in the case where set A for data collection is configured as a non-periodic resource, it can be sent less frequently and / or on demand than set B).

[0218] Fig.13 , a first example is shown for the case where set B is configured as a periodic resource set, set B is used for both CSI measurements to be used as input for spatial domain prediction of set A and for data collection for training AI / ML models; and set A is also configured as a periodic resource set with a longer periodicity than set B (where transmissions of set A are mainly used for data collection for training AI / ML models). In one option, if set A is available, the wireless device 22 actually reports CSI measurements for A instead of predictions.

[0219] Fig.14, a second example is shown for the case where set B is configured as a periodic resource set, set B is used for both CSI measurements to be used as input for spatial domain prediction for set A and for data collection for training AI / ML models; and set A is also configured as an aperiodic or semi-persistent resource set (with a longer periodicity than set B in the case of semi-persistence, where transmissions of set A are mainly used for data collection for training AI / ML models). In one option, if set A is available, the wireless device 22 actually reports CSI measurements on A instead of predictions.

[0220] In at least one embodiment, the wireless device 22 sends a request to the network node 16 for a configuration to activate set A transmissions so that the wireless device 22 performs data collection for training the AI / ML model. In other words, in response to the request, the wireless device 22 receives a command (e.g., DCI and / or medium access control (MAC) control element (CE)) to activate set A resources so that the wireless device 22 can perform CSI measurements on set A for data collection.

[0221] When set A starts being sent, the wireless device 22 can perform CSI measurements on A, which is the set the network wants CSI reports on, and the wireless device 22 can perform CSI measurements on A for reporting purposes without using set B to predict set A. Therefore, the network node 16 can stop sending set B when it sends set A.

[0222] In at least one embodiment, the wireless device 22 indicates to the network that data collection is finished, for example, when the wireless device 22 completes AI / ML model training. In at least one embodiment, the wireless device 22 receives from the network node 16 an indication that the network node 16 has stopped sending the DL RS set and an indication for deactivation at the wireless device (e.g., MAC CE and / or DCI) and / or for removal of the DL RS resource set (e.g., RRC reconfiguration message).

[0223] In at least one embodiment, when the wireless device is configured to perform data collection according to the method, the wireless device starts a timer (Txxx), and while the timer is running, the wireless device performs data collection for training and expects the network to send DL RSs in set A and set B. When the timer expires, the wireless device stops data collection, for example, stops performing measurements on the DL RSs configured in set A and set B. The network node 16 also maintains an instance of the timer and stops the transmission of the DL RS upon expiration. Additional Details

[0224] As described above, spatial domain prediction of beams is a way to reduce CSI measurements that the wireless device 22 may need to perform for beam management. For example, based on the AI / ML functionality at the wireless device 22, a spatial AI / ML beam prediction method is to select one or more beams from the beams of set A (which the network can use to serve the wireless device 22 and are associated with one or more TCI states with which the wireless device 22 is configured) based on measurements of the beams of set B (for example, where the measurements are on the DL RS transmitted in these beams of set V), where the beams of set B are different from the beams of set A (for example, the beams of set B are wide beams, while the beams of set A are narrow beams).

[0225] 3GPP may need to agree on a way to configure set A beams and set B beams to the wireless device 22 in a way that supports AI / ML model training and inference to reduce beam management overhead.

[0226] In the present disclosure, the spatial domain beam prediction (SDBP) AI / ML model may be considered as part of a function or functionality related to spatial domain beam prediction and deployed / implemented / configured / defined in the wireless device 22. Furthermore, although the focus is on spatial beam prediction, it should be noted that the wireless device 22 may support joint spatial and time domain prediction, and thus spatial domain beam prediction may also include time domain prediction.

[0227] The SDBP AI / ML model may be defined as a function or part of a function implemented / supported in the wireless device 22, and the wireless device 22 may indicate the function version to another node (e.g., the network node 16). If the AI / ML model is updated, the wireless device 22 may change the function version. The AI / ML model may be any trainable ML algorithm, including but not limited to, for example, artificial neural networks, decision trees, random forests, nearest neighbors, and support vector machines.

[0228] The SDBP AI / ML model may correspond to a function that receives one or more inputs (e.g., channel measurements for beams from set B) and outputs one or more decisions, estimates, or predictions of a particular type (e.g., CSI for beams from set A or the top K predicted beams from beams from set A).

[0229] Fig.15 Schematic examples of beams of set A and beams of set B are shown, where the beams of set B are a subset of the beams of set A.

[0230] - Fig.15 The top portion of depicts all feasible (eg, possible) candidate network node 16 beams.

[0231] - Fig.15The middle part of depicts an example of beams for set A (the beams of set A may be all network node 16 beams or a subset of all network node 16 beams), so here F=16. For example, The beams of set A may be all F = 16 beams with azimuth angles in the range [0,90] degrees, such as Fig.15 As shown (eg, wireless device 22 is located in the left half of the partition). • The beams of set A may be all beams having a zenith angle pointing towards the horizon (eg, if the distance from the wireless device 22 to the network node 16 is large). In one embodiment, set A may be selected by the network using measurements and reports from the wireless device 22 regarding SSBs.

[0232] - Fig.13 The lower part of depicts the beams of set B (which is a subset of the beams of set A). • Therefore, the NW / network node 16 may only need to send 4 DL RSs, and the wireless device 22 may only need to measure 4 DL RSs instead of a full F=16.

[0233] Another aspect of the present disclosure is Fig.16 For inference, i.e. beam prediction purposes, the wireless device 22 is configured with a set A of reference signals by the network / network node 16. Within set A, some reference signals (set B) are transmitted so they can be measured by the wireless device 22, while some reference signals are not transmitted.

[0234] The wireless device 22 may, after being triggered by the network node 16, perform measurements on a subset of the transmitted set B reference signals and, based on the measurements, aim to perform a prediction of the best or k best reference signals within the set A reference signals.

[0235] Thus, the inference may use both set A and set B measurements, and the output from the inference is in the space of set A reference signal indices (ie, beam indices).

