Configuration of monitoring resource set for resource management

Abstract

Apparatuses, methods and computer readable storage medium for configuration of a monitoring resource set for resource management are provided. In a method, a first apparatus receives, from a second apparatus, a monitoring configuration related to a monitoring resource set. The monitoring resource set is used for performance monitoring of a first machine learning model for resource management. The first apparatus receives, from the second apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

Description

CONFIGURATION OF MONITORING RESOURCE SET FOR RESOURCE MANAGEMENT CROSS-REFERENCE TO RELATED APPLCIATION

[0001] This application claims priority from, and the benefit of US Provisional Application No.63 / 754665, 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 a monitoring resource set 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: receive, from a second apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; and receive, from the second apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

[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: transmit, to a first apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; and transmit, to the first apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

[0006] In a third aspect of the present disclosure, there is provided a third apparatus. The third apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the third apparatus at least to: determine a prediction of a monitoring configuration related to performance monitoring of a first machine learning model, by using a second machine learning model, wherein the first machine learning model is used for resource management associated with a first apparatus; and determine a first recommendation for an adjustment of the monitoring configuration, based on the prediction.

[0007] In a fourth aspect of the present disclosure, there is provided a method at a first apparatus. The method comprises: receiving, from a second apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; and receiving, from the second apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

[0008] I n a fifth aspect of the present disclosure, there is provided a method at a second apparatus. The method comprises: transmitting, to a first apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; and transmitting, to the first apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

[0009] In a sixth aspect of the present disclosure, there is provided a method at a third apparatus. The method comprises: determining a prediction of a monitoring configuration related to performance monitoring of a first machine learning model, by using a second machine learning model, wherein the first machine learning model is used for resource management associated with a first apparatus; and determining a first recommendation for an adjustment of the monitoring configuration, based on the prediction.

[0010] In a seventh aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises means for receiving, from a second apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; and means for receiving, from the second apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

[0011] In an eighth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises means for transmitting, to a first apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; and means for transmitting,to the first apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

[0012] In a ninth aspect of the present disclosure, there is provided a third apparatus. The third apparatus comprises means for determining a prediction of a monitoring configuration related to performance monitoring of a first machine learning model, by using a second machine learning model, wherein the first machine learning model is used for resource management associated with a first apparatus; and means for determining a first recommendation for an adjustment of the monitoring configuration, based on the prediction.

[0013] In a tenth 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 fourth, fifth and sixth aspects.

[0014] 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

[0015] Some example embodiments will now be described with reference to the accompanying drawings, where:

[0016] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;

[0017] FIG. 2 illustrates an example signaling flow for a dynamic monitoring resource update procedure in accordance with some example embodiments of the present disclosure;

[0018] FIG. 3 illustrates another example signaling flow for a unified configuration reporting procedure in accordance with some other example embodiments of the present disclosure;

[0019] FIG. 4 illustrates another example signaling flow another dynamic monitoring resource update procedure and unified configuration reporting procedure accordance with some other example embodiments of the present disclosure;

[0020] FIG. 5 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0021] FIG. 6 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0022] FIG. 7 illustrates a flowchart of a method implemented at a third apparatus in accordance with some example embodiments of the present disclosure;

[0023] FIG. 8 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0024] FIG. 9 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0025] FIG. 10 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0026] FIG. 11 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0027] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION

[0028] 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.

[0029] 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.

[0030] 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 not explicitly described.

[0031] 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.

[0032] 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 theelements, or at least all the elements.

[0033] 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.

[0034] 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.

[0035] As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and(b) combinations of hardware circuits and software, such as (as applicable):(i) a combination of analog and / or digital hardware circuit(s) with software / firmware and(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(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.

[0036] 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 an implementation 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.

[0037] 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 secondgeneration (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.

[0038] 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 a mobile 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.

[0039] 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, smartdevices, 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.

[0040] 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.

[0041] 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, to evaluate 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.

[0042] 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.

[0043] 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 theprocess / 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.

[0044] 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.

[0045] 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.

[0046] The term “reinforcement learning (RL)” refers to a process of training the AI / ML model from the 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.

[0047] The term “beam” as used herein is synonymous with “spatial filter” or “spatial-domain filter”, as used in 3GPP standards.

[0048] 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 aUE. 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.

[0049] In addition, the communication environment 100 may comprise a third apparatus 130 which may operate as a user device such as a UE or a network device such as a gNB or a core network device. In some example embodiments, the third apparatus 130 may include a machine learning (ML) engine to provide training and inference of a machine learning model.

[0050] 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. For example, in some example embodiments, there may be no third apparatus 130 in the communication environment 100, Instead, an ML engine may be deployed the first apparatus 110 or the second apparatus 120.

[0051] 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.

[0052] 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 resource management related functionality. The resource management may involve management for any resource such as beam, a cell and some other time, frequency and / or special resources. For the purpose of discussion, some example embodiments will be described by taking beam management as an example of the resource management. Training, 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.

[0053] 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.

[0054] 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 resultsfrom a set of beams (referred to as Set B) to predict an optimal set of beams (referred to as 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.

[0055] 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.

[0056] Performance monitoring for beam prediction functionality, for example, on the UE side, may be implemented using different options. For BM-Case1 and BM-Case2 where an AI / ML model operates on the UE side, there are two types of performance monitoring, including Type 1 performance monitoring and Type 2 performance monitoring. Type 1 performance monitoring includes both NW-side performance monitoring (referred to as Option 1) and UE-assisted performance monitoring (referred to as Option 2). On the other hand, Type 2 performance monitoring considers UE-side performance monitoring.

[0057] Regarding Type 1 performance monitoring, in Option 1 (referred to as NW-side performance monitoring), the UE may transmit a report to the network, allowing the network to calculate the performance metrics. The report may include measurement results from the resource set used for monitoring, such as layer 1 (L1 preference signal receiving power (RSRP) and / or a reference signal (RS) index. Further study may be required to determine additional content for the report. The reporting process may be configured or triggered by the network, and this approach may or may not introduce additional specification impacts. In Option 2 (referred to as UE-assisted performance monitoring), the UE may perform calculations to determine performance metrics. Further study may be required to define the reporting format and content. Additionally, whether the report is triggered based on specific events, either in Option 1 or Option 2, may also require further analysis.

