Configuration of resource sets for resource management

Abstract

Apparatuses, methods and computer readable storage medium for configuration of resource sets for resource management are provided. In a method, a first apparatus transmits, to a second apparatus, a configuration request for at least one of a first resource set for training and performance monitoring of a machine learning model for resource management, or a second resource set for inference of the machine learning model. The first apparatus receives, from the second apparatus, a configuration response for the configuration request, which includes at least one configuration of the at least one of the first resource set or the second resource set, to indicate at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

Description

CONFIGURATION OF RESOURCE SETS FOR RESOURCE MANAGEMENTCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims priority from, and the benefit of, US Provisional Application No.63 / 754698, filed February 6, 2025, the contents of which are hereby incorporated by reference in their entirety.FIELD

[0002] Various example embodiments of the present disclosure generally relate to the field of telecommunication and in particular, to apparatuses, methods and computer readable storage medium for configuration of resource sets for resource management.BACKGROUND

[0003] With developments in an integration of artificial intelligence (Al) / machine learning (ML) within the fifth generation (5G) mobile network and emerging the sixth generation (6G) mobile network, opportunities for enhancing network adaptability and efficiency are being explored. AI / ML may be applied in various use cases including beam management (BM) and beam selection. Traditionally, BM or beam selection may rely on static configurations or predefined rules, which may not be able to keep up with the dynamic nature of modern networks. The introduction of AI / ML may bring possibilities for optimizing network performance by enabling data-driven decision making and predictive adaptation.SUMMARY

[0004] In a first aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: transmit, to a second apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; and receive, from the second apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set, wherein the configuration request indicates at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

[0005] In a second aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises at least one processor; and at least one memory storing instructions that,when executed by the at least one processor, cause the second apparatus at least to: receive, from a first apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; and transmit, to the first apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set, wherein the configuration request indicates at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

[0006] In a third aspect of the present disclosure, there is provided a method at a first apparatus. The method comprises: transmitting, to a second apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; and receiving, from the second apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set, wherein the configuration request indicates at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

[0007] In a fourth aspect of the present disclosure, there is provided a method at a second apparatus. The method comprises: receiving, from a first apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; and transmitting, to the first apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set, wherein the configuration request indicates at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

[0008] In a fifth aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises means for transmitting, to a second apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; and means for receiving, from thesecond apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set, wherein the configuration request indicates at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

[0009] In a sixth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises means for receiving, from a first apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; and means for transmitting, to the first apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set, wherein the configuration request indicates at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

[0010] In a seventh aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the third and fourth aspects.

[0011] It is to be understood that the Summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Some example embodiments will now be described with reference to the accompanying drawings, where:

[0013] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;

[0014] FIG. 2 illustrates an example signaling flow for a process of configuration of resource sets in accordance with some example embodiments of the present disclosure;

[0015] FIG. 3 illustrates another example signaling flow for a process of a resource set configuration update in accordance with some other example embodiments of the present disclosure;

[0016] FIG. 4 illustrates another example signaling flow for an RS measurement process in accordance with some other example embodiments of the present disclosure;

[0017] FIG. 5 illustrates another example signaling flow for an example process of dynamic resource set configuration and dynamic Top-K beam reporting in accordance with some exampleembodiments of the present disclosure;

[0018] FIG. 6 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0019] FIG. 7 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0020] FIG. 8 illustrates a flowchart of another method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0021] FIG. 9 illustrates a flowchart of another method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0022] FIG. 10 illustrates a flowchart of a method implemented at a first apparatus in accordance with some other example embodiments of the present disclosure;

[0023] FIG. 11 illustrates a flowchart of a method implemented at a second apparatus in accordance with some other example embodiments of the present disclosure;

[0024] FIG. 12 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0025] FIG. 13 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0026] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION

[0027] Principles of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

[0028] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0029] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or notexplicitly described.

[0030] It shall be understood that although the terms “first,” “second,”..., etc. in front of noun(s) and the like 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 limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0031] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0032] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0033] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example 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 the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0034] As used in this application, the term “circuitry” may refer to one or more or all of the following:

[0035] (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and

[0036] (b) combinations of hardware circuits and software, such as (as applicable):

[0037] (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and

[0038] (ii) any portions of hardware processor(s) with software (including digital signal processor(s), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and

[0039] (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0040] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers animplementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0041] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-loT) and so on. Furthermore, the communications between a user device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1 G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), 5G-advanced, the sixth generation (6G) communication protocols, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Moreover, the communication may utilize any proper wireless communication technology, comprising 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), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s-OFDM) and / or any other technologies currently known or to be developed in the future. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0042] As used herein, the term “network device” refers to a node in a communication network via which a user device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a relay, an integrated access and backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a centralized unit (CU) and a distributed unit (DU) at an IAB donor node. An IAB node comprises amobile terminal (IAB-MT) part that behaves like a UE toward the parent node, and a DU part of an IAB node behaves like a base station toward the next-hop IAB node.

[0043] The term “user device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a user device may also be referred to as user equipment (UE), a subscriber station (SS), a portable subscriber station, a mobile station (MS), or an access terminal (AT). The user device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable user device, a personal digital assistant (PDA), portable computers, desktop computer, image capture user devices such as digital cameras, gaming user devices, music storage and playback appliances, vehicle-mounted wireless user devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), universal serial bus (USB) dongles, smart devices, wireless customer-premises equipment (CPE), an internet of things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. The user device may also correspond to a mobile termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “user device”, “terminal device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0044] The term “artificial intelligence (Al) / machine learning (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. The term “AI / ML model delivery” refers to a generic term related to delivery of the AI / ML model from one entity to another entity in any manner. It is noted that the entity could mean a network node / function (e.g., the gNB, a location management function (LMF), etc.), the user device, a proprietary server, etc. The term “AI / ML model inference” refers to a process of using a trained AI / ML model to produce the set of outputs based on the set of inputs.

[0045] The term “AI / ML model testing” refers to a subprocess of training, to evaluate the performance of a final AI / ML model using a dataset different from one used for model training and validation. Differently from the AI / ML model validation, the AI / ML model testing does not assume subsequent tuning of the model. The term “AI / ML model training” refers to a process to train the AI / ML Model (by learning input / output relationship) in a data driven manner and obtain the trained AI / ML Model for inference. The term “AI / ML model transfer” refers to a delivery of the AI / ML model over an air interface in a manner that is not transparent to 3GPP signaling, either parameters of a model structure known at a receiving end or a new model with parameters. The delivery may contain a full model or a partial model. The term “AI / ML model validation” refers to a subprocess of training, toevaluate the quality of the AI / ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for the model training.