[0236] The wireless device 22 may also report the predicted result, i.e., the best or k best predicted reference signals in the set A within a certain metric, to the network node 16. The reference signals may be reported in the form of their IDs to reduce overhead, and the metric may be, for example, one of the following: RSRP, RSRQ, RSSI, SINR, rank, CQI, and any other radio-related measurement.

[0237] Some reference signals in set A and set B are transmitted in the same beam, which can be indicated to the wireless device 22 by some form of identification. This can be indicated, for example, by them sharing the same spatial correlation or the same TCI state or being associated with QCL type D. Or they just have the same DL RS identifier.

[0238] The reference signals of set B are typically transmitted less frequently than the reference signals of set A. The wireless device 22 may utilize the set A reference signals for data collection or to monitor the prediction accuracy of its prediction model. The wireless device 22 may compare the predictions of the model by running the predictions and comparing them to actual measurements within set A. If the model performs below a certain threshold, the wireless device 22 may indicate to the network node 16 that the prediction is no longer supported or that the prediction may be inaccurate.

[0239] The following example methods are provided:

[0240] - First step: The network node 16 sends CSI-RS beam scanning using all F narrow beams of set A. Therefore, F CSI-RS resources are used, each resource typically having two or more antenna ports.

[0241] - Second step: The network node 16 sends a subsequent CSI-RS beam scan in a subset of the beams used in the first step (i.e. using beams of set B that are a subset of beams of set A). This transmission may be wireless device 22 specific (configured for a single wireless device 22) or cell specific (same configuration used by all wireless devices 22 in a cell).

[0242] - Third step: The wireless device 22 predicts the preferred beam from the beams of set A using at least the measurements of the beams of set B. The SDBP AI / ML model may take additional inputs / features such as an estimate of the wireless device 22 location or line-of-sight / non-line-of-sight classification probabilities or a wireless device 22 antenna panel identifier. The SDBP AI / ML model may also explicitly or implicitly input the association between the DL RSs in set A and the DL RSs in set B, e.g., whether they are transmitted using the same MIMO precoder / DL spatial filter / QCL type D relationship. This information is important for the AI / ML model to "know" that it is measuring the actual beam in the output set A. ●Since Set B has fewer beams than Set A, the associated CSI-RS overhead is reduced compared to sending CSI-RS resources in all beams of Set A for each beam scan (with limited performance degradation if the AI / ML model predicts the beams in an efficient manner). Set A beams may be triggered infrequently to allow the wireless device 22 to collect training data and / or calibrate or fine-tune its SDBP AI / ML model. In one embodiment, the triggering may be based on the wireless device 22, where the wireless device 22 may trigger Set A beams if its performance degrades (e.g., RSRP drops below a certain threshold). Another triggering approach is based on the NW / network node 16, where the NW / network node 16 requires the wireless device 22 to test the model with a certain periodicity.

[0243] Fig.17 A schematic example of an AI / ML model using RSRP measurements from both set A and set B and the corresponding DL-RS IDs as input is shown. In this example, the set A beam scan includes 4 beams, numbered (RSID) {1, 2, 3, 4}, which correspond to 4 RSRP measurements. The set B beam scan can use a subset of set A, where only two of the four beams numbered {1, 4} correspond to two RSRP measurements. Since fewer DL-RS are sent in set B compared to set A, we reduce both the DL-RS resource overhead and the measurement complexity of the wireless device 22. The inferred inputs (beam predictions) of the AI / ML model are the set A and set B RSRP measurements and the associated set A index from {1, 2, 3, 4} and set B index from {1, 4}.

[0244] In one embodiment, the wireless device 22 performs prediction based on several set B-beam scans, such as by averaging RSRP measurements over multiple scans.

[0245] Fig.18 A flow chart of an example method according to some embodiments of the present disclosure is shown. In block S200, the wireless device reports support for performing spatial beam prediction from a set A of network node 16 beams based on measurements of a set B of network node 16 beams, for example during wireless device capability signaling. The wireless device capability signaling ("DL TX spatial beam prediction capability") may, for example, include one or more of the following information: ● Support of spatially predicted beam reporting from set A beams based on measurements on set B beams, where set B beams are a subset of set A beams. ●The maximum number of beams supported in set A. ●The maximum number of beams supported in set B. ●The minimum number of beams supported in set B. The predicted performance of each supported combination of beams from set A and beams from set B. For example, N1 beams in set B and N2 beams in set A imply a certain performance. ML model processing power (e.g., how much time does the wireless device need to retain / update its model, This may affect the configuration of DL RS transmission, for example, the periodicity of transmitting the beams of set A, and the delta time between transmitting the beams of set A and transmitting the beams of set B).

[0246] In block S202, the network node 16 indicates relevant configurations for spatial beam prediction, such as "DL reference signal configuration", "CSI report configuration" and possibly "network node TX beam assistance information". The "DL reference signal configuration" may, for example, include one or more of the following: = Resource configuration (ie CSI-ResourceConfig as specified in, for example, 3GPP TS 38.311) = CSI-RS resource set (ie NZP-CSI- RS-ResourceSet) ● CSI-RS resources (i.e., NZP-CSI-RS- as specified in, for example, 3GPP TS 38.311) Resource) ● New potential DL-RS resource configurations for 6G

[0247] “CSI reporting configuration” may, for example, include one or more of the following: ● Reporting settings (i.e. CSI-ReportConfig as specified in e.g. 3GPP TS 38.311) ● New potential CSI reporting configurations for 6G

[0248] The “network node TX beam assist information” may, for example, include one or more of the following: ●Spatial correlation between 16Tx beams of different network nodes ● QCL correlation between 16TX beams at different network nodes ● Azimuth and elevation pointing angles of 16TX beams at different network nodes ● Beam width of 16TX beams for different network nodes

[0249] In box S204, the network node 16 performs a first beam scan by sending a first set of DL reference signals associated with the beams of set A, and in box S206, the wireless device 22 performs measurements on the beams of set A and uses these measurements as input to the AI / ML model (e.g., to train / retrain / update AI / ML parameters).

