Rule-based ensuring consistency between training and inference

Abstract

Systems, methods, apparatuses, and computer program products for consistency between training and inference. A method may include receiving from at least one user equipment during a training phase, a report based on at least one measurement performed based on a first rule. The method may further include training at least one model using the report based on the at least one measurement performed based on the first rule transmitted with a first configuration. The method may further include receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on a second rule. In addition, the method may include performing prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with a second configuration during the inference phase.

Description

RULE-BASED ENSURING CONSISTENCY BETWEEN TRAINING AND INFERENCETECHNICAL FIELD

[0001] The examples and non-limiting example embodiments relate generally to communications and, more particularly, to rule-based ensuring consistency between training and inference.BACKGROUND

[0002] A communication device may gain access to a communication network through an access network node.SUMMARY

[0003] In accordance with an aspect, an apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; perform the at least one measurement based on the first rule received with the first configuration during the training phase; transmit, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; perform the at least one measurement based on the second rule received with the second configuration during the inference phase; and transmit, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

[0004] In accordance with an aspect, an apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to at least one user equipment, at least one configurationcomprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; receive, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; train, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; receive, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; and perform, during the inference phase, prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase.

[0005] In accordance with an aspect, an apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine at least one rule for performing at least one measurement; wherein the at least one rule for performing the at least one measurement comprises a first rule for performing the at least one measurement during a training phase and a second rule for performing the at least one measurement during an inference phase; perform the at least one measurement based on the first rule during the training phase; transmit, to a network, a report based on the at least one measurement performed based on the first rule during the training phase; perform the at least one measurement based on the second rule during the inference phase; and transmit, to the network, a report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement during the training phase is the same as the second rule for performing the at least one measurement during the inference phase.

[0006] In accordance with an aspect, an apparatus includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, causethe apparatus at least to: receive, from at least one user equipment during a training phase, a report based on at least one measurement performed based on a first rule during the training phase; train, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule during the training phase; receive, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on a second rule during the inference phase; and perform, during the inference phase, prediction using the at least one model and the report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule for performing the at least one measurement used to perform the prediction during the inference phase.BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The foregoing aspects and other features are explained in the following description, taken in connection with the accompanying drawings.

[0008] FIG. 1 is a block diagram of one possible and non-limiting system in which the example embodiments may be practiced.

[0009] FIG. 2 shows multi-TRP operation in FR2.

[0010] FIG. 3A shows a first portion of a signaling flowchart with rule-based consistency for an NW-sided model.

[0011] FIG. 3B shows a second portion of a signaling flowchart with rule-based consistency for an NW-sided model, where FIG. 3A shows the first portion.

[0012] FIG. 4 shows an example of input / output of Tx beam pair prediction for group-based beam reporting.

[0013] FIG. 5 shows an example of input / output of Tx beam pair prediction for group-based beam reporting when a UE specific type is considered as one additional input to the AI / ML model.

[0014] FIG. 6 shows an example of input / output of Tx beam pair prediction for group-based beam reporting in a temporal domain.

[0015] FIG. 7 shows an example of input / output of Tx beam pair prediction for group-based beam reporting in a temporal domain when a UE specific type is considered as one additional input to the AI / ML model.

[0016] FIG. 8 is an example apparatus configured to implement the examples described herein.

[0017] FIG. 9 shows a representation of an example of non-volatile memory media used to store instructions that implement the examples described herein.

[0018] FIG. 10 is an example method, based on the examples described herein.

[0019] FIG. 11 is an example method, based on the examples described herein.

[0020] FIG. 12 is an example method, based on the examples described herein.

[0021] FIG. 13 is an example method, based on the examples described herein.DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0022] Turning to FIG. 1, this figure shows a block diagram of one possible and nonlimiting example in which the examples may be practiced. A user equipment (UE) 110, radio access network (RAN) node 170, and network element(s) 190 are illustrated. In the example of FIG. 1, the user equipment (UE) 110 is in wireless communication with a wireless network 100. A UE is a wireless device that can access the wireless network 100. The UE 110 includes one or more processors 120, one or more memories 125, and one or more transceivers 130 interconnected through one or more buses 127. Each of the one or more transceivers 130 includes a receiver, Rx, 132 and a transmitter, Tx, 133. The one or more buses 127 may be address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, and the like. The one or more transceivers 130 are connected to one or more antennas 128. The one or more memories 125 include computer program code 123. The UE 110 includes a module 140, comprising one of or both parts 140-1 and / or 140- 2, which may be implemented in a number of ways. The module 140 may be implemented in hardware as module 140-1, such as being implemented as part of the one or more processors 120. The module 140-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the module 140 may beimplemented as module 140-2, which is implemented as computer program code 123 and is executed by the one or more processors 120. For instance, the one or more memories 125 and the computer program code 123 may be configured to, with the one or more processors 120, cause the user equipment 110 to perform one or more of the operations as described herein. The UE 110 communicates with RAN node 170 via a wireless link 111.

[0023] The RAN node 170 in this example is a base station that provides access for wireless devices such as the UE 110 to the wireless network 100. The RAN node 170 may be, for example, a base station for 5G, also called New Radio (NR). In 5G, the RAN node 170 may be a NG-RAN node, which is defined as either a gNB or an ng-eNB. A gNB is a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface (such as connection 131) to a 5GC (such as, for example, the network element(s) 190). The ng-eNB is a node providing E-UTRA user plane and control plane protocol terminations towards the UE, and connected via the NG interface (such as connection 131) to the 5GC. The NG-RAN node may include multiple gNBs, which may also include a central unit (CU) (gNB-CU) 196 and distributed unit(s) (DUs) (gNB-DUs), of which DU 195 is shown. Note that the DU 195 may include or be coupled to and control a radio unit (RU). The gNB-CU 196 is a logical node hosting radio resource control (RRC), SDAP and PDCP protocols of the gNB or RRC and PDCP protocols of the en-gNB that control the operation of one or more gNB-DUs. The gNB-CU 196 terminates the Fl interface connected with the gNB -DU 195. The Fl interface is illustrated as reference 198, although reference 198 also illustrates a link between remote elements of the RAN node 170 and centralized elements of the RAN node 170, such as between the gNB-CU 196 and the gNB- DU 195. The gNB -DU 195 is a logical node hosting RLC, MAC and PHY layers of the gNB or en-gNB, and its operation is partly controlled by gNB-CU 196. One gNB-CU 196 supports one or multiple cells. One cell may be supported with one gNB -DU 195, or one cell may be supported / shared with multiple DUs under RAN sharing. The gNB-DU 195 terminates the Fl interface 198 connected with the gNB-CU 196. Note that the DU 195 is considered to include the transceiver 160, e.g., as part of a RU, but some examples of this may have the transceiver 160 as part of a separate RU, e.g., under control of and connected to the DU 195. The RAN node 170 may also be an eNB (evolved NodeB) base station, for LTE (long term evolution), or any other suitable base station or node.

[0024] The RAN node 170 includes one or more processors 152, one or more memories155, one or more network interfaces (N / W I / F(s)) 161, and one or more transceivers 160 interconnected through one or more buses 157. Each of the one or more transceivers 160 includes a receiver, Rx, 162 and a transmitter, Tx, 163. The one or more transceivers 160 are connected to one or more antennas 158. The one or more memories 155 include computer program code 153. The CU 196 may include the processor(s) 152, one or more memories 155, and network interfaces 161. Note that the DU 195 may also contain its own memory / memories and processor(s), and / or other hardware, but these are not shown.

[0025] The RAN node 170 includes a module 150, comprising one of or both parts 150-1 and / or 150-2, which may be implemented in a number of ways. The module 150 may be implemented in hardware as module 150-1, such as being implemented as part of the one or more processors 152. The module 150-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the module 150 may be implemented as module 150-2, which is implemented as computer program code 153 and is executed by the one or more processors 152. For instance, the one or more memories 155 and the computer program code 153 are configured to, with the one or more processors 152, cause the RAN node 170 to perform one or more of the operations as described herein. Note that the functionality of the module 150 may be distributed, such as being distributed between the DU 195 and the CU 196, or be implemented solely in the DU 195.

[0026] The one or more network interfaces 161 communicate over a network such as via the links 176 and 131. Two or more gNBs 170 may communicate using, e.g., link 176. The link 176 may be wired or wireless or both and may implement, for example, an Xn interface for 5G, an X2 interface for LTE, or other suitable interface for other standards.

[0027] The one or more buses 157 may be address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, wireless channels, and the like. For example, the one or more transceivers 160 may be implemented as a remote radio head (RRH) 195 for LTE or a distributed unit (DU) 195 for gNB implementation for 5G, with the other elements of the RAN node 170 possibly being physically in a different location from the RRH / DU 195, and the one or more buses 157 could be implemented in part as, for example, fiber optic cable or other suitable network connection to connect the other elements (e.g., a central unit (CU), gNB-CU 196) of the RAN node 170 to the RRH / DU 195. Reference198 also indicates those suitable network link(s).

[0028] A RAN node / gNB can comprise one or more TRPs to which the methods described herein may be applied. FIG. 1 shows that the RAN node 170 comprises TRP 51 and TRP 52, in addition to the TRP represented by transceiver 160. Similar to transceiver 160, TRP 51 and TRP 52 may each include a transmitter and a receiver. The RAN node 170 may host or comprise other TRPs not shown in FIG. 1.

[0029] A relay node in NR is called an integrated access and backhaul node. A mobile termination part of the IAB node facilitates the backhaul (parent link) connection. In other words, the mobile termination part comprises the functionality which carries UE functionalities. The distributed unit part of the IAB node facilitates the so called access link (child link) connections (i.e. for access link UEs, and backhaul for other IAB nodes, in the case of multi-hop IAB). In other words, the distributed unit part is responsible for certain base station functionalities. The IAB scenario may follow the so called split architecture, where the central unit hosts the higher layer protocols to the UE and terminates the control plane and user plane interfaces to the 5G core network.

[0030] It is noted that the description herein indicates that “cells” perform functions, but it should be clear that equipment which forms the cell may perform the functions. The cell makes up part of a base station. That is, there can be multiple cells per base station. For example, there could be three cells for a single carrier frequency and associated bandwidth, each cell covering one-third of a 360 degree area so that the single base station’s coverage area covers an approximate oval or circle. Furthermore, each cell can correspond to a single carrier and a base station may use multiple carriers. So if there are three 120 degree cells per carrier and two carriers, then the base station has a total of 6 cells.

[0031] The wireless network 100 may include a network element or elements 190 that may include core network functionality, and which provides connectivity via a link or links 181 with a further network, such as a telephone network and / or a data communications network (e.g., the Internet). Such core network functionality for 5G may include location management functions (LMF(s)) and / or access and mobility management function(s) (AMF(S)) and / or user plane functions (UPF(s)) and / or session management function(s) (SMF(s)). Such core network functionality for LTE may include MME (mobility management entity) / SGW (serving gateway) functionality. Such core network functionality may include SON (self-organizing / optimizing network) functionality. These are merely example functions that may be supported by the network element(s) 190, and note that both 5G and LTE functions might be supported. The RAN node 170 is coupled via a link 131 to the network element 190. The link 131 may be implemented as, e.g., an NG interface for 5G, or an SI interface for LTE, or other suitable interface for other standards. The network element 190 includes one or more processors 175, one or more memories 171, and one or more network interfaces (N / W I / F(s)) 180, interconnected through one or more buses 185. The one or more memories 171 include computer program code 173. Computer program code 173 may include SON and / or MRO functionality 172.

[0032] The wireless network 100 may implement network virtualization, which is the process of combining hardware and software network resources and network functionality into a single, software-based administrative entity, or a virtual network. Network virtualization involves platform virtualization, often combined with resource virtualization. Network virtualization is categorized as either external, combining many networks, or parts of networks, into a virtual unit, or internal, providing network-like functionality to software containers on a single system. Note that the virtualized entities that result from the network virtualization are still implemented, at some level, using hardware such as processors 152 or 175 and memories 155 and 171, and also such virtualized entities create technical effects.

[0033] The computer readable memories 125, 155, and 171 may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, non-transitory memory, transitory memory, fixed memory and removable memory. The computer readable memories 125, 155, and 171 may be means for performing storage functions. The processors 120, 152, and 175 may be of any type suitable to the local technical environment, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on a multi-core processor architecture, as nonlimiting examples. The processors 120, 152, and 175 may be means for performing functions, such as controlling the UE 110, RAN node 170, network element(s) 190, and other functions as described herein.

[0034] In general, the various example embodiments of the user equipment 110 can include, but are not limited to, cellular telephones such as smart phones, tablets, personal digitalassistants (PDAs) having wireless communication capabilities, portable computers having wireless communication capabilities, image capture devices such as digital cameras having wireless communication capabilities, gaming devices having wireless communication capabilities, music storage and playback devices having wireless communication capabilities, internet appliances including those permitting wireless internet access and browsing, tablets with wireless communication capabilities, head mounted displays such as those that implement virtual / augmented / mixed reality, as well as portable units or terminals that incorporate combinations of such functions. The UE 110 can also be a vehicle such as a car, or a UE mounted in a vehicle, a UAV such as e.g. a drone, or a UE mounted in a UAV. The user equipment 110 may be a terminal device, such as mobile phone, mobile device, sensor device etc., the terminal device being a device used by the user or not used by the user.

[0035] UE 110, RAN node 170, and / or network element(s) 190, (and associated memories, computer program code and modules) may be configured to implement (e.g. in part) the methods described herein. Thus, computer program code 123, module 140-1, module 140-2, and other elements / features shown in FIG. 1 of UE 110 may implement user equipment related aspects of the examples described herein. Similarly, computer program code 153, module 150-1, module 150-2, and other elements / features shown in FIG. 1 of RAN node 170 may implement gNB / TRP related aspects of the examples described herein. Computer program code 173 and other elements / features shown in FIG. 1 of network element(s) 190 may be configured to implement network element related aspects of the examples described herein.

[0036] Having thus introduced a suitable but non-limiting technical context for the practice of the example embodiments, the example embodiments are now described with greater specificity.

[0037] The examples described herein relate to a 6G NW-sided model for beam-pair prediction in a Multi-TRP scenario.

[0038] Rel-18 / Rel-19 AI-ML for beam prediction:

[0039] AI / ML-based beam management includes leveraging AI / ML models to predict the best beam(s) based on a limited set of measurements. Two sub-use cases include spatial- domain prediction and time-domain prediction. Spatial-Domain Prediction relates to beam prediction based on a limited set of measurements that does not contain any historicalinformation. Time-Domain Prediction relates to Beam prediction into the future based on a limited set of measurements that contains historical information. Measurements and prediction are based on two Beam Sets, Set A and Set B. Set A is the complete set of beams over which the prediction operates. Set B is the set of beams whose measurements are inputted to the AI / ML model (e.g., Ll-RSRP, etc.). Set B can be: different from Set A (spacedomain and time-domain prediction), or A subset of Set A (space-domain and time-domain prediction), or the Same as Set A (time-domain prediction).