[0046] The term “data collection” refers to a process of collecting data by the network nodes, a management entity, or the user device for the purpose of the AI / ML model training, data analytics and inference. The term “federated learning / federated training” refers to the ML technique that trains the AI / ML model across multiple decentralized edge nodes (e.g., the user devices, the gNBs) each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of the local data samples.

[0047] The term “model download” refers to a model transfer from the network device to the user device. The term “model identification” refers to a process / method of identifying the AI / ML model for the common understanding between the network device and the user device. It is notes that the process / method of model identification may or may not be applicable. It is noted that information regarding the AI / ML model may be shared during the model identification. The term “model monitoring” refers to a procedure that monitors an inference performance of the AI / ML model. The term “model update” refers to a process of updating the model parameters and / or model structure of the model. The term “model upload” refers to a model transfer from the user device to the network device.

[0048] The term “network-side AI / ML model” refers to an AI / ML model whose inference is performed entirely at the network device. The term “UE-side AI / ML model” refers to an AI / ML model whose inference is performed entirely at the user device. The term “two-sided AI / ML model” refers to a paired AI / ML model(s) over which a joint inference is performed, where the joint inference comprises AI / ML inference whose inference is performed jointly across the user device and the network device, i.e, thefirst partof the inference is firstly performed by the UE and then the remaining partis performed by the gNB, or vice versa.

[0049] The term “offline training” refers to an AI / ML training process where the model is trained based on the collected dataset, and where the trained model is later used or delivered for the inference. It is noted that this definition only serves as a guidance. There may be cases that may not exactly conform to this definition but could still be categorized as the offline training by commonly accepted conventions. The term “online training” refers to the AI / ML training process where the model being used for the inference is (typically continuously) trained in (near) real-time with an arrival of new training samples. It is noted that a notion of (near) real-time vs. non-real-time is context-dependent and is relative to the inference timescale. It is also noted that this definition only serves as a guidance. There may be cases that may not exactly conform to this definition but could still be categorized as the online training by commonly accepted conventions. It is also noted that fine-tuning / re-training may be done via the online or the offline training.

[0050] The term “reinforcement learning (RL)” refers to a process of training the AI / ML model fromthe input (as known as a state) and a feedback signal (also known as reward) resulting from the output (also known as an action) in an environment the model is interacting with. The term “semi-supervised learning” refers to a process of training a model with a mix of labeled data and unlabeled data. The term “supervised learning” refers to a process of training a model from input and its corresponding labels. The term “unsupervised learning” refers to the process of training a model without labelled data.

[0051] The term “beam” as used herein is synonymous with “spatial filter” or “spatial-domain filter”, as used in 3GPP standards.

[0052] FIG. 1 illustrates an example communication environment 100 in which example embodiments of the present disclosure can be implemented. As shown in FIG. 1, the communication environment 100 may comprise a first apparatus 110 which may operate as a user device such as a UE. The communication environment 100 may further comprise a second apparatus 120, which may operate as a network device such as a BS or a gNB.

[0053] In some example embodiments, the second apparatus 120 may operate as a resource management entity to provide a resource management related function in the communication environment 100. The resource management may involve management for any resource such as beam, a cell and some other time, frequency and special resources. For the purpose of discussion, some example embodiments will be described by taking beam management as an example of the resource management.

[0054] It is to be understood that the number or type of apparatuses and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication environment 100 may include any suitable number or type of apparatuses configured to implement some example embodiments.

[0055] In the following, for purpose of illustration, some example embodiments are described with the first apparatus 110 operating as a user device, e.g., a UE, and the second apparatus 120 operating as a network device. However, in some example embodiments, operations described in connection with a user device may be implemented at a network device or other devices, and operations described in connection with a network device may be implemented at a user device.

[0056] In the communication environment 100, a machine learning model such as an AI / ML model may be used for augmenting air interface. The machine learning model, which may be a UE-side model or a network-side model, may be configured to implement an algorithm to provide a configured functionality in the communication environment 100 in FIG. 1. For example, the model may be configured to provide a function related to resource management such as beam management. T raining, performance monitoring, and / or inference of the model may be performed at the first apparatus 110 that may operate as a UE or the second apparatus 120 which may operate as a network device.

[0057] AI / ML may enhance beam management, for example, in downlink (DL) transmission beam prediction (Tx beam prediction). Both UE-sided and network (NW)-sided AI / ML models may enable more efficient and adaptive beam selection by utilizing real-time and historical network conditions. Given the potential of AI / ML in beam management, further exploration may help refine its application in dynamic wireless environments.

[0058] One area of focus may be the prediction of transmission beams using AI / ML techniques, which may rely on different approaches depending on spatial and temporal factors. For a spatial-domain prediction case (referred to as BM-Case1), the AI / ML model may use measurement results from a set of beams (referred to as Resource Set B or Set B) to predict an optimal set of beams (referred to as Resource Set A or Set A) for transmission. Meanwhile, for temporal-domain prediction case (referred to as BM-Case2), the AI / ML model may use historical measurement results of Set B to predict future beam selections for Set A and this may be useful for a scenario where mobile users are experiencing rapid changing network conditions.

[0059] Beyond beam prediction, other aspects may also require consideration. For instance, the signaling or mechanism(s) needed to support lifecycle management (LCM) operations specific to beam management may require further evaluation. LCM may involve continuously updating the AI / ML model(s), transferring data between for example a BS and a UE, and updating the training data to ensure AI / ML model(s) remain effective under evolving network conditions. Additionally, ensuring consistency between communication conditions for the training and the inference of an AI / ML model may be of importance to ensure model performance, particularly when network-side additional conditions are identified for during inference.