[0250] In box S208, the network node 16 sends a subsequent beam scan by sending a second set of DL reference signals associated with the beams of set B, and in box S210, the wireless device 22 performs measurements on the beams of set B and uses these measurements to predict the best N beams from the beams of set A.

[0251] In block S212 , the wireless device 22 reports N predicted beams from set A.

[0252] Steps block S208 through block S212 may then be repeated one or more times until the network node 16 starts again with block S204.

[0253] In at least one embodiment, the linking of two different CSI-RS resource sets (associated with beams of set A and beams of set B) is explicitly indicated in the aperiodic triggered state (i.e., CSI-AperiodicTriggerState as specified in, for example, 3GPP TS 38.331). For example, the information element "CSI-AssociedReportConfigInfo" included in the aperiodic triggered state (as specified in, for example, 3GPP TS 38.331) can be configured with an additional "reportConfigId" or an additional "resourceForChannel", which can indicate to the wireless device that the two CSI-RS resource sets (associated with either of the two "reportConfigIds" or the two "resourceForChannels") are linked together. The bold text below shows an example of how this may look, where the additional "reportConfigId" is added. When two CSI-RS resource sets are linked together, the wireless device may assume that the CSI-RS resources configured in the two CSI-RS resource sets should be transmitted in the same network node 16TX beam, regardless of which of the two linked CSI-RS resource sets they are transmitted in.

[0254] Various example methods according to the present invention may be as follows:

[0255] 1. A method for selecting (and / or predicting) a preferred number k (k is equal to or greater than 1) of DL reference signals in a wireless device 22, the method comprising: a. Receiving a DL reference signal configuration that configures two or more sets of reference signal resources (e.g., where at least one reference signal is configured as part of more than one set, the sets at least partially overlapping, such as at least some reference signal resources of one set may be included in another set); i. Includes configurations for set A (F beams that are candidates for prediction and measured during training) and configurations for set B (beams measured during inference and / or training); ii. The configuration may also include the concept of a QCL type D relationship or the same spatial Tx filter between the transmissions of the DL reference signals in set A and the DL reference signals in set B; b. Receiving a CSI reporting configuration associated with a DL reference signal configuration; c. Receiving a trigger message to measure a subset of the reference signals of the first set (set A) according to the CSI reporting configuration; and d. Performing measurements on a subset of DL reference signals associated with set B; e. Based on the measured subset of reference signals in set B, report the identifiers of the preferred k reference signals within the reference signals of set A.

[0256] 2. According to the method of Example 1 above, the wireless device 22 receives a trigger (or a higher-level periodic configuration thereof) to measure set A reference signals, where the set A reference signals may be received from the network node 16 less frequently than the set B reference signals.

[0257] 2b. A method according to Example 1 above, wherein the configuration for set A (DL RSs associated with beams to be predicted and measured during training) is sent with a different (typically longer) periodicity (e.g., less frequent) than set B.

[0258] 3. The method according to example 2 and / or 2a above, wherein measurements from the set B reference signals are reported to the network node 16 .

[0259] 4. The method of Example 1 above, wherein the wireless device 22 performs data collection or monitors the performance of beam prediction based on the set B measurements.

[0260] 5. According to the method of Example 1 above, the wireless device 22 sends a capability indicating support of beam prediction to the network node 16, and the capability may also indicate one or more of the following: a. Support spatial prediction beam reporting for beams from set A based on measurements on beams from set B, where beams from set B are a subset of beams from set A. b. Maximum number of beams / DL RSs supported in set A; c. Maximum number of beams / DL RSs supported in set B; d. The minimum number of beams / DL RSs supported in set B; e.ML model processing capabilities; f. Prediction performance for various combinations of set A and set B g. The number of DL RSs configured in set A divided by the number of DL RSs configured in set B Maximum support ratio of the target

[0261] 6. The method according to example 1 above, wherein the wireless device 22 sends a message ("UL assistance information") to the network node 16, the message including one or more of the following: a. Location information of the wireless device 22, where the location can be a physical location or a direction toward the network The relative position of the antenna of the network node 16; b. An estimate of the speed and / or rotation of the wireless device 22 (in the Earth bounded coordinate system); c. Information about the antenna panel of the wireless device 22; d. Information about the antenna panel of the wireless 22 device; configuration and use.

[0262] 7. The method according to Example 1 above, wherein the DL reference signal configuration includes two CSI-RS resource sets: a. The first CSI-RS resource set includes M CSI-RS resources (associated with the beam of set A), and b. The second CSI-RS resource set includes N CSI-RS resources (associated with beams of set B).

[0263] 8. The method according to Example 6 above, wherein the second CSI-RS resource set is a subset of the first CSI-RS resource set.

[0264] 9. A method according to Example 6 above, wherein there is an association between two CSI-RS resource sets, and wherein the association indicates that when a CSI-RS resource is transmitted as part of a first CSI-RS resource set, and when the same CSI-RS resource is transmitted as part of a second CSI-RS resource set, the same beam of the network node 16 is to be used for the CSI-RS resource.

[0265] 10. The method according to Example 8 above, wherein the association is explicitly configured according to the CSI-RS resource set (for example, the field can be configured per CSI-RS resource set, and the CSI-RS resource sets configured with the same field are linked together).

[0266] 11. The method according to example 8 above, wherein the association is directly configured by a field in the CSI report configuration.

[0267] 12. A method according to Example 8 above, wherein the CSI report configuration includes two report settings (i.e., CSI-ReportConfig as specified in 3GPP TS38.311, for example), wherein each report setting points to a CSI-RS resource set, and wherein parameters / flags are configured per report setting, and when two report settings are configured with the same parameters / flags, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together.

[0268] 13. The method according to example 6 above, wherein the association is explicitly configured in the resource setting (ie CSI-ResourceConfig as specified in, for example, 3GPP TS38.311).

[0269] 14. The method of example 4 above, wherein there is an explicit indication to link the two CSI-RS resource sets together.

[0270] 15. The method according to Examples 4 and / or 11 above, wherein it is explicitly indicated to link the CSI-RS resources in the first CSI-RS resource set with the CSI-RS resources in the second CSI-RS resource set.