[0040] RAN #102 meeting approved the Rel-19 WI on AI / ML for NR Air Interface [RP- 234039], based on the AI / ML techniques to NR air interface has been studied in FS_NR_AIML_Air [TR 38.843]. Described herein are enhancements related to AI / ML for beam management, and the related to objectives are as follows:

[0041] One initial use case includes beam management, e.g., beam prediction in the spatial domain (BM-Casel) and beam prediction in the time domain (BM-Case2) for overhead and latency reduction, which is the focus of the examples described herein.

[0042] Group-based beam reporting (Rel-15 / 17 summary)

[0043] Group-based beam reporting has been supported since NR Rel-15 and further optimized in Rel-17 to support multi-TRP operations. The features of group-based beam reporting are summarized as follows. Rel-15 group-based beam reporting (groupBasedBeamReporting) allows UE to report two beams that can be received simultaneously by the UE. The UE is unaware that two beams are from the same TRP or different TRPs. Rel-15 reporting is valid for Ll-RSRP or Ll-SINR reporting (a CSI- ReportConfig with reportQuantity set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-RSRP-Capability [Set]Index', 'ssb-Index-RSRP-Capability[Set]Index', 'cri-SINR', 'ssb-Index-SINR', 'cri-SINR- Capability[Set]Index' or 'ssb-Index-SINR-Capability[Set]Index' ). Rel-17 group-based beam reporting allows UE to report group(s) of two CRIs or SSBRIs selecting one CSI-RS or SSB from each of the two CSI Resource Sets for the report setting, where CSI-RS and / or SSB resources of each group can be received simultaneously by the UE. Here, the UE is aware of the beam to TRP association, and reported beams in a beam group are from different TRPs. Rel-17 group-based beam reporting (groupBasedBeamReporting-rl7) is supported by configuring the UE two CSI Resource Sets. Otherwise, the number of CSI-RS Resource Sets configured is limited to one. Rel-17 reporting is valid for Ll-RSRP reporting (a CSI- ReportConfig with reportQuantity set to 'cri-RSRP', 'ssb-Index-RSRP', 'cri-RSRP-Capability [Set]Index', or 'ssb-Index-RSRP-Capability [Set]Index').

[0044] Described herein is a method of NW-sided model beam-pair prediction for multi- TRP scenario, where the AI / ML model inference operation is considered for each TRP. As the examples described herein focus on the method of NW-sided model beam-pair prediction for the multi-TRP scenario, where the AI / ML model inference operation is considered for each TRP, the examples described herein do not just focus on an AI / ML BM for single-TRP or a UE-sided model prediction for a multi-TRP scenario. The examples described herein relate to NW-sided model prediction and rule-based consistency.

[0045] FIG. 2 shows MP-UE 110 comprising panel #1, panel #2, and panel #3. Panel #1 receives one or more transmissions on beam #P1 and / or beam #P2 of TRP 1 (51, 251). Panel #2 receives one or more transmissions on beam #Q1 and / or #Q2 of TRP 2 (52, 252). TRP1 51 and TRP2 52 may be of the same RAN node 170, or TRP1 251 may be of a first RAN node and TRP2 252 may be of a second RAN node different from the first RAN node, where the first RAN node and the second RAN node are configured similar to RAN node 170 shown in FIG. 1.

[0046] Referring to FIG. 2, to support multi-TRP (m-TRP) operations, the UE 101 could use multiple panels, as beams shall be received from different panels such that simultaneous reception is facilitated. As illustrated in FIG. 2, not all beams may be suitable for joint transmission towards the UE 110. In particular, FIG. 2 shows multi-TRP operation in FR2. The UE 110 cannot simultaneously receive beams #Q3 and #P1 (or #P2) as they are received at the same panel.

[0047] In other words, there are not many occasions in FR2 where a UE would be able to receive simultaneously from two TRPs unless the UE has different panels, and hence the benefit for the network of scheduling transmission on both beams is questionable. This is solved in Rel-17 group-based beam reporting, beams are divided into the two sets and reporting can be done for beam groups. However, the beams used by each TRP should separately follow beam refinement and pairs of beams (beam group) may be reported after such beam refinement stages per TRP.

[0048] Each TRP has to transmit a large number of reference signals like SSBs and CSI- RSs, which cause overhead concerns as each beam is associated to a different SSB or CSI- RS resource.

[0049] Beam-pair prediction helps to reduce the frequency of measurements reporting, where the beam-pair corresponds to beams from each UE panel pairs with TRP (two TRP can serve UE at the same time). The NW or UE can perform beam-pair prediction by using measured small set of beams, therefore, it is not necessary for NW to configure UE to report full set of beam measurements to NW.

[0050] However, when the NW performs Tx beam-pair prediction, how to ensure the consistency between AI / ML model training phase and inference phase is still open. Also, when the consistency condition between training phase and inference phase is ensured, howto configure UE to report beam measurements with simultaneous reception, e.g., during inference phase.

[0051] Consistency between training and inference

[0052] For a NW-sided beam pair prediction, to ensure the consistency between training and inference, a rule-based consistency (including some signaling) is introduced, and the details are as follows: Different UEs might be configured with different number of panels, e.g., one UE might have two panels, another UE might have four panels. A four-panel UE may use all or sub-set of four panels for measurements during the inference phase (inference is reported to the NW without the panel information), while a two-panel UE may use just two panels for measurements during the data collection for training. There may be clear inconsistency that the NW-sided model performance may degrade due to this.

[0053] Rule-based consistency is introduced as follows: As the UE may use UE-specific rule for measurements (e.g., Ll-RSRP from two TRPs) in the training data collection and the information on UE-specific rule for measurements (can refer as “rule-based consistency” information) should be reported to the NW, the details are further explained in Section 7. The NW may collect data from different UEs and consider the ‘rule-based consistency’ information when categorizing the datasets for model training. In one variant, after model training based on the collected data, the NW may consider the rule-based consistency information as metadata of a ML model. When the NW wish to use beam pair prediction (inference phase), the NW may indicate or receive by the UE ‘rule-based consistency” information, the details are further explained in Section 7. The NW may use the received measurements corresponding to the aligned rule-based consistency information with a corresponding matching model (selected based on the rule-based information) to predict best beam pairs towards the UE.

[0054] Measurements and reporting for inference operation

[0055] In the context of multi TRP measurements, the NW can configure the UE to report measurements and other additional information as follows: The UE receives a CSI (beam) report configuration (e.g., CSI-reportConfig in NR) where it configures / indicates two measurements sets of beams (corresponding to SetBl from TRP-1 and SetB2 from TRP-2) for measurements, as highlighted before, the UE can be configured to consider “rule-based consistency” information, to perform measurements. The UE reports quantities (configuredas beam pair report or best beam report) associated with the measurements corresponding to both SetBl and SetB2 to NW. In one variant, as the reporting quantities, the UE may report Top-N best beam-pairs and corresponding Ll-RSRP (or Ll-SINR) corresponding to two TRPs according to the rule-based consistency defined to the UE. In another variant, as the reporting quantities, the UE may report Top-N best beams and corresponding Ll-RSRP (or Ll-SINR) corresponding to each TRPs according to the rule-based consistency defined to the UE. More details are in Embodiment 5.

[0056] NW-sided beam pair prediction

[0057] A beam-pair prediction at the NW-sided is as follows, where a NW entity (primary TRP, gNB, or serving cell TRP) uses a ML model that consider following measurements at the ML model input and produce output quantities at the ML model output. “Rule-based consistency”, discussed earlier, may consider at the model input depending on when a generalized model is developed for multiple UE-types or in the model selection when different models are developed for multiple UE-types.

[0058] For NW-side model development, the following aspects are considered. For Spatial Domain beam-pair prediction, model input includes variant 1 and variant 2. Model input variant 1: At least beam level measurements, i.e., Ll-RSRPs of SetBl and Ll-RSRPs of SetB2, are used at the model input. Model input variant 2: At least beam pair information and corresponding measurements, i.e., N best beam pairs and corresponding Ll-RSRPs from SetBl and SetB2 for simultaneous reception at the UE, are used at the model input. Additionally, some other information (angle information, TRP location information, history of measurements) and pre-processing stages can be considered at the model input.

[0059] For NW-side model development, the following aspects are considered. For Spatial Domain beam-pair prediction, model output may include predicted best Top-K (including K=l) beam pairs (beam IDs) from Set Al and Set A2, and additionally, predicted RSRP of best Top-K beam pairs (beam IDs) from Set Al and Set A2, and additionally, probability values of best Top-K beam pairs (beam IDs) from Set Al and Set A2. Set Bl and Set Al may corresponding to a first TRP (or PCI / CORESETPoolIndex) and Set B2 and Set A2 may correspond to a second TRP (or PCI / CORESETPoolIndex)

[0060] For Temporal Domain beam-pair prediction: further details are provided in the description of Embodiment 4.

[0061] Described herein are methods for beam-pair prediction for both spatial domain and temporal domain, where UE supports multi-TRP operation with simultaneous reception feature. The UE with simultaneous reception (single DCI or multi-DCI) is required to report beam pairs that the UE can receive simultaneously.

[0062] For beam-pair prediction in spatial domain: the output of beam-pairs prediction could be Top-K Tx predicted beam-pair (PCRI-beam-pair or PSSBRI-beam-pair) or Top-K Tx predicted-beam-pair-Ll-RSRP (PRSRP-beam-pair) in next future time stance.

[0063] For BM-Case2: the output of beam-pairs prediction could be Top-K Tx predicted- beam-pair (PCRI-beam-pair or PSSBRI-beam-pair) or Top-K Tx predicted-beam-pair-Ll- RSRP (PRSRP-beam-pair) in multiple future time stances.

[0064] Embodiment 1: Rule-based consistency for NW-sided model training and inference

[0065] The rule-based consistency is as follows:

[0066] Option 1 : UE may determine and uses UE-specific rule for measurements in data collection for AI / ML model training and the information on UE-specific rule for measurements. In one variant, UE reports its specific type for NW data collection for AI / ML model training measurements (e.g., Ll-RSRP from two TRPs) and the information on UE- specific rule for measurements (“rule-based consistency” information). In another variant, the UE can report UE-specific rule by reporting the UE-panels which are used for data collection. Here, the UE may disclose explicit information on UE-panel assumptions (additionally any other UE-specific Rx beam assumptions, antenna set-ups) for collecting measurements. In another variant, the UE can report UE-specific rule by reporting an identifier (e.g., UE-associated ID) that is applicable for data collection. The identifier may be unique to a UE vendor where it carries implicit information on UE-panel assumptions (and other UE-specific Rx beam assumptions, antenna set-ups) used when collecting measurements from multiple TRPs. In another variant, the UE can determine rule-based consistency and trigger the rules to NW. The NW may collect data from different UEs and consider the ‘rule-based consistency’ information when categorizing the datasets for model training. In one variant, after model training based on the collected data, the NW may consider the rule-based consistency information as metadata of a ML model.

[0067] Option 2 : NW could indicate or receive by the UE “rule-based consistency”information. When the NW wish to use beam pair prediction (inference phase), the NW may indicate or receive by the UE ‘rule-based consistency” information. In one variant, the NW may indicate the ‘rule-based consistency” information to a UE which support measurements for inference operation, and the UE is expected to use the information provided by the NW to do the measurements corresponding to the multiple TRPs. In another variant, the NW may receive the ‘rule-based consistency” information from a UE, prior to inference operation, and the UE is expected (when enabled by the NW) to use the information provided by the UE when doing the measurements corresponding to the multiple TRPs. The NW may use the received measurements corresponding to the aligned rule-based consistency information with a corresponding matching model (selected based on the rule-based information) to predict best beam pairs towards the UE.

[0068] FIG. 3A and FIG. 3B shows embodiment 2, and in particular a signaling flowchart with rule-based consistency for NW-sided model. FIG. 3A and FIG. 3B show a signaling exchange between UE 110 and the network that includes TRP1 (51, 251) and TRP 2 (52, 252).

[0069] Step 1 is the training phase comprised of steps 2-17.

[0070] Step 2: UE sends capability indication group-based beam reporting) to NW. The capability message may include, e.g., (i) a parameter indicating the maximum number of measured RS resources (M_max) to be reported in one report instance, e.g., M_max may be up to 8 beams report, (ii) UE type indicator (e.g., UE has two panels or four panels that are capable to support multi- TRP joint DLUL or only UL mode).

[0071] Step 3: NW determines the CSI report configuration based on UE capability reporting, and The NW may determine CSI report configuration based on the configured RS resource set (resources for channel measurement, SetBl and SetB2).

[0072] For training phase:

[0073] Step 4: NW configures CSI-ReportConfig with group-based beam reporting and indicate RS sets (Set B1 / B2) for AI / ML beam prediction.

[0074] Step 5: NW sends CSI report configuration containing the measurement reporting indication of RS resources (NZP-CSI-RS resources and / or SSB resources of SetBl andSetB2). For example, SSB indices in CSI-SSB-ResourceSet of SetBl and SSB indices in CSI- SSB-ResourceSet of SetB2.

[0075] Option 1: NW sends rule-based consistency information to UE 110.

[0076] Step 7: NW sends data collection configuration (transmit RS SetBl), e.g., through CSI-ReportConfig or MAC-CE (including configuring UE to follow rule-based consistency).

[0077] Step 8: NW sends data collection configuration (transmit RS SetB2), e.g., through CSI-ReportConfig or MAC-CE (including configuring UE to follow rule-based consistency).

[0078] Step 9: Based on the received reporting configuration, the UE performs measurement reporting according to rule-based consistency.

[0079] Step 10: UE sends CSI report (SetBl and SetB2) to NW for beam-pair prediction.

[0080] Step 11 : NW performs offline training for Top-K beam pairs prediction.

[0081] Option 2 : UE determines rule-based consistency by itself.

[0082] Step 13: NW sends data collection configuration (transmit RS SetBl), e.g., through CSI-ReportConfig or MAC-CE (including configuring UE to follow rule-based consistency).

[0083] Step 14: NW sends data collection configuration (transmit RS SetB2), e.g., through CSI-ReportConfig or MAC-CE (including configuring UE to follow rule-based consistency).

[0084] Step 15: UE determines rule-based consistency.

[0085] Step 16: Based on the received reporting configuration, the UE performs measurement reporting according to rule-based consistency (determined in Step 9).