[0058] Different approaches may be considered to support performance monitoring in beam prediction. One approach involves Type 1 performance monitoring, which includes network-side and UE-assisted monitoring. However, certain challenges arise, particularly in high-mobility scenarios. For example, configuration updates may be relied on radio resource control (RRC) reconfiguration. Such reliance on an RRC reconfiguration for updates may introduce latency, compromising the accuracy ofmonitoring data and potentially degrading network performance. Additionally, CSI reports for both AI / ML inference and performance monitoring may be configured separately. Such dual configuration of CSI reports for both AI / ML inference and performance monitoring may increase complexity, leading to potential misalignment between the two functions and reducing operational efficiency. A more unified approach may be needed to ensure seamless coordination between monitoring and inference processes.

[0059] To address these challenges, different options may be explored for configuring monitoring resource sets that are used for the performance monitoring. One approach allows for the configuration of a subset of Set A via RRC as a monitoring resource set, ensuring initial alignment with network settings. Another approach enables the configuration of Set A within a CSI-ReportConfig filed in an RRC reconfiguration, where a subset of Set is indicated as the monitoring set dynamically using a medium access control control element (MAC CE). This latter approach may allow for quicker updates, which is particularly beneficial in dynamic environments where real-time adjustments are required. However, while these approaches help reduce latency to some extent, the continued reliance on RRC for initial configuration may still introduce delays, making it less suitable for scenarios requiring rapid adaptation. Moreover, managing subsets within the broader Set A may lead to additional operational inefficiencies, particularly if the configurations are not well-aligned with varying UE capabilities and mobility conditions.

[0060] Another approach aims to provide greater flexibility by allowing report configurations to be adapted based on specific UE requirements. This may enable network operators to optimize performance monitoring based on their deployment scenarios. While such flexibility is beneficial, it may also increase complexity in managing multiple configurations, potentially resulting in inconsistencies between performance monitoring and AI / ML inference needs. The lack of a standardized mechanism to determine when to use unified versus separate configurations may further complicate decision-making, potentially impacting resource utilization and system efficiency.

[0061] While existing signaling and configuration mechanisms define the general principles of RRC and CSI reporting, they do not fully address the challenges posed by high-mobility UEs, particularly the latency associated with monitoring updates. Current approaches largely depend on RRC reconfiguration, which may be slow and resource-intensive, making it difficult to maintain real-time performance monitoring in dynamic network conditions. Additionally, the dual configuration of CSI reports creates additional challenges in aligning inference and monitoring requirements, leading to inefficiencies in network operation.

[0062] A more effective solution may involve reducing dependency on RRC reconfiguration by adopting dynamic and responsive mechanisms that can adapt to real-time network conditions. Furthermore, clearer guidelines for configuration management may help seamlessly integrateperformance monitoring and AI / ML inference requirements, enhancing both operational efficiency and resource utilization. Addressing these limitations may ensure optimal network performance, particularly in high-mobility scenarios, where rapid adjustments and accurate monitoring are critical.

[0063] The current configuration of the monitoring resource set for Type 1 performance monitoring Option 2 within the current communication system may face challenges as described above, particularly under conditions of high-speed UE movement. The reliance on RRC reconfiguration for timely updates may introduce latency, which may lead to outdated monitoring information and ultimately degrade network performance. Furthermore, the decision-making process regarding the use of a unified CSI report configuration for both AI / ML inference and performance monitoring versus separate configurations may complicate management and operational efficiency. This duality may not only increase the complexity of configuration management but may also risk misalignment between performance monitoring and inference requirements, potentially resulting in suboptimal resource utilization and performance metrics. To address these issues, it may be needed to develop a streamlined approach that minimizes latency in monitoring resource updates while providing clear guidelines for configuration management that can adapt to varying UE scenarios, ensuring that performance monitoring remains accurate and responsive to real-time network conditions.

[0064] To overcome the abovementioned challenges associated with Type 1 performance monitoring Option 2, in accordance with some example embodiments, there is provided a solution of dynamically monitoring resource set for resource management.

[0065] In some example embodiments, the second apparatus (such as a base station) may send a monitoring configuration to the first apparatus (such as a UE), specifying a monitoring resource set used for performance monitoring of a first machine learning model responsible for resource management. The second apparatus may also send a monitoring configuration update message to the first apparatus, indicating changes to at least one parameter within the configuration. A third apparatus, which may be the first apparatus, the second apparatus, or another separate device, may use a second machine learning model to predict an optimal monitoring configuration for performance monitoring of the first machine learning model. Based on this prediction, the third apparatus may generate a recommendation to adjust the monitoring configuration to improve its effectiveness.

[0066] This solution may enable clear communication between the first apparatus and the second apparatus regarding the current state of a monitoring resource set for performance monitoring, ensuring configuration alignment and reducing configuration duplication.

[0067] Reference is now made to FIG. 2, which illustrates an example signaling flow 200 of a dynamic monitoring resource configuration process according to some example embodiments. The signaling flow involves the first apparatus 110 which may be a UE, the second apparatus 120 which may be a gNB, and a third apparatus 130 which may be a UE (i.e., the first apparatus 110), a gNB(i.e., the second apparatus 120), another device such as another gNB or a core network code.

[0068] As illustrated in FIG. 2, the second apparatus 120 transmits (202) to the first apparatus 110, a monitoring configuration related to a monitoring resource set. The monitoring resource set is used for performance monitoring of a first machine learning model for resource management. Correspondingly, the first apparatus 110 receives (204) from the second apparatus 120, the monitoring configuration related to the monitoring resource set.

[0069] In some examples, the first apparatus 110 may begin operation with a baseline measurement and reporting configuration, which may be received via a standard RRC reconfiguration during an initialization procedure or connection setup. A default configuration may include conventional parameters such as measurement objects, event triggers (e.g., A1, A2, A3), and reporting intervals, enabling the first apparatus 110 to perform initial measurement and reporting functions.