[0271] 16. The method according to example 12 above, wherein the association between the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set indicates that the same beam of the network node 16 is used for both CSI-RS resources.

[0272] 17. The method according to Example 13 above, wherein the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are the same CSI-RS resources.

[0273] 18. The method according to Example 13 above, wherein the CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are different CSI-RS resources.

[0274] 19. A method according to any one of Examples 4, 11, 12, 13, 14 or 15 above, wherein the linkage of two CSI-RS resources is explicitly configured for each CSI-RS resource (using parameters configured by a high layer) so that two CSI-RS resources with the same parameter settings are linked together.

[0275] 20. A method according to any one of Examples 4, 11, 12, 13, 14 or 15 above, wherein the linkage of two CSI-RS resources is explicitly configured in a table / list, wherein the table / list includes pairs of CSI-RS resources and wherein the two CSI-RS resources in a pair of CSI-RS resources are linked together.

[0276] 21. A method according to Example 17 above, wherein a first CSI-RS resource in a pair of CSI-RS resources is associated with a first CSI-RS resource set, and a second CSI-RS resource in the pair of CSI-RS resources is associated with a second CSI-RS resource set.

[0277] 22. A method according to any one of Examples 4, 11, 12, 13, 14, 15, 16, 17 and 18 above, wherein the linkage of two CSI-RS resources can be dynamically indicated using, for example, DCI and / or MAC-CE.

[0278] 23. The method according to Example 9 above, wherein the bit field in the DCI for triggering the transmission of the CSI-RS resource set is used to indicate which CSI-RS resource(s) the wireless device 22 should perform measurement on (i.e., indicating the beam of set B).

[0279] 24. A method according to any one of the above examples, wherein the first CSI-RS resource set and the second CSI-RS resource set have the same time domain behavior (eg, both CSI-RS resource sets are sent periodically).

[0280] 25. A method according to any one of the above examples, wherein the first CSI-RS resource set and the second CSI-RS resource set have different time domain behaviors (for example, the first CSI-RS resource set is periodically transmitted, while the second CSI-RS resource set is non-periodically transmitted).

[0281] 26. A method according to Example 1 above, wherein the DL reference signal configuration includes a single CSI-RS resource set, the single CSI-RS resource set including M CSI-RS resources (associated with beams of set A).

[0282] 27. The method of Example 23 above, wherein the CSI reporting configuration indicates which CSI-RS resource in the set of CSI-RS resources the wireless device 22 should perform measurements on (ie, indicating a beam of set B).

[0283] 28. A method according to example 24 above, wherein the CSI reporting configuration includes a single reporting setting (i.e., CSI-ReportConfig as specified in, for example, 3GPP TS 38.311), and which CSI-RS resource(s) in the CSI-RS resource set the wireless device 22 should perform measurements on (i.e., beams of set B) is explicitly indicated in the reporting setting.

[0284] 29. The method of Example 23 above, wherein the DL reference signal configuration indicates which CSI-RS resource in the set of CSI-RS resources the wireless device 22 should perform measurements on (ie, indicating a beam of set B).

[0285] 30. The method of example 26 above, wherein the indication is explicitly configured in a resource setting (ie, CSI-ResourceConfig as specified in, for example, 3GPP TS 38.311).

[0286] 31. A method according to Example 26 above, wherein the indication is explicitly configured in the CSI-RS resource set.

[0287] 32. The method according to Example 1 above, wherein the DL reference signal configuration includes a single CSI-RS resource set including N CSI-RS resources (associated with beam set B).

[0288] 33. A method according to Example 29 above, wherein the CSI reporting configuration indicates the CSI-RS resources that should be used for reporting (i.e., the CSI-RS resources associated with beam set A).

[0289] 34. The method of example 30 above, wherein the CSI reporting configuration comprises a single report setting (ie, CSI-ReportConfig as specified in, for example, 3GPP TS 38.311), and the indication is explicitly indicated in the report setting.

[0290] 35. A method according to Example 1 above, wherein the wireless device 22 receives beam assistance information (1c) indicating a spatial correlation and / or QCL relationship between one or more beams (CSI-RS resources) in set A.

[0291] 36. A method according to Example 32 above, wherein the wireless device 22 uses beam assistance information as input to the AI / ML model when predicting beams from set A based on measurements of beams from set B.

[0292] 37. A method according to Example 1 above, wherein steps (1h, 1i and 1j) associated with set B transmissions are performed more frequently than steps (1e, 1f and 1g) associated with set A transmissions.

[0293] 38. The method according to any one of the above examples, wherein the first CSI-RS resource set and the second CSI-RS resource set are determined by the network node 16 by using the auxiliary information in 3.

[0294] The method according to example 1 above, wherein the reported predicted measurements have associated uncertainties. The uncertainties may include the probability that each corresponding reference signal is the best (strongest).

[0295] The following is a non-limiting list of example embodiments.

[0296] Embodiment A1. A network node configured to communicate with a wireless device (WD), the network node being configured to and / or comprising a radio interface and / or comprising a processing circuit, the processing circuit being configured to: sending a downlink (DL) reference signal configuration to a wireless device, the configuration corresponding to at least a first set of reference signal resources and a second set of reference signal resources, the first set and the second set at least partially overlapping; and The wireless device is communicated with according to a preferred subset of reference signals in the first set of reference signals, the preferred subset of reference signals selected based in part on the second set of reference signals.

[0297] Embodiment A2. The network node of embodiment A1, wherein the reference signal configuration includes at least one of a quasi co-location type D relationship and a spatial transmitter filter.

[0298] Embodiment A3. A network node according to embodiment A1, wherein the network node is configured to and / or includes a radio interface and / or includes a processing circuit, and the processing circuit is configured to send a trigger on a preferred reference signal subset to cause the wireless device to perform at least one measurement related to the reference signals of the second set.

[0299] Embodiment B1. A method implemented in a network node, the method comprising: sending a downlink (DL) reference signal configuration to a wireless device, the configuration corresponding to at least a first set of reference signal resources and a second set of reference signal resources, the first set and the second set at least partially overlapping; and The wireless device is communicated with according to a preferred subset of reference signals in the first set of reference signals, the preferred subset of reference signals selected based in part on the second set of reference signals.

