Interference prediction for a beam set based on reference signal received power measurements on another beam set

Abstract

Example embodiments of the present disclosure relate to interference prediction of a set of beams based on reference signal received power (RSRP) measurements on another set of beams. A method includes receiving, from a second apparatus, an inference configuration associated with an interference prediction using a model and a prediction report of the interference prediction, performing, based on the inference configuration, reference signal received power, RSRP, measurements of a reference signal at one or more measurement time instances, the reference signal being transmitted from at least one transmission point on a first set of beams, performing, based on the inference configuration, an interference prediction for a second set of beams for one or more prediction time instances by providing the RSRP measurements as input to the model, and transmitting, to the second apparatus, the prediction report, wherein the prediction report is based on the interference prediction.

Description

Cross-reference to related applications

[0001] This application claims priority and interest in EP application No. 25171560.3, filed on April 22, 2025, the contents of which are incorporated herein by reference in their entirety. Technical Field

[0002] Various example embodiments of this disclosure generally relate to the telecommunications field, and more specifically to methods, apparatus, devices, and computer-readable storage media for predicting interference to a beam set based on a reference signal received power (RSRP) measurement on another beam set. Background Technology

[0003] With the development towards 6G networks, enhancing the reliability and efficiency of data transmission is crucial. In this context, artificial intelligence / machine learning (AI / ML) models can improve transmission reliability by predicting interference in beamsets. Summary of the Invention

[0004] In a first aspect of this disclosure, a first apparatus is provided. The first apparatus includes: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus to at least: receive from a second apparatus an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction; perform a reference signal received power (RSRP) measurement on a reference signal transmitted from at least one transmission point on a first beamset at one or more measurement time instances based on the inference configuration; perform interference prediction on a second beamset for one or more prediction time instances by providing the RSRP measurement as input to a model based on the inference configuration; and send a prediction report to the second apparatus, wherein the prediction report is based on the interference prediction.

[0005] In a second aspect of this disclosure, a second apparatus is provided. The second apparatus includes: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus to at least: transmit to a first apparatus an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction, wherein the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set from at least one transmission point associated with the second apparatus; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set; and receiving a prediction report from the first apparatus, wherein the prediction report is based on interference predictions for the second beam set for one or more prediction time instances.

[0006] In a third aspect of this disclosure, a method is provided. The method includes: receiving, by a first device, an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction from a second device; performing a reference signal received power (RSRP) measurement on a reference signal transmitted from at least one transmission point on a first beamset at one or more measurement time instances based on the inference configuration; performing interference prediction on a second beamset for one or more prediction time instances based on the inference configuration by providing the RSRP measurement as input to a model; and sending a prediction report to the second device, wherein the prediction report is based on the interference prediction.

[0007] In a fourth aspect of this disclosure, a method is provided. The method includes: transmitting from a second device to a first device an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction, wherein the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set from at least one transmission point associated with the second device; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set; and receiving a prediction report from the first device, wherein the prediction report is based on interference predictions for the second beam set for one or more prediction time instances.

[0008] In a fifth aspect of this disclosure, a first apparatus is provided. The first apparatus includes: means for receiving from a second apparatus an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction; means for performing a reference signal received power (RSRP) measurement on a reference signal at one or more measurement time instances based on the inference configuration, the reference signal being transmitted from at least one transmission point on a first beamset; means for performing interference prediction on a second beamset for one or more prediction time instances based on the inference configuration by providing the RSRP measurement as input to a model; and means for sending a prediction report to the second apparatus, wherein the prediction report is based on the interference prediction.

[0009] In a sixth aspect of this disclosure, a second apparatus is provided. The second apparatus includes: components for transmitting to a first apparatus an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction, wherein the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set from at least one transmission point associated with the second apparatus; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set; and components for receiving a prediction report from the first apparatus, wherein the prediction report is based on interference predictions of the second beam set for one or more prediction time instances.

[0010] In a seventh aspect of this disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to at least perform the method according to a third aspect.

[0011] In an eighth aspect of this disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to perform at least the method according to the fourth aspect.

[0012] It should be understood that the summary portion is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] Some exemplary embodiments will now be described with reference to the accompanying drawings, in which: Figure 1 An example communication environment in which example embodiments of this disclosure may be implemented is shown; Figure 2 A schematic diagram of beam management is shown; Figure 3 A schematic diagram of L1-RSRP measurement and interference measurement of the beam set is shown; Figure 4 Example signaling flows for interference prediction according to some example embodiments of this disclosure are shown; Figure 5 Example signaling flows for interference prediction according to some example embodiments of this disclosure are shown; Figure 6 A flowchart is shown illustrating a method implemented at a first device according to some exemplary embodiments of the present disclosure; Figure 7 A flowchart is shown illustrating a method implemented at a second device according to some example embodiments of the present disclosure; Figure 8 A flowchart is shown illustrating a method implemented at a first device according to some exemplary embodiments of the present disclosure; Figure 9 A flowchart is shown illustrating a method implemented at a second device according to some example embodiments of the present disclosure; Figure 10 A simplified block diagram of a device suitable for implementing example embodiments of the present disclosure is shown; and Figure 11 A block diagram of an example computer-readable medium according to some example embodiments of the present disclosure is shown.

[0014] In all the accompanying drawings, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0015] The principles of this disclosure will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only and to assist those skilled in the art in understanding and implementing this disclosure, and do not imply any limitation on the scope of this disclosure. The embodiments described herein can be implemented in various ways other than those described below.

[0016] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0017] References to "an embodiment," "embodiment," "example embodiment," etc., in this disclosure indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment must include that particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Additionally, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is believed that incorporating other embodiments, whether explicitly described or not, to affect such a feature, structure, or characteristic is within the knowledge of those skilled in the art.

[0018] It should be understood that although terms such as "first," "second," etc., preceding nouns may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another, and they do not restrict the order of nouns. For example, without departing from the scope of the exemplary embodiments, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0019] As used herein, “at least one of the following: a list of two or more elements” and “at least one of the following: a list of two or more elements” and similar wording (where the list of two or more elements is connected by “and” or “or”) means at least any one of the elements, or at least any two or more of the elements, or at least all of the elements.

[0020] As used herein, unless explicitly stated otherwise, the execution step “in response to A” does not indicate that the step is performed immediately after “A” occurs, and may include one or more intermediate steps.

[0021] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. As used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that, when used herein, the terms “comprising,” “including,” “having,” “having,” “covering,” and / or “encompassing” specify the presence of the stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0022] As used in this application, the term "circuit" may refer to one or more of the following: (a) Hardware circuit implementation only (such as implementation in analog and / or digital circuits only) and (b) A combination of hardware circuitry and software, such as (if applicable): (i) A combination of (multiple) analog and / or digital hardware circuits and software / firmware, and (ii) Any part of a hardware processor(s) having software (including (multiple) digital signal processors), software, and (multiple) memories, which work together to enable a device such as a mobile phone or server to perform various functions, and (c) (Multiple) hardware circuits and / or (multiple) processors, such as (multiple) microprocessors or a portion thereof, which require software (e.g., firmware) to operate, but may not exist when the software is not required to operate.

[0023] This definition of "circuit" applies to all uses of the term in this application (including in any claim). As another example, as used herein, the term "circuit" also encompasses only hardware circuitry or a processor (or multiple processors) or a portion thereof and its accompanying software and / or firmware implementation. The term "circuit" also encompasses, for example and if applicable to a particular claim element, baseband integrated circuits or processor integrated circuits for mobile devices or similar integrated circuits in servers, cellular network devices, or other computing or network devices.