[0086] Step 17: UE sends CSI report (SetB 1 and SetB2) to NW and UE could send the rulebased consistency to NW in the same CSI report or UE could send rule-based consistency separately, e.g., through another CSI report or MAC-CE.

[0087] For Inference phase:

[0088] Step 18 shows the inference phase including steps 18-33.

[0089] Step 19: UE sends capability indication group-based beam reporting) to NW.

[0090] Step 20: NW configures CSI-ReportConfig with group-based beam reporting and indicate RS sets (Set B1 / B2).

[0091] Step 21: NW sends CSI report configuration containing the measurement reporting indication of RS resources (NZP-CSI-RS resources and / or SSB resources of SetBl and SetB2). For example, SSB indices in CSI-SSB-ResourceSet of SetBl and SSB indices in CSI- SSB-ResourceSet of SetB2.

[0092] Step 22: UE determines an association of RS Set-to-CORESETPoolIndex (Set Bl - > CORESETPoolindex 1 / TRP-l and Set B2 -> CORESETPoolindex 2 / TRP-2 ).

[0093] Option 1 : NW sends rule-based consistency information to UE.

[0094] Step 24: NW sends data collection configuration (transmit RS SetBl), e.g., through CSI-ReportConfig or MAC-CE (including configuring UE to follow rule-based consistency).

[0095] Step 25: NW sends data collection configuration (transmit RS SetB2), e.g., through CSI-ReportConfig or MAC-CE (including configuring UE to follow rule-based consistency).

[0096] Step 26: Based on the received reporting configuration, the UE performs measurement reporting according to rule-based consistency (same rule as in training phase).

[0097] Step 27 : NW sends CSI report configuration containing the measurement reporting indication of RS resources (NZP-CSI-RS resources and / or SSB resources of SetBl and SetB2). For example, SSB indices in CSI-SSB-ResourceSet of SetBl and SSB indices in CSI- SSB-ResourceSet of SetB2.

[0098] Option 2 : UE determines rule-based consistency by itself.

[0099] Step 29: NW sends data collection configuration (transmit RS SetBl), e.g., through CSI-ReportConfig or MAC-CE (including configuring UE to follow rule-based consistency).

[0100] Step 30: NW sends data collection configuration (transmit RS SetB2), e.g., through CSI-ReportConfig or MAC-CE (including configuring UE to follow rule-based consistency).

[0101] Step 31: UE determines rule-based consistency.

[0102] Step 32: Based on the received reporting configuration, the UE performs measurement RS of RS SetBl and SetB2 according to rule-based consistency (determined inStep 30), wherein the rule is the same as in training phase.

[0103] Step 33: UE sends CSI report (SetBl and SetB2) to NW for beam-pair prediction.

[0104] Step 34: NW performs Top-K beam-pairs prediction.

[0105] Embodiment 3: NW-sided beam pair prediction (Spatial domain multi-TRP Tx beam-pair prediction) : Implementation

[0106] In one example, for spatial domain Tx beam-pair prediction at NW-side, the NW might deploy convolutional neural network (CNN) model (other models are also possible) to predict Top-K Tx best beam-pair from Set Al (TRP-1) and Set A2 (TRP-2).

[0107] FIG. 4 shows an example of input / output of Tx beam pair prediction for group-based beam reporting. FIG. 5 shows an example of input / output of Tx beam pair prediction for group-based beam reporting, when the UE specific type 520 is considered as one additional input to the AI / ML model.

[0108] Referring to FIG. 4 and FIG. 5, CNN could be used for prediction (411, 511) where the first layer of neural network could be concatenate layer, such that the input could be concatenated before passing through convolutional layers, pooling layers, fully connected layers, and batch normalization layer. Eastly, in order to obtain Top-K Tx beam-pair IDs the SoftMax function could be used to obtain the probability of Tx beam-pairs output and then NW ranks these probabilities to select Top-K Tx beam-pairs. However, other models are also possible (not limited to CNN).

[0109] Referring to FIG. 4 and FIG. 5, the input for AI / ME model can be (i) El-RSRP measurements of Set Bl beams (xl,. . .,xN) CSI-RS resources (402, 502), (ii) El-RSRP of Set B2 (yl,. . -,yN) CSI-RS resources (404, 504) and (iii) Top-N best Tx beam-pair (from both Set Bl and Set B2) for simultaneous reception at the UE (406, 506), wherein Set Bl may be a subset of Set Al and Set B2 may be a subset of Set A2 or Set Bl and Set Al may differ and Set B2 and Set A2 may differ (e.g., Set Bl and Set B2 are wide-beams and Set Al and Set A2 are narrow beams). CRI of Set B 1 beams and CRI of Set B2 beams could be used as input to AI / ML model as well (optional).

[0110] The output could be (i) Top-K predicted beam pairs (beam IDs), e.g., predicted beam pairs CRI (PCRI_xi, PCRI_yl),. . .until, Kth (PCRI_xl, PCRI_yp) from Set Al and Set A2, orpredicted beam pairs SSBRI (‘pSSBRI_xi, pSSBRI_yl’),... until, Kth (PSSBRI_xl, PSSBRI_yp) from Set Al and Set A2 (412, 512), or (ii) Predicted RSRP of best Top-K beam pairs (beam IDs), e.g., predicted RSRP (PRSRP_xi, PRSRP_yl),... until, Kth (PRSRP_xl, PRSRP_yp) from Set Al and Set A2 (414, 514), or (iii) Top-K predicted beam pairs (beam IDs) and Predicted RSRP of best Top-K beam pairs (beam IDs), e.g., (PCRI_xi, PCRI_yl) and (PRSRP_ xj, PRSRP_ yl) until, Kth (PCRI_xj, PCRI_yl) and (PRSRP_ xl, PRSRP_ yp) (416, 516), or (iv) Probability values of best Top-K beam pairs (beam IDs) from Set Al and Set A2.

[0111] The NW may use Rx panel #ID (corresponding to UE specific type#ID regarding rule-based consistency) as one additional input to AI / ML model. The UE type could be obtained through rule-based consistency.

[0112] Embodiment 4: NW-sided beam pair prediction (Temporal domain multi-TRP Tx beam-pair prediction) : Implementation

[0113] FIG. 6 shows an example of input / output of Tx beam pair prediction for group-based beam reporting in the temporal domain prediction. LSTM or transformer or auto encoderdecoder could be used for prediction. FIG. 7 shows an example of input / output of Tx beam pair prediction for group-based beam reporting for temporal domain prediction, wherein the UE specific type 720 could be considered as one of input to AI / ML model.

[0114] Referring to FIG. 6 and FIG. 7, in one example, for temporal domain Tx beam-pair prediction (611, 711) at NW-side, the NW might deploy long-short-term-memory (LSTM) model or transformer model or auto encoder-decoder model for time series prediction to predict Top-K Tx best beam-pair from Set Al (TRP-1) and Set A2 (TRP-2) in multiple future time instances. Other models are also possible.

[0115] Referring to FIG. 6 and FIG. 7, the input for the AI / ML model can be (i) Historical of Ll-RSRP measurements of Set Bl beams (xl,...,xN) CSLRS resources (602, 702), (ii) Historical of Ll-RSRP of Set B2 (yl,...,yN) CSI-RS resources (604, 704) and (iii) Historical of Top-N best Tx beam-pair (from both Set Bl and Set B2) for simultaneous reception at the UE (606, 706), wherein Set Bl may be a subset of Set Al and Set B2 may be a subset of Set A2 or Set Bl and Set Al may differ and Set B2 and Set A2 may differ (e.g., Set Bl and Set B2 are wide-beams and Set Al and Set A2 are narrow beams). Historical information of CRI of Set B 1 beams and CRI of Set B2 beams could be used as input to AI / ML model as well(optional).

[0116] However, other AI / ML models for time series prediction, e.g., Arima model might be used.

[0117] In all the possible models, the SoftMax function could be consider after the last layer of AI / ML model to obtain the probability of Tx beam-pairs output in single or multiple future time instances and then NW ranks these probabilities to select Top-K Tx beam-pairs in single or multiple future time instances.

[0118] The output could be Top-K predicted beam-pair IDs, e.g., predicted CRI (PCRI_xi, PCRI_yl) for time t+1 to time t+Q,. . .until Kth (PCRI_xl, PCRI_yp) for time t+1 to time t+Q.

[0119] Referring to FIG. 6 and FIG. 6, the output could be (i) Top-K predicted beam pairs (beam IDs), e.g., predicted beam pairs CRI (PCRI_xi, PCRI_yl),... until, Kth (PCRI_xl, PCRI_yp) from Set Al and Set A2 for time t+1 to time t+Q, or predicted beam pairs SSBRI (‘pSSBRI_xi, pSSBRI_yl’),... until, Kth (PSSBRI_xl, PSSBRI_yp) from Set Al and Set A2 for time t+1 to time t+Q (612, 712), or (ii) Predicted RSRP of best Top-K beam pairs (beam IDs), e.g., predicted RSRP (PRSRP_xi, PRSRP_yl),... until, Kth (PRSRP_xl, PRSRP_yp) from Set Al and Set A2 for time t+1 to time t+Q (612, 712), or (iii) Top-K predicted beam pairs (beam IDs) and Predicted RSRP of best Top-K beam pairs (beam IDs), e.g., (PCRI_xi, PCRI_yl) and (PRSRP_ xj, PRSRP_ yl) until, Kth (PCRI_xj, PCRI_yl) and (PRSRP_ xl, PRSRP_ yp) from Set Al and SetAl for time t+1 to time t+Q (616, 716), or (iv) Probability values of best Top-K beam pairs (beam IDs) from Set Al and Set A2 for time t+1 to time t+Q.

[0120] The NW might use Rx panel #ID (corresponding to UE specific type#ID regarding rule-based consistency) as one additional input to AI / ML model.

[0121] Embodiment 5: Measurements and reporting for inference operation

[0122] The rule-based consistency would be sent from UE to NW before inference operation.

[0123] The UE reports quantities (configured as beam pair report or best beam report) associated with the measurements corresponding to both SetBl and SetB2 to NW. In one variant, as the reporting quantities, the UE may report Top-N best beam-pairs andcorresponding Ll-RSRP (or Ll-SINR) corresponding to two TRPs according to the rulebased consistency defined to the UE. - beam pair report for two TRPs. This report may be configured when group-based beam reporting is enabled, e.g., in RRC. In another variant, as the reporting quantities, the UE may report Top-N best beams and corresponding Ll-RSRP (or Ll-SINR) corresponding to each TRPs according to the rule-based consistency defined to the UE. - best beam report for each TRP. This report may be configured when group-based beam reporting is disabled, e.g., in RRC. As highlighted before, the UE can report the “rulebased consistency” information that is considered by the UE to perform measurements.

[0124] TRPs (Set B1 / B2) may be associated with a TRP ID, CORESET Group / Pool ID, PCI, or by other means such that the UE knows grouping of beams (beam pairs) or reporting the best-beams separately.

[0125] Based on the reported quantities, the NW performs beam-pair prediction, where the association between a set of measurement (SetBl / SetB2) associate with a set of beams prediction (SetAl / A2). Set Bl may be a subset of Set Al and Set B2 may be a subset of Set A2. Set Bl and Set Al may differ and Set B2 and Set A2 may differ (e.g., SetBl and SetB2 are wide-beams and SetAl and SetA2 are narrow beams). Meta learning method can be applied here as well.

[0126] The examples described herein are applicable to 6G AI / ML multi-TRP MIMO.

[0127] FIG. 8 is an example apparatus 800, which may be implemented in hardware, configured to implement the examples described herein. The apparatus 800 comprises at least one processor 802 (e.g. an FPGA and / or CPU), one or more memories 804 including computer program code 805, the computer program code 805 having instructions to carry out the methods described herein, wherein the at least one memory 804 and the computer program code 805 are configured to, with the at least one processor 802, cause the apparatus 800 to implement circuitry, a process, component, module, or function (implemented with control module 806) to implement the examples described herein. The one or more memories 804 may include a non-transitory memory, a transitory memory, a volatile memory (e.g. RAM), or a non-volatile memory (e.g. ROM).

[0128] Rule based consistency 830 implements the examples described herein, including the embodiments related to rule-based ensuring consistency between training and inference.

[0129] The apparatus 800 includes a display and / or I / O interface 808, which includes user interface (UI) circuitry and elements, that may be used to display aspects or a status of the methods described herein (e.g., as one of the methods is being performed or at a subsequent time), or to receive input from a user such as with using a keypad, camera, touchscreen, touch area, microphone, biometric recognition, one or more sensors, etc. The apparatus 800 includes one or more communication e.g. network (N / W) interfaces (I / F(s)) 810. The communication I / F(s) 810 may be wired and / or wireless and communicate over the Internet / other network(s) via any communication technique including via one or more links 824. The link(s) 824 may be the link(s) 131 and / or 176 from FIG. 1. The link(s) 131 and / or 176 from FIG. 1 may also be implemented using transceiver(s) 816 and corresponding wireless link(s) 826. The communication I / F(s) 810 may comprise one or more transmitters or one or more receivers.

[0130] The transceiver 816 comprises one or more transmitters 818 and one or more receivers 820. The transceiver 816 and / or communication I / F(s) 810 may comprise standard well-known components such as an amplifier, filter, frequency-converter, (de)modulator, and encoder / decoder circuitries and one or more antennas, such as antennas 814 used for communication over wireless link 826.

[0131] The control module 806 of the apparatus 800 comprises one of or both parts 806-1 and / or 806-2, which may be implemented in a number of ways. The control module 806 may be implemented in hardware as control module 806-1, such as being implemented as part of the one or more processors 802. The control module 806-1 may be implemented also as an integrated circuit or through other hardware such as a programmable gate array. In another example, the control module 806 may be implemented as control module 806-2, which is implemented as computer program code (having corresponding instructions) 805 and is executed by the one or more processors 802. For instance, the one or more memories 804 store instructions that, when executed by the one or more processors 802, cause the apparatus 800 to perform one or more of the operations as described herein. Furthermore, the one or more processors 802, the one or more memories 804, and example algorithms (e.g., as flowcharts and / or signaling diagrams), encoded as instructions, programs, or code, are means for causing performance of the operations described herein.

[0132] The apparatus 800 to implement the functionality of control 806 may be UE 110, RAN node 170 (e.g. gNB), or network element(s) 190 (e.g. LMF 190). Thus, processor 802may correspond to processor(s) 120, processor(s) 152 and / or processor(s) 175, memory 804 may correspond to one or more memories 125, one or more memories 155 and / or one or more memories 171, computer program code 805 may correspond to computer program code 123, computer program code 153, and / or computer program code 173, control module 806 may correspond to module 140-1, module 140-2, module 150-1, and / or module 150-2, and communication I / F(s) 810 and / or transceiver 816 may correspond to transceiver 130, antenna(s) 128, transceiver 160, antenna(s) 158, N / W I / F(s) 161, and / or N / W I / F(s) 180. Alternatively, apparatus 800 and its elements may not correspond to either of UE 110, RAN node 170, or network element(s) 190 and their respective elements, as apparatus 800 may be part of a self-organizing / optimizing network (SON) node or other node, such as a node in a cloud.