[0300] Embodiment B2. The method of embodiment B1, wherein the reference signal configuration includes at least one of a quasi co-sited type D relationship and a spatial transmitter filter.

[0301] Embodiment B3. The method of embodiment B1 further includes: sending a trigger on the preferred reference signal subset to cause the wireless device to perform at least one measurement related to the reference signals of the second set.

[0302] Embodiment C1. A wireless device (WD) configured to communicate with a network node, the WD configured to and / or including a radio interface and / or a processing circuit, the processing circuit configured to: receiving a downlink DL reference signal configuration corresponding to at least a first set of reference signal resources and a second set of reference signal resources, the first set and the second set at least partially overlapping; performing at least one measurement of at least one reference signal in the second set; and A preferred subset of reference signals in the first set of reference signals is determined based at least in part on the measurement.

[0303] Embodiment C2. The WD of embodiment C1, wherein the reference signal configuration includes at least one of a quasi co-sited type D relationship and a spatial transmitter filter.

[0304] Embodiment C3. The WD of embodiment C1, wherein the wireless device is configured to and / or includes a radio interface and / or includes a processing circuit configured to perform at least one measurement related to the second set of reference signals in response to receiving a trigger.

[0305] Embodiment D1. A method implemented in a wireless device (WD), the method comprising: receiving a downlink DL reference signal configuration corresponding to at least a first set of reference signal resources and a second set of reference signal resources, the first set and the second set at least partially overlapping; performing at least one measurement of at least one reference signal in the second set; and A preferred subset of reference signals in the first set of reference signals is determined based at least in part on the measurement.

[0306] Embodiment D2. The method of embodiment D1, wherein the reference signal configuration includes at least one of a quasi co-sited type D relationship and a spatial transmitter filter.

[0307] Embodiment D3. The method of embodiment D1, wherein performing at least one measurement related to the second set of reference signals is in response to receiving a trigger.

[0308] As will be appreciated by those skilled in the art, the concepts described herein may be embodied as methods, data processing systems, computer program products, and / or computer storage media for storing executable computer programs. Therefore, the concepts described herein may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware embodiments, all collectively referred to herein as "circuits" or "modules". Any process, step, action, and / or function described herein may be performed and / or associated with a corresponding module, which may be implemented in software and / or firmware and / or hardware. In addition, the present disclosure may take the form of a computer program product on a tangible computer-usable storage medium having a computer program code embodied in a medium that may be executed by a computer. Any suitable tangible computer-readable medium may be used, including a hard disk, a CD-ROM, an electronic storage device, an optical storage device, or a magnetic storage device.

[0309] Some embodiments are described herein with reference to the flowchart and / or block diagram of method, system and computer program product.It should be understood that each frame in the flowchart and / or block diagram and the combination of frames in the flowchart and / or block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of general-purpose computer (thereby creating a special-purpose computer), special-purpose computer or other programmable data processing device to produce machine, so that the instruction executed by the processor of computer or other programmable data processing device creates the parts for realizing the function / action specified in the flowchart and / or block diagram or frame.

[0310] These computer program instructions may also be stored in a computer-readable memory or storage medium, which may direct a computer or other programmable data processing device to function in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture, including instruction components that implement the functions / actions specified in the flowchart and / or block diagram.

[0311] Computer program instructions may also be loaded onto a computer or other programmable data processing apparatus so that a series of operational steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions / actions specified in the flowchart and / or block diagram or box.

[0312] It should be understood that the functions / actions mentioned in the blocks may not occur in the order indicated in the operational diagram. For example, two blocks shown in succession may actually be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order, depending on the functions / actions involved. Although some figures include arrows on communication paths to illustrate the primary communication direction, it should be understood that communication may occur in the direction opposite to the arrows depicted.

[0313] Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, The computer program code for performing the operations of the present disclosure may be written in a conventional procedural programming language such as the "C" programming language. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer. In the latter case, the remote computer may be connected to the user's computer via a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0314] Many different embodiments have been disclosed herein in conjunction with the above description and accompanying drawings. It should be understood that it would be excessively repetitive and confusing to describe and illustrate verbatim every combination and subcombination of these embodiments. Therefore, all embodiments may be combined in any manner and / or combination, and this specification including the accompanying drawings will be interpreted as constituting a complete written description of all combinations and subcombinations of the embodiments described herein, as well as the manner and process of making and using them, and should support claims to any such combination or subcombination.

[0315] Abbreviations that may be used in the preceding description include: 3GPP Third Generation Partnership Project 5G Fifth Generation ACK AI AoA Angle of Arrival CORESET Control resource collection CSI Channel State Information CSI-RS CSI reference signal DCI Downlink Control Information DoA Direction of Arrival DL Downlink DMRS Downlink Demodulation Reference Signal FDD Frequency Division Duplex FR2 Frequency Range 2 HARQ Hybrid Automatic Repeat Request ID gNB gNodeB MAC Media Access Control MAC-CE MAC Control Element ML Machine Learning NR New Radio NW Network OFDM Orthogonal Frequency Division Multiplexing PBCH Physical Broadcast Channel PCI Physical Cell Identifier PDCCH Physical Downlink Control Channel PDSCH Physical Downlink Shared Channel PRB Physical Resource Block QCL Quasi-Co-sited RB Resource Block RRC Radio Resource Control RSRP Reference Signal Strength Indicator RSRQ Reference Signal Received Quality RSSI Received Signal Strength Indicator SCS Subcarrier Spacing SINR Signal to Interference and Noise Ratio SSB Synchronous Signal Block RL RS reference signal Rx Receiver TB Transfer Block TDD Time Division Duplex TCI Transmission Configuration Indicator TRP Transmission / Reception Point Tx Transmitter UE User Equipment UL Uplink

[0316] Those skilled in the art will appreciate that the embodiments described herein are not limited to the embodiments specifically shown and described above. In addition, unless otherwise mentioned above, it should be noted that all drawings are not drawn to scale. Various modifications and variations are possible according to the above teachings without departing from the scope of the appended claims.