[0024] As used herein, the term "communication network" refers to a network that conforms to any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), LTE-A Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. Furthermore, communication between terminal devices and network devices in a communication network can be performed according to any suitable generation of communication protocol, including but not limited to first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G), 5.5G, sixth-generation (6G) communication protocols and / or any other currently known or future-developed protocols. Embodiments of this disclosure can be applied to a variety of communication systems. Given the rapid development of communications, there will certainly be future types of communication technologies and systems that embody the future types of this disclosure. The scope of this disclosure should not be construed as limited to the aforementioned systems.

[0025] As used herein, the term "network device" refers to a node in a communications network through which terminal devices access the network and receive services. Depending on the terminology and technology applied, a network device can refer to a base station (BS) or access point (AP), such as a Node B (NodeB or NB), an evolved Node B (eNodeB or eNB), an NR NB (also known as a gNB), a Remote Radio Unit (RRU), a Radio Header (RH), a Remote Radio Header End (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low-power node (such as a femtosecond or picosecond), a non-terrestrial network (NTN) or non-terrestrial network device (such as a satellite network device), a low Earth orbit (LEO) satellite and a geostationary Earth orbit (GEO) satellite, a spacecraft network device, etc. In some example embodiments, the Radio Access Network (RAN) split architecture includes a centralized unit (CU) and a distributed unit (DU) at the IAB donor node. The IAB node includes a mobile terminal (IAB-MT) portion that behaves as a UE toward the parent node, and the DU portion of the IAB node behaves as a base station toward the next-hop IAB node.

[0026] The term "terminal device" refers to any terminal device capable of wireless communication. By way of example and not limitation, a terminal device may also be referred to as a communication device, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS), or access terminal (AT). Terminal devices may include, but are not limited to, mobile phones, cellular phones, smartphones, Voice over IP (VoIP) phones, wireless local loop phones, tablets, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and recycle bins, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded devices (LEEs), laptop mounted devices (LMEs), USB dongles, smart devices, wireless customer premises equipment (CPEs), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of industrial and / or automated processing chains), consumer electronics devices, devices operating on commercial and / or industrial wireless networks, etc. The terminal equipment may also correspond to the mobile termination (MT) portion of an IAB node (e.g., a relay node). In the following description, the terms "terminal equipment," "communication equipment," "terminal," "user equipment," and "UE" are used interchangeably.

[0027] As used herein, the terms “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” can refer to any resource used to perform communication, such as communication between a terminal device and a network device, including resources in the time domain, frequency domain, spatial domain, code domain, or any other combination of time, frequency, spatial, and / or code domain resources used to enable communication. In the following, unless explicitly stated otherwise, resources in the frequency and time domains will be used as examples of transmission resources used to describe some exemplary embodiments of this disclosure. Note that the exemplary embodiments of this disclosure are equally applicable to other resources in other domains.

[0028] As used in this article, the term "AI / ML model" refers to a data-driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs.

[0029] As used herein, the term "AI / ML model delivery" is a general term referring to the delivery of AI / ML models from one entity to another in any manner. Entities can refer to network nodes / functions (e.g., gNB, Location Management Function (LMF), etc.), UEs, proprietary servers, etc. As used in this article, the term "AI / ML model inference" refers to the process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0030] As used in this article, the term "AI / ML model testing" refers to the training sub-process used to evaluate the performance of the final AI / ML model using a different dataset than that used for model training and validation. Unlike AI / ML model validation, testing does not assume subsequent adjustments to the model.

[0031] As used in this article, the term "AI / ML model training" refers to the process of training an AI / ML model in a data-driven manner (by learning input / output relationships) and obtaining a trained AI / ML model for inference.

[0032] As used herein, the term "AI / ML model delivery" refers to the delivery of an AI / ML model over the air interface in a manner opaque to 3GPP signaling, which is either a parameter of a model structure known to the receiving end or a new model with parameters. The delivery may contain a complete model or a partial model.

[0033] As used in this paper, the term "AI / ML model validation" refers to the training sub-process of evaluating the quality of an AI / ML model using a dataset different from the dataset used for model training. This helps in selecting model parameters that generalize to datasets other than those used for model training.

[0034] As used herein, the term "data collection" refers to the process by which network nodes, management entities, or user units collect data for use in AI / ML model training, data analysis, and inference.

[0035] As used in this paper, the term "federated learning / federated training" refers to a machine learning technique that trains AI / ML models across multiple distributed edge nodes (e.g., UE, gNB), with each distributed edge node performing local model training using local data samples. This technique requires multiple interactions between the models but does not require the exchange of local data samples.

[0036] As used in this article, the term "model download" refers to the transfer of a model from the network to the UE.

[0037] As used herein, the term "model identification" refers to the process / method of identifying AI / ML models used for common understanding between NW and UE. Note: process / method of model identification.

[0038] As used in this article, the term "model monitoring" refers to the process of monitoring the inference performance of AI / ML models.

[0039] As used in this article, the term "model update" refers to the process of updating model parameters and / or the model structure.

[0040] As used in this article, the term "model upload" refers to the transfer of a model from the UE to the network.

[0041] As used in this paper, the term "network-side (AI / ML) model" refers to an AI / ML model whose inference is performed entirely at the network.

[0042] As used herein, the term "offline training" refers to an AI / ML training process in which a model is trained based on a collected dataset, and the trained model is later used or delivered for inference. This definition in this paper is for guidance only. There may be cases that do not perfectly fit this definition but can still be classified as offline training by generally accepted conventions.

[0043] As used herein, the term "online training" refers to an AI / ML training process in which the model used for inference is trained (near) real-time (typically continuously) as new training samples arrive. The concepts of (near) real-time and non-real-time are context-dependent and relative to the inference timescale. This definition may be used as a guideline only. There may be cases that do not perfectly fit this definition but can still be classified as online training by generally accepted conventions. Fine-tuning / retraining can be done via online or offline training.

[0044] As used in this article, the term "reinforcement learning (RL)" refers to the process of training an AI / ML model in an environment with which the model is interacting, from inputs (also called states) and feedback signals (also called rewards) generated by the model's outputs (also called actions).

[0045] As used in this article, the term "semi-supervised learning" refers to the process of training a model using a mixture of labeled and unlabeled data.

[0046] As used in this article, the term "supervised learning" refers to the process of training a model from inputs and their corresponding labels.

[0047] As used herein, the term “two-sided (AI / ML) model” refers to a pair of AI / ML models on which joint inference is performed, wherein joint inference includes AI / ML inference performed jointly across the UE and the network, i.e., the first part of the inference is performed by the UE first, and then the remainder is performed by the gNB, and vice versa.

[0048] As used in this paper, the term "UE-side (AI / ML) model" refers to an AI / ML model whose inference is performed entirely at the UE.

[0049] As used in this article, the term "unsupervised learning" refers to the process of training a model without labeled data.

[0050] As used herein, the term "transmitter point (TP)" refers to a set of geographically co-located transmit antennas (e.g., an antenna array (with one or more antenna elements)) for a cell, a portion of a cell, or only a DL Positioning Reference Signal (PRS)-TP. A transmit point may include base station (ng-eNB or gNB) antennas, remote radio head ends, remote antennas of a base station, antennas for a DL-PRS-only TP, etc. A cell may include one or more transmit points. For homogeneous deployments, each transmit point may correspond to one cell.