[0133] Apparatus 800 may be or correspond TRP1 51, TRP1 251, TRP2 52, or TRP2 252. TRP 51 and TRP2 52 are part of the same RAN node (e.g. a gNB), and TRP1 251 and TRP2 252 are part of different RAN nodes (e.g. gNBs), such that for example, TRP1 251 is part of a first RAN node and TRP2 252 is part of a second RAN node where the first RAN node is different from the second RAN node.

[0134] The apparatus 800 may also be distributed throughout the network (e.g. 100) including within and between apparatus 800 and any network element (such as a network control element (NCE) 190 and / or the RAN node 170 and / or UE 110).

[0135] Interface 812 enables data communication and signaling between the various items of apparatus 800, as shown in FIG. 8. For example, the interface 812 may be one or more buses such as address, data, or control buses, and may include any interconnection mechanism, such as a series of lines on a motherboard or integrated circuit, fiber optics or other optical communication equipment, and the like. Computer program code (e.g. instructions) 805, including control 806 may comprise object-oriented software configured to pass data or messages between objects within computer program code 805, or computer program code (e.g. instructions) 805, including control 806 may include functional, scripting, or procedural code. The apparatus 800 need not comprise each of the features mentioned, or may comprise other features as well. The various components of apparatus 800 may at least partially reside in a common housing 828, or a subset of the various components of apparatus 800 may at least partially be located in different housings, which different housings may include housing 828.

[0136] FIG. 9 shows a schematic representation of non-volatile memory media 900a (e.g. computer / compact disc (CD) or digital versatile disc (DVD)) and 900b (e.g. universal serial bus (USB) memory stick) and 900c (e.g. cloud storage for downloading instructions and / or parameters 902 or receiving emailed instructions and / or parameters 902) storing instructions and / or parameters 902 which when executed by a processor allows the processor to perform one or more of the steps of the methods described herein. Instructions and / or parameters 902 may represent a computer readable medium.

[0137] FIG. 10 is an example method 1000 based on the examples described herein. At 1010, the method includes receiving, from a network, at least one configuration comprising at least one rule for performing at least one measurement. At 1020, the method includes wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase. At 1030, the method includes performing the at least one measurement based on the first rule received with the first configuration during the training phase. At 1040, the method includes transmitting, to the network, a report based on the at least one measurement performed based on the first rule during the training phase. At 1050, the method includes performing the at least one measurement based on the second rule received with the second configuration during the inference phase. At 1060, the method includes transmitting, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase. At 1070, the method includes wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase. Method 1000 may be performed with UE 110 or apparatus 800.

[0138] FIG. 11 is an example method 1100 based on the examples described herein. At 1110, the method includes transmitting, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement. At 1120, the method includes wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase. At 1130, the method includes receiving, from the atleast one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase. At 1140, the method includes training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase. At 1150, the method includes receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase. At 1160, the method includes performing, during the inference phase, prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase. At 1170, the method includes wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase. Method 1100 may be performed with RAN node 170, one or more network elements 190, TRP 51, TRP 251, TRP 52, TRP 252, or apparatus 800.

[0139] FIG. 12 is an example method 1200 based on the examples described herein. At 1210, the method includes determining at least one rule for performing at least one measurement. At 1220, the method includes wherein the at least one rule for performing the at least one measurement comprises a first rule for performing the at least one measurement during a training phase and a second rule for performing the at least one measurement during an inference phase. At 1230, the method includes performing the at least one measurement based on the first rule during the training phase. At 1240, the method includes transmitting, to a network, a report based on the at least one measurement performed based on the first rule during the training phase. At 1250, the method includes performing the at least one measurement based on the second rule during the inference phase. At 1260, the method includes transmitting, to the network, a report based on the at least one measurement performed based on the second rule during the inference phase. At 1270, the method includes wherein the first rule for performing the at least one measurement during the training phase is the same as the second rule for performing the at least one measurement during the inference phase. Method 1200 may be performed with UE 110 or apparatus 800.

[0140] FIG. 13 is an example method 1300 based on the examples described herein. At1310, the method includes receiving, from at least one user equipment during a training phase, a report based on at least one measurement performed based on a first rule during the training phase. At 1320, the method includes training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule during the training phase. At 1330, the method includes receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on a second rule during the inference phase. At 1340, the method includes performing, during the inference phase, prediction using the at least one model and the report based on the at least one measurement performed based on the second rule during the inference phase. At 1350, the method includes wherein the first rule for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule for performing the at least one measurement used to perform the prediction during the inference phase. Method 1300 may be performed with RAN node 170, one or more network elements 190, TRP 51, TRP 251, TRP 52, TRP 252, or apparatus 800.

[0141] A set of examples where the network determines at least one rule for rule based consistency is as follows:

[0142] Example 1. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; perform the at least one measurement based on the first rule received with the first configuration during the training phase; transmit, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; perform the at least one measurement based on the second rule received with the second configuration during the inference phase; and transmit, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

[0143] Example 2. The apparatus of example 1, wherein the at least one measurement performed based on the second rule during the inference phase is based on a model that is trained based on the first rule that is the same as the second rule.

[0144] Example 3. The apparatus of any of examples 1 to 2, wherein the at least one measurement performed based on the first rule during the training phase is configured to be used to train at least one model during the training phase, wherein the at least one model trained during the training phase based on the at least one measurement performed based on the first rule during the training phase comprises a statistical model.

[0145] Example 4. The apparatus of any of examples 1 to 3, wherein at least one model trained during the training phase based on the at least one measurement performed based on the first rule received with the first configuration during the training phase comprises a beam pair prediction model.

[0146] Example 5. The apparatus of any of examples 1 to 4, wherein the at least one measurement performed based on the second rule received with the second configuration is configured to be used to perform beam pair prediction using at least one beam pair prediction model.

[0147] Example 6. The apparatus of any of examples 5, wherein the beam pair prediction comprises multiple predictions of: at least one pair of beams of the network for respective multiple time instances, or information related to at least one pair of beams of the network for respective multiple time instances.

[0148] Example 7. The apparatus example 6, wherein at least one beam pair prediction model used to perform the beam pair prediction comprising the multiple predictions of the at least one pair of beams of the network for respective multiple time instances or the information related to the at least one pair of beams of the network for the respective multiple time instances comprises a long-short-term-memory model, an artificial intelligence machine learning model, or a transformer model.

[0149] Example 8. The apparatus of any of examples 1 to 7, wherein the apparatus is further caused to: compare the first rule to the second rule; wherein the at least one measurement performed based on the second rule during the inference phase is based on a model that is trained based on the first rule that is the same as the second rule.

[0150] Example 9. The apparatus of any of examples 1 to 18, wherein: the at least one measurement performed based on the first rule received with the first configuration during the training phase comprises a channel state information measurement, and the at least one measurement performed based on the second rule received with the second configuration during the inference phase comprises a channel state information measurement.

[0151] Example 10. The apparatus of any of examples 1 to 9, wherein the apparatus is further caused to: receive, from the network, a first rule for performing the at least one measurement; wherein the first rule for performing the at least one measurement is associated with a first transmission reception point; perform the at least one measurement based on the first rule during the training phase; receive, from the network, a second rule for performing the at least one measurement; wherein the second rule for performing the at least one measurement is associated with a second transmission reception point; perform the at least one measurement based on the second rule during the training phase; transmit, to the network, at least one report based on the at least one measurement performed based on the first rule during the training phase and the at least one measurement performed based on the second rule during the training phase; receive, from the network, a third rule for performing the at least one measurement; wherein the third rule for performing the at least one measurement is associated with the first transmission reception point; perform the at least one measurement based on the third rule during the inference phase; receive, from the network, a fourth rule for performing the at least one measurement; wherein the fourth rule for performing the at least one measurement is associated with the second transmission reception point; perform the at least one measurement based on the fourth rule during the training phase; perform the at least one measurement based on the first rule during the inference phase; perform the at least one measurement based on the second rule during the inference phase; and transmit, to the network, at least one report based on the at least one measurement performed based on the third rule during the inference phase and the at least one measurement performed based on the fourth rule during the inference phase; wherein the first rule associated with the first transmission reception point for performing the at least one measurement during the training phase is the same as the third rule associated with the first transmission reception point for performing the at least one measurement during the inference phase, and the second rule associated with the second transmission reception point for performing the at least one measurement during the training phase is the same as the fourth rule associated with the second transmission reception point for performing the at least one measurement during theinference phase.

[0152] Example 11. The apparatus of example 10, wherein: the at least one report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase is configured to be used to train at least one beam pair prediction model for the first transmission reception point, and the at least one report based on the at least one measurement performed based on the second rule associated with the second transmission reception point during the training phase is configured to be used to train at least one beam pair prediction model for the second transmission reception point, and the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase is configured to be used to perform beam pair prediction using the at least one beam pair prediction model for the first transmission reception point, and the at least one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase is configured to be used to perform beam pair prediction using the at least one beam pair prediction model for the second transmission reception point.

[0153] Example 12. The apparatus of any of examples 1 to 11, wherein the at least one rule is based on the apparatus performing the at least one measurement using a subset of panels of the apparatus.

[0154] Example 13. The apparatus of any of examples 1 to 12, wherein the at least one rule is based on the at least one measurement performed based on the at least one rule being a type of measurement.

[0155] Example 14. The apparatus of example 13, wherein the type of measurement is at least one of: at least one layer 1 reference signal received power, or at least one layer 1 reference signal received power of at least one transmission reception point.

[0156] Example 15. The apparatus of any of examples 10 to 14, wherein the apparatus is further caused to: receive, from the network, a first transmission with a pair of beams of the first transmission reception point, based on the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase; and receive, from the network, a second transmission with a pair of beams of the second transmission reception point, based on the atleast one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first transmission received from the network with the pair of beams of the first transmission reception point and the second transmission received from the network with the pair of beams of the second transmission reception point are received from the network at least partially simultaneously.

[0157] Example 16. The apparatus of any of examples 11 to 15, wherein: the at least one configuration comprises: a first configuration that indicates first reference signal resources to use for performing the at least one measurement during the training phase, and a second configuration that indicates second reference signal resources to use for performing the at least one measurement during the training phase, and the first reference signal resources are associated with the first transmission reception point, and the second reference signal resources are associated with the second transmission reception point, and the at least one measurement is performed based on the first rule associated with the first transmission reception point during the training phase using the first reference signal resources and the second rule associated with the second transmission reception point during the training phase using the second reference signal resources, and the at least one configuration comprises: a third configuration that indicates third reference signal resources to use for performing the at least one measurement during the inference phase, and a fourth configuration that indicates fourth reference signal resources to use for performing the at least one measurement during the inference phase, and the third reference signal resources are associated with the first transmission reception point, and the fourth reference signal resources are associated with the second transmission reception point, and the at least one measurement is performed based on the third rule associated with the first transmission reception point during the inference phase using the third reference signal resources and the fourth rule associated with the second transmission reception point during the inference phase using the fourth reference signal resources.

[0158] Example 17. The apparatus of any of examples 1 to 16, wherein the apparatus is further caused to: transmit, to the network, at least one indication that the apparatus is capable of performing the at least one measurement during the training phase using resources associated with a first transmission reception point and resources associated with a second transmission reception point, and the at least one measurement during the inference phaseusing the resources associated with the first transmission reception point and the resources associated with a second transmission reception point; wherein the at least one configuration received from the network is based on the at least one indication that the apparatus is capable of performing the at least one measurement during the training phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point.

[0159] Example 18. The apparatus of any of examples 1 to 17, wherein the apparatus is further caused to: transmit, to the network during the training phase, information comprising a best set of at least one pair of beams of a first transmission reception point among a plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of a second transmission reception point among a plurality of pairs of beams of the second transmission reception point, and transmit, to the network during the inference phase, information comprising a best set of at least one pair of beams of the first transmission reception point among the plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of the second transmission reception point among the plurality of pairs of beams of the second transmission reception point.

[0160] Example 19. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; receive, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; train, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; receive, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; and perform, during the inference phase, prediction using the at least model and thereport based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase.

[0161] Example 20. The apparatus of example 19, wherein the at least one measurement performed based on the second rule during the inference phase used to perform the prediction is based on the at least one model that is trained based on the first rule that is the same as the second rule.

[0162] Example 21. The apparatus of any of examples 19 to 20, wherein the at least one model trained during the training phase based on the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase comprises a statistical model.

[0163] Example 22. The apparatus of any of examples 19 to 21, wherein the at least one model trained during the training phase based on the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase is trained offline to perform Top-K beam pairs prediction, where K is an integer.

[0164] Example 23. The apparatus of any of examples 19 to 22, wherein: the at least one model trained during the training phase using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase comprises at least one beam pair prediction model, and the prediction performed during the inference phase using the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase and the least one model comprises beam pair prediction to predict: at least one pair of beams of a network or information related to at least one pair of beams of a network using the at least one beam pair prediction model.

[0165] Example 24. The apparatus of example 23, wherein the beam pair prediction comprises multiple predictions of: the at least one pair of beams of the network for respective multiple time instances or the information related to at least one pair of beams of the networkfor respective multiple time instances.

[0166] Example 25. The apparatus of example 24, wherein the at least one beam pair prediction model used to perform the beam pair prediction comprising the multiple predictions of the at least one pair of beams of the network for the respective multiple time instances or the information related to the at least one pair of beams of the network for the respective multiple time instances comprises a long-short-term-memory model, an artificial intelligence machine learning model, or a transformer model.

[0167] Example 26. The apparatus of any of examples 19 to 25, wherein: the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase comprises a channel state information measurement, and the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase comprises a channel state information measurement.

[0168] Example 27. The apparatus of any of examples 19 to 26, wherein the apparatus is further caused to: transmit, to the at least one user equipment, a first rule associated with a first transmission reception point for performing the at least one measurement during the training phase; transmit, to the at least one user equipment, a second rule associated with a second transmission reception point for performing the at least one measurement during the training phase; receive, from the at least one user equipment during the training phase, at least one report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase and the at least one measurement performed based on the second rule associated with the second transmission reception point during the training phase; transmit, to the at least one user equipment, a third rule associated with the first transmission reception point for performing the at least one measurement during the inference phase; transmit, to the at least one user equipment, a fourth rule associated with the second transmission reception point for performing the at least one measurement during the inference phase; and receive, from the at least one user equipment during the inference phase, at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase and based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first rule associated with the first transmission reception point for performing the at least one measurement during the training phase is the same as the third rule associatedwith the first transmission reception point for performing the at least one measurement during the inference phase, and the second rule associated with the second transmission reception point for performing the at least one measurement during the training phase is the same as the fourth rule associated with the second transmission reception point for performing the at least one measurement during the inference phase.