[0070] The second apparatus 120 transmits (214), to the first apparatus 110, a monitoring configuration update message, also referred to as a monitoring resource configuration update (MRCU) message indicating an update to at least one configuration parameter in the monitoring configuration. Correspondingly, the first apparatus 110 receives (216) the monitoring configuration update message from the second apparatus.

[0071] In some example embodiments, the at least one configuration parameter may comprise a measurement interval of CSI measurements for the performance monitoring. In some examples, the measurement interval may be indicated by a sample rate representing frequency of data collection. Alternatively, or in addition, the at least one configuration parameter may comprise a measurement type of the CSI measurements such as a type of data being monitored, for example, including a reference signal strength indicator (RSSI), an RSRP, and a signal-to-interference-plus-noise ratio (SINR).

[0072] In some example embodiments, the at least one configuration parameter may comprise a reporting interval of CSI reporting for the performance monitoring, which may indicate frequency of data reporting to the network. Alternatively, or in addition, the at least one configuration parameter may comprise a condition for triggering the CSI reporting. In an example, this condition may comprise a reporting trigger indicating an event that triggers data reporting. For example, the data reporting may be triggered periodically, or triggered when a threshold is crossing. In another example, the condition for triggering the CSI reporting may comprise one or more thresholds that are trigger values for reporting events. For example, the thresholds may comprise a certain RSSI threshold. In this example, if the measured RSSI exceeds the RSSI threshold, the CSI reporting may be triggered.

[0073] In some example embodiments, the monitoring configuration update message may contain an identifier (ID) of an updated monitoring resource in the monitoring resource set, such as amonitoring resource ID that is an identifier of the monitoring resource being updated.

[0074] In some example embodiments, the monitoring configuration update message may further contain an indication whether a unified measurement report or two separate measurement reports are enabled for both the performance monitoring and inference of the first machine learning model. By using such an indication, as will be detailed in the following paragraphs with reference to FIG. 3, a standardized approach may be used for configuring CSI reports, which integrates both AI / ML inference and performance monitoring requirements.

[0075] In some examples, the second apparatus 120 may transmit the monitoring configuration update message to the first apparatus 110 via a lightweight control signaling channel. The monitoring configuration update signaling mechanism may be a more lightweight signaling mechanism and it may allow quick parameter changes without a full overhead of, for example, a RRC reconfiguration. This lightweighted signaling mechanism may be suitable for scenarios which may require frequent parameter updates, for example in high mobility scenarios of UEs. This dynamic monitoring update mechanism may enable real-time updates to the first apparatus 110 without solely relying on a full RRC reconfiguration for configuration changes, thereby reducing latency and signaling overhead compared to a full RRC reconfiguration.

[0076] In some example embodiments, the at least one of the identifier of the updated monitoring resource in the monitoring resource set , the indication whether a unified measurement report or two separate measurement reports are enabled for both the performance monitoring and inference of the first machine learning model, or the at least one configuration parameter may be carried in a payload of the monitoring configuration update message.

[0077] In some example embodiments, the header of the monitoring configuration update message contains at least one of: an identifier of the monitoring configuration update message, an identifier of the first apparatus 110, or a timestamp of the monitoring configuration update message. In some examples, a message ID may be used as an identifier of the monitoring configuration update message and it may serve as a unique identifier for the message. In the example embodiments where the first apparatus 110 operates as a UE, the UE ID may represent the identifier of the first apparatus 110 that receives the update. The timestamp may indicate any time related to the monitoring configuration update message. For example, include the time at which the message was generated or the time at which the message was transmitted.

[0078] In some example embodiments, the monitoring configuration update message may contain at least one of: a reporting destination of CSI reporting for the performance monitoring, or a format of reported data for the CSI reporting. In some examples, the reporting destination and data format may be comprised as optional parameters. The reporting destination may specify the network entity designated to receive the reported data. The data format may specify the structure of the reporteddata, which may include raw measurement values, or aggregated statistics, depending on reporting requirements. These option parameters may be contained in the header or payload of the monitoring configuration update message.

[0079] By way of example, an example MRCU message may be constructed as below:Message Type: MRCUHeader:• Message ID: Unique identifier for the message.• UE ID: Identifier of the UE receiving the update.• Timestamp: Time of message generation.Payload:• Monitoring Resource ID: Identifier of the monitoring resource being updated.• Configuration Parameters:Sampling Rate: Frequency of data collection.Reporting Interval: Frequency of data reporting to the network.Measurement Type: Type of data being monitored (e.g., RSSI, RSRP, SINR).Thresholds: Trigger values for reporting events (e.g., exceeding a certain RSSI threshold).Reporting Trigger: Event that triggers data reporting (e.g., periodic, threshold crossing).• Optional Parameters:Reporting Destination: Specific network entity to receive the data.Data Format: Format of the reported data (e.g., raw values, aggregated statistics).

[0080] The second apparatus 120 may determine the monitoring configuration update message in any proper way. The second apparatus 120 may then transmit the determined monitoring configuration update message to the first apparatus 110 and the first apparatus 110 may then subsequently apply the updated configuration parameters specified in the received message.

[0081] In some example embodiments, the first apparatus 110 may update the at least one configuration parameter based on the monitoring configuration update message. In some examples, the first apparatus 110 may apply the newly received parameters, adjusting measurement intervals, threshold values, or the selection between unified and separate reporting procedures.

[0082] In some example embodiments, the first apparatus 110 may perform measurements and reporting for the monitoring resource set, based on the updated at least one configuration parameter. In some examples, when the updated event conditions are met, such as the RSSI falling below -90 dBm, the first apparatus 110 may generate and transmit a report to the second apparatus 120.

[0083] In some example embodiments, the second apparatus 120 may determine the monitoring configuration update message based on, for example, a first recommendation for an adjustment of the monitoring configuration received (212) from the third apparatus 130. For example, as shown in FIG.2, the third apparatus 130 determines (206) a prediction of a monitoring configuration related to performance monitoring of the first machine learning model, by using a second machine learning model. The first machine learning model may be used for resource management (i.e., beammanagement) associated with the first apparatus 110. In some example embodiments, the first apparatus 110 and the third apparatus 130 may be the same apparatus. The integration of AI / ML models and machine learning algorisms may allow adaptive resource allocation. The second machine learning model (e.g., another AI / ML model) may analyze real-time data to predict optical monitoring configuration based on the behavior of the first apparatus 110 and the environment conditions of the first apparatus 110. This AI / ML driven approach may enable proactive adjustments to monitor resources in real-time, allowing for dynamic optimization without requiring manual intervention, thereby optimizing resource allocation.