[0051] As used herein, the term "receiver point (RP)" refers to a group of geographically co-located receive antennas (e.g., an antenna array (with one or more antenna elements)) used for a cell, a portion of a cell, or only a UL Sound Reference Signal (SRS) RP. A receiver point may include base station (ng-eNB or gNB) antennas, remote radio head ends, remote antennas of a base station, antennas for a UL-SRS-only RP, etc. A cell may include one or more receiver points. For homogeneous deployments, each receiver point may correspond to one cell.

[0052] As used herein, the term “transmitter receiving point (TRP)” refers to a group of antennas (e.g., an antenna array (with one or more antenna elements) that are geographically located in the same place and support TP and / or RP functions.

[0053] As used herein, the term "SS signal-to-noise ratio and interference ratio (SS-SINR)" refers to the linear average of the power contribution (in [W]) of the resource element carrying the secondary synchronization signal, divided by the linear average of the noise and interference power contributions (in [W]). If SS-SINR is used for Layer 1 (L1)-SINR reporting with dedicated interference measurement resources, interference and noise are measured on the resources(s) indicated by the higher layer. Otherwise, interference and noise are measured on resource elements carrying the secondary synchronization signal within the same frequency bandwidth.

[0054] As used herein, the term "Channel State Information (CSI) Signal-to-Noise Ratio and Interference Ratio (CSI-SINR)" refers to the linear average of the power contribution (in [W]) of a resource element carrying the CSI reference signal, divided by the linear average of the noise and interference power contributions (in [W]). If CSI-SINR is used for L1-SINR reporting with dedicated interference measurement resources, interference and noise are measured on the resources(s) indicated by the higher layer. Otherwise, interference and noise are measured on resource elements carrying the CSI reference signal within the same frequency bandwidth.

[0055] As used in this paper, the term "mutual information" refers to a measure of the interdependence between two variables (e.g., two random variables (X, Y)). More specifically, it quantifies the "amount of information" gained about a random variable by observing other random variables.

[0056] The exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings. Figure 1 An example communication network 100 in which exemplary embodiments of the present disclosure can be implemented is shown. For example... Figure 1 As shown, the communication network 100 may include a first device 110, which may also be referred to as a terminal device or UE, for example.

[0057] The communication network 100 may also include a second device 120, which may be considered, for example, a network device or included in a network device. In some example embodiments, the network device may be discussed as a BS, gNB, or eNB.

[0058] The service area provided by the second device 120 is referred to as a cell. The second device 120 can provide services to one or more cells of the first device. For example, the first device 110 can communicate with the second device 120 within cell 104. In some scenarios, cell 104 can be considered as a cell serving the first device 110.

[0059] In the following description, for illustrative purposes, some exemplary embodiments are described in which the first device 110 operates as a terminal device and the second device 120 operates as a network device. However, in some exemplary embodiments, the operations described in connection with the terminal device can be implemented at the network device or other devices, and the operations described in connection with the network device can be implemented at the terminal device or other devices.

[0060] In some example embodiments, if the first device 110 is a terminal device and the second device 120 is a network device, the link from the second device 120 to the first device 110 is referred to as a downlink (DL), and the link from the first device 110 to the second device 120 is referred to as a UL. In the DL, the second device 120 is a transmitting (TX) device (or transmitter), and the first device 110 is a receiving (RX) device (or receiver). In the UL, the first device 110 is a TX device (or transmitter), and the second device 120 is an RX device (or receiver).

[0061] It should be understood that Figure 1The number of devices and their connections shown are for illustrative purposes only and do not imply any limitation. Communication environment 100 may include any suitable number of devices configured to implement the exemplary embodiments of this disclosure. Although not shown, it should be understood that one or more additional devices may be located in cell 104, and one or more additional cells may be deployed in communication environment 100. Note that although shown as a network device, the second device 120 may be another device besides a network device. Although shown as a terminal device, the first device 110 may be another device besides a terminal device.

[0062] In the following description, for illustrative purposes, some example embodiments are described in which the first device 110 operates as a UE and the second device 120 operates as a base station. However, in some example embodiments, the operations described in connection with the terminal device can be implemented at the network device or other device, and the operations described in connection with the network device can be implemented at the terminal device or other device.

[0063] Communication in communication environment 100 may be implemented according to any suitable communication protocol(s), including but not limited to cellular communication protocols, wireless local network communication protocols such as IEEE 802.11, and / or any other currently known or future-developed protocols. Furthermore, communication may utilize any suitable wireless communication technology, including but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), MIMO, Orthogonal Frequency Division Multiplexing (OFDM), Discrete Fourier Transform Extended OFDM (DFT-s-OFDM), and / or any other currently known or future-developed technologies.

[0064] For beam prediction based on AI / ML models, there are some sub-use cases: Beam Management (BM) - Case 1: Spatial domain downlink beam prediction of beam set A based on measurements of beam set B should be considered as an alternative: Option 1): AI / ML model training and inference on the NW side.

[0065] Option 2): AI / ML model training and inference on the UE side.

[0066] And the following can be further considered: Option i): Set A and set B are different (set B is not a subset of set A).

[0067] Alternative ii): Set B is a subset of set A (set A is used for DL ​​beam prediction).

[0068] AI / ML model input considerations: Option 1): L1-RSRP measurements based solely on set B; Option 2): L1-RSRP measurement based on set B and auxiliary information; Option 3): CIR based on set B; Option 4): L1-RSRP measurement based on set B and the corresponding DL Tx and / or Rx beam ID.

[0069] BM-Case 2: Temporal downlink beam prediction of beam set A based on historical measurement results of beam set B should be considered in the following aspects: Option 1): AI / ML model training and inference on the NW side.

[0070] Option 2): AI / ML model training and inference on the UE side.

[0071] And the following can be further considered: Option i): Set A and set B are different (set B is not a subset of set A).

[0072] Option ii): Set B is a subset of set A (sets A and B are not the same).

[0073] Option iii): Set A and set B are the same.

[0074] AI / ML model input considers: measurement results of K (K≥1) most recent measurement instances, with the following options: Option 1): L1-RSRP measurements based solely on set B; Option 2): L1-RSRP measurement based on set B and auxiliary information; Option 3): CIR based on set B; Option 4): L1-RSRP measurement based on set B and the corresponding DL Tx and / or Rx beam ID.

[0075] F predictions for F future time instances can be obtained based on the output of an AI / ML model, where each prediction is specific to each time instance. At least F=1.

[0076] Set B is the set of beams whose measurements serve as input to the AI / ML model (beams in sets A and B can be in the same frequency range). For both sub-use cases, the following alternatives are investigated for predicting the beam: Option 1: DL Tx Beam Prediction Option 2: DL Rx beam prediction (de-prioritization) Option 3: Beam pair prediction (a beam pair consists of a DL Tx beam and a corresponding DL Rx beam) Consider the following alternatives based on the output of the AI / ML model: Option 1: N predicted DL Tx and / or Rx beam IDs and / or predicted L1-RSRPs. For example, N predicted beams could be the first N predicted beams. Option 2: Multiple Tx and / or Rx beam IDs and other information for N predicted DL Tx and / or Rx beams. For example, N predicted beams could be the first N predicted beams. Option 3: N predicted DL Tx and / or Rx beam angles and / or predicted L1-RSRP For example, N predicted beams could be the first N predicted beams. All outputs in the above options can vary depending on whether the inference is made on the UE side or the gNB side based on the AI / ML model. The first N beam IDs may have already been derived from the post-processing of the ML model output.