[0169] Example 28. The apparatus of example 27, wherein the apparatus is further caused to: train at least one beam pair prediction model for the first transmission reception point using the at least one report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase; train at least one beam pair prediction model for the second transmission reception point using the at least one report based on the at least one measurement performed based on the second rule associated with the second transmission reception point during the training phase; perform beam pair prediction to predict at least one pair of beams of the first transmission reception point or information related to at least one pair of beams of the first transmission reception point using the at least one beam pair prediction model for the first transmission reception point and the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase; and perform beam pair prediction to predict at least one pair of beams of the second transmission reception point or information related to at least one pair of beams of the second transmission reception point using the at least one beam pair prediction model for the second transmission reception point and the at least one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase.

[0170] Example 29. The apparatus of example 28, wherein the predicted information related to the at least one pair of beams of the first transmission reception point, or the predicted information related to the at least one pair of beams of the second transmission reception point, comprises one or more of: a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on at least one metric of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifierscorresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective layer 1 reference signal received power values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective probability values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams.

[0171] Example 30. The apparatus of any of examples 28 to 29, wherein the predicted information related to the at least one pair of beams of the first transmission reception point, or the predicted information related to the at least one pair of beams of the second transmission reception point, comprises one or more of: predicted Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and probability values of predicted Top-K beam pairs IDs for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs IDs and probability values of predicted Top-K beam pairs IDs for an integer K.

[0172] Example 31. The apparatus of any of examples 19 to 30, wherein the at least one rule is based on the at least one measurement performed using a subset of panels of the at least one user equipment.

[0173] Example 32. The apparatus of any of examples 19 to 31, wherein the at least one rule is based on the at least one measurement performed based on the at least one rule being a type of measurement.

[0174] Example 33. The apparatus of example 32, wherein the type of measurement is at least one of: at least one layer 1 reference signal received power, or at least one layer 1 reference signal received power of at least one transmission reception point.

[0175] Example 34. The apparatus of any of examples 28 to 33, wherein the apparatus isfurther caused to: transmit, to the at least one user equipment, a first transmission with a pair of beams of the first transmission reception point, based on the beam pair prediction to predict the at least one pair of beams of the first transmission reception point and the report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase; and transmit, to the at least one user equipment, a second transmission with a pair of beams of the second transmission reception point, based on the beam pair prediction to predict the at least one pair of beams of the second transmission reception point and the report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first transmission transmitted to the at least one user equipment with the pair of beams of the first transmission reception point and the second transmission transmitted to the at least one user equipment with the pair of beams of the second transmission reception point are transmitted to the at least one user equipment at least partially simultaneously.

[0176] Example 35. The apparatus of any of examples 19 to 34, wherein the apparatus is further caused to: transmit, to a first user equipment, a first configuration comprising at least one first rule for performing the at least one measurement during the training phase configured to be used to train at least one beam pair prediction model; receive, from the first user equipment, a report based on the at least one measurement performed based on the at least one first rule during the training phase; transmit, to a second user equipment, a second configuration comprising at least one second rule for performing the at least one measurement during the training phase configured to be used to train the at least one beam pair prediction model; receive, from the second user equipment, a report based on the at least one measurement performed based on the at least one second rule during the training phase; and train, during the training phase, the at least one beam pair prediction model using the report received from the first user equipment based on the at least one measurement performed based on the at least one first rule during the training phase and the report received from the second user equipment based on the at least one measurement performed based on the at least one second rule during the training phase.

[0177] Example 36. The apparatus of example 35, wherein the apparatus is further caused to: transmit, to the first user equipment, a third configuration comprising at least one third rule for performing the at least one measurement during the inference phase; receive, fromthe first user equipment, a report based on the at least one measurement performed based on the at least one third rule during the inference phase; transmit, to the first user equipment, a fourth configuration comprising at least one fourth rule for performing the at least one measurement during the inference phase; receive, from the second user equipment, a report based on the at least one measurement performed based on the at least one fourth rule during the inference phase; and perform beam pair prediction to predict the at least one pair of beams of a network or the information related to the at least one pair of beams of a network during the inference phase using the at least one beam pair prediction model, the report received from the first user equipment based on the at least one measurement performed based on the at least one third rule during the inference phase, and the report received from the second user equipment based on the at least one measurement performed based on the at least one fourth rule during the inference phase; wherein the at least one first rule for performing the at least one measurement by the first user equipment during the training phase is the same as the at least one third rule for performing the at least one measurement by the first user equipment during the inference phase, and the at least one second rule for performing the at least one measurement by the second user equipment during the training phase is the same as the at least one fourth rule for performing the at least one measurement by the second user equipment during the inference phase.

[0178] Example 37. The apparatus of any of examples 23 to 36, wherein the predicted at least one pair of beams of the network using the at least one beam pair prediction model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase comprises a pair of beams of the network predicted to have a highest reference signal received power among a set of pairs of beams of the network.

[0179] Example 38. The apparatus of example 37, wherein the pair of beams of the network predicted to have the highest reference signal received power among the set of pairs of beams of the network comprises Top-K beams, where K is an integer.

[0180] Example 39. The apparatus of any of examples 23 to 38, wherein the predicted information related to the at least one pair of beams of the network comprises one or more of: a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on at least onemetric of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective layer 1 reference signal received power values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective probability values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams.

[0181] Example 40. The apparatus of any of examples 23 to 39, wherein the predicted information related to the at least one pair of beams of the network comprises one or more of: predicted Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and probability values of predicted Top-K beam pairs IDs for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs IDs and probability values of predicted Top-K beam pairs IDs for an integer K.

[0182] Example 41. The apparatus of any of examples 27 to 40, wherein: the at least one configuration comprises: a first configuration that indicates first reference signal resources to use for performing the at least one measurement during the training phase, and a second configuration that indicates second reference signal resources to use for performing the at least one measurement during the training phase, and the first reference signal resources are associated with a first transmission reception point, and the second reference signal resources are associated with a second transmission reception point, and the at least one report is received from the at least one user equipment during the training phase based on the at least one measurement performed based on the first rule associated with the first transmissionreception point transmitted with the first configuration during the training phase using the first reference signal resources and the second rule associated with the second transmission reception point using the second reference signal resources, and the at least one configuration comprises: a third configuration that indicates third reference signal resources to use for performing the at least one measurement during the inference phase, and a fourth configuration that indicates fourth reference signal resources to use for performing the at least one measurement during the inference phase, and wherein the third reference signal resources are associated with the first transmission reception point, and the fourth reference signal resources are associated with the second transmission reception point, and the at least one report is received from the at least one user equipment during the inference phase based on the at least one measurement performed based on the third rule associated with the first transmission reception point transmitted with the third configuration during the inference phase using the third reference signal resources and the fourth rule associated with the second transmission reception point transmitted with the fourth configuration during the inference phase using the fourth reference signal resources.

[0183] Example 42. The apparatus of any of examples 19 to 41, wherein the apparatus is further caused to: receive, from the at least one user equipment, at least one indication that the at least one user equipment is capable of performing the at least one measurement during the training phase using resources associated with a first transmission reception point and resources associated with a second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with a second transmission reception point; wherein the at least one configuration transmitted to the at least one user equipment is based on the at least one indication that the at least one user equipment is capable of performing the at least one measurement during the training phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point.

[0184] Example 43. The apparatus of example 42, wherein: the report received from the at least one user equipment during the training phase comprises the at least one measurement performed using the resources associated with the first transmission reception point and theresources associated with the second transmission reception point, and at least one beam pair prediction model is trained using the at least one measurement performed during the training phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and the report received from the at least one user equipment during the inference phase comprises the at least one measurement performed during the inference phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and at least one predicted pair of beams of a network comprises at least one pair of beams of the first transmission reception point and at least one pair of beams of the second transmission reception point, or information related to at least one pair of beams of a network comprises information related to at least one pair of beams of the first transmission reception point and at least one pair of beams of the second transmission reception point.

[0185] Example 44. The apparatus of any of examples 23 to 43, wherein the apparatus is further caused to: receive, from the at least one user equipment during the training phase, information used to train the at least one beam pair prediction model, wherein the information used to train the at least one beam pair prediction model comprises a best set of at least one pair of beams of a first transmission reception point among a plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of a second transmission reception point among a plurality of pairs of beams of the second transmission reception point; and receive, from the at least one user equipment during the inference phase, information used to perform the beam pair prediction, wherein the information used to perform the beam pair prediction comprises a best set at least one pair of beams of the first transmission reception point among the plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of the second transmission reception point among the plurality of pairs of beams of the second transmission reception point.

[0186] Example 45. A method including: receiving, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; performing the at least one measurement based on the first rule received with the firstconfiguration during the training phase; transmitting, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; performing the at least one measurement based on the second rule received with the second configuration during the inference phase; and transmitting, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

[0187] Example 46. A method including: transmitting, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; receiving, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; and performing, during the inference phase, prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase.

[0188] Example 47. An apparatus including: means for receiving, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; means for performing the at least one measurement based on the first rulereceived with the first configuration during the training phase; means for transmitting, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; means for performing the at least one measurement based on the second rule received with the second configuration during the inference phase; and means for transmitting, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

[0189] Example 48. An apparatus including: means for transmitting, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; means for receiving, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; means for training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; means for receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; and means for performing, during the inference phase, prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase.

[0190] Example 49. A computer readable medium including instructions stored thereon for performing at least the following: receiving, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at leastone measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; performing the at least one measurement based on the first rule received with the first configuration during the training phase; transmitting, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; performing the at least one measurement based on the second rule received with the second configuration during the inference phase; and transmitting, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

[0191] Example 50. A computer readable medium including instructions stored thereon for performing at least the following: transmitting, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; receiving, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; and performing, during the inference phase, prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase.

[0192] A set of examples where the user equipment determines at least one rule for rule based consistency is as follows:

[0193] Example 1. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine at least one rule for performing at least one measurement; wherein the at least one rule for performing the at least one measurement comprises a first rule for performing the at least one measurement during a training phase and a second rule for performing the at least one measurement during an inference phase; perform the at least one measurement based on the first rule during the training phase; transmit, to a network, a report based on the at least one measurement performed based on the first rule during the training phase; perform the at least one measurement based on the second rule during the inference phase; and transmit, to the network, a report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement during the training phase is the same as the second rule for performing the at least one measurement during the inference phase.

[0194] Example 2. The apparatus of example 1, wherein the at least one measurement performed based on the second rule during the inference phase is based on a model that is trained based on the first rule that is the same as the second rule.

[0195] Example 3. The apparatus of any of examples 1 to 2, wherein the at least one measurement performed based on the first rule during the training phase is configured to be used to train at least one model during the training phase, wherein the at least one model trained during the training phase based on the at least one measurement performed based on the first rule during the training phase comprises a statistical model.

[0196] Example 4. The apparatus of example 3, wherein the at least one model trained during the training phase based on the at least one measurement performed based on the first during the training phase comprises a beam pair prediction model.

[0197] Example 5. The apparatus of any of examples 1 to 4, wherein the at least one measurement performed based on the second rule is configured to be used to perform beam pair prediction using at least one beam pair prediction model.

[0198] Example 6. The apparatus of any of examples 5, wherein the beam pair prediction comprises multiple predictions of: at least one pair of beams of the network for respective multiple time instances, or information related to at least one pair of beams of the network for respective multiple time instances.

[0199] Example 7. The apparatus example 6, wherein at least one beam pair prediction model used to perform the beam pair prediction comprising the multiple predictions of the at least one pair of beams of the network for respective multiple time instances or the information related to the at least one pair of beams of the network for the respective multiple time instances comprises a long-short-term-memory model, an artificial intelligence machine learning model, or a transformer model.

[0200] Example 8. The apparatus of any of examples 1 to 7, wherein the apparatus is further caused to: compare the first rule to the second rule; wherein the at least one measurement performed based on the second rule during the inference phase is based on a model that is trained based on the first rule that is the same as the second rule.

[0201] Example 9. The apparatus of any of examples 1 to 8, wherein: the at least one measurement performed based on the first rule during the training phase comprises a channel state information measurement, and the at least one measurement performed based on the second rule during the inference phase comprises a channel state information measurement.

[0202] Example 10. The apparatus of any of examples 1 to 9, wherein the apparatus is further caused to: determine a first rule associated with a first transmission reception point for performing the at least one measurement; perform the at least one measurement based on the first rule associated with the first transmission reception point during the training phase; determine a second rule associated with a second transmission reception point for performing the at least one measurement; perform the at least one measurement based on the second rule associated with the second transmission reception point during the training phase; transmit, to the network, at least one report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase and the at least one second measurement performed based on the second rule associated with the second transmission reception point during the training phase; determine a third rule associated with the first transmission reception point for performing the at least one measurement; perform the at least one measurement based on the third rule associated with the first transmission reception point during the inference phase; determine a fourth rule associated with the second transmission reception point for performing the at least one measurement; perform the at least one measurement based on the fourth rule associated with the second transmission reception point during the inference phase; and transmit, to the network, at least one report based on the at least one measurement performed based on thethird rule associated with the first transmission reception point during the inference phase and the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first rule associated with the first transmission reception point for performing the at least one measurement during the training phase is the same as the third rule associated with the first transmission reception point for performing the at least one measurement during the inference phase, and the second rule associated with the second transmission reception point for performing the at least one measurement during the training phase is the same as the fourth rule associated with the second transmission reception point for performing the at least one measurement during the inference phase.

[0203] Example 11. The apparatus of example 10, wherein: the at least one report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase is configured to be used to train at least one beam pair prediction model for the first transmission reception point, and the at least one report based on the at least one measurement performed based on the second rule associated with the second transmission reception point during the training phase is configured to be used to train at least one beam pair prediction model for the second transmission reception point, and the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase is configured to be used to perform beam pair prediction using the at least one beam pair prediction model for the first transmission reception, and the at least one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase is configured to be used to perform beam pair prediction using the at least one beam pair prediction model for the second transmission reception point.

[0204] Example 12. The apparatus of any of examples 1 to 11, wherein the at least one rule is based on the apparatus performing the at least one measurement using a subset of panels of the apparatus.

[0205] Example 13. The apparatus of any of examples 1 to 12, wherein the at least one rule is based on the at least one measurement performed based on the at least one rule being a type of measurement.