Claims

1. A wireless device WD (22) configured to communicate with a network node (16) and to predict at least a reference signal RS associated with the network node (16), the WD (22) being configured to: receiving a downlink DL RS configuration for configuring two or more sets of reference signal resources, the DL RS configuration comprising a first configuration for beams of a first set and a second configuration for beams of a second set, the beams of the second set being a subset of the beams of the first set; receiving a CSI reporting configuration associated with the DL reference signal configuration; receiving a first message requesting the WD (22) to measure a subset of DL RSs in a first set of DL RSs associated with beams of the first set according to the CSI reporting configuration; performing measurement on a subset of DL RSs in a second set of DL RSs associated with beams in the second set; performing one or more actions associated with an artificial intelligence model using at least the measurements of the subset of DL RSs in the second set of DL RSs; predicting one or more DL RSs from the first set of DL RSs associated with the first set of beams based in part on the one or more actions; and Information about the predicted one or more RSs is sent to the network node (16).

2. The WD (22) according to claim 1, wherein the WD (22) is further configured to: A second message is received, the second message requesting the WD (22) to measure the first set of DL RSs, the first set of DL RSs being transmitted less frequently than the second set of DL RSs.

3. The WD (22) according to any one of claims 1 and 2, wherein the WD (22) is further configured to: Based on the measurement of the DL RSs of the second set, the collection of data associated with the predicted performance of the one or more DL RSs from the first set of DL RSs is performed.

4. The WD (22) according to any one of claims 1 to 3, wherein the WD (22) is further configured to: Sending a capability indication to the network node (16) indicating one or more of the following: Forecast support; support for spatial prediction beam reporting for predicting one or both of a beam in the first set of beams and a reference signal in an RS from the first set; a first maximum number of one or both of beams in the first set of beams and DL RSs in the first set of DL RSs; a second maximum number of one or both of beams in the second set of beams and DL RSs in the second set of DL RSs; a minimum number of one or both of beams in the second set of beams and DL RSs in the second set of DL RSs; Machine learning (ML) model processing capabilities associated with the artificial intelligence model; and Predicted performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

5. The WD (22) according to any one of claims 1 to 4, wherein the WD (22) is further configured to: Sending a third message to the network node (16), wherein the third message includes uplink (UL) assistance information, wherein the UL assistance information includes one or more of the following: WD location information; an estimate of one or both of WD speed and WD rotation; Information about the WD antenna panel; and Information about the configuration and use of the WD antenna panel.

6. The WD (22) according to any one of claims 1 to 5, wherein the DL RS configuration comprises two CSI-RS resource sets, the two CSI-RS resource sets comprising: a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; as well as A second CSI-RS resource set has N CSI-RS resources associated with the beam of the second set.

7. The WD (22) according to claim 6, wherein one or more of the following: The second CSI-RS resource set is a subset of the first CSI-RS resource set; The first set of CSI-RS resources and the second set of CSI-RS resources are linked via an association, the association indicating that the same beam from the network node (16) is to be used for the CSI-RS resources when the CSI-RS resources are transmitted as part of the first set of CSI-RS resources and when the CSI-RS resources are transmitted as part of the second set of CSI-RS resources; The association is explicitly configured according to a CSI-RS resource set; and The association is configured by a field in the CSI report configuration.

8. The WD (22) according to any one of claims 6 and 7, wherein one or more of the following: The CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; The association is explicitly configured in a resource setting; explicitly indicating that the two CSI-RS resource sets are linked together; The CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; The association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; The association of two CSI-RS resources is explicitly configured in a table; The association of two CSI-RS resources is dynamically indicated; and The first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behaviors.

9. The WD (22) according to any one of claims 1 to 5, wherein: The DL RS configuration includes: a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with beams of the second set; and One or both of the following: The CSI reporting configuration indicates a CSI-RS resource in the CSI-RS resource set that the WD (22) is to measure; and The DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD (22) is to measure.

10. The WD (22) according to any one of claims 1 to 9, wherein the WD (22) is further configured to: Receive beam-assist information indicating spatial correlation and quasi-co-located QCL relationships between one or more beams in the first set of beams, the beam-assist information being usable as an input to the artificial intelligence model.

11. The WD (22) according to any one of claims 1 to 10, wherein the WD (22) is further configured to: predicting one or more sets of beams from the first set of beams based in part on the one or more actions; and Information about the predicted one or more sets of beams is sent to the network node (16).

12. The WD (22) according to any one of claims 1 to 11, wherein the one or more actions include one or more of the following: training the artificial model; retraining the artificial model; and The artificial model is updated.

13. A method in a wireless device WD (22), the WD (22) being configured to communicate with a network node (16) and to predict at least a reference signal RS associated with the network node (16), the method comprising: receiving (S144) a downlink DL RS configuration for configuring two or more sets of reference signal resources, the DL RS configuration comprising a first configuration for beams of a first set and a second configuration for beams of a second set, the beams of the second set being a subset of the beams of the first set; receiving (S146) a CSI report configuration associated with the DL reference signal configuration; receiving (S148) a first message, the first message requesting the WD (22) to measure a subset of DL RSs in a first set of DL RSs associated with beams of the first set according to the CSI reporting configuration; measuring a subset of DL RSs in a second set of DL RSs associated with the beams of the second set (S150); performing (S152) one or more actions associated with an artificial intelligence model using at least the measurements of the subset of DL RSs in the second set of DL RSs; predicting (S154) one or more DL RSs from the first set of DL RSs associated with the first set of beams based in part on the one or more actions; and Information about the predicted one or more RSs is sent (S156) to the network node (16).

14. The method according to claim 13, wherein the method further comprises: A second message is received, the second message requesting the WD (22) to measure the first set of DL RSs, the first set of DL RSs being transmitted less frequently than the second set of DL RSs.

15. The method according to any one of claims 13 and 14, wherein the method further comprises: Based on the measurement of the DL RSs of the second set, the collection of data associated with the predicted performance of the one or more DL RSs from the first set of DL RSs is performed.