[0077] For BM-Case 1 and BM-Case 2 with UE-side AI / ML models, the necessity of (multiple) functions and / or (multiple) models and potential BM-specific / additional conditions should be considered from at least the following aspects: Information about model reasoning Set A / Set B configuration Performance monitoring Data collection Auxiliary information For beam management use cases: For model training, training data can be generated by UE / gNB.

[0078] For NW-side model inference, the input data can be generated by the UE and terminated at the gNB.

[0079] For UE-side model inference, the input data is available internally at the UE.

[0080] For performance monitoring on the NW side, the calculated performance metrics (if needed) or the data required for performance metric calculation (if needed) can be generated by the UE and terminated at the gNB.

[0081] refer to Figure 2 . Figure 2 A schematic diagram 200 of beam management is shown. (e.g.) Figure 2 As shown, the input of AI / ML model 210 can be beam set B, and the output of AI / ML model 210 can be beam set A. AI / ML model 210 can be deployed on the UE side.

[0082] In addition, beam ID information can also be provided as input to the AI / ML model 210. Based on the model output (e.g., the probability that each beam in set A is the first beam, the predicted L1-RSRP), the top 1 / N beams in beam set A can be predicted and / or the predicted L1-RSRP can be potentially used (depending on the label).

[0083] For BM-Case 1, measurements from set B (stated otherwise) are used as model input to predict the first 1 / N beams from set A, and for BM-Case 2, measurements from (multiple) historical time instances are used as model input for time DL beam prediction of beams from set A.

[0084] For both BM-Case 1 and BM-Case 2, the UE can report the prediction results to the NW based on the output of the UE-side model, or the NW can predict (multiple) front 1 / N beams based on the measurement of set B reported for the NW-side model.

[0085] Figure 3 A schematic diagram 300 shows L1-RSRP measurements and interference measurements for a beamset. (As shown...) Figure 3As shown, there is a static interference source 310 (e.g., a neighboring cell), and the L1-RSRP measurements and interference measurements of the DL beam 320 (or beam pair) set at different locations or time instances (t1, t2, t3, t4) of the UE 330 have high mutual information (i.e., they are statistically correlated). Therefore, knowing the (multiple) DL Tx-R x beam pairs with the maximum L1-RSRP (and the actual L1-RSRP) can be highly informative about the (multiple) DL Rx beams exposed to the maximum interference (and the actual interference power) (i.e., significantly reducing uncertainty).

[0086] In some of the discussed schemes, UE-side model inference is specified to predict the reference signal received power (RSRP) on beam set A based on the measured L1-RSRP on beam set B. Based on this, the UE is configured to report the top K predicted beams, for example, the beam with the largest predicted RSRP.

[0087] However, RSRP does not account for interference. A better quality metric for beam (pairs) is the signal-to-interference-plus-noise ratio (SINR) because it takes into account the impact of potential interference sources (e.g., from neighboring cells). Therefore, it is expected that the UE-side model will predict SINR based on the DL Tx-R x beam pair with the maximum predicted SINR rather than the maximum predicted RSRP and report the top K predicted beams.

[0088] To predict interference (or SINR) on a beam(pair), the measured interference power (or measured L1-SINR) on the beam(or beam pair) set can be used as input to the model. However, performing interference (or L1-SINR) measurements on a large number of DL Rx beams (or DLTx-R x beam pairs) every time interference needs to be predicted can unnecessarily increase UE complexity and UE power consumption. Therefore, it is desirable to be able to predict the interference power (or SINR) without needing to perform interference (or L1-SINR) measurements during inference.

[0089] According to some example embodiments of this disclosure, a solution is provided for interference prediction of a beam set based on RSRP measurements on another beam set. Specifically, a first device receives from a second device an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction. Based on the inference configuration, the first device performs Reference Signal Received Power (RSRP) measurements on a reference signal transmitted from at least one transmission point on a first beam set at one or more measurement time instances. Based on the inference configuration, the first device performs interference prediction on a second beam set for one or more prediction time instances by providing the RSRP measurements as input to a model, and then the first device sends a prediction report to the second device, wherein the prediction report is based on the interference prediction.

[0090] The interference prediction method provided in this disclosure can predict interference by utilizing the statistical correlation or mutual information between non-interference-related beam measurements (L1-RSRP) and interference-related beam measurements (interference power or L1-SINR), without requiring interference measurements to be performed every time interference prediction is needed, thereby reducing UE power consumption. The larger the set and / or the more informative the additional non-interference-related input variables (e.g., time / frequency domain information, UE location information, etc.) used to learn the statistical relationship (i.e., fit the model), the higher the prediction accuracy and model generalization performance achievable in different scenarios (thus broadening its applicability).

[0091] Example embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the following drawings may be implemented individually or in any suitable combination, and are not limited thereto in this disclosure.

[0092] refer to Figure 4 This illustrates an example signaling flow 400 for interference prediction according to some example embodiments of this disclosure. For discussion purposes, reference will be made to... Figure 1 For example, signaling flow 400 is described by using first device 110 and second device 120.

[0093] like Figure 4 As shown, the first device 110 can send (402) capability information to the second device 120, which indicates that the first device 110 is capable of performing interference prediction based on L1-RSRP. Based on such capability information, the second device 120 can send (404) inference configuration for using the model to perform interference prediction to the first device 110.

[0094] In some example embodiments, the inference configuration may include at least one MRS for performing RSRP measurements and at least one prediction resource set (PRS) for performing interference prediction.

[0095] In some example implementations, interference prediction can be performed in the spatial domain (BM-case 1) or the temporal domain (BM-case 2) (i.e., in one or more future time instances).

[0096] Furthermore, the first device 110 can perform (406) RSRP measurements on reference signals transmitted from at least one transmission point on a first beam set (e.g., beam set B) at one or more measurement time instances. In some example embodiments, the first device 110 can obtain at least one MRS from an inference configuration and receive reference signals from the first beam set from the second device 120 at at least one MRS on one or more measurement time instances.

[0097] It should be understood that the term “beam” used in this article is synonymous with “spatial filter” or “spatial domain filter”.

[0098] In some example embodiments, the first device 110 may obtain at least one PRS from an inference configuration for performing interference prediction on a second beam set (e.g., beam set A). Alternatively, the second beam set may include DL transmit beams (s1, ..., s12) at one or more transmit points associated with the second device 120 or a transmit-receive point (TRP) and DL receive beams (r1, ..., r36) at the first device 110.

[0099] Furthermore, the first device 110 can perform (408) interference prediction on the second beam set for one or more prediction time instances by providing RSRP measurements as input to the model based on inference configuration.

[0100] In some example embodiments, the first device 110 may provide one or more additional inputs to model interference prediction. Alternatively, the additional inputs may include time-domain information, which may refer to, for example, the time of day, a day of the week, etc. Information about the time of day or a day of the week can be highly informative for predicting interference at different times (e.g., lower interference during the night) or on different days of the week (e.g., lower interference on weekends).

[0101] As an alternative, additional inputs may include frequency domain information, which can be highly informative for predicting interference at different frequencies (e.g., some interference sources may only operate at certain frequencies).