[0206] Example 14. The apparatus of example 13, wherein the type of measurement is at least one of: at least one layer 1 reference signal received power, or at least one layer 1 reference signal received power of at least one transmission reception point.

[0207] Example 15. The apparatus of any of examples 10 to 14, wherein the apparatus is further caused to: receive, from the network, a first transmission with a pair of beams of the first transmission reception point, based on the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase; and receive, from the network, a second transmission with a pair of beams of the second transmission reception point, based on the at least one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first transmission received from the network with the pair of beams of the first transmission reception point and the second transmission received from the network with the pair of beams of the second transmission reception point are received from the network at least partially simultaneously.

[0208] Example 16. The apparatus of any of examples 1 to 15, wherein the apparatus is further caused to: transmit, to the network, an indication of the first rule used to determine the report based on the at least one measurement performed during the training phase; and transmit, to the network, an indication of the second rule used to determine the report based on the at least one measurement performed during the inference phase.

[0209] Example 17. The apparatus of any of examples 11 to 16, wherein the apparatus is further caused to: receive, from the network, a first configuration that indicates first reference signal resources to use for performing the at least one measurement during the training phase, and a second configuration that indicates second reference signal resources to use for performing the at least one measurement during the training phase; wherein the first reference signal resources are associated with the first transmission reception point, and the second reference signal resources are associated with the second transmission reception point; wherein the at least one measurement is performed based on the first rule associated with the first transmission reception point during the training phase using the first reference signal resources and the second rule associated with the second transmission reception point during the training phase using the second reference signal resources; and receive, from the network, a third configuration that indicates third reference signal resources to use for performing theat least one measurement during the inference phase, and a fourth configuration that indicates fourth reference signal resources to use for performing the at least one second measurement during the inference phase; wherein the third reference signal resources are associated with the first transmission reception point, and the fourth reference signal resources are associated with the second transmission reception point; wherein the at least one measurement is performed based on the third rule associated with the first transmission reception point during the inference phase using the third reference signal resources and the fourth rule associated with the second transmission reception point during the inference phase using the fourth reference signal resources.

[0210] Example 18. The apparatus of any of examples 1 to 17, wherein the apparatus is further caused to: transmit, to the network, at least one indication that the apparatus is capable of performing the at least one measurement during the training phase using resources associated with a first transmission reception point and resources associated with a second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with a second transmission reception point; wherein the at least one measurement is performed during the training phase using the resources of the first transmission reception point and the resources associated with the second transmission reception point; wherein the at least one measurement is performed during the inference phase using the resources associated with first transmission reception point and using the resources associated with the second transmission reception point.

[0211] Example 19. The apparatus of any of examples 1 to 18, wherein the apparatus is further caused to: transmit, to the network during the training phase, information comprising a best set of at least one pair of beams of a first transmission reception point among a plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of a second transmission reception point among a plurality of pairs of beams of the second transmission reception point, and transmit, to the network during the inference phase, information comprising a best set of at least one pair of beams of the first transmission reception point among the plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of the second transmission reception point among the plurality of pairs of beams of the second transmission reception point.

[0212] Example 20. An apparatus including: at least one processor; and at least one memorystoring instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from at least one user equipment during a training phase, a report based on at least one measurement performed based on a first rule during the training phase; train, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule during the training phase; receive, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on a second rule during the inference phase; and perform, during the inference phase, prediction using the at least one model and the report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule for performing the at least one measurement used to perform the prediction during the inference phase.

[0213] Example 21. The apparatus of example 20, wherein the at least one measurement performed based on the second rule during the inference phase used to perform the prediction is based on the at least one model that is trained based on the first rule that is the same as the second rule.

[0214] Example 22. The apparatus of any of examples 20 to 21, wherein the at least one model trained during the training phase based on the report based on the at least one measurement performed based on the first rule during the training phase comprises a statistical model.

[0215] Example 23. The apparatus of any of examples 20 to 22, wherein the at least one model trained during the training phase based on the report based on the at least one measurement performed based on the first rule during the training phase is trained offline to perform Top-K beam pairs prediction, where K is an integer.

[0216] Example 24. The apparatus of any of examples 20 to 23, wherein: the at least one model trained during the training phase using the report based on the at least one measurement performed based on the first rule during the training phase comprises at least one beam pair prediction model, and the prediction performed during the inference phase using the report based on the at least one measurement performed based on the second rule during the inference phase and the least one model comprises beam pair prediction to predict: at least one pair of beams of a network or information related to at least one pair of beams of a networkusing the at least one beam pair prediction model.

[0217] Example 25. The apparatus of example 24, wherein the beam pair prediction comprises multiple predictions of: the at least one pair of beams of the network for respective multiple time instances or the information related to at least one pair of beams of the network for respective multiple time instances.

[0218] Example 26. The apparatus of example 25, wherein the at least one beam pair prediction model used to perform the beam pair prediction comprising the multiple predictions of the at least one pair of beams of the network for the respective multiple time instances or the information related to the at least one pair of beams of the network for the respective multiple time instances comprises a long-short-term-memory model, an artificial intelligence machine learning model, or a transformer model.

[0219] Example 27. The apparatus of any of examples 20 to 26, wherein: the at least one measurement performed based on the first rule during the training phase comprises a channel state information measurement, and the at least one measurement performed based on the second rule during the inference phase comprises a channel state information measurement.

[0220] Example 28. The apparatus of any of examples 20 to 27, wherein the apparatus is further caused to: receive, from the at least one user equipment during the training phase, at least one report based on the at least one measurement performed based on a first rule associated with a first transmission reception point during the training phase and the at least one measurement performed based on a second rule associated with a second transmission reception point during the training phase; and receive, from the at least one user equipment during the inference phase, at least one report based on the at least one measurement performed based on a third rule associated with the first transmission reception point during the inference phase and based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first rule associated with the first transmission reception point for performing the at least one measurement during the training phase is the same as the third rule associated with the first transmission reception point for performing the at least one measurement during the inference phase, and the second rule associated with the second transmission reception point for performing the at least one measurement during the training phase is the same as the fourth rule associated with the second transmission reception point for performing the at leastone measurement during the inference phase.

[0221] Example 29. The apparatus of example 28, wherein the apparatus is further caused to: train at least one beam pair prediction model for the first transmission reception point using the at least one report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase; train at least one beam pair prediction model for the second transmission reception point using the at least one report based on the at least one measurement performed based on the second rule associated with the second transmission reception point during the training phase; perform beam pair prediction to predict at least one pair of beams of the first transmission reception point or information related to at least one pair of beams of the first transmission reception point using the at least one beam pair prediction model for the first transmission reception point and the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase; and perform beam pair prediction to predict at least one pair of beams of the second transmission reception point or information related to at least one pair of beams of the second transmission reception point using the at least one beam pair prediction model for the second transmission reception point and the at least one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase.

[0222] Example 30. The apparatus of example 29, wherein the predicted information related to the at least one pair of beams of the first transmission reception point, or the predicted information related to the at least one pair of beams of the second transmission reception point, comprises one or more of: a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on at least one metric of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective layer 1 reference signal received power values of the beams of the subset of beams and the beams of the set of beams,and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective probability values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams.

[0223] Example 31. The apparatus of any of examples 29 to 30, wherein the predicted information related to the at least one pair of beams of the first transmission reception point, or the predicted information related to the at least one pair of beams of the second transmission reception point, comprises one or more of: predicted Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and probability values of predicted Top-K beam pairs IDs for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs IDs and probability values of predicted Top-K beam pairs IDs for an integer K.

[0224] Example 32. The apparatus of any of examples 20 to 31 , wherein the first rule and the second rule are based on the at least one measurement performed using a subset of panels of the at least one user equipment.

[0225] Example 33. The apparatus of any of examples 20 to 32, wherein the first rule and the second rule are based on the at least one measurement performed based on the first rule and the second rule being a type of measurement.

[0226] Example 34. The apparatus of example 33, wherein the type of measurement is at least one of: at least one layer 1 reference signal received power, or at least one layer 1 reference signal received power of at least one transmission reception point.

[0227] Example 35. The apparatus of any of examples 29 to 34, wherein the apparatus is further caused to: transmit, to the at least one user equipment, a first transmission with a pair of beams of the first transmission reception point, based on the beam pair prediction to predict the at least one pair of beams of the first transmission reception point and the report based on the at least one measurement performed based on the third rule associated with the firsttransmission reception point during the inference phase; and transmit, to the at least one user equipment, a second transmission with a pair of beams of the second transmission reception point, based on the beam pair prediction to predict the at least one pair of beams of the second transmission reception point and the report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first transmission transmitted to the at least one user equipment with the pair of beams of the first transmission reception point and the second transmission transmitted to the at least one user equipment with the pair of beams of the second transmission reception point are transmitted to the at least one user equipment at least partially simultaneously.

[0228] Example 36. The apparatus of any of examples 20 to 35, wherein the apparatus is further caused to: receive, from a first user equipment, a report based on the at least one measurement performed based on at least one first rule during the training phase; receive, from a second user equipment, a report based on the at least one measurement performed based on at least one second rule during the training phase; and train, during the training phase, at least one beam pair prediction model using the report received from the first user equipment based on the at least one measurement performed based on the at least one first rule during the training phase and the report received from the second user equipment based on the at least one measurement performed based on the at least one second rule during the training phase.

[0229] Example 37. The apparatus of example 36, wherein the apparatus is further caused to: receive, from the first user equipment, a report based on the at least one measurement performed based on at least one third rule during the inference phase; receive, from the second user equipment, a report based on the at least one measurement performed based on at least one fourth rule during the inference phase; and perform beam pair prediction to predict the at least one pair of beams of a network or information related to the at least one pair of beams of a network during the inference phase using the at least one beam pair prediction model, the report received from the first user equipment based on the at least one measurement performed based on the at least one third rule during the inference phase, and the report received from the second user equipment based on the at least one measurement performed based on the at least one fourth rule during the inference phase; wherein the at least one first rule for performing the at least one measurement by the first user equipment during the training phaseis the same as the at least one third rule for performing the at least one measurement by the first user equipment during the inference phase, and the at least one second rule for performing the at least one measurement by the second user equipment during the training phase is the same as the at least one fourth rule for performing the at least one measurement by the second user equipment during the inference phase.

[0230] Example 38. The apparatus of any of examples 24 to 37, wherein the apparatus is further caused to: receive, from the at least one user equipment, an indication of the first rule used to determine the report based on the at least one measurement performed during the training phase; wherein the at least one beam pair prediction model is trained based on the indication received from the user equipment of the first rule used to determine the report based on the at least one measurement performed during the training phase; and receive, from the at least one user equipment, an indication of the second rule used to determine the report based on the at least one measurement performed during the inference phase; wherein the beam pair prediction to predict the at least one pair of beams of the network or the information related to at least one pair of beams of the network is performed based on the indication received from the user equipment of the second rule used to determine the report based on the at least one measurement performed during the inference phase.

[0231] Example 39. The apparatus of any of examples 24 to 38, wherein the predicted at least one pair of beams of the network using the at least one beam pair prediction model and the report based on the at least one measurement performed based on the second rule during the inference phase comprises a pair of beams of the network predicted to have a highest reference signal received power among a set of pairs of beams of the network.

[0232] Example 40. The apparatus of example 39, wherein the pair of beams of the network predicted to have the highest reference signal received power among the set of pairs of beams of the network comprises Top-K beams, where K is an integer.

[0233] Example 41. The apparatus any of examples 24 to 40, wherein the predicted information related to the at least one pair of beams of the network comprises one or more of: a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on at least one metric of the beams of the subset of beams and the beams of the set of beams, and there are anumber of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective layer 1 reference signal received power values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective probability values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams.

[0234] Example 42. The apparatus of any of examples 24 to 41, wherein the predicted information related to the at least one pair of beams of the network comprises one or more of: predicted Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and probability values of predicted Top-K beam pairs IDs for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs IDs and probability values of predicted Top-K beam pairs IDs for an integer K.

[0235] Example 43. The apparatus of any of examples 28 to 42, wherein the apparatus is further caused to: transmit, to the at least one user equipment, a first configuration that indicates first reference signal resources to use for performing the at least one measurement during the training phase, and a second configuration that indicates second reference signal resources to use for performing the at least one measurement during the training phase; wherein the first reference signal resources are associated with the first transmission reception point, and the second reference signal resources are associated with the second transmission reception point; wherein the at least one report received from the at least one user equipment during the training phase is based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase usingthe first reference signal resources and the second rule associated with the second transmission reception point using the second reference signal resources; transmit, to the at least one user equipment, a third configuration that indicates third reference signal resources to use for performing the at least one measurement during the inference phase, and a fourth configuration that indicates fourth reference signal resources to use for performing the at least one measurement during the inference phase; wherein the third reference signal resources are associated with the first transmission reception point, and the fourth reference signal resources are associated with the second transmission reception point; wherein the at least one report received from the at last one user equipment during the inference phase is based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase using the third reference signal resources and the fourth rule associated with the second transmission reception point the fourth reference signal resources.

[0236] Example 44. The apparatus of any of examples 24 to 43, wherein the apparatus is further caused to: receive, from at least one user equipment, at least one indication that the at least one user equipment is capable of performing the at least one measurement during the training phase using resources associated with a first transmission reception point and resources associated with a second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point; wherein the report received from the at least one user equipment during the training phase comprises the at least one measurement performed using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point; wherein the at least one beam pair prediction model is trained using the at least one measurement performed during the training phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point; wherein the report received from the at least one user equipment during the inference phase comprises the at least one measurement performed during the inference phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point; wherein the at least one predicted pair of beams of the network comprises at least one pair of beams of the first transmission reception point and at least one pair of beams of the second transmission reception point, or the information related to at least one pair ofbeams of a network comprises information related to at least one pair of beams of the first transmission reception point and at least one pair of beams of the second transmission reception point.

[0237] Example 45. The apparatus of any of examples 24 to 44, wherein the apparatus is further caused to: receive, from the at least one user equipment during the training phase, information used to train the at least one beam pair prediction model, wherein the information used to train the at least one beam pair prediction model comprises a best set of at least one pair of beams of a first transmission reception point among a plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of a second transmission reception point among a plurality of pairs of beams of the second transmission reception point; and receive, from the at least one user equipment during the inference phase, information used to perform the beam pair prediction, wherein the information used to perform the beam pair prediction comprises a best set of at least one pair of beams of the first transmission reception point among the plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of the second transmission reception point among the plurality of pairs of beams of the second transmission reception point.