[0084] In some example embodiments, the prediction conducted by the third apparatus 130 may be determined based on real-time data related to at least one of a behavior of the first apparatus 110 or an environment surrounding the first apparatus 110. In some examples, the second machine learning model employed by the third apparatus 130 may employ machine learning algorisms to analyze real-time data, enabling the prediction of optimal monitoring configurations based on the behavior of the first apparatus 110 and environmental conditions. This approach may allow for proactive adjustments to monitoring configurations without requiring manual intervention, thereby improving efficiency in dynamic network conditions.

[0085] In some example embodiments, the third apparatus 130 may obtain real-time and historical data related to at least one of a behavior of the first apparatus 110 or an environment surrounding the first apparatus 110 and may build the second machine learning model using the obtained real-time and historical data. In some examples, the third apparatus 130 may continuously gather real-time data, such as a RSRP, a SINR, and mobility status of the first apparatus 110. The third apparatus 130 may utilize the gathered real-time data and historical logs to build the predictive model.

[0086] Based on the analysis, the third apparatus 130 may determine when the first apparatus 110 requires an updated monitoring strategy, such as an adjustment of the reporting frequency during high-speed movement to maintain accurate performance monitoring. In some examples, upon determining that the current monitoring configuration of the first apparatus 110 is suboptimal, the third apparatus 130 may determine a recommendation proposing specific updates. In case an update is needed, the third apparatus 130 determines (208) the first recommendation for an adjustment of the monitoring configuration, based on the prediction.

[0087] In some example embodiments, the third apparatus 130 may send (210) the first recommendation to the second apparatus 120. In some example embodiments, the first recommendation may indicate an adjustment of the at least one configuration parameter. Correspondingly, the second apparatus 120 may receive (212) the first recommendation from the third apparatus 130. In some example, in the case that the second machine learning model or the ML engine is deployed in the second apparatus 120, the second apparatus 120 may determine the firstrecommendation by itselfl 30.

[0088] The second apparatus 120 may assess the recommendation received (212) from the third apparatus 130, considering factors such as a current cell load, capabilities of the first apparatus 110, and existing measurement configurations. Based on this assessment, the second apparatus 120 may construct the monitoring configuration update message, specifying updated parameters, including thresholds, triggers, and other relevant configuration details as well as a monitoring resource ID. In some examples, if the first recommendation includes a unified CSI configuration for both AI / ML inference and performance monitoring, this configuration may be explicitly indicated within the payload of the monitoring configuration update message.

[0089] In some example embodiments, the second apparatus 120 may send the at least one of the measurement data or the performance metric to the third apparatus 130. And correspondingly, the third apparatus 130 may receive the at least one of the measurement data or the performance metric. In some examples, the second apparatus 120 may receive and process the measurement reports from the first apparatus 110. To facilitate continuous improvement, the second apparatus 120 may share the updated measurements and relevant performance metrics with the third apparatus 130. In some examples, the third apparatus 130 may refine its AI / ML model or initiate further analyses, ensuring that future monitoring configuration updates (e.g., by using a further MRCU messages) become more precise and predictive overtime.

[0090] In some example embodiments, the third apparatus 130 may determine a second recommendation for the adjustment of the monitoring configuration, by using the refined second machine learning model. In some examples, if the third apparatus 130 detects further changes, such as the first apparatus 110 transitioning from vehicular to stationary mode or variations in channel conditions, it may generate additional recommendations and transmit them to the second apparatus 120. AI / ML model refinement may ensure that monitoring configuration remains adaptive to changing network conditions, ensuring the accuracy of performance monitoring and AI / ML-based predictions.

[0091] Accordingly, the second apparatus 120 may obtain the second recommendation for the adjustment of the monitoring configuration. The second recommendation is generated by using the second machine learning model based on at least one of measurement data of the first apparatus with respect to the performance monitoring, or a performance metric of the first machine learning model, and the at least one of the measurement data or the performance metric is responsive to the update to the at least one configuration parameter. Depending on whether the ML engine is deployed at the third apparatus 130 or the second apparatus 120, the second recommendation may be generated by the third apparatus 130 or the second apparatus 120.

[0092] In some examples, based on the second recommendation, the second apparatus 120 may issue an updated monitoring configuration update message, to adjust thresholds and reporting triggers,or to switch between unified and separate monitoring configurations. The first apparatus 110 subsequently may apply the latest parameter accordingly. This process may continue iteratively, ensuring that the monitoring parameters of the first apparatus 110 remain aligned with real-time network conditions and operational objectives.

[0093] This AI / ML driven closed-loop adaptation mechanism may enable a predictive approach rather than a reactive one, allowing the third apparatus 130 to anticipate potential performance degradation or coverage issues, prompting timely monitoring configuration adjustments. The AI / ML model may undergo continuous refinement by incorporating newly reported data from the first apparatus 110.

[0094] To optimize monitoring and resource management, it may be beneficial to establish a structured approach that ensures seamless integrity of AI / ML inference and performance monitoring. Given the dynamic nature of UE mobility patterns and network conditions, determining whether to apply a unified or separate configuration for CSI report may enhance efficiency. A streamlined and unified configuration framework may simply the decision making process by providing clear guidance.

[0095] In some example embodiments, the first apparatus 110 may receive, from a second apparatus 120, an indication specifying whether a single CSI reporting procedure or two separate CSI reporting procedures are enabled for both performance monitoring and inference of a machine learning model used for resource management. Based on the received indication, the first apparatus 110 may perform either the single CSI reporting procedure or the two separate CSI reporting procedures for both performance monitoring and inference. The first apparatus 110 may then transmit to the second apparatus 120 either a single CSI measurement report or two separate CSI measurement reports, depending on the indication of whether a unified or separate CSI reporting procedure is enabled.

[0096] Reference is now made to FIG. 3, which illustrates an example signaling flow 300 of a CSI reporting procedure according to some example embodiments. The signaling flow involves the first apparatus 110 and the second apparatus 120.