[0102] As an alternative, additional inputs may include the position information of the first device 110, which can further resolve any ambiguities in the spatial domain that cannot be prevented by L1-RSRP beam measurements alone (e.g., in non-line-of-sight (NLOS) scenarios).

[0103] As an alternative, additional inputs may include network load information, which can be highly informative for predicting interference under different conditions (e.g., in hotspot situations, such as during a sporting event in a crowded stadium, the interference to nearby cells may be greater than usual).

[0104] In some example embodiments, the first device 110 may determine one or more predicted interference-related quantities for each resource in at least one PRS, including at least one of predicted interference power or predicted interference plus noise power associated with the resource. For example, the model may be configured to predict the interference power of each DL receive beam in a set of DL receive beams(s) based on L1-RSRP measurements.

[0105] In some other example embodiments, the predicted interference-related quantities may include the predicted signal-to-interference ratio (SIR) or the predicted signal-to-interference-plus-noise ratio (SINR) associated with the resource. For example, the model may be configured to predict the SINR of each of the (multiple) DL transmit-receive beampair sets based on L1-RSRP measurements.

[0106] In some example embodiments, the first device 110 may generate a prediction report based at least on one or more predicted interference correlation quantities. Optionally, the prediction report may include at least one resource indicator for indicating at least one resource with the highest predicted SINR. The first device 110 may then send the prediction report (410) to the second device 120 based on the interference prediction.

[0107] In some example embodiments, the first device 110 may determine an appropriate subset of the received beams for performing interference measurements based on one or more predicted interference correlation quantities for the second beam set.

[0108] In some embodiments, the first device 110 may use predicted interference (or predicted SINR) to determine a strict (or appropriate) subset of the received beams for actual interference (or L1-SINR) measurements. For example, instead of replacing the actual L1-SINR measurement with the predicted L1-SINR (which may be inaccurate), the prediction may be used as an initial step to determine a small subset of received beams with potential exposure (based on past experience), followed by actual interference measurements limited to that small subset (e.g., only one received beam). In this way, the first device 110 can save some energy by not measuring interference on received beams where interference has never been observed (e.g., directions corresponding to where there is no interference source).

[0109] In some example embodiments, the first device 110 may perform interference measurements on a second beamset used for model performance monitoring, and report model performance metrics to the second device based on interference predictions and interference measurements used for model performance monitoring.

[0110] In some example embodiments, the first device 110 can monitor the model's predictive performance and report model performance metrics (e.g., interference power prediction accuracy, SINR prediction accuracy, or beam prediction accuracy based on the beam set with the highest predicted SINR and the beam set with the highest measured SINR).

[0111] In the following text, reference will be made to Figure 5 Describe the model training process in detail. Figure 5 An example signaling flow 500 for interference prediction according to some example embodiments of this disclosure is shown. For discussion purposes, reference will be made to... Figure 1For example, signaling flow 500 is described by using first device 110 and second device 120.

[0112] like Figure 5 As shown, the first device 110 can receive (502) data collection resource configuration from the second device 120 for training the model.

[0113] Upon receiving a data collection resource configuration, the first device 110 may perform (504) RSRP measurements on a reference signal transmitted from at least one transmission point on a first beam set at one or more first measurement time instances based on at least one first MRS indicated in the data collection resource configuration.

[0114] Then, the first device 110 can perform (506) interference measurements on the second beam set at one or more second measurement time instances based on at least one second MRS indicated in the data collection resource configuration.

[0115] Furthermore, the first device 110 can train (508) a model based on RSRP measurements and interference measurements. In some example embodiments, the first device 110 can train the model by using RSRP measurements as input to the model and interference measurements as labels.

[0116] In some example embodiments, RSRP measurements, as non-interference-related input variables for fitting (e.g., supervised training) a model (and for performing predictions), may include a set of Layer 1 reference signal received power (L1-RSRP), such as multiple SS-RSRPs and / or multiple CSI-RSRPs measured at the user equipment based on a set of reference signals (SSB, CSI-RS) transmitted by a network device (gNB) from one or more transmit points (or TRPs) using a set of DL transmit beams (s1, ..., s12), and received by the user equipment using a set of DL receive beams (r1, ..., r36). In some cases, the input variables for fitting the model may include a matrix of L1-RSRP values ​​measured at different time instances using different receive beams. Optionally, RSRP measurements may also include time-domain information, frequency-domain information, UE location information, network load information, etc. The definition of each measurement may be the same as the one described above and will not be repeated here.

[0117] In some example embodiments, as an interference-related quantity (or label) for fitting (e.g., supervised training) a model, interference measurement may include a set of interference power (or interference and noise power) measured at the first device 110 using a set of DL receive beams (r1, ..., r36). In some other example embodiments, the metric (or label) may include a set of Layer 1 signal to interference-plus-noise ratios (L1-SINR, such as multiple SS-SINRs and / or multiple CSI-SINRs) measured at the first device 110, based on a set of reference signals (SSB, CSI-RS) transmitted by the second device 120 (e.g., gNB) using a set of DL transmit beams (s1, ..., s12) from one or more transmission points (or TRPs) and received by the first device 110 using a set of DL receive beams (r1, ..., r36). In some cases, the interference-related quantities used to fit the model may include a matrix of interference (or interference and noise) power values ​​(or L1-SINR values) measured at different time instances using different receive beams (or different transmit-receive beam pairs).

[0118] In some example embodiments, the first device 110 can obtain an interference prediction result from the model by providing the RSRP measurement as input and comparing the interference prediction result with the interference measurement. If the difference between the interference prediction result and the interference measurement is less than a threshold, the first device 110 can use the model for interference prediction.

[0119] In some example embodiments, upon receiving a prediction report of inference configuration and interference prediction associated with interference prediction using the model from the second device 120, the first device 110 may perform interference prediction on the second beam set for one or more prediction time instances based on the inference configuration by providing RSRP measurements as input to the model.

[0120] According to the process described above in this disclosure, by utilizing the statistical correlation or mutual information between non-interference-related beamforming measurements (L1-RSRP) and interference-related beamforming measurements (interference power or L1-SINR), interference can be predicted without having to perform interference measurements every time interference prediction is needed, thereby reducing UE power consumption.

[0121] Figure 6 A flowchart of an example method 600 implemented at a first device according to some example embodiments of the present disclosure is shown. For the purposes of discussion, [the following will be discussed]. Figure 1 Method 600 is described by the angle of the first device 110 in the middle.

[0122] At box 610, the first device 110 receives from the second device an inference configuration associated with the interference prediction and the prediction report of the interference prediction using the model.

[0123] In block 620, the first device 110, based on an inference configuration, performs a reference signal received power (RSRP) measurement on a reference signal transmitted from at least one transmission point on a first beamset at one or more measurement time instances.

[0124] At box 630, the first device 110, based on an inference configuration, performs interference prediction on the second beam set for one or more prediction time instances by providing RSRP measurements as input to the model.

[0125] At frame 640, the first device 110 sends a prediction report to the second device, wherein the prediction report is based on interference prediction.

[0126] In some example embodiments, the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set.

[0127] In some example embodiments, method 600 further includes: obtaining at least one MRS from an inference configuration; and receiving a reference signal from a first beam set from a second device at one or more measurement time instances, on at least one MRS.

[0128] In some example embodiments, method 600 further includes: obtaining at least one PRS from an inference configuration; and for each resource in the at least one PRS, determining one or more predicted interference-related quantities including at least one of the following: predicted interference power associated with the resource, or predicted signal-to-interference-plus-noise ratio (SINR) associated with the resource.