[0060] To effectively implement AI / ML driven beam prediction, a structured solution may be required to manage measurement data and inference outputs. Resource Set A, or Set A, may serve as a component in AI / ML-driven beam management. Its primary role may be to provide model output and play a part in inference configuration. Each beam configuration in Resource Set A may be singularly tied to a specific training dataset identifier (ID) or Al ID (identifying an AI / ML model), ensuring a one-to-one mapping between a dataset ID and an Al ID. Each configuration in Resource Set A may indicate a number of beams transmitted from the base station, the power levels assigned to each beam, and the beamforming directions for each antenna element on the base station. The dataset ID associated with each configuration may correspond to training data, which may include measurement information about Set B, such as a received signal strength indicator (RSSI). This structure may establish a one-to-one mapping between a specific dataset and an Al model, ensuring consistency between training data and inference processes. Additionally, Resource Set A may be used together with Resource Set B to manage associations of, for example, measurement and prediction time instances, reporting intervals and reporting quantities.

[0061] As part of its inference configuration, Resource Set A may include parameters defining time instances, such as measurement and prediction time instances. Configuring of Resource Set A may also handle reporting details and associations with Resource Set B, ensuring effective utilization of measurement data in the inference process. Resource Set A may allow alternative configurations using the same dataset ID or Al ID across different resource sets, offering flexibility. However, NW-side additional conditions or associated IDs, while related, may not be inherently considered as part of the inference configuration within Resource Set A. Given its role in structuring Al-driven beam selection, Resource Set A may play a role in maintaining precise spatial and temporal inference within AI / ML applications.

[0062] Resource Set B, or Set B, in contrast, may support multiple configurations and function as part of the inference configuration, often linked to Resource Set A. Unlike Resource Set A, Resource Set B may accommodate various spatial-domain beam prediction patterns and various historical time instances for time-domain beam prediction.

[0063] Resource Set B may be associated with Resource Set A through specific signaling mechanisms, allowing for structured communication between measurement collection and inference execution. These associations may include signaling mechanisms indicating the connection between Resource Set B and Resource Set A, with variations depending on the implementation approach. Given its dynamic nature, Resource Set B may support flexible configurations to accommodate different spatial and temporal requirements in beam management. Additionally, its signaling configuration may include or exclude explicit signaling mechanisms, depending on system requirements, offering adaptability.

[0064] The configuration of resource sets, such as Set A and Set B, may be important for optimizing beam management in both NW-sided and UE-sided AI / ML models. Ambiguities in the configuration of these sets may lead to inefficiencies, increased signaling overhead, and misalignment in measurement reporting, which may ultimately impact the performance of AI / ML models. Various approaches may be proposed to specify configurations for Set A and Set B, each presenting potential advantages and limitations.

[0065] One approach may involve configuring Set A for training and performance monitoring, while Set B may be designated for inference. To distinguish their roles, different CSI-ResourceConfiglds, which may be carried in a radio resource control (RRC) reconfiguration, may be utilized for each set. However, such an approach may not fully resolve the question whether Set B is cell-specific or model-determined, potentially resulting in duplication of configurations, particularly when Set B is often a subset of Set A. Furthermore, while multiple resource sets may be needed for Set B in BM-Case 2, there is not a comprehensive framework for dynamic adjustments based on varying beam report sizes, which may be needed for effective inference.

[0066] Another approach may propose reusing legacy aperiodic channel state information (A-CSI) reports while introducing dynamic signaling for reference signal (RS) resources, which may streamline the configuration process. However, this approach may not address the constraints imposed by the maximum number of RSs for reference signal received power (RSRP) measurement, which is currently capped at 64. This constraint may hinder the ability to effectively measure and report Top-K beams (where K is a positive integer), requiring a trade-off between measurement overhead and prediction accuracy.

[0067] An alternative configuration approach may emphasize the need for an explicit configuration of Set B for the UE, including details on beam IDs and periodicity. While this may allow the UE to perform necessary measurements, it may lack a clear mechanism for dynamically indicating which beams are part of the Top-K measurements, which is a factor for optimizing beam selection. Another approach may support multiple resource sets for both Set A and Set B, which may enhance flexibility, though it may not clarify how these configurations may be communicated to the UE.

[0068] The dynamic nature of AI / ML predictions may need a flexible configuration approach that can accommodate variable sizes for beam reports and support multiple measurement instances for inference, particularly in BM-Case 2. Existing CSI frameworks may allow for the configuration of both sets, though they may lack the provisions to dynamically indicate which beams are part of the Top-K measurements, leading to increased signaling overhead and potential inefficiencies in beam selection. The absence of such provisions may limit adaptability in AI / ML-based beam prediction. Further study may be needed on how to dynamically configure RS resources for measurements, particularly given the evolving nature of AI / ML-based beam management.

[0069] Additionally, some approaches may propose configuring both Set A and Set B within a CSI -ReportConfig field in an RRC reconfiguration, though such approaches may not resolve the ambiguity regarding the relationship between Set A and Set B, which may be crucial for effective performance monitoring and inference reporting. The absence of a clearly defined configuration process that aligns with both NW-sided and UE-sided models may remain a limitation.

[0070] In summary, while multiple approaches may exist to address the configuration of resource sets for beam management, challenges remain, which may involve the ambiguity regarding the relationship between Set A and Set B, constraints on the maximum number of RSs for RSRP measurement, and the lack of dynamic configuration capabilities. This may hinder the effective deployment of AI / ML models. These issues may further need establishment of a clear and standardized configuration process that can adapt to the evolving demands of beam management in future wireless networks. The need for a comprehensive framework that allows for dynamic adjustments and clear communication of resource configurations may be important to overcoming the current limitations and optimizing performance.

[0071] To address these issues, a well-defined configuration process for Set A and Set B may be needed to align with both NW-sided and UE-sided models. This may include defining the relationship between the two sets, ensuring that the configurations may be interpreted by both the gNB and the UE, and allowing for dynamic adjustments of resource sets to optimize performance monitoring and inference reporting.

[0072] In accordance with some example embodiments, there is provided a solution of configuration of a resource set for resource management. In some example embodiments, the first apparatus 110 (e.g., a UE) transmits to the second apparatus 120 (e.g., a gNB), a configuration request for at least one of a first resource set (e.g., Set A) or a second resource set (e.g., Set B). The first resource set may be used for training and performance monitoring of a machine learning model for resource management. The second resource set may be used for inference of the machine learning model. The configuration request may indicate one of: a capability of the first apparatus 110 with respect to the resource management, a channel condition of the first apparatus 110, or at least one preferred configuration of the at least one of the first resource set or the second resource set. In response, the first apparatus 110 receives from the second apparatus 120 a configuration response for the configuration request and the configuration response includes at least one configuration of the at least one of the first resource set or the second resource set.