[0097] As illustrated in FIG. 3, the second apparatus 120 transmits (302) to the first apparatus 110 an indication whether a single CSI reporting procedure or two separate CSI reporting procedures are enabled for both performance monitoring and inference of a machine learning model for resource management. Correspondingly, the first apparatus 110 receives (304) this indication from the second apparatus 120.

[0098] The second apparatus 120 may determine whether the single CSI reporting procedure or the two separate CSI reporting procedures are enabled in any proper way. In some example embodiments, the second apparatus 120 may further determine whether the single CSI reporting procedure or the two separate CSI reporting procedures are enabled, based on a recommendation for an adjustment of the monitoring configuration, wherein the recommendation is generated by using asecond machine learning model.

[0099] The recommendation may be generated in any proper way. In some example embodiments, the second apparatus 120 may receive the recommendation from a third apparatus which may be a separate apparatus different from the second apparatus 120.

[0100] In some example embodiments, the second apparatus 120 may determine the indication based on at least one of: network conditions, a CSI reporting capability of the first apparatus 110, or a mobility pattern of the first apparatus 110. In some examples, a single CSI reporting approach may be selected to support both performance monitoring and AI / ML inference, or alternatively, separate CSI repotting configurations may be applied if necessary. The selection between a unified configuration or separate configurations may be determined dynamically based on network conditions, UE mobility patterns and UE capability in CSI reporting.

[0101] In some example embodiments, the indication may be received by the first apparatus 110 via a monitoring configuration update message from the second apparatus 120, the monitoring configuration update message indicating an update to at least one configuration parameter in a monitoring configuration related to the performance monitoring. In some example embodiments, the indication may be carried in a payload of the monitoring configuration update message. In some examples, if the recommendation determined by the Al / ML model proposes a unified CSI configuration for both AI / ML inference and performance monitoring, it may be explicitly indicated in the MRCU payload.

[0102] In some example embodiments, the at least one configuration parameter comprises at least one of: a measurement interval of CSI measurements for the performance monitoring, a measurement type of the CSI measurements, a reporting interval of CSI reporting for the performance monitoring, or a condition for triggering the CSI reporting. In some example embodiments, the monitoring configuration update message may contain at least one of: a reporting destination of CSI reporting for the performance monitoring, or a format of reported data for the CSI reporting.

[0103] After receiving (304) the indication, the first apparatus 110 performs (306) the single CSI reporting procedure or the two separate CSI reporting procedures for both the performance monitoring and the inference, based on the received indication. In some example embodiments, the first apparatus 110 may perform the single CSI reporting procedure for both the performance monitoring and the inference using the at least one configuration parameter, based on the indication indicating that the single CSI reporting procedure is enabled for both the performance monitoring and the inference.

[0104] Accordingly, the first apparatus 110 transmits (308) to the second apparatus 120 a single CSI measurement report or two separate CSI measurement reports for both the performance monitoring and the inference. The single CSI measurement report or the two separate CSImeasurement reports are based on the indication whether the single CSI reporting procedure or the two separate CSI reporting procedures are enabled. And correspondingly, the second apparatus 120 receives (310) from the first apparatus 110 a single CSI measurement report or two separate CSI measurement reports for both the performance monitoring and the inference.

[0105] It is to be understood that the features and operations related to the first apparatus 110, the second apparatus 120 and the third apparatus 130 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] This adaptive unified or separate CSI reporting configuration mechanism may allow for a flexible CSI reporting approach, where a single CSI reporting procedure may be used for both performance monitoring and AI / ML inference tasks, or sperate configurations may be applied if necessary. This selection may be determined dynamically based on real-time network conditions and UE capabilities. By adapting the configuration accordingly, this may simplify the monitoring procedures or provide customized reporting to optimize performance based on real-time operational requirements.

[0107] An example process for configuring a monitoring resource for resource management will be discussed below with reference to FIG. 4 which illustrates an example signaling flow 400 of an example dynamic monitoring resource configuration process according to some example embodiments. In this example, a UE 401 is an example of the first apparatus 110 and a gNB 502 may be an example of the second apparatus 120. The ML engine 403 may be deployed at the third apparatus 130.

[0108] As shown in FIG. 4, the process may begin with initialization and default configuration, where the UE 401 may start with a predefined monitoring setup, for example, received through an RRC reconfiguration at step 405.

[0109] At step 410, the ML engine 403 may collect and analyze historical and real-time data, such as network conditions and prior measurement reports. Based on this analysis, at step 415, the ML engine 403 may generate a recommendation (e.g., the first recommendation) for an MRCU message, which may include adjustments to the configuration parameters such as sampling rates and reporting intervals, or a recommended CSI reporting procedure between a single CSI reporting procedure and two separate CSI reporting procedures. The gNB 402 may evaluate these recommendations and determine an appropriate configuration update at step 420.

[0110] Following this, at step 425, the gNB 402 may construct an MRCU message, specifying updated monitoring resource IDs, new thresholds, triggers, intervals, and whether a single CSI reporting procedure or two separate CSI reporting procedures is applied. The MRCU message may then be transmitted to the UE 401 at step 430, ensuring minimal signaling overhead compared to a full RRC reconfiguration. Upon reception, at step 435, the UE 401 may parse and apply the parameters received in the MRCU message.

[0111] During updated monitoring, at step 440, the UE 401 may trigger a report if certain event conditions, such as RSSI falling below -90 dBm, are met. At step 445, the gNB 402 may receive the updated reports and assess network performance.

[0112] A feedback loop and AI / ML model refinement may occur at step 450, where the updated measurement data is forwarded to the ML engine 403 for further optimization. Based on this data, at step 455, the ML engine 403 may refine its model and, if conditions change, generate a recommendation for the next adjustment at step 460.

[0113] If further modifications are necessary, the process may proceed to subsequent MRCU updates at step 465, where the gNB 402 may send a new MRCU message, updating thresholds or switching between a single CSI reporting configuration and two separate CSI reporting configurations. The UE 401 may apply the latest parameters at step 470, ensuring continued adaptation to network conditions.

[0114] This iterative process may continue, ensuring that the monitoring configuration remains optimized based on real-time network conditions and historical data analysis.