[0129] In some example embodiments, method 600 further includes generating a prediction report based at least on one or more predicted interference-related quantities.

[0130] In some example embodiments, the prediction report includes at least one resource indicator for indicating at least one resource with the highest predicted SINR.

[0131] In some example embodiments, the second beam set includes at least one of the following: a transmission beam set at at least one transmission point associated with the second device, or a reception beam set at the first device.

[0132] In some example embodiments, method 600 further includes providing the model with one or more additional inputs including at least one of the following: time-domain information, frequency-domain information, location information of the first device, or network load information.

[0133] In some example embodiments, method 600 further includes determining an appropriate subset of the received beams for performing interference measurements based on one or more predicted interference correlation quantities for the second beam set.

[0134] In some example embodiments, method 600 further includes: performing interference measurements on the second beamset for model performance monitoring; and reporting model performance metrics to a second device based on interference prediction and interference measurements for model performance monitoring.

[0135] In some example embodiments, method 600 further includes sending information to the second device indicating the capability of the first device to perform interference prediction based on RSRP measurements.

[0136] In some example embodiments, the first device includes a terminal device, and the second device includes a network node.

[0137] Figure 7 A flowchart of an example method 700 implemented at a second device according to some example embodiments of the present disclosure is shown. For the purposes of discussion, [the following will be discussed]. Figure 1 Method 700 is described by the angle of the second device 120 in the middle.

[0138] In block 710, the second device 120 sends an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction, wherein the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set from at least one transmission point associated with the second device; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set.

[0139] At box 720, the second device 120 receives a prediction report from the first device, wherein the prediction report is based on interference predictions for the second beam set for one or more prediction time instances.

[0140] In some example embodiments, method 700 further includes: receiving a prediction report from a first device, the prediction report including at least one or more predicted interference-related quantities, wherein the one or more predicted interference-related quantities include at least one of the following: predicted interference power associated with a resource in at least one PRS, or predicted signal-to-interference-plus-noise ratio (SINR) associated with a resource in at least one PRS.

[0141] In some example embodiments, the prediction report includes at least one resource indicator for indicating at least one resource with the highest predicted SINR.

[0142] In some example embodiments, the beam set includes at least one of the following: a transmit beam set at at least one transmission point associated with the second device, or a receive beam set at the first device.

[0143] In some example embodiments, the first device includes a terminal device, and the second device includes a network node.

[0144] Figure 8 A flowchart of an example method 800 implemented at a first device according to some example embodiments of the present disclosure is shown. For the purposes of discussion, [the following will be discussed]. Figure 1 Method 800 is described by the angle of the first device 110 in the middle.

[0145] At frame 810, the first device 110 receives a data collection resource configuration from the second device for collecting data used to train the model.

[0146] At block 820, the first device 110 performs a reference signal received power (RSRP) measurement on a reference signal at one or more first measurement time instances based on at least one first measurement resource set (MRS) indicated in the data collection resource configuration, the reference signal being transmitted from at least one transmission point on the first beam set.

[0147] In block 830, the first device 110 performs interference measurements on the second beam set at one or more second measurement time instances based on at least one second MRS indicated in the data collection resource configuration.

[0148] In box 840, the first device 110 is based on a training model of RSRP measurement and interference measurement.

[0149] In some example embodiments, method 800 further includes training the model by using RSRP measurements as input to the model and interference measurements as labels.

[0150] In some example embodiments, method 800 further includes: obtaining interference prediction results from the model by providing RSRP measurements as input; comparing the interference prediction results with the interference measurements; and using the model for interference prediction if it is determined that the difference between the interference prediction results and the interference measurements is less than a threshold.

[0151] In some example embodiments, the second beam set includes at least one of the following: a transmission beam set at at least one transmission point associated with the second device, or a reception beam set at the first device.

[0152] In some example embodiments, method 800 further includes sending information to the second device indicating the capability of the first device to perform interference prediction based on RSRP measurements.

[0153] In some example embodiments, method 800 further includes: if an inference configuration associated with interference prediction and a prediction report of interference prediction using a model is received from the second device, performing interference prediction on the second beam set for one or more prediction time instances based on the inference configuration by providing RSRP measurements as input to the model.

[0154] In some example embodiments, the first device includes a terminal device, and the second device includes a network node.

[0155] Figure 9 A flowchart of an example method 900 implemented at a second device according to some example embodiments of the present disclosure is shown. For the purposes of discussion, [the following will be discussed]. Figure 1 Method 900 is described by the angle of the second device 120 in the middle.

[0156] In block 910, the second device 120 generates a data collection resource configuration for collecting data used to train a model at the first device. The data collection resource configuration includes at least: at least one first measurement resource set (MRS) for performing reference signal received power (RSRP) measurements on a reference signal at one or more first measurement time instances, the reference signal being transmitted from at least one transmission point on a first beam set; and at least one second MRS for performing interference measurements on a second beam set at one or more second measurement time instances.

[0157] At frame 920, the second device 120 sends a data collection resource configuration to the first device.

[0158] In some example embodiments, method 900 further includes receiving from the first device capability information indicating that the first device is capable of performing interference prediction based on RSRP measurements.

[0159] In some example embodiments, the first device includes a terminal device, and the second device includes a network node.

[0160] In some example embodiments, a first device capable of performing any method 600 (e.g., Figure 1 The first device 110 may include a component for performing a corresponding operation of method 600. This component may be implemented in any suitable form. For example, the component may be implemented in a circuit or software module. The first device may be implemented as or included in... Figure 1 In the first device 110.

[0161] In some example embodiments, the first device includes: components for receiving from the second device an inference configuration associated with interference predictions and a prediction report of the interference predictions using a model; components for performing reference signal received power (RSRP) measurements on a reference signal transmitted from at least one transmission point on a first beamset at one or more measurement time instances based on the inference configuration; components for performing interference predictions on a second beamset for one or more prediction time instances based on the inference configuration by providing the RSRP measurements as input to the model; and components for sending a prediction report to the second device, wherein the prediction report is based on the interference predictions.

[0162] In some example embodiments, the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set.

[0163] In some example embodiments, the first device further includes: components for obtaining at least one MRS from an inference configuration; and components for receiving reference signals from the first beam set from the second device at one or more measurement time instances, on at least one MRS.

[0164] In some example embodiments, the first apparatus further includes: components for obtaining at least one PRS from an inference configuration; and components for determining, for each resource in the at least one PRS, one or more predicted interference-related quantities including at least one of the following: predicted interference power associated with the resource, or predicted signal-to-interference-plus-noise ratio (SINR) associated with the resource.

[0165] In some example embodiments, the first apparatus further includes a component for generating a prediction report based at least on one or more predicted interference-related quantities.

[0166] In some example embodiments, the prediction report includes at least one resource indicator for indicating at least one resource with the highest predicted SINR.

[0167] In some example embodiments, the second beam set includes at least one of the following: a transmission beam set at at least one transmission point associated with the second device, or a reception beam set at the first device.

[0168] In some example embodiments, the first device further includes a component for providing the model with one or more other inputs including at least one of the following: time-domain information, frequency-domain information, location information of the first device, or network load information.

[0169] In some example embodiments, the first apparatus further includes components for determining an appropriate subset of the received beams for performing interference measurements based on one or more predicted interference correlation quantities for the second beam set.