[0073] In this way, clear communication may be enabled between the first apparatus and the second apparatus regarding the current state of resource sets for both training and performance monitoring of a machine learning model, ensuring configuration alignment and reducing configuration duplication for these resource sets.

[0074] Reference is now made to FIG. 2, which illustrates an example signaling flow 200 of a process of resource set configuration according to some example embodiments. The signaling flow 200 involves the first apparatus 110 and the second apparatus 120.

[0075] As illustrated in FIG. 2, the first apparatus 110 transmits (202) to a second apparatus 120, a configuration request for at least one of a first resource set or a second resource set. The first resource set is used for training and performance monitoring of a machine learning model for resource management, and the second resource set is used for inference of the machine learning model. Correspondingly, the second apparatus 120 receives (204) the configuration request from the first apparatus 110. In some examples, the first resource set may be Resource Set A or Set A and the second resource set may be Resource Set B or Set B.

[0076] In some examples, before transmitting (202) the configuration request, the first apparatus 110 may establish an RRC connection with the second apparatus 120 to enable further signaling exchange. The first apparatus 110 may initiate a standard RRC procedure by sending an RRC Connection Request message to indicate its intent to establish an RRC connection with the secondapparatus 120. In response, the second apparatus 120 may proceed with the connection setup and transmit an RRC Connection Setup Complete message, finalizing the connection setup so that higher-layer signaling, for example the Set A / B configuration request related signaling, may proceed.

[0077] In some examples, the configuration request may be used to request for both Set A and Set B. Such configuration request may be transmitted via a message called a Set A / B configuration request message.

[0078] The configuration request may indicate a capability of the first apparatus 110 with respect to the resource management. In some examples, in the case that the beam management is enabled, the indicated capability may include parameters such as the maximum number of beams supported or the beamforming modes supported, allowing the second apparatus 120 to allocate resources accordingly.

[0079] The configuration request may indicate a channel condition of the first apparatus 110. In some examples, the indicated channel conditions may include parameters such as signal strength (e.g., RSRP) or the mobility state of the first apparatus 110, allowing the second apparatus 120 to access the channel condition and adjust beam management strategies.

[0080] The configuration request may indicate at least one preferred configuration of the at least one of the first resource set or the second resource set. In some examples, in the case that the beam management is enabled, the indicated preferred Set A / B configuration may include parameters such as desired number of beams and resource block assignment, providing the second apparatus 120 information to optimize the resource allocation for beam selection and prediction.

[0081] In some example embodiments, the second resource set, such as Set B, may be defined as a subset of the first resource set, such as Set A. In some examples, this relationship information may be explicitly communicated between the first apparatus 110 and second apparatus 120 through the configuration request. The defined relationship between Set A and Set B may introduce a hierarchical structure for resource management, allowing for efficient resource allocation and minimizing redundancy.

[0082] In some example embodiments, in response to receiving the configuration request, the second apparatus 120 may determine at least one configuration based on conditions including at least one of: a network load associated with available resources, interferences associated with the available resources, or measurement data associated with the available resources prior to the configuration request. It is to be understood that the listed conditions are merely for illustrative purposes but do not imply any limitations.

[0083] In some example embodiments, the at least one configuration may be determined by using a machine learning model (e.g., an AI / ML model deployed on the second apparatus 120). In some examples, after receiving the configuration request, within the second apparatus 120 (e.g., a gNB),an AI / ML augmented resource management entity of the second apparatus 120 may evaluate the configuration request by analyzing the network load, interference levels and prior measurement data. An AI / ML model may serve as a predictive tool, assisting the resource management entity in optimizing the resource allocation and resource (e.g., beam) configuration based on trained patterns and realtime conditions received from the first apparatus 110.

[0084] The second apparatus 120 then transmit (206) to the first apparatus 110, a configuration response for the configuration request. The configuration response includes at least one configuration of the at least one of the first resource set or the second resource set. Correspondingly, the first apparatus 110 receives (208) the configuration response from the second apparatus 120.

[0085] In some examples, the configuration response including the configuration for both Set A and Set B may be transmitted via a message called a Set A / B configuration response message. It is to be understood that the configuration request and response may be transmitted in any proper way. Using the Set A / B configuration request and response messages may provide a standardized signaling approach, ensuring a clear and consistent understanding between the first apparatus 110 and the second apparatus 120.

[0086] In some example embodiments, the configuration response may indicate at least one of the first resource set or the second resource set responsive to the configuration request for the at least one of the first resource set or the second resource set. In some examples, the configuration response may specify the resource allocation for the configured Set A and / or Set B. For example, in the case that the beam management is enabled, the response message may indicate how beams or resource blocks (RBs) are distributed between Set A and Set B, where Set B may include resources designated for measurements and Set A may include resources selected for inference.

[0087] In some example embodiments, the configuration response may indicate scheduling information about the at least one of the first resource set (e.g. Set A) or the second resource set (e.g. Set B). In some examples, the configuration response may specify the periodicity or time-domain allocation for Set A and Set B. For example, the response message may indicate at what time intervals the first apparatus 110 is to perform measurements for Set B and perform inference based on Set A.

[0088] In some example embodiments, the configuration response may indicate a status whether the configuration request is accepted or partially accepted by the second apparatus 120. In some examples, the configuration response may specify whether the configuration request has been fully accepted, partially accepted or rejected. If the configuration request is partially accepted or rejected, the response may include specific conditions / reasons such as interference concerns or network load conditions, to inform the first apparatus 110 of factors for the decision.

[0089] In some example embodiments, the determined at least one configuration may be transmitted from the second apparatus 120 to the first apparatus 110 via a channel state information(CSI) resource configuration such as CSI-resourceConfigID in an RRC reconfiguration. In some example embodiments, the at least one configuration may comprise a configuration of the first resource set (e.g. Set A) and a separate configuration of the second resource set (e.g. Set B). In some examples, the configuration response may specify different CSI-resourceConfigIDs for Set A and Set B, ensuring their different roles are clearly distinguished. For example, Set A may be associated with a CSI-resourceConfigID related to training and performance monitoring where Set B may be associated with a CSI-resourceConfigID related to inference.