[0115] The proposed solution introduces a hybrid approach that integrates real-time monitoring resource updates with a dynamic configuration management framework. In addition, this solution incorporates a lightweight signaling mechanism to facilitate rapid updates to monitoring resource sets based on rea-time network conditions. The proposed solution is designed to be compatible with existing specification, ensuring that the proposed solution can be implemented without significate changes to the current architecture.

[0116] FIG. 5 shows a flowchart of an example method 500 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 500 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0117] At block 510, the first apparatus 110 receives, from a second apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management.

[0118] At block 520, the first apparatus 110 receives, from the second apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

[0119] In some example embodiments, the at least one configuration parameter may comprise at least one of: a measurement interval of channel state information (CSI) measurements for the performance monitoring, a measurement type of the CSI measurements, a reporting interval of CSI reporting for the performance monitoring, or a condition for triggering the CSI reporting.

[0120] In some example embodiments, the monitoring configuration update message may contain an identifier of an updated monitoring resource in the monitoring resource set.

[0121] In some example embodiments, the monitoring configuration update message may further contain an indication whether a unified measurement report or two separate measurement reports are enabled for both the performance monitoring and inference of the first machine learning model.

[0122] In some example embodiments, at least one of the identifier, the indication, or the at least one configuration parameter may be carried in a payload of the monitoring configuration update message.

[0123] In some example embodiments, a header of the monitoring configuration update message may contain at least one of: an identifier of the monitoring configuration update message, an identifier of the first apparatus, or a timestamp of the monitoring configuration update message.

[0124] In some example embodiments, the monitoring configuration update message may contain at least one of: a reporting destination of channel state information (CSI) reporting for the performance monitoring, or a format of reported data for the CSI reporting.

[0125] In some example embodiments, the method 500 further comprises: the first apparatus 110 may update the at least one configuration parameter based on the monitoring configuration update message; and performing measurements and reporting for the monitoring resource set, based on the updated at least one configuration parameter.

[0126] In some example embodiments, a first apparatus capable of performing any of the method 500 (for example, the first apparatus 110 in FIG. 1 ) may comprise means for performing the respective operations of the method 500. 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.

[0127] FIG. 6 shows a flowchart of an example method 600 implemented at a second 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 second apparatus 120 in FIG. 1.

[0128] At block 610, the second apparatus 120 transmits, to a first apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management.

[0129] At block 620, the second apparatus 120 transmits, to the first apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

[0130] In some example embodiments, the at least one configuration parameter may comprise at least one of: a measurement interval of channel state information (CSI) measurements for the performance monitoring, a measurement type of the CSI measurements, a reporting interval of CSI reporting for the performance monitoring, or a condition for triggering the CSI reporting.

[0131] In some example embodiments, the monitoring configuration update message may containan identifier of an updated monitoring resource in the monitoring resource set.

[0132] In some example embodiments, the monitoring configuration update message may further contain an indication whether a single channel state information (CSI) reporting procedure or two separate CSI reporting procedures are enabled for both the performance monitoring and inference of the first machine learning model.

[0133] In some example embodiments, at least one of the identifier, the indication, or the at least one configuration parameter may be carried in a payload of the monitoring configuration update message.

[0134] In some example embodiments, a header of the monitoring configuration update message may contain at least one of: an identifier of the monitoring configuration update message, an identifier of the first apparatus, or a timestamp of the monitoring configuration update message.

[0135] In some example embodiments, the monitoring configuration update message may contain at least one of: a reporting destination of channel state information (CSI) reporting for the performance monitoring, or a format of reported data for the CSI reporting.

[0136] In some example embodiments, the method 600 further comprises: the second apparatus 120 may obtain a first recommendation for an adjustment of the monitoring configuration, wherein the recommendation is generated by using a second machine learning model; and determining the update to the at least one configuration parameter, based on the first recommendation.

[0137] In some example embodiments, the second apparatus caused to obtain the recommendation may be caused to: receiving the first recommendation from a third apparatus.

[0138] In some example embodiments, the first recommendation may indicate an adjustment of the at least one configuration parameter.

[0139] In some example embodiments, the first recommendation may indicate whether a single channel state information (CSI) reporting procedure or two separate CSI reporting procedures are enabled for both the performance monitoring and inference of the first machine learning model.

[0140] In some example embodiments, the third apparatus may be further caused to: obtaining a second recommendation for the adjustment of the monitoring configuration, wherein the second recommendation is generated by using a second machine learning model based on at least one of measurement data of the first apparatus with respect to the performance monitoring, or a performance metric of the first machine learning model, and the at least one of the measurement data or the performance metric is responsive to the update to the at least one configuration parameter.

[0141] In some example embodiments, the third apparatus caused to obtain the second recommendation may be caused to: sending the at least one of the measurement data or the performance metric to a third apparatus; and receiving the second recommendation from the third apparatus, wherein the second recommendation is generated by the third apparatus using the secondmachine learning model based on the at least one of the measurement data or the performance metric.

[0142] In some example embodiments, a second apparatus capable of performing any of the method 600 (for example, the second apparatus 120 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 second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0143] FIG. 7 shows a flowchart of an example method 700 implemented at a third 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 third apparatus 130 in FIG. 2.

[0144] At block 710, the third apparatus 130 determines a prediction of a monitoring configuration related to performance monitoring of a first machine learning model, by using a second machine learning model, wherein the first machine learning model is used for resource management associated with a first apparatus.

[0145] At block 720, the third apparatus 130 determines a first recommendation for an adjustment of the monitoring configuration, based on the prediction.

[0146] In some example embodiments, the method 700 further comprises: the third apparatus 130 may send the first recommendation to a second apparatus.

[0147] In some example embodiments, the prediction may be determined based on real-time data related to at least one of a behavior of the first apparatus or an environment surrounding the first apparatus.

[0148] In some example embodiments, the method 700 further comprises: the third apparatus 130 may obtain real-time and historical data related to at least one of a behavior of the first apparatus or an environment surrounding the first apparatus; and the third apparatus 130 may build the second machine learning model using the obtained real-time and historical data.