[0238] Example 46. A method including: determining at least one rule for performing at least one measurement; wherein the at least one rule for performing the at least one measurement comprises a first rule for performing the at least one measurement during a training phase and a second rule for performing the at least one measurement during an inference phase; performing the at least one measurement based on the first rule during the training phase; transmitting, to a network, a report based on the at least one measurement performed based on the first rule during the training phase; performing the at least one measurement based on the second rule during the inference phase; and transmitting, to the network, a report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement during the training phase is the same as the second rule for performing the at least one measurement during the inference phase.

[0239] Example 47. A method including: receiving, from at least one user equipment during a training phase, a report based on at least one measurement performed based on a first rule during the training phase; training, during the training phase, at least one model using thereport based on the at least one measurement performed based on the first rule during the training phase; receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on a second rule during the inference phase; and performing, during the inference phase, prediction using the at least one model and the report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule for performing the at least one measurement used to perform the prediction during the inference phase.

[0240] Example 48. An apparatus including: means for determining at least one rule for performing at least one measurement; wherein the at least one rule for performing the at least one measurement comprises a first rule for performing the at least one measurement during a training phase and a second rule for performing the at least one measurement during an inference phase; means for performing the at least one measurement based on the first rule during the training phase; means for transmitting, to a network, a report based on the at least one measurement performed based on the first rule during the training phase; means for performing the at least one measurement based on the second rule during the inference phase; and means for transmitting, to the network, a report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement during the training phase is the same as the second rule for performing the at least one measurement during the inference phase.

[0241] Example 49. An apparatus including: means for receiving, from at least one user equipment during a training phase, a report based on at least one measurement performed based on a first rule during the training phase; means for training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule during the training phase; means for receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on a second rule during the inference phase; and means for performing, during the inference phase, prediction using the at least one model and the report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule for performing the at leastone measurement used to perform the prediction during the inference phase.

[0242] Example 50. A computer readable medium including instructions stored thereon for performing at least the following: determining at least one rule for performing at least one measurement; wherein the at least one rule for performing the at least one measurement comprises a first rule for performing the at least one measurement during a training phase and a second rule for performing the at least one measurement during an inference phase; performing the at least one measurement based on the first rule during the training phase; transmitting, to a network, a report based on the at least one measurement performed based on the first rule during the training phase; performing the at least one measurement based on the second rule during the inference phase; and transmitting, to the network, a report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement during the training phase is the same as the second rule for performing the at least one measurement during the inference phase.

[0243] Example 51. A computer readable medium including instructions stored thereon for performing at least the following: receiving, from at least one user equipment during a training phase, a report based on at least one measurement performed based on a first rule during the training phase; training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule during the training phase; receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on a second rule during the inference phase; and performing, during the inference phase, prediction using the at least one model and the report based on the at least one measurement performed based on the second rule during the inference phase; wherein the first rule for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule for performing the at least one measurement used to perform the prediction during the inference phase.

[0244] References to a ‘computer’, ‘processor’, etc. should be understood to encompass not only computers having different architectures such as single / multi-processor architectures and sequential or parallel architectures but also specialized circuits such as field- programmable gate arrays (FPGAs), application specific circuits (ASICs), signal processing devices and other processing circuitry. References to computer program, instructions, codeetc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc.

[0245] The memories as described herein may be implemented using any suitable data storage technology, such as semiconductor based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, non-transitory memory, transitory memory, fixed memory and removable memory. The memories may comprise a database for storing data.

[0246] The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0247] As used herein, the term ‘circuitry’ may refer to the following: (a) hardware circuit implementations, such as implementations in analog and / or digital circuitry, and (b) combinations of circuits and software (and / or firmware), such as (as applicable): (i) a combination of processor(s) or (ii) portions of processor(s) / software including digital signal processor(s), software, and memories that work together to cause an apparatus to perform various functions, and (c) circuits, such as a microprocessor(s) or a portion of a microprocessor(s), that require software or firmware for operation, even if the software or firmware is not physically present. As a further example, as used herein, the term ‘circuitry’ would also cover an implementation of merely a processor (or multiple processors) or a portion of a processor and its (or their) accompanying software and / or firmware. The term ‘circuitry’ would also cover, for example and if applicable to the particular element, a baseband integrated circuit or applications processor integrated circuit for a mobile phone or a similar integrated circuit in a server, a cellular network device, or another network device.

[0248] It should be understood that the foregoing description is only illustrative. Various alternatives and modifications may be devised by those skilled in the art. For example, features recited in the various dependent claims could be combined with each other in any suitable combination(s). In addition, features from different example embodiments described above could be selectively combined into a new example embodiment. Accordingly, this description is intended to embrace all such alternatives, modifications and variances whichfall within the scope of the appended claims.

[0249] The following acronyms and abbreviations that may be found in the specification and / or the drawing figures are given as follows (the abbreviations and acronyms may be appended / combined with each other or with other characters using e.g. a dash, hyphen, slash, letter, or number, and may be case insensitive):4G fourth generation5G fifth generation5GC 5G core network6G sixth generationAl artificial intelligenceAMF access and mobility management functionASIC application- specific integrated circuitBM beam managementCD compact / computer discCN core networkCNN convolutional neural networkCORESET control resource setCPU central processing unitCRI CSI-RS resource indicatorCSI channel state informationCSI-RS channel state information reference signal cu central unit or centralized unitDC dual connectivityDL downlinkDSP digital signal processorDU distributed unitDVD digital versatile disc eNB evolved Node B (e.g., an LTE base station)EN-DC, EN DC E-UTRAN new radio - dual connectivity en-gNB node providing NR user plane and control plane protocol terminations towards the UE, and acting as a secondary node in EN-DCEPC evolved packet core E-UTRA evolved UMTS terrestrial radio access, i.e., the LTE radio access technologyE-UTRAN E-UTRA network Fl interface between the CU and the DU FPGA field-programmable gate array FR2 frequency range 2 FS feature study gNB generalized node B, base station for 5G / NR, i.e., a node providing NR user plane and control plane protocol terminations towards the UE, and connected via the NG interface to the 5GCIAB integrated access and backhaul ID identifier I / F interface I / O input / output LI layer 1 LCM lifecycle management LMF location management function LSTM long short term memoryLTE long term evolution (4G) MAC medium access control MAC-CE medium access control control elementMIMO multiple input multiple output ML machine learning MME mobility management entity MRO mobility robustness optimization NCE network control element ng or NG new generation ng-eNB new generation eNB NG-RAN new generation radio access networkNR new radioNW network N / W network NZP non-zero-powerOAM operations administration and maintenance, or operations and managementOTT over the topPCI physical cell identifierPCRI predicted CRIPDA personal digital assistantPDCP packet data convergence protocolPHY physical layerPRSRP predicted RSRPPSSBRI predicted SSBRI r release (e.g. rl7)RAM random access memoryRAN radio access networkRAN 1 radio layer 1 , or RAN working group 1RAN2 radio layer 2, or RAN working group 2Rel releaseRLC radio link controlROM read-only memoryRP RAN plenaryRRC radio resource controlRS reference signalRSRP reference signal received powerRU radio unitRx, RX receive, or receiver, or receptionSA system aspectsSI interface between the mobility management entity (MME) in theEPC and the evolved Node B’s in the E-UTRANSDAP service data adaptation protocolSet A the complete set of beams over which the prediction operatesSet Al the complete set of beams of or associated with TRP1 over which the prediction operatesSet A2 the complete set of beams of or associated with TRP2 over which the prediction operatesSet B the set of beams whose measurements are inputted to the AI / MLmodelSet Bl the set of beams of or associated with TRP1 whose measurements are inputted to the AI / ML modelSet B2 the set of beams of or associated with TRP2 whose measurements are inputted to the AI / ML modelSGW serving gatewaySINR signal to interference plus noise ratioSMF session management functionSON self-organizing / optimizing networkSSB synchronization signal block, or synchronization and physical broadcast channel blockSSBRI synchronization signal block resource indicator, or synchronization signal and physical broadcast channel block resource indicatorTR technical reportTRP transmission reception pointTx transmit, or transmitter, or transmissionUAV unmanned aerial vehicleUE user equipment (e.g., a wireless, typically mobile device)UI user interfaceUL uplinkUMTS Universal Mobile Telecommunications SystemUPF user plane functionUSB universal serial busUTRAN universal terrestrial radio access networkWG working groupWI work itemX2 network interface between RAN nodes and between RAN and the core networkXn network interface between NG-RAN nodes

Claims

CLAIMSWhat is claimed is:

1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; perform the at least one measurement based on the first rule received with the first configuration during the training phase; transmit, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; perform the at least one measurement based on the second rule received with the second configuration during the inference phase; and transmit, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

2. The apparatus of claim 1, wherein the at least one measurement performed based on the second rule during the inference phase is based on a model that is trained based on the first rule that is the same as the second rule.

3. The apparatus of any of claims 1 to 2, wherein the at least one measurement performed based on the first rule during the training phase is configured to be used to train at least one model during the training phase, wherein the at least one model trained during the training phase based on the at least one measurement performed based on the first rule during the training phase comprises a statistical model.

4. The apparatus of any of claims 1 to 3, wherein at least one model trained during the training phase based on the at least one measurement performed based on the first rule received with the first configuration during the training phase comprises a beam pair prediction model.

5. The apparatus of any of claims 1 to 4, wherein the at least one measurement performed based on the second rule received with the second configuration is configured to be used to perform beam pair prediction using at least one beam pair prediction model.

6. The apparatus of any of claims 5, wherein the beam pair prediction comprises multiple predictions of: at least one pair of beams of the network for respective multiple time instances, or information related to at least one pair of beams of the network for respective multiple time instances.

7. The apparatus claim 6, wherein at least one beam pair prediction model used to perform the beam pair prediction comprising the multiple predictions of the at least one pair of beams of the network for respective multiple time instances or the information related to the at least one pair of beams of the network for the respective multiple time instances comprises a long-short-term-memory model, an artificial intelligence machine learning model, or a transformer model.

8. The apparatus of any of claims 1 to 7, wherein the apparatus is further caused to: compare the first rule to the second rule;wherein the at least one measurement performed based on the second rule during the inference phase is based on a model that is trained based on the first rule that is the same as the second rule.

9. The apparatus of any of claims 1 to 18, wherein: the at least one measurement performed based on the first rule received with the first configuration during the training phase comprises a channel state information measurement, and the at least one measurement performed based on the second rule received with the second configuration during the inference phase comprises a channel state information measurement.

10. The apparatus of any of claims 1 to 9, wherein the apparatus is further caused to: receive, from the network, a first rule for performing the at least one measurement; wherein the first rule for performing the at least one measurement is associated with a first transmission reception point; perform the at least one measurement based on the first rule during the training phase; receive, from the network, a second rule for performing the at least one measurement; wherein the second rule for performing the at least one measurement is associated with a second transmission reception point; perform the at least one measurement based on the second rule during the training phase; transmit, to the network, at least one report based on the at least one measurement performed based on the first rule during the training phase and the at least one measurement performed based on the second rule during the training phase;receive, from the network, a third rule for performing the at least one measurement; wherein the third rule for performing the at least one measurement is associated with the first transmission reception point; perform the at least one measurement based on the third rule during the inference phase; receive, from the network, a fourth rule for performing the at least one measurement; wherein the fourth rule for performing the at least one measurement is associated with the second transmission reception point; perform the at least one measurement based on the fourth rule during the training phase; perform the at least one measurement based on the first rule during the inference phase; perform the at least one measurement based on the second rule during the inference phase; and transmit, to the network, at least one report based on the at least one measurement performed based on the third rule during the inference phase and the at least one measurement performed based on the fourth rule during the inference phase; wherein the first rule associated with the first transmission reception point for performing the at least one measurement during the training phase is the same as the third rule associated with the first transmission reception point for performing the at least one measurement during the inference phase, and the second rule associated with the second transmission reception point for performing the at least one measurement during the training phase is the same as the fourth rule associated with the second transmission reception point for performing the at least one measurement during the inference phase.

11. The apparatus of claim 10, wherein: the at least one report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase is configured to be used to train at least one beam pair prediction model for the first transmission reception point, and the at least one report based on the at least one measurement performed based on the second rule associated with the second transmission reception point during the training phase is configured to be used to train at least one beam pair prediction model for the second transmission reception point, and the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase is configured to be used to perform beam pair prediction using the at least one beam pair prediction model for the first transmission reception point, and the at least one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase is configured to be used to perform beam pair prediction using the at least one beam pair prediction model for the second transmission reception point.

12. The apparatus of any of claims 1 to 11, wherein the at least one rule is based on the apparatus performing the at least one measurement using a subset of panels of the apparatus.

13. The apparatus of any of claims 1 to 12, wherein the at least one rule is based on the at least one measurement performed based on the at least one rule being a type of measurement.

14. The apparatus of claim 13, wherein the type of measurement is at least one of: at least one layer 1 reference signal received power, or at least one layer 1 reference signal received power of at least one transmission reception point.

15. The apparatus of any of claims 10 to 14, wherein the apparatus is further caused to: receive, from the network, a first transmission with a pair of beams of the first transmission reception point, based on the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase; and receive, from the network, a second transmission with a pair of beams of the second transmission reception point, based on the at least one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first transmission received from the network with the pair of beams of the first transmission reception point and the second transmission received from the network with the pair of beams of the second transmission reception point are received from the network at least partially simultaneously.

16. The apparatus of any of claims 11 to 15, wherein: the at least one configuration comprises: a first configuration that indicates first reference signal resources to use for performing the at least one measurement during the training phase, and a second configuration that indicates second reference signal resources to use for performing the at least one measurement during the training phase, and the first reference signal resources are associated with the first transmission reception point, and the second reference signal resources are associated with the second transmission reception point, and the at least one measurement is performed based on the first rule associated with the first transmission reception point during the training phase using the first reference signal resources and the second rule associated with the second transmission reception point during the training phase using the second reference signal resources, and the at least one configuration comprises: a third configuration that indicates third reference signal resources to use for performing the at least one measurementduring the inference phase, and a fourth configuration that indicates fourth reference signal resources to use for performing the at least one measurement during the inference phase, and the third reference signal resources are associated with the first transmission reception point, and the fourth reference signal resources are associated with the second transmission reception point, and the at least one measurement is performed based on the third rule associated with the first transmission reception point during the inference phase using the third reference signal resources and the fourth rule associated with the second transmission reception point during the inference phase using the fourth reference signal resources.

17. The apparatus of any of claims 1 to 16, wherein the apparatus is further caused to: transmit, to the network, at least one indication that the apparatus is capable of performing the at least one measurement during the training phase using resources associated with a first transmission reception point and resources associated with a second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with a second transmission reception point; wherein the at least one configuration received from the network is based on the at least one indication that the apparatus is capable of performing the at least one measurement during the training phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point.