[0090] In some example embodiments, after receiving the configuration response, the first apparatus 110 may apply the at least one configuration to perform the resource management using the machine learning model. In some examples, in the case that the beam management is enabled, the first apparatus 110 may internally configure its beam management based on the received configuration for Set A and Set B. Set A may include active beams designated for transmission and Set B may include dynamic standby beams for measurements. Set B may be configured as a subset of Set A by the second apparatus 120 as discussed. The configured relationship may be transmitted from the second apparatus 120 to the first apparatus 110 via the configuration response, ensuring a mutual understanding. This understanding may allow the first apparatus 110 to perform only necessary measurements.

[0091] The abovementioned configuration procedure and the related signaling mechanism may establish a clear and standardized configuration process for Set A and Set B, ensuring that both the network device and the UE have mutual understanding of the respective resource set configuration for each resource set and this may enhance the overall network performance.

[0092] Changes in wireless environment such as channel quality, network load and UE location / mobility may impact beam management and resource allocation. As the network condition fluctuates, the initially configured parameters for Set A and Set B may no longer be optimal, and the configuration for Set A and Set B may need to adapt dynamically to maintain optical performance, ensuring efficient beam selection and resource allocation.

[0093] In some example embodiments, the first apparatus 110 may receive from the second apparatus 120 at least one first configuration and a configuration update for the first resource set and the second resource set. The configuration update may indicate at least one second configuration of the first resource set and the second resource set. The configuration update may indicate at least: a reason for the configuration update, or effective time when the at least one second configuration is valid.

[0094] Reference is now made to FIG. 3, which illustrates an example signaling flow 300 of a process of resource set configuration update according to some example embodiments. The signaling flow 300 involves the first apparatus 110 and the second apparatus 120.

[0095] As illustrated in FIG. 3, the second apparatus 120 transmits (302) to the first apparatus 110 at least one first configuration of a first resource set (such as Resource Set A or Set A) and a second resource set (such as Resource Set B or Set B) and correspondingly the first apparatus 110 receives (304) the at least one first configuration of the first resource set and the second resource set.

[0096] In some example embodiments, the second apparatus 120 may determine that the at least one first configuration is to be updated into the at least one second configuration, based at least one of: a channel quality associated with the first apparatus, a network load associated with available resources, a location or mobility of the first apparatus, or a prediction of the first resource set and the second resource set using a machine learning model.

[0097] In some examples, after the initial configuration, the resource management entity of the second apparatus 120 (e.g., gNB) may evaluate real time data including but not limited to a channel quality, a network load, UE location / mobility and AI / ML predictions, to determine whether an update to the resource set configuration is needed in order to maintain optical performance and adaptability to the changing conditions.

[0098] If the second apparatus 120 determines that an update is needed, the second apparatus 120 transmits (306) to the first apparatus 110 a configuration update for the first resource set and the second resource set. Correspondingly the first apparatus 110 receives (308) from the second apparatus 120 the configuration update for the first resource set and the second resource set.

[0099] In some example embodiments, the configuration update may indicate at least one second configuration of the first resource set (e.g. Set A) and the second resource set (e.g. Set B). In some examples, if the network condition change exceeds a threshold, the second apparatus 120 may transmit a message such as a Set A / B update (SA / BU) message to indicate the updated composition of Set A and Set B.

[0100] In some example embodiments, the configuration update may indicate at least one of: a reason for the configuration update, or effective time when the at least one second configuration is valid. In some examples, the message may include a reason for the update such as load balancing or mobility changes. The message may further include effective time, specifying when the updated configuration becomes valid.

[0101] In some example embodiments, similar to the scenario of initial configuration, during configuration update, the configuration update response may be transmitted from the second apparatus 120 to the first apparatus 110 via a CSI resource configuration such as CSI-resourceConfiglD in an RRC reconfiguration. The configuration of the first resource set (e.g. Set A) and the configuration of the second resource set (e.g. Set B) may be separate. In some examples, the configuration response may specify different CSI-resourceConfigIDs for Set A and Set B during configuration update, ensuring their different roles are clearly distinguished. For example, Set A maybe associated with a CSI-resourceConfig I D related to training and performance monitoring where Set B may be associated with a CSI-resourceConfigID related to inference.

[0102] In some example embodiments, Set B may still be designated as a subsetof Set A. In some examples, Set B may be defined and communicated as a dynamic subset of Set A. As discussed, this may prevent duplicated configuration and simplify resource allocation.

[0103] In some example embodiments, in the case that the configuration update indicates the effective time when the updated at least one second configuration is valid, the first apparatus 110 may update the at least one first configuration into the at least one second configuration at or before the effective time. In some examples, the first apparatus 110 may update its local beam set usage accordingly at or before the effective time, ensuring seamless adaptation to the new configuration and alignment with network conditions.

[0104] If the second apparatus 120 determines that an update is not needed, the second apparatus 120 may continue monitoring network conditions without transmitting additional signaling.

[0105] It is to be understood that the features and operations related to the first apparatus 110 and the second apparatus 120 as described above with reference to FIG. 2 are also applicable to the process in FIG. 3 and have similar effects. For the purpose of simplification, the details thereof will not be repeated.

[0106] Some example embodiments propose an extension of the RS capacity through an introduction of an extended measurement category that allows for the reporting of Top-K beams beyond the limitation of the maximum number of RSs for RSRP measurement. In some example embodiments, the first apparatus 110 may receive from a second apparatus 120, a first indication that an extended number of reference signals are enabled for performance monitoring of a machine learning model for resource management. The first apparatus 110 may perform measurements related to the extended number of reference signals, on resources in a resource set. Subsequently, the first apparatus 110 may transmit to the second apparatus 120, a measurement report based on the measurements, the measurement report indicating a target number of candidate resources from the resource set. The target number is less than or equal to a total number of resources in the resource set.

[0107] Reference is now made to FIG. 4, which illustrates an example signaling flow 400 of an RS measurement process according to some example embodiments. The signaling flow 400 involves the first apparatus 110 and the second apparatus 120.

[0108] The second apparatus 120 transmits (402) to the first apparatus 110 a first indication that an extended number of RSs are enabled for performance monitoring of a machine learning model for resource management. Correspondingly, the first apparatus 110 receives (404) the first indication from the second apparatus 120.