16. The method according to any one of claims 13 to 15, wherein the method further comprises: Sending a capability indication to the network node (16) indicating one or more of the following: Forecast support; support for spatial prediction beam reporting for predicting one or both of a beam in the first set of beams and a reference signal in an RS from the first set; a first maximum number of one or both of beams in the first set of beams and DL RSs in the first set of DL RSs; a second maximum number of one or both of beams in the second set of beams and DL RSs in the second set of DL RSs; a minimum number of one or both of beams in the second set of beams and DL RSs in the second set of DL RSs; A machine learning (ML) model processing capability associated with the artificial intelligence model; and a predictive performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

17. The method according to any one of claims 13 to 16, wherein the method further comprises: Sending a third message to the network node (16), wherein the third message includes uplink (UL) assistance information, wherein the UL assistance information includes one or more of the following: WD location information; an estimate of one or both of WD speed and WD rotation; Information about the WD antenna panel; and Information about the configuration and use of the WD antenna panel.

18. The method according to any one of claims 13 to 17, wherein the DL RS configuration comprises two CSI-RS resource sets, and the two CSI-RS resource sets comprise: a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; as well as A second CSI-RS resource set has N CSI-RS resources associated with the beam of the second set.

19. The method of claim 18, wherein one or more of the following: The second CSI-RS resource set is a subset of the first CSI-RS resource set; The first set of CSI-RS resources and the second set of CSI-RS resources are linked via an association, the association indicating that the same beam from the network node (16) is to be used for the CSI-RS resources when the CSI-RS resources are transmitted as part of the first set of CSI-RS resources and when the CSI-RS resources are transmitted as part of the second set of CSI-RS resources; The association is explicitly configured according to a CSI-RS resource set; and The association is configured by a field in the CSI report configuration.

20. The method according to any one of claims 18 and 19, wherein one or more of the following: The CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; The association is explicitly configured in a resource setting; explicitly indicating that the two CSI-RS resource sets are linked together; The CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; The association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; The association of two CSI-RS resources is explicitly configured in a table; The association of two CSI-RS resources is dynamically indicated; and The first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behaviors.

21. The method according to any one of claims 13 to 17, wherein: The DL RS configuration includes: a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with beams of the second set; and One or both of the following: The CSI reporting configuration indicates a CSI-RS resource in the CSI-RS resource set that the WD (22) is to measure; and The DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD (22) is to measure.

22. The method according to any one of claims 13 to 21, wherein the method further comprises: Receive beam-assist information indicating spatial correlation and quasi-co-located QCL relationships between one or more beams in the first set of beams, the beam-assist information being usable as an input to the artificial intelligence model.

23. The method according to any one of claims 13 to 22, wherein the method further comprises: predicting one or more sets of beams from the first set of beams based in part on the one or more actions; as well as Information about the predicted one or more sets of beams is sent to the network node (16).

24. The method of any one of claims 13 to 23, wherein the one or more actions include one or more of the following: training the artificial model; retraining the artificial model; and The artificial model is updated.

25. A network node (16) configured to communicate with a wireless device WD (22), the wireless device WD (22) being configured to at least predict a reference signal RS associated with the network node (16), the network node (16) being configured to: sending a downlink DL RS configuration for configuring two or more sets of reference signal resources, the DL RS configuration comprising a first configuration for beams of a first set and a second configuration for beams of a second set, the beams of the second set being a subset of the beams of the first set; sending a CSI report configuration associated with the DL reference signal configuration; sending a first message, wherein the first message requests the WD (22) to measure a subset of DL RSs in a first set of DL RSs associated with the beams of the first set according to the CSI reporting configuration; receiving, from the WD (22), information about one or more RSs predicted from the first set of DL RSs associated with the first set of beams based in part on one or more WD actions, the one or more WD actions being associated with an artificial intelligence model and performed using at least measurements of the subset of DL RSs in the second set of DL RSs; as well as One or more network node actions are performed based on information about the one or more RSs predicted from the first set of DL RSs.

26. The network node (16) according to claim 25, wherein the network node (16) is further configured to: A second message is sent, the second message requesting the WD (22) to measure the first set of DL RSs, the first set of DL RSs being sent less frequently than the second set of DL RSs.

27. The network node (16) according to any one of claims 25 to 26, wherein the network node (16) is further configured to: Receiving a capability indication from the WD (22) indicating one or more of the following: Forecast support; support for spatial prediction beam reporting for predicting one or both of a beam in the first set of beams and a reference signal in an RS from the first set; a first maximum number of one or both of beams in the first set of beams and DL RSs in the first set of DL RSs; a second maximum number of one or both of beams in the second set of beams and DL RSs in the second set of DL RSs; a minimum number of one or both of beams in the second set of beams and DL RSs in the second set of DL RSs; Machine learning (ML) model processing capabilities associated with the artificial intelligence model; and Predicted performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

28. The network node (16) according to any one of claims 25 to 27, wherein the network node (16) is further configured to: Sending a third message to the network node (16), wherein the third message includes uplink (UL) assistance information, wherein the UL assistance information includes one or more of the following: WD location information; an estimate of one or both of WD speed and WD rotation; Information about the WD antenna panel; and Information about the configuration and use of the WD antenna panel.

29. The network node (16) according to any one of claims 25 to 28, wherein the DL RS configuration comprises two CSI-RS resource sets, the two CSI-RS resource sets comprising: a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; as well as A second CSI-RS resource set has N CSI-RS resources associated with the beam of the second set.

30. The network node (16) of claim 29, wherein one or more of the following: The second CSI-RS resource set is a subset of the first CSI-RS resource set; The first set of CSI-RS resources and the second set of CSI-RS resources are linked via an association, the association indicating that the same beam from the network node (16) is to be used for the CSI-RS resources when the CSI-RS resources are transmitted as part of the first set of CSI-RS resources and when the CSI-RS resources are transmitted as part of the second set of CSI-RS resources; The association is explicitly configured according to a CSI-RS resource set; and The association is configured by a field in the CSI report configuration.