18. The apparatus of any of claims 1 to 17, wherein the apparatus is further caused to: transmit, to the network during the training phase, information comprising a best set of at least one pair of beams of a first transmission reception point among a plurality of pairs of beams of the first transmission reception point, and a best set of atleast one pair of beams of a second transmission reception point among a plurality of pairs of beams of the second transmission reception point, and transmit, to the network during the inference phase, information comprising a best set of at least one pair of beams of the first transmission reception point among the plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of the second transmission reception point among the plurality of pairs of beams of the second transmission reception point.

19. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; receive, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; train, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; receive, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; and perform, during the inference phase, prediction using the at least model and thereport based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase.

20. The apparatus of claim 19, wherein the at least one measurement performed based on the second rule during the inference phase used to perform the prediction is based on the at least one model that is trained based on the first rule that is the same as the second rule.

21. The apparatus of any of claims 19 to 20, wherein the at least one model trained during the training phase based on the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase comprises a statistical model.

22. The apparatus of any of claims 19 to 21, wherein the at least one model trained during the training phase based on the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase is trained offline to perform Top-K beam pairs prediction, where K is an integer.

23. The apparatus of any of claims 19 to 22, wherein: the at least one model trained during the training phase using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase comprises at least one beam pair prediction model, and the prediction performed during the inference phase using the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase and the least one model comprises beam pair prediction to predict: at least one pair of beams of a network or informationrelated to at least one pair of beams of a network using the at least one beam pair prediction model.

24. The apparatus of claim 23, wherein the beam pair prediction comprises multiple predictions of: the at least one pair of beams of the network for respective multiple time instances or the information related to at least one pair of beams of the network for respective multiple time instances.

25. The apparatus of claim 24, wherein the at least one beam pair prediction model used to perform the beam pair prediction comprising the multiple predictions of the at least one pair of beams of the network for the respective multiple time instances or the information related to the at least one pair of beams of the network for the respective multiple time instances comprises a long-short-term-memory model, an artificial intelligence machine learning model, or a transformer model.

26. The apparatus of any of claims 19 to 25, wherein: the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase comprises a channel state information measurement, and the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase comprises a channel state information measurement.

27. The apparatus of any of claims 19 to 26, wherein the apparatus is further caused to: transmit, to the at least one user equipment, a first rule associated with a first transmission reception point for performing the at least one measurement during the training phase; transmit, to the at least one user equipment, a second rule associated with a second transmission reception point for performing the at least one measurement during the training phase; receive, from the at least one user equipment during the training phase, at leastone report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase and the at least one measurement performed based on the second rule associated with the second transmission reception point during the training phase; transmit, to the at least one user equipment, a third rule associated with the first transmission reception point for performing the at least one measurement during the inference phase; transmit, to the at least one user equipment, a fourth rule associated with the second transmission reception point for performing the at least one measurement during the inference phase; and receive, from the at least one user equipment during the inference phase, at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase and based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first rule associated with the first transmission reception point for performing the at least one measurement during the training phase is the same as the third rule associated with the first transmission reception point for performing the at least one measurement during the inference phase, and the second rule associated with the second transmission reception point for performing the at least one measurement during the training phase is the same as the fourth rule associated with the second transmission reception point for performing the at least one measurement during the inference phase.

28. The apparatus of claim 27, wherein the apparatus is further caused to: train at least one beam pair prediction model for the first transmission reception point using the at least one report based on the at least one measurement performed based on the first rule associated with the first transmission reception point during the training phase;train at least one beam pair prediction model for the second transmission reception point using the at least one report based on the at least one measurement performed based on the second rule associated with the second transmission reception point during the training phase; perform beam pair prediction to predict at least one pair of beams of the first transmission reception point or information related to at least one pair of beams of the first transmission reception point using the at least one beam pair prediction model for the first transmission reception point and the at least one report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase; and perform beam pair prediction to predict at least one pair of beams of the second transmission reception point or information related to at least one pair of beams of the second transmission reception point using the at least one beam pair prediction model for the second transmission reception point and the at least one report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase.

29. The apparatus of claim 28, wherein the predicted information related to the at least one pair of beams of the first transmission reception point, or the predicted information related to the at least one pair of beams of the second transmission reception point, comprises one or more of: a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on at least one metric of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective layer 1 reference signal received power values of the beams ofthe subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective probability values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams.

30. The apparatus of any of claims 28 to 29, wherein the predicted information related to the at least one pair of beams of the first transmission reception point, or the predicted information related to the at least one pair of beams of the second transmission reception point, comprises one or more of: predicted Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and probability values of predicted Top-K beam pairs IDs for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs IDs and probability values of predicted Top-K beam pairs IDs for an integer K.

31. The apparatus of any of claims 19 to 30, wherein the at least one rule is based on the at least one measurement performed using a subset of panels of the at least one user equipment.

32. The apparatus of any of claims 19 to 31, wherein the at least one rule is based on the at least one measurement performed based on the at least one rule being a type of measurement.

33. The apparatus of claim 32, wherein the type of measurement is at least one of: at least one layer 1 reference signal received power, or at least one layer 1 reference signal received power of at least one transmission reception point.

34. The apparatus of any of claims 28 to 33, wherein the apparatus is further caused to: transmit, to the at least one user equipment, a first transmission with a pair of beams of the first transmission reception point, based on the beam pair prediction to predict the at least one pair of beams of the first transmission reception point and the report based on the at least one measurement performed based on the third rule associated with the first transmission reception point during the inference phase; and transmit, to the at least one user equipment, a second transmission with a pair of beams of the second transmission reception point, based on the beam pair prediction to predict the at least one pair of beams of the second transmission reception point and the report based on the at least one measurement performed based on the fourth rule associated with the second transmission reception point during the inference phase; wherein the first transmission transmitted to the at least one user equipment with the pair of beams of the first transmission reception point and the second transmission transmitted to the at least one user equipment with the pair of beams of the second transmission reception point are transmitted to the at least one user equipment at least partially simultaneously.

35. The apparatus of any of claims 19 to 34, wherein the apparatus is further caused to: transmit, to a first user equipment, a first configuration comprising at least one first rule for performing the at least one measurement during the training phase configured to be used to train at least one beam pair prediction model; receive, from the first user equipment, a report based on the at least one measurement performed based on the at least one first rule during the training phase; transmit, to a second user equipment, a second configuration comprising at leastone second rule for performing the at least one measurement during the training phase configured to be used to train the at least one beam pair prediction model; receive, from the second user equipment, a report based on the at least one measurement performed based on the at least one second rule during the training phase; and train, during the training phase, the at least one beam pair prediction model using the report received from the first user equipment based on the at least one measurement performed based on the at least one first rule during the training phase and the report received from the second user equipment based on the at least one measurement performed based on the at least one second rule during the training phase.

36. The apparatus of claim 35, wherein the apparatus is further caused to: transmit, to the first user equipment, a third configuration comprising at least one third rule for performing the at least one measurement during the inference phase; receive, from the first user equipment, a report based on the at least one measurement performed based on the at least one third rule during the inference phase; transmit, to the first user equipment, a fourth configuration comprising at least one fourth rule for performing the at least one measurement during the inference phase; receive, from the second user equipment, a report based on the at least one measurement performed based on the at least one fourth rule during the inference phase; and perform beam pair prediction to predict the at least one pair of beams of a network or the information related to the at least one pair of beams of a network during the inference phase using the at least one beam pair prediction model, the report received from the first user equipment based on the at least one measurement performed based on the at least one third rule during the inference phase, and the report received from the second user equipment based on the at least one measurement performed based on the at least one fourth rule during the inference phase;wherein the at least one first rule for performing the at least one measurement by the first user equipment during the training phase is the same as the at least one third rule for performing the at least one measurement by the first user equipment during the inference phase, and the at least one second rule for performing the at least one measurement by the second user equipment during the training phase is the same as the at least one fourth rule for performing the at least one measurement by the second user equipment during the inference phase.

37. The apparatus of any of claims 23 to 36, wherein the predicted at least one pair of beams of the network using the at least one beam pair prediction model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase comprises a pair of beams of the network predicted to have a highest reference signal received power among a set of pairs of beams of the network.

38. The apparatus of claim 37, wherein the pair of beams of the network predicted to have the highest reference signal received power among the set of pairs of beams of the network comprises Top-K beams, where K is an integer.

39. The apparatus of any of claims 23 to 38, wherein the predicted information related to the at least one pair of beams of the network comprises one or more of: a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on at least one metric of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective layer 1 reference signal received power values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset ofbeams, or a subset of beam pair identifiers corresponding to a subset of beams of a set of beam pair identifiers corresponding to a set of beams, wherein the beams of the subset of beams having the beam pair identifiers are considered top among the beams of the set based on respective probability values of the beams of the subset of beams and the beams of the set of beams, and there are a number of the beam pair identifiers of the subset of beam pair identifier and beams of the subset of beams.

40. The apparatus of any of claims 23 to 39, wherein the predicted information related to the at least one pair of beams of the network comprises one or more of: predicted Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs identifiers (IDs) for an integer K, or predicted Top-K beam pairs identifiers (IDs) and probability values of predicted Top-K beam pairs IDs for an integer K, or predicted Top-K beam pairs identifiers (IDs) and predicted Top-K layer 1 reference signal received power (Ll-RSRP) of Top-K beam pairs IDs and probability values of predicted Top-K beam pairs IDs for an integer K.

41. The apparatus of any of claims 27 to 40, wherein: the at least one configuration comprises: a first configuration that indicates first reference signal resources to use for performing the at least one measurement during the training phase, and a second configuration that indicates second reference signal resources to use for performing the at least one measurement during the training phase, and the first reference signal resources are associated with a first transmission reception point, and the second reference signal resources are associated with a second transmission reception point, andthe at least one report is received from the at least one user equipment during the training phase based on the at least one measurement performed based on the first rule associated with the first transmission reception point transmitted with the first configuration during the training phase using the first reference signal resources and the second rule associated with the second transmission reception point using the second reference signal resources, and the at least one configuration comprises: a third configuration that indicates third reference signal resources to use for performing the at least one measurement during the inference phase, and a fourth configuration that indicates fourth reference signal resources to use for performing the at least one measurement during the inference phase, and wherein the third reference signal resources are associated with the first transmission reception point, and the fourth reference signal resources are associated with the second transmission reception point, and the at least one report is received from the at least one user equipment during the inference phase based on the at least one measurement performed based on the third rule associated with the first transmission reception point transmitted with the third configuration during the inference phase using the third reference signal resources and the fourth rule associated with the second transmission reception point transmitted with the fourth configuration during the inference phase using the fourth reference signal resources.

42. The apparatus of any of claims 19 to 41, wherein the apparatus is further caused to: receive, from the at least one user equipment, at least one indication that the at least one user equipment is capable of performing the at least one measurement during the training phase using resources associated with a first transmission reception point and resources associated with a second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with a second transmission reception point;wherein the at least one configuration transmitted to the at least one user equipment is based on the at least one indication that the at least one user equipment is capable of performing the at least one measurement during the training phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and the at least one measurement during the inference phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point.

43. The apparatus of claim 42, wherein: the report received from the at least one user equipment during the training phase comprises the at least one measurement performed using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and at least one beam pair prediction model is trained using the at least one measurement performed during the training phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and the report received from the at least one user equipment during the inference phase comprises the at least one measurement performed during the inference phase using the resources associated with the first transmission reception point and the resources associated with the second transmission reception point, and at least one predicted pair of beams of a network comprises at least one pair of beams of the first transmission reception point and at least one pair of beams of the second transmission reception point, or information related to at least one pair of beams of a network comprises information related to at least one pair of beams of the first transmission reception point and at least one pair of beams of the second transmission reception point.

44. The apparatus of any of claims 23 to 43, wherein the apparatus is further caused to:receive, from the at least one user equipment during the training phase, information used to train the at least one beam pair prediction model, wherein the information used to train the at least one beam pair prediction model comprises a best set of at least one pair of beams of a first transmission reception point among a plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of a second transmission reception point among a plurality of pairs of beams of the second transmission reception point; and receive, from the at least one user equipment during the inference phase, information used to perform the beam pair prediction, wherein the information used to perform the beam pair prediction comprises a best set at least one pair of beams of the first transmission reception point among the plurality of pairs of beams of the first transmission reception point, and a best set of at least one pair of beams of the second transmission reception point among the plurality of pairs of beams of the second transmission reception point.

45. A method comprising: receiving, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; performing the at least one measurement based on the first rule received with the first configuration during the training phase; transmitting, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; performing the at least one measurement based on the second rule received with the second configuration during the inference phase; and transmitting, to the network, a report based on the at least one measurementperformed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

46. A method comprising: transmitting, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; receiving, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; and performing, during the inference phase, prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performingthe at least one measurement used to perform the prediction during the inference phase.

47. An apparatus comprising: means for receiving, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; means for performing the at least one measurement based on the first rule received with the first configuration during the training phase; means for transmitting, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; means for performing the at least one measurement based on the second rule received with the second configuration during the inference phase; and means for transmitting, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

48. An apparatus comprising: means for transmitting, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at leastone measurement during an inference phase; means for receiving, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; means for training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; means for receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; and means for performing, during the inference phase, prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase.

49. A computer readable medium comprising instructions stored thereon for performing at least the following: receiving, from a network, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; performing the at least one measurement based on the first rule received with the first configuration during the training phase;transmitting, to the network, a report based on the at least one measurement performed based on the first rule during the training phase; performing the at least one measurement based on the second rule received with the second configuration during the inference phase; and transmitting, to the network, a report based on the at least one measurement performed based on the at least one rule during the inference phase; wherein the first rule received with the first configuration for performing the at least one measurement during the training phase is the same as the second rule received with the second configuration for performing the at least one measurement during the inference phase.

50. A computer readable medium comprising instructions stored thereon for performing at least the following: transmitting, to at least one user equipment, at least one configuration comprising at least one rule for performing at least one measurement; wherein the at least one configuration comprises a first configuration comprising a first rule for performing the at least one measurement during a training phase, and a second configuration comprising a second rule for performing the at least one measurement during an inference phase; receiving, from the at least one user equipment during the training phase, a report based on the at least one measurement performed based on the first rule during the training phase; training, during the training phase, at least one model using the report based on the at least one measurement performed based on the first rule transmitted with the first configuration during the training phase; receiving, from the at least one user equipment during an inference phase, a report based on the at least one measurement performed based on the second rule during the inference phase; andperforming, during the inference phase, prediction using the at least model and the report based on the at least one measurement performed based on the second rule transmitted with the second configuration during the inference phase; wherein the first rule transmitted with the first configuration for performing the at least one measurement used to train the at least one model during the training phase is the same as the second rule transmitted with the second configuration for performing the at least one measurement used to perform the prediction during the inference phase.

Images