[0109] In some examples, the first indication may correspond to the information from the second apparatus 120 to instruct the first apparatus 110 to enable an extended reference signal measurement category to extend the allowed number (or the maximum number) of RSs, allowing the first apparatus 110 to measure more than the maximum number of RSs such as 64 RSs. This may ensure that a broader set of beams to be captured by measuring the number of available RSs exceeding 64. By measuring the number of RSs beyond the standard limit (i.e., 64), the first apparatus 110 may capture a larger pool of beams for enhanced measurement accuracy.

[0110] In some example embodiments, the first apparatus 110 may receive from the second apparatus 120 a second indication for the target number. In some examples, the second indicator may correspond to the information regarding how the first apparatus 110 may report the Top-K beams and the target number of beams to be reported.

[0111] In some example embodiments, at least one of the first or the second indication is carried in a CSI report configuration such as a CSI-ReportConfig field in an RRC reconfiguration. In some examples, during RRC reconfiguration, a new CSI-ReportConfig field may be configured to carry information corresponding to at least one of the first indication or the second indication. It is also possible that an existing CSI-ReportConfig field is reused or repurposed for carrying at least one of the first indication or the second indication.

[0112] The first apparatus 110 performs (406) measurements related to the extended number of reference signals, on resources in a resource set such as the first resource set (e.g. Set A) for training and performance monitoring of a machine learning model for resource management and the second resource set (e.g. Set B) for inference of the machine learning model. In some examples, the first apparatus 110 may scan a larger set of RSs, collecting RSRP, reference signal receiving quality (RSRQ) or other relevant signal quality metrics to access beam performance.

[0113] The first apparatus 110 transmits (408) to the second apparatus 120, a measurement report based on the measurements, the measurement report indicating a target number of candidate resources from the resource set, the target number being less than or equal to a total number of resources in the resource set. Corresponding, the second apparatus 120 receives from the first apparatus 110, the measurement report based on the measurements.

[0114] In some example embodiments, the first apparatus 110 may select top N candidate resources from the resource set based on measured qualities or priorities of the reference signals, N equaling to the target number. The measurement report transmitted by the first apparatus 110 to the second apparatus 120 indicates the selected top N candidate resources. For example, the first apparatus 110 may then select the Top-N beams with the highest signal quality or priority, ensuring that the most suitable beams are selected for reporting.

[0115] In some example embodiments, the measurement report may indicate relative priorities ofthe target number of candidate resources. In some examples, the first apparatus 110 may return a CSI measurement report to the second apparatus 120, indicating the Top-N beams and their relative priorities. This dynamic Top-N reporting mechanism may minimize the overhead associated with reporting a large set of beams by focusing only on the most suitable candidates, ensuring efficient resource utilization and optimized beam selection.

[0116] It is to be understood that the features and operations related to the first apparatus 110 and the second apparatus 120 as described above with reference to FIGS. 2 and 3 are also applicable to the process in FIG. 4 and have similar effects. For the purpose of simplification, the details thereof will not be repeated.

[0117] An example process of dynamic resource set configuration and dynamic Top-K beam reporting will be described below with reference to FIG. 5. In this example, a UE 501 is an example of the first apparatus 110 and a NW 502 includes a gNB (an example of the second apparatus 120) with a resource management entity.

[0118] During RRC connection setup, as shown in FIG. 5, in a process 500, at step 505, the UE 501 may initiate an RRC connection request to establish communication with the NW 502. The NW 502 may then complete the connection setup at step 510, enabling higher-layer signaling and subsequent configuration procedures.

[0119] During initial configuration, at step 515, the UE 501 may send a Set A / B Configuration Request (SA / BCR) to the NW 502, including its capabilities, current channel conditions, and preferred Sets A and B. At step 520, the NW 502 may evaluate the received request, using the resource management entity and the AI / ML model, to determine the optimal beam configuration. At step 525, the NW 502 may transmit a Set A / B Configuration Response (SA / BCR) to the UE 501, specifying the configured Sets A and B, resource blocks and beams assigned for each resource set, scheduling information, and status of the request.

[0120] At step 530, the UE 501 may apply the received configuration, establishing Set B as a subset of Set A, ensuring a hierarchical structure for beam management.

[0121] For extended RS and Top-K reporting, at step 535, the NW 502 may initiate RRC Reconfiguration to enable an extended reference signal measurement category, allowing the UE 501 to measure more than 64 RS. At step 540, the UE 501 may scan a larger set of RS and identify the Top-K beams based on signal quality or priority. At step 545, the UE 501 may generate and send a CSI Report to the NW 502, including Top-K beam IDs and their priority rankings.

[0122] Regarding dynamic Set A / B update, at step 550, the NW 502 may continuously re-evaluate the need for reconfiguration based on changes in channel conditions, network load, and the mobility of the UE 501. If an update is required, the NW 502 may send a Set A / B Update (SA / BU) at step 555, specifying the updated Sets A and B, the reason for the update, and the effective time. At step 560,the UE 501 may apply the updated configuration.

[0123] If no update is needed, the NW 502 may continue monitoring without additional signaling.

[0124] The proposed solutions according to some example embodiments address the challenges in the ambiguities in resource set configuration, limited reference signal capacity and large signaling overhead associated with beam management, by introducing a standard configuration process, enabling hierarchical resource management, and supporting dynamic resource set configuration. Additionally, the solutions expand the capability by allowing extended reference signal capacity and optimizing dynamic Top-K beam reporting, reducing measurement overhead while maintaining high prediction accuracy.

[0125] FIG. 6 shows a flowchart of an example method 600 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 600 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0126] At block 610, the first apparatus 110 transmits, to a second apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model, and

[0127] At block 620, the first apparatus 110 receives, from the second apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set, wherein the configuration request indicates at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

[0128] In some example embodiments, the at least one configuration may indicate at least one of: the at least one of the first resource set or the second resource set, scheduling information about the at least one of the first resource set or the second resource set, or a status whether the configuration request is accepted or partially accepted by the second apparatus.

[0129] In some example embodiments, the at least one configuration may comprise a configuration of the first resource set and a separate configuration of the second resource set.

[0130] In some example embodiments, the at least one configuration may be received via a channel state information (CSI) resource configuration.

[0131] In some example embodiments, the second resource set may be a subset of the first resource set.

[0132] In some example embodiments, the at least one configuration may be related to at least one of: a network load associated with available resources, interferences associated with the available resources, or measurement data associated with the available resources prior to the configurationrequest.