[0170] In some example embodiments, the first device further includes: components for performing interference measurements on the second beamset for model performance monitoring; and components for reporting model performance metrics to the second device based on interference prediction and interference measurements for model performance monitoring.

[0171] In some example embodiments, the first device further includes a component for sending information to the second device indicating the first device's ability to perform interference prediction based on RSRP measurements.

[0172] In some example embodiments, the first device includes a terminal device, and the second device includes a network node.

[0173] In some example embodiments, a second device capable of performing any method 700 (e.g., Figure 1 The second device 120 may include a component for performing the corresponding operation of method 700. This component may be implemented in any suitable form. For example, the component may be implemented in a circuit or software module. The second device may be implemented as or included in... Figure 1 The second device 120 in the middle.

[0174] In some example embodiments, the second device includes: a component for transmitting to the first device an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction, wherein the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set from at least one transmission point associated with the second device; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set; and a component for receiving a prediction report from the first device, wherein the prediction report is based on interference predictions of the second beam set for one or more prediction time instances.

[0175] In some example embodiments, the second device further includes: a component for receiving a prediction report from the first device, the prediction report including at least one or more predicted interference-related quantities, wherein the one or more predicted interference-related quantities include at least one of the following: predicted interference power associated with a resource in at least one PRS, or predicted signal-to-interference-plus-noise ratio (SINR) associated with a resource in at least one PRS.

[0176] In some example embodiments, the prediction report includes at least one resource indicator for indicating at least one resource with the highest predicted SINR.

[0177] In some example embodiments, the second beam set includes at least one of the following: a transmit beam set at at least one transmission point associated with the second device, or a receive beam set at the first device.

[0178] In some example embodiments, the first device includes a terminal device, and the second device includes a network node.

[0179] In some example embodiments, a first device capable of performing any method 800 (e.g., Figure 1 The first device 110 may include a component for performing a corresponding operation of method 800. This component may be implemented in any suitable form. For example, the component may be implemented in a circuit or software module. The first device may be implemented as or included in... Figure 1 In the first device 110.

[0180] In some example embodiments, the first apparatus includes: means for receiving from the second apparatus a data collection resource configuration for collecting data for training a model; means for performing a reference signal received power (RSRP) measurement on a reference signal at one or more first measurement time instances based on at least one first measurement resource set (MRS) indicated in the data collection resource configuration, the reference signal being transmitted from at least one transmission point on a first beam set; means for performing an interference measurement on a second beam set at one or more second measurement time instances based on at least one second MRS indicated in the data collection resource configuration; and means for training the model using RSRP-based measurements and interference measurements.

[0181] In some example embodiments, the first device further includes a component for training the model by using RSRP measurements as input to the model and interference measurements as labels.

[0182] In some example embodiments, the first apparatus further includes: components for obtaining interference prediction results from the model by providing RSRP measurements as input to the model; components for comparing the interference prediction results with the interference measurements; and components for using the model for interference prediction if it is determined that the difference between the interference prediction results and the interference measurements is less than a threshold.

[0183] In some example embodiments, the second beam set includes at least one of the following: a transmission beam set at at least one transmission point associated with the second device, or a reception beam set at the first device.

[0184] In some example embodiments, the first device further includes a component for sending information to the second device indicating the first device's ability to perform interference prediction based on RSRP measurements.

[0185] In some example embodiments, the first apparatus further includes a component for performing interference prediction on a second beam set for one or more prediction time instances based on an inference configuration that is associated with interference prediction and a prediction report using the model, if an inference configuration is received from the second apparatus.

[0186] In some example embodiments, the first device includes a terminal device, and the second device includes a network node.

[0187] In some example embodiments, a second device capable of performing any method 900 (e.g., Figure 1 The second device 120 may include a component for performing the corresponding operation of method 900. This component may be implemented in any suitable form. For example, the component may be implemented in a circuit or software module. The second device may be implemented as or included in... Figure 1 The second device 120 in the middle.

[0188] In some example embodiments, the second device includes: components for generating a data collection resource configuration for collecting data used to train a model at the first device; the data collection resource configuration includes at least: at least one first measurement resource set (MRS) for performing reference signal received power (RSRP) measurements on a reference signal at one or more first measurement time instances, the reference signal being transmitted from at least one transmission point on a first beam set; and at least one second MRS for performing interference measurements on a second beam set at one or more second measurement time instances; and means for transmitting the data collection resource configuration to the first device.

[0189] In some example embodiments, the second device further includes a component for receiving information from the first device indicating the capability of the first device to perform interference prediction based on RSRP measurements.

[0190] In some example embodiments, the first device includes a terminal device, and the second device includes a network node.

[0191] Figure 10 This is a simplified block diagram of a device 1000 suitable for implementing exemplary embodiments of the present disclosure. The device 1000 can be provided to implement a communication device, such as... Figure 1 The first device 110 or the second device 120 shown. As shown, the device 1000 includes one or more processors 1010, one or more memories 1020 coupled to the processors 1010, and one or more communication modules 1040 coupled to the processors 1010.

[0192] Communication module 1040 is used for bidirectional communication. Communication module 1040 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface can represent any interface required for communication with other network elements. In some example embodiments, communication module 1040 may include at least one antenna.

[0193] As a non-limiting example, processor 1010 can be any type suitable for a local technology network and can include one or more of the following: general-purpose computer, special-purpose computer, microprocessor, digital signal processor (DSP), and processor based on a multi-core processor architecture. Device 1000 can have multiple processors, such as application-specific integrated circuit chips that are time-dependent on a clock of a synchronous main processor.

[0194] Memory 1020 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 1024, electrically programmable read-only memory (EPROM), flash memory, hard disk, optical disc (CD), digital video disc (DVD), optical disc, laser disc, and other magnetic and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 1022 and other volatile memories that will not be maintained during the duration of a power outage.

[0195] Computer program 1030 includes computer-executable instructions that are executed by an associated processor 1010. The instructions of program 1030 may include instructions for performing operations / actions of some example embodiments of this disclosure. Program 1030 may be stored in memory (e.g., ROM 1024). Processor 1010 can perform any suitable actions and processes by loading program 1030 into RAM 1022.

[0196] The exemplary embodiments of this disclosure can be implemented by program 1030, enabling device 1000 to execute as described in the reference. Figures 2 to 9 Any process discussed in this disclosure. Exemplary embodiments of this disclosure may also be implemented by hardware or by a combination of software and hardware.

[0197] In some example embodiments, program 1030 may be tangibly contained in a computer-readable medium, which may be included in device 1000 (such as memory 1020) or other storage device accessible by device 1000. Device 1000 may load program 1030 from the computer-readable medium into RAM 1022 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. As used herein, the term "non-transitory" is a limitation on the medium itself (i.e., tangible, not tactile), rather than a limitation on the persistence of data storage (e.g., RAM and ROM).

[0198] Figure 11 An example of a computer-readable medium 1100 is shown, which may be in the form of a CD, DVD, or other optical storage disc. A program 1030 is stored on the computer-readable medium 1100.

[0199] Generally, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of this disclosure are illustrated and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, as non-limiting examples, the blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0200] Some exemplary embodiments of this disclosure also provide at least one computer program product tangibly stored on a computer-readable medium, such as a non-transitory computer-readable medium. The computer program product includes computer-executable instructions that execute in a device on a target physical or virtual processor, such as those included in a program module, to perform any of the methods described above. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform a particular task or implement a particular abstract data type. In various embodiments, the functionality of a program module can be combined or split among program modules as needed. The machine-executable instructions for a program module can execute within a local or distributed device. In a distributed device, the program module can reside in both local and remote storage media.