31. The network node (16) according to any one of claims 29 and 30, wherein one or more of the following: The CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; The association is explicitly configured in a resource setting; explicitly indicating that the two CSI-RS resource sets are linked together; The CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; The association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; The association of two CSI-RS resources is explicitly configured in a table; The association of two CSI-RS resources is dynamically indicated; and The first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behaviors.

32. The network node (16) according to any one of claims 25 to 28, wherein: The DL RS configuration includes: a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with beams of the second set; and One or more of the following: The CSI reporting configuration indicates a CSI-RS resource in the CSI-RS resource set that the WD (22) is to measure; and The DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD (22) is to measure.

33. The network node (16) according to any one of claims 25 to 32, wherein the network node (16) is further configured to: Transmitting beam assistance information indicating spatial correlation and quasi-co-located QCL relationship between one or more beams in the first set of beams, the beam assistance information being capable of being used as an input to the artificial intelligence model.

34. The network node (16) according to any one of claims 25 to 33, wherein the network node (16) is further configured to: Information about the predicted one or more sets of beams is received from the WD (22).

35. The network node (16) of claim 34, wherein the one or more network node actions include: Signaling is transmitted using one or more beams corresponding to the information about the predicted one or more sets of beams.

36. A method in a network node (16), the network node (16) being configured to communicate with a wireless device WD (22), the wireless device WD (22) being configured to at least predict a reference signal RS associated with the network node (16), the method comprising: sending (S158) a downlink DL RS configuration for configuring two or more sets of reference signal resources, the DL RS configuration comprising a first configuration for beams of a first set and a second configuration for beams of a second set, the beams of the second set being a subset of the beams of the first set; sending (S160) a CSI report configuration associated with the DL reference signal configuration; sending (S162) a first message, the first message requesting the WD (22) to measure a subset of DL RSs in a first set of DL RSs associated with the beams of the first set according to the CSI reporting configuration; receiving (S164) information about one or more RSs from the WD (22), the one or more RSs being predicted from the first set of DL RSs associated with the first set of beams based in part on one or more WD actions, the one or more WD actions being associated with an artificial intelligence model and being performed using at least measurements of the subset of DL RSs in the second set of DL RSs; as well as One or more network node actions are performed (S166) based on the information about the one or more RSs predicted from the first set of DL RSs.

37. The method of claim 36, wherein the method further comprises: A second message is sent, the second message requesting the WD (22) to measure the first set of DL RSs, the first set of DL RSs being sent less frequently than the second set of DL RSs.

38. The method according to any one of claims 36 to 37, wherein the method further comprises: Receiving a capability indication from the WD (22) indicating one or more of the following: Forecast support; support for spatial prediction beam reporting for predicting one or both of a beam in the first set of beams and a reference signal in an RS from the first set; a first maximum number of one or both of beams in the first set of beams and DL RSs in the first set of DL RSs; a second maximum number of one or both of beams in the second set of beams and DL RSs in the second set of DL RSs; a minimum number of one or both of beams in the second set of beams and DL RSs in the second set of DL RSs; Machine learning (ML) model processing capabilities associated with the artificial intelligence model; and Predicted performance for one or more combinations of the first set of DL RSs and the second set of DL RSs.

39. The method according to any one of claims 36 to 38, wherein the method further comprises: Sending a third message to the network node (16), wherein the third message includes uplink (UL) assistance information, wherein the UL assistance information includes one or more of the following: WD location information; an estimate of one or both of WD speed and WD rotation; Information about the WD antenna panel; and Information about the configuration and use of the WD antenna panel.

40. The method according to any one of claims 36 to 39, wherein the DL RS configuration comprises two CSI-RS resource sets, the two CSI-RS resource sets comprising: a first CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; as well as A second CSI-RS resource set has N CSI-RS resources associated with the beam of the second set.

41. The method of claim 40, wherein one or more of the following: The second CSI-RS resource set is a subset of the first CSI-RS resource set; The first set of CSI-RS resources and the second set of CSI-RS resources are linked via an association, the association indicating that the same beam from the network node (16) is to be used for the CSI-RS resources when the CSI-RS resources are transmitted as part of the first set of CSI-RS resources and when the CSI-RS resources are transmitted as part of the second set of CSI-RS resources; The association is explicitly configured according to a CSI-RS resource set; and The association is configured by a field in the CSI report configuration.

42. The method according to any one of claims 40 and 41, wherein one or more of the following: The CSI report configuration includes two report settings, each report setting points to a CSI-RS resource set, each report setting is configured with a parameter, and when the two report settings are configured with the same parameter, the two CSI-RS resource sets associated with the two report settings are assumed to be linked together; The association is explicitly configured in a resource setting; explicitly indicating that the two CSI-RS resource sets are linked together; The CSI-RS resources in the first CSI-RS resource set and the CSI-RS resources in the second CSI-RS resource set are one of the same CSI-RS resources and different CSI-RS resources; The association of the two CSI-RS resources is explicitly configured according to the CSI-RS resources; The association of two CSI-RS resources is explicitly configured in a table; The association of the two CSI-RS resources is dynamically indicated; The first CSI-RS resource set and the second CSI-RS resource set have one of the same time domain behavior and different time domain behaviors.

43. A method according to any one of claims 36 to 39, wherein: The DL RS configuration includes: a first single CSI-RS resource set having M CSI-RS resources associated with a beam of the first set; or a second single CSI-RS resource set having N CSI-RS resources associated with beams of the second set; and One or more of the following: The CSI reporting configuration indicates a CSI-RS resource in the CSI-RS resource set that the WD (22) is to measure; and The DL RS configuration indicates which CSI-RS resources in the CSI-RS resource set the WD (22) is to measure.

44. The method according to any one of claims 36 to 43, wherein the method further comprises: Transmitting beam assistance information indicating spatial correlation and quasi-co-located QCL relationship between one or more beams in the first set of beams, the beam assistance information being capable of being used as an input to the artificial intelligence model.

45. The method according to any one of claims 36 to 44, wherein the method further comprises: Information about the predicted one or more sets of beams is received from the WD (22).

46. ​​The method of claim 45, wherein the one or more network node actions include: Signaling is transmitted using one or more beams corresponding to the information about the predicted one or more sets of beams.

Images