[0133] In some example embodiments, the method 600 further comprises: the first apparatus 110 may apply the at least one configuration to perform the resource management using the machine learning model.

[0134] In some example embodiments, a first apparatus capable of performing any of the method 600 (for example, the first apparatus 110 in FIG. 1 ) may comprise means for performing the respective operations of the method 600. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0135] FIG. 7 shows a flowchart of an example method 700 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 700 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0136] At block 710, the second apparatus 120 receives, from a first apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model, and

[0137] At block 720, the second apparatus 120 transmits, to the first apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set, wherein the configuration request indicates at least one of: a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, or at least one preferred configuration of the at least one of the first resource set or the second resource set.

[0138] In some example embodiments, the at least one configuration may indicate at least one of: the at least one of the first resource set or the second resource set, scheduling information about the at least one of the first resource set or the second resource set, or a status whether the configuration request is accepted or partially accepted by the second apparatus.

[0139] In some example embodiments, the at least one configuration may comprise a configuration of the first resource set and a separate configuration of the second resource set.

[0140] In some example embodiments, the at least one configuration may be transmitted via a channel state information (CSI) resource configuration.

[0141] In some example embodiments, the second resource set may be a subset of the first resource set.

[0142] In some example embodiments, the method 700 further comprises: responsive to the configuration request, the second apparatus 120 may determine the at least one configuration based on at least one of: a network load associated with available resources, interferences associated withthe available resources, or measurement data associated with the available resources prior to the configuration request.

[0143] In some example embodiments, the at least one configuration may be determined by using a machine learning model.

[0144] In some example embodiments, a second apparatus capable of performing any of the method 700 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 700. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0145] FIG. 8 shows a flowchart of an example method 800 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 800 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0146] At block 810, the first apparatus 110 receives, from a second apparatus, at least one first configuration of a first resource set and a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model, and

[0147] At block 820, the first apparatus 110 receives, from the second apparatus, a configuration update for the first resource set and the second resource set, the configuration update indicating: at least one second configuration of the first resource set and the second resource set, at least one of: a reason for the configuration update, or effective time when the at least one second configuration is valid.

[0148] In some example embodiments, the method 800 further comprises: the first apparatus 110 may update the at least one first configuration into the at least one second configuration at or before the effective time.

[0149] In some example embodiments, the second resource set may be a subset of the first resource set.

[0150] In some example embodiments, the at least one second configuration may comprise a configuration of the first resource set and a separate configuration of the second resource set.

[0151] In some example embodiments, the at least one second configuration may be received via a channel state information (CSI) resource configuration.

[0152] In some example embodiments, the at least one second configuration may be related to at least one of: a channel quality associated with the first apparatus, a network load, a location or mobility of the first apparatus, or a prediction of the first resource set and the second resource set using the machine learning model.

[0153] In some example embodiments, a first apparatus capable of performing any of the method 800 (for example, the first apparatus 110 in FIG. 1 ) may comprise means for performing the respective operations of the method 800. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0154] FIG. 9 shows a flowchart of an example method 900 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 900 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0155] At block 910, the second apparatus 120 transmits, to a first apparatus, at least one first configuration of a first resource set and a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model, and

[0156] At block 920, the second apparatus 120 transmits, to the first apparatus, a configuration update for the first resource set and the second resource set, the configuration update indicating: at least one second configuration of the first resource set and the second resource set, at least one of: a reason for the configuration update, or effective time when the at least one second configuration is valid, the second resource set is a subset of the first resource set.

[0157] In some example embodiments, the at least one second configuration may comprise a configuration of the first resource set and a separate configuration of the second resource set.

[0158] In some example embodiments, the at least one second configuration may be transmitted via a channel state information (CSI) resource configuration.

[0159] In some example embodiments, the method 900 further comprises: the second apparatus 120 may determine that the at least one first configuration is to be updated into the at least one second configuration, based at least one of: a channel quality associated with the first apparatus, a network load associated with available resources, a location or mobility of the first apparatus, or a prediction of the first resource set and the second resource set using the machine learning model.

[0160] In some example embodiments, a second apparatus capable of performing any of the method 900 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 900. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0161] FIG. 10 shows a flowchart of an example method 1000 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1000 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0162] At block 1010, the first apparatus 110 receives, from a second apparatus, a first indication that an extended number of reference signals are enabled for performance monitoring of a machine learning model for resource management.

[0163] At block 1020, the first apparatus 110 performs measurements related to the extended number of reference signals, on resources in a resource set.

[0164] At block 1030, the first apparatus 110 transmits, to the second apparatus, a measurement report based on the measurements, the measurement report indicating a target number of candidate resources from the resource set, the target number being less than or equal to a total number of resources in the resource set.

[0165] In some example embodiments, the method 1000 further comprises: the first apparatus 110 may receive, from the second apparatus, a second indication for the target number.

[0166] In some example embodiments, at least one of the first indication or the second indication may be carried in a channel state information (CSI) report configuration.

[0167] In some example embodiments, the measurement report may further indicate relative priorities of the target number of candidate resources.

[0168] In some example embodiments, the method 1000 further comprises: the first apparatus 110 may select top N candidate resources from the resource set based on measured qualities or priorities of the reference signals, N equaling to the target number, where the measurement report indicates the selected top N candidate resources.

[0169] In some example embodiments, a first apparatus capable of performing any of the method 1000 (for example, the first apparatus 110 in FIG. 1) may comprise means for performing the respective operations of the method 1000. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0170] FIG. 11 shows a flowchart of an example method 1100 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1100 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0171] At block 1110, the second apparatus 120 transmits, to a first apparatus, a first indication that an extended number of reference signals are enabled for performance monitoring of a machine learning model for resource management.

[0172] At block 1120, the second apparatus 120 receives, from the first apparatus, a measurement report indicating a target number of candidate resources from the resource set, the target number being less than or equal to a total number of resources in the resource set.

[0173] In some example embodiments, the method 1100 further comprises: the second apparatus120 may transmit, to the first apparatus, a second indication for the target number.

[0174] In some example embodiments, at least one of the first indication or the second indication may be carried in a channel state information (CSI) report configuration.

[0175] In some example embodiments, the measurement report may further indicate relative priorities of the target number of candidate resources.