[0201] Program code used to perform the methods of this disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a stand-alone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0202] In the context of this disclosure, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc.

[0203] Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable media can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. More specific examples of computer-readable storage media will include electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0204] Furthermore, although operations are described in a specific order, this should not be construed as requiring that such operations be performed in the specific order shown or sequentially, or that all shown operations be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the discussion above, these details should not be construed as limiting the scope of this disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated otherwise, certain features described in the context of a single embodiment may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated otherwise, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0205] Although this disclosure has been described in language specific to structural features and / or methodological actions, it should be understood that the disclosure as defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as exemplary forms for implementing the claims.

[0206] Example 1. A first device for communication, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first device to at least: receive from a second device an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction; perform a reference signal received power (RSRP) measurement on a reference signal at one or more measurement time instances based on the inference configuration, the reference signal being transmitted from at least one transmission point on a first beamset; perform interference prediction on a second beamset for one or more prediction time instances based on the inference configuration by providing the RSRP measurement as input to a model; and send a prediction report to the second device, wherein the prediction report is based on the interference prediction.

[0207] Example 2. According to the first apparatus of Example 1, the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set.

[0208] Example 3. According to the first apparatus of Example 2, wherein the first apparatus is caused to: acquire at least one MRS from an inference configuration; and receive a reference signal from a first beam set from a second apparatus at one or more measurement time instances, on at least one MRS.

[0209] Example 4. According to the first apparatus of Example 2, wherein the first apparatus is caused to: obtain at least one PRS from an inference configuration; and for each resource in the at least one PRS, determine one or more predicted interference-related quantities including at least one of the following: predicted interference power associated with the resource, or predicted signal-to-interference-plus-noise ratio (SINR) associated with the resource.

[0210] Example 5. According to the first device of Example 4, wherein the first device is caused to generate a prediction report based at least on one or more predicted interference-related quantities.

[0211] Example 6. According to the first apparatus of Example 4, wherein the prediction report includes at least one resource indicator for indicating at least one resource having the highest predicted SINR.

[0212] Example 7. A first device according to any one of Examples 1-6, wherein the second beam set includes at least one of the following: a transmission beam set at at least one transmission point associated with the second device, or a reception beam set at the first device.

[0213] Example 8. A first device according to any one of Examples 2-6, wherein the first device is caused to provide the model with one or more other inputs including at least one of the following: time domain information, frequency domain information, location information of the first device, or network load information.

[0214] Example 9. According to the first apparatus of Example 4, wherein the first apparatus is caused to: determine an appropriate subset of the received beams for performing interference measurements based on one or more predicted interference correlation quantities for a second beam set.

[0215] Example 10. According to the first apparatus of Example 9, wherein the first apparatus is caused to: perform interference measurements on the second beam set for model performance monitoring; and report model performance metrics to the second apparatus based on interference prediction and interference measurements for model performance monitoring.

[0216] Example 11. A first device according to any one of Examples 1-6, wherein the first device is caused to send information to a second device indicating the capability of the first device to perform interference prediction based on RSRP measurements.

[0217] Example 12. A second means for communication, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second means to at least: transmit to a first means an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction, wherein the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set from at least one transmission point associated with the second means; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set; and receiving a prediction report from the first means, wherein the prediction report is based on interference predictions for the second beam set for one or more prediction time instances.

[0218] Example 13. A second apparatus according to Example 12, wherein the second apparatus is caused to: receive a prediction report from a first apparatus, the prediction report including at least one or more predicted interference-related quantities, wherein the one or more predicted interference-related quantities include at least one of the following: predicted interference power associated with a resource in at least one PRS, or predicted signal-to-interference-plus-noise ratio (SINR) associated with a resource in at least one PRS.

[0219] Example 14. A method for communication, comprising: receiving, by a first device, an inference configuration associated with interference prediction and a prediction report of interference prediction using a model from a second device; performing a reference signal received power (RSRP) measurement on a reference signal transmitted from at least one transmission point on a first beamset at one or more measurement time instances based on the inference configuration; performing interference prediction on a second beamset for one or more prediction time instances based on the inference configuration by providing the RSRP measurement as input to a model; and sending a prediction report to the second device, wherein the prediction report is based on the interference prediction.

[0220] Example 15. A method for communication, comprising: transmitting from a second device to a first device an inference configuration associated with interference prediction using a model and a prediction report of the interference prediction, wherein the inference configuration includes: at least one measurement resource set (MRS) for performing RSRP measurements on a reference signal transmitted on a first beam set from at least one transmission point associated with the second device; and at least one prediction resource set (PRS) for performing interference prediction on a second beam set; and receiving a prediction report from the first device, wherein the prediction report is based on interference predictions of the second beam set for one or more prediction time instances.

Claims

1. A first device for communication, comprising: At least one processor; as well as At least one memory, the at least one memory storing instructions, the instructions causing the first device to at least: Receive from the second device an inference configuration associated with the interference predictions using the model and a prediction report of the interference predictions; Based on the inference configuration, a reference signal received power (RSRP) measurement is performed on a reference signal at one or more measurement time instances, the reference signal being transmitted from at least one transmission point on a first beam set; Based on the inference configuration, the interference prediction is performed on the second beam set for one or more prediction time instances by providing the RSRP measurement as input to the model. as well as The prediction report is sent to the second device, wherein the prediction report is based on the interference prediction.

2. The first apparatus according to claim 1, wherein the inference configuration includes: At least one measurement resource set (MRS) is used to perform the RSRP measurement on the reference signal transmitted on the first beam set; as well as At least one prediction resource set (PRS) is used to perform the interference prediction on the second beam set.

3. The first device according to claim 2, wherein the first device causes: Obtain the at least one MRS from the inference configuration; and The reference signal from the first beam set is received from the second device at one or more measurement time instances, at at least one MRS.

4. The first device according to claim 2, wherein the first device causes: Obtain the at least one PRS from the inference configuration; and For each resource in the at least one PRS, determine one or more predicted interference-related quantities including at least one of the following: Predicted interference power associated with resources, or The predicted signal-to-interference-plus-noise ratio (SINR) associated with resources.

5. The first device according to claim 4, wherein the first device causes: The prediction report is generated based on at least one or more of the predicted interference-related quantities.

6. The first apparatus of claim 4, wherein the prediction report includes at least one resource indicator for indicating at least one resource having the highest predicted SINR.

7. The first device according to any one of claims 1-6, wherein the second beamset comprises at least one of the following: The transmission beam set at the at least one transmission point associated with the second device, or The receiving beam set at the first device.

8. The first device according to any one of claims 2-6, wherein the first device causes: Provide the model with one or more other inputs including at least one of the following: Time domain information, Frequency domain information, The location information of the first device, or Network load information.

9. The first device according to claim 4, wherein the first device causes: Based on the one or more predicted interference correlation quantities for the second beam set, an appropriate subset of the received beams for performing interference measurements is determined.

10. The first device according to claim 9, wherein the first device causes: Interference measurements are performed on the second beamset for model performance monitoring; and Based on the interference prediction and the interference measurement, the performance metrics of the model are reported to the second device for model performance monitoring.

Images