[0149] In some example embodiments, the method 700 further comprises: the third apparatus 130 may obtain at least one of measurement data of the first apparatus with respect to the performance monitoring, or a performance metric of the first machine learning model, wherein the at least one of the measurement data or the performance metric may be responsive to the update of the monitoring configuration; and the third apparatus 130 may refine the second machine learning model using the at least one of the measurement data or the performance metric.

[0150] In some example embodiments, the third apparatus caused to obtain the at least one of the measurement data or the performance metric may be caused to: receiving the at least one of the measurement data or the performance metric from a second apparatus.

[0151] In some example embodiments, the method 700 further comprises: the third apparatus 130 may determine a second recommendation for the adjustment of the monitoring configuration, by usingthe refined second machine learning model.

[0152] In some example embodiments, the method 700 further comprises: the third apparatus 130 may send the second recommendation to a second apparatus.

[0153] In some example embodiments, the first recommendation may indicate an adjustment to at least one configuration parameter in the monitoring configuration, the at least one configuration parameter comprising at least one of: a measurement interval of channel state information (CSI) measurements for the performance monitoring, a measurement type of the CSI measurements, a reporting interval of CSI reporting for the performance monitoring, or a condition for triggering the CSI reporting.

[0154] In some example embodiments, the first recommendation may indicate whether a single channel state information (CSI) reporting procedure or two separate CSI reporting procedures are enabled for both performance monitoring and inference of the first machine learning model.

[0155] In some example embodiments, a third apparatus capable of performing any of the method 700 (for example, the third apparatus 130 in FIG. 2) 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 third apparatus may be implemented as or included in the third apparatus 130 in FIG. 2.

[0156] 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.

[0157] At block 810, the first apparatus 110 receives, from a second apparatus, an indication whether a single channel state information (CSI) reporting procedure or two separate CSI reporting procedures are enabled for both performance monitoring and inference of a machine learning model for resource management.

[0158] At block 820, the first apparatus 110 performs the single CSI reporting procedure or the two separate CSI reporting procedures for both the performance monitoring and the inference, based on the received indication.

[0159] In some example embodiments, the indication may be received via a monitoring configuration update message from the second apparatus, the monitoring configuration update message indicating an update to at least one configuration parameter in a monitoring configuration related to the performance monitoring.

[0160] In some example embodiments, the indication may be carried in a payload of the monitoring configuration update message.

[0161] In some example embodiments, the at least one configuration parameter may comprise at least one of: a measurement interval of CSI measurements for the performance monitoring, ameasurement type of the CSI measurements, a reporting interval of CSI reporting for the performance monitoring, or a condition for triggering the CSI reporting.

[0162] In some example embodiments, the monitoring configuration update message may contain at least one of: a reporting destination of CSI reporting for the performance monitoring, or a format of reported data for the CSI reporting.

[0163] In some example embodiments, the first apparatus caused to perform the single CSI reporting procedure or the two separate CSI reporting procedures may be caused to: performing the single CSI reporting procedure for both the performance monitoring and the inference using the at least one configuration parameter, based on the indication indicating that the single CSI reporting procedure is enabled for both the performance monitoring and the inference.

[0164] In some example embodiments, the indication may be related to at least one of: network conditions, a CSI reporting capability of the first apparatus, or a mobility pattern of the first apparatus.

[0165] 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.

[0166] 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.

[0167] At block 910, the second apparatus 120 transmits, to a first apparatus, an indication whether a single channel state information (CSI) reporting procedure or two separate CSI reporting procedures are enabled for both performance monitoring and inference of a machine learning model for resource management.

[0168] At block 920, the second apparatus 120 receives, from the first apparatus, a single CSI measurement report or two separate CSI measurement reports for both the performance monitoring and the inference, the single CSI measurement report or the two separate CSI measurement reports being based on the indication whether the single CSI reporting procedure or the two separate CSI reporting procedures are enabled.

[0169] In some example embodiments, the indication may be transmitted via a monitoring configuration update message, the monitoring configuration update message indicating an update to at least one configuration parameter in a monitoring configuration related to the performance monitoring.

[0170] In some example embodiments, the indication may be carried in a payload of the monitoring configuration update message.

[0171] In some example embodiments, the at least one configuration parameter may comprise at least one of: a measurement interval of CSI measurements for the performance monitoring, a measurement type of the CSI measurements, a reporting interval of CSI reporting for the performance monitoring, or a condition for triggering the CSI reporting.

[0172] In some example embodiments, the monitoring configuration update message may contain at least one of: a reporting destination of CSI reporting for the performance monitoring, or a format of reported data for the CSI reporting.

[0173] In some example embodiments, the method 900 further comprises: the second apparatus 120 may determine whether the single CSI reporting procedure or the two separate CSI reporting procedures are enabled for both the performance monitoring and the inference, based on at least one of: networking conditions, a CSI reporting capability of the first apparatus, or a mobility pattern of the first apparatus.

[0174] In some example embodiments, the second apparatus is caused to determine whether the single CSI reporting procedure or the two separate CSI reporting procedures are enabled may be caused to: determining whether the single CSI reporting procedure or the two separate CSI reporting procedures are enabled, further based on a recommendation for an adjustment of the monitoring configuration, wherein the recommendation is generated by using a second machine learning model.

[0175] In some example embodiments, the method 900 further comprises: the second apparatus 120 may receive the recommendation from a third apparatus.

[0176] In some example embodiments, a second apparatus capable of performing any of the method 900 (for example, the second apparatus 110 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.

[0177] FIG. 10 is a simplified block diagram of a device 1000 that is suitable for implementing example embodiments of the present disclosure. The device 1000 may be provided to implement a communication device, for example, the first apparatus 110, or the second apparatus 120, or the third apparatus 130 as shown in FIG. 1. As shown, the device 1000 includes one or more processors 1010, one or more memories 1020 coupled to the processor 1010, and one or more communication modules 1040 coupled to the processor 1010.

[0178] The communication module 1040 is for bidirectional communications. The communication module 1040 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 1040 may include at least one antenna.

[0179] The processor 1010 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 1000 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.

[0180] The memory 1020 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) 1024, 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, a random-access memory (RAM) 1022 and other volatile memories that will not last in the power-down duration.

[0181] A computer program 1030 includes computer executable instructions that are executed by the associated processor 1010. The instructions of the program 1030 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 1030 may be stored in the memory, e.g., the ROM 1024. The processor 1010 may perform any suitable actions and processing by loading the program 1030 into the RAM 1022.

[0182] The example embodiments of the present disclosure may be implemented by means of the program 1030 so that the device 1000 may perform any process of the disclosure as discussed with reference to FIG. 1 to FIG. 9. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0183] In some example embodiments, the program 1030 may be tangibly contained in a computer readable medium which may be included in the device 1000 (such as in the memory 1020) or other storage devices that are accessible by the device 1000. The device 1000 may load the program 1030 from the computer readable medium to the RAM 1022 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).

[0184] FIG. 11 shows an example of the computer readable medium 1100 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 1100 has the program 1030 stored thereon.

[0185] 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 beimplemented 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.

[0186] 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 virtual processor, 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.

[0187] 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.

[0188] 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.

[0189] 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 programmableread-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.

[0190] 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.

[0191] 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

1. 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:receive, from a second apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; andreceive, from the second apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

2. The first apparatus of claim 1 , wherein the at least one configuration parameter comprises at least one of:a measurement interval of channel state information (CSI) measurements for the performance monitoring,a measurement type of the CSI measurements,a reporting interval of CSI reporting for the performance monitoring, ora condition for triggering the CSI reporting.

3. The first apparatus of any of claims 1 to 2, wherein the monitoring configuration update message contains an identifier of an updated monitoring resource in the monitoring resource set.

4. The first apparatus of claim 3, wherein the monitoring configuration update message further contains an indication whether a unified measurement report or two separate measurement reports are enabled for both the performance monitoring and inference of the first machine learning model.

5. The first apparatus of claim 4, wherein at least one of the identifier, the indication, or the at least one configuration parameter is carried in a payload of the monitoring configuration updatemessage.

6. The first apparatus of any of claims 1 to 5, wherein a header of the monitoring configuration update message contains at least one of:an identifier of the monitoring configuration update message,an identifier of the first apparatus, ora timestamp of the monitoring configuration update message.

7. The first apparatus of any of claims 1 to 6, wherein the monitoring configuration update message contains at least one of:a reporting destination of channel state information (CSI) reporting for the performance monitoring, ora format of reported data for the CSI reporting.

8. The first apparatus of any of claims 1 to 7, wherein the first apparatus is further caused to: update the at least one configuration parameter based on the monitoring configuration update message; andperform measurements and reporting for the monitoring resource set, based on the updated at least one configuration parameter.

9. 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:transmit, to a first apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; andreceive, from the second apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

10. The second apparatus of claim 9, wherein the at least one configuration parameter comprises at least one of:a measurement interval of channel state information (CSI) measurements for the performance monitoring,a measurement type of the CSI measurements,a reporting interval of CSI reporting for the performance monitoring, ora condition for triggering the CSI reporting.

11. The second apparatus of any of claims 9 to 10, wherein the monitoring configuration update message contains an identifier of an updated monitoring resource in the monitoring resource set.

12. The second apparatus of claim 11, wherein the monitoring configuration update message further contains an indication whether a single channel state information (CSI) reporting procedure or two separate CSI reporting procedures are enabled for both the performance monitoring and inference of the first machine learning model.

13. The second apparatus of claim 12, wherein at least one of the identification, the indication, or the at least one configuration parameter is carried in a payload of the monitoring configuration update message.

14. The second apparatus of any of claims 9 to 13, wherein a header of the monitoring configuration update message contains at least one of:an identifier of the monitoring configuration update message,an identifier of the first apparatus, ora timestamp of the monitoring configuration update message.

15. The second apparatus of any of claims 9 to 14, wherein the monitoring configuration update message contains at least one of:a reporting destination of channel state information (CSI) reporting for the performance monitoring, ora format of reported data for the CSI reporting.

16. The second apparatus of any of claims 9 to 15, wherein the second apparatus is further caused to:obtain a first recommendation for an adjustment of the monitoring configuration, wherein the recommendation is generated by using a second machine learning model; anddetermine the update to the at least one configuration parameter, based on the first recommendation.

17. The second apparatus of claim 16, wherein the second apparatus caused to obtain the recommendation is caused to:receive the first recommendation from a third apparatus.

18. The second apparatus of claim 16 or 17, wherein the first recommendation indicates an adjustment of the at least one configuration parameter.

19. The second apparatus of any of claims 16 to 18, wherein the first recommendation indicates whether a single channel state information (CSI) reporting procedure or two separate CSI reporting procedures are enabled for both the performance monitoring and inference of the first machine learning model.

20. The second apparatus of any of claims 9 to 19, wherein the third apparatus is further caused to:obtain a second recommendation for the adjustment of the monitoring configuration, wherein the second recommendation is generated by using a second machine learning model based on at least one of measurement data of the first apparatus with respect to the performance monitoring, or a performance metric of the first machine learning model, and the at least one of the measurement data or the performance metric is responsive to the update to the at least one configuration parameter.

21. The second apparatus of claim 20, wherein the third apparatus caused to obtain the secondrecommendation is caused to:send the at least one of the measurement data or the performance metric to a third apparatus; andreceive the second recommendation from the third apparatus, wherein the second recommendation is generated by the third apparatus using the second machine learning model based on the at least one of the measurement data or the performance metric.

22. A third apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the third apparatus at least to:determine a prediction of a monitoring configuration related to performance monitoring of a first machine learning model, by using a second machine learning model, wherein the first machine learning model is used for resource management associated with a first apparatus; and determine a first recommendation for an adjustment of the monitoring configuration, based on the prediction.

23. The third apparatus of claim 22, wherein the third apparatus is further caused to: send the first recommendation to a second apparatus.

24. The third apparatus of any of claims 22 to 23, wherein the prediction is determined based on real-time data related to at least one of a behavior of the first apparatus or an environment surrounding the first apparatus.

25. The third apparatus of any of claims 22 to 24, wherein the third apparatus is further caused to:obtain real-time and historical data related to at least one of a behavior of the first apparatus or an environment surrounding the first apparatus; andbuild the second machine learning model using the obtained real-time and historical data.

26. The third apparatus of