[0176] In some example embodiments, the target number of candidate resources may comprise top N candidate resources from the resource set based on measured qualities or priorities of the reference signals, N equaling to the target number.

[0177] In some example embodiments, a second apparatus capable of performing any of the method 1100 (for example, the second apparatus 120 in FIG. 1]) may comprise means for performing the respective operations of the method 1100. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0178] FIG. 12 is a simplified block diagram of a device 1200 that is suitable for implementing example embodiments of the present disclosure. The device 1200 may be provided to implement a communication device, for example, the first apparatus 110 or the second apparatus 120 as shown in FIG. 1. As shown, the device 1200 includes one or more processors 1210, one or more memories 1220 coupled to the processor 1210, and one or more communication modules 1240 coupled to the processor 1210.

[0179] The communication module 1240 is for bidirectional communications. The communication module 1240 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interfaces may represent any interface that is necessary for communication with other network elements. In some example embodiments, the communication module 1240 may include at least one antenna.

[0180] The processor 1210 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 1200 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

[0181] The memory 1220 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 1224, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, arandom-access memory (RAM) 1222 and other volatile memories that will not last in the power-down duration.

[0182] A computer program 1230 includes computer executable instructions that are executed by the associated processor 1210. The instructions of the program 1230 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 1230 may be stored in the memory, e.g., the ROM 1224. The processor 1210 may perform any suitable actions and processing by loading the program 1230 into the RAM 1222.

[0183] The example embodiments of the present disclosure may be implemented by means of the program 1230 so that the device 1200 may perform any process of the disclosure as discussed with reference to FIG. 1 to FIG. 11. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0184] In some example embodiments, the program 1230 may be tangibly contained in a computer readable medium which may be included in the device 1200 (such as in the memory 1220) or other storage devices that are accessible by the device 1200. The device 1200 may load the program 1230 from the computer readable medium to the RAM 1222 for execution. In some example embodiments, the computer readable medium may include any types of non-transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e. , tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0185] FIG. 13 shows an example of the computer readable medium 1300 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 1300 has the program 1230 stored thereon.

[0186] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0187] Some example embodiments of the present 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, such as those included in program modules, being executed in a device on a target physical or virtualprocessor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machineexecutable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[0188] Program code for carrying out methods of the present 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 the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0189] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0190] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random-access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0191] Further, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment.Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable subcombination.

[0192] Although the present disclosure has been described in languages specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

WHAT IS CLAIMED IS:

1. A first apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to:transmit, to a second apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; andreceive, from the second apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set,wherein the configuration request indicates at least one of:a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, orat least one preferred configuration of the at least one of the first resource set or the second resource set.

2. The first apparatus of claim 1 , wherein the at least one configuration indicates at least one of: the at least one of the first resource set or the second resource set,scheduling information about the at least one of the first resource set or the second resource set, ora status whether the configuration request is accepted or partially accepted by the second apparatus.

3. The first apparatus of any of claims 1 to 2, wherein the at least one configuration comprises a configuration of the first resource set and a separate configuration of the second resource set.

4. The first apparatus of any of claims 1 to 3, wherein the at least one configuration is received via a channel state information (CSI) resource configuration.

5. The first apparatus of any of claims 1 to 4, wherein the second resource set is a subset of the first resource set.

6. The first apparatus of any of claims 1 to 5, wherein the at least one configuration is related to at least one of:a network load associated with available resources,interferences associated with the available resources, ormeasurement data associated with the available resources prior to the configuration request.

7. The first apparatus of any of claims 1 to 6, wherein the first apparatus is further caused to: apply the at least one configuration to perform the resource management using the machine learning model.

8. A second apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to:receive, from a first apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; andtransmit, to the first apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set,wherein the configuration request indicates at least one of:a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, orat least one preferred configuration of the at least one of the first resource set or the second resource set.

9. The second apparatus of claim 8, wherein the at least one configuration indicates at least one of:the at least one of the first resource set or the second resource set,scheduling information about the at least one of the first resource set or the second resource set, ora status whether the configuration request is accepted or partially accepted by the second apparatus.

10. The second apparatus of any of claims 8 to 9, wherein the at least one configuration comprises a configuration of the first resource set and a separate configuration of the second resource set.

11. The second apparatus of any of claims 8 to 10, wherein the at least one configuration is transmitted via a channel state information (CSI) resource configuration.

12. The second apparatus of any of claims 8 to 11 , wherein the second resource set is a subset of the first resource set.

13. The second apparatus of any of claims 8 to 12, wherein the second apparatus is further caused to:responsive to the configuration request, determine the at least one configuration based on at least one of:a network load associated with available resources,interferences associated with the available resources, ormeasurement data associated with the available resources prior to the configuration request.

14. The second apparatus of claim 13, wherein the at least one configuration is determined by using a machine learning model.

15. A method comprising:at a first apparatus,transmitting, to a second apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; andreceiving, from the second apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set,wherein the configuration request indicates at least one of:a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, orat least one preferred configuration of the at least one of the first resource set or the second resource set.

16. A method comprising:at a second apparatus,receiving, from a first apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; andtransmitting, to the first apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set,wherein the configuration request indicates at least one of:a capability of the first apparatus with respect to the resource management, a channel condition of the first apparatus, orat least one preferred configuration of the at least one of the first resource set or the second resource set.

17. A first apparatus comprising:means for transmitting, to a second apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; andmeans for receiving, from the second apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set,wherein the configuration request indicates at least one of:a capability of the first apparatus with respect to the resource management,a channel condition of the first apparatus, orat least one preferred configuration of the at least one of the first resource set or the second resource set.

18. A second apparatus comprising:means for receiving, from a first apparatus, a configuration request for at least one of a first resource set or a second resource set, the first resource set used for training and performance monitoring of a machine learning model for resource management, and the second resource set used for inference of the machine learning model; andmeans for transmitting, to the first apparatus, a configuration response for the configuration request, the configuration response including at least one configuration of the at least one of the first resource set or the second resource set,wherein the configuration request indicates at least one of:a capability of the first apparatus with respect to the resource management,a channel condition of the first apparatus, orat least one preferred configuration of the at least one of the first resource set or the second resource set.

19. A computer readable medium comprising instructions stored thereon for causing an apparatus at least to perform the method of claim 15 or the method of claim 16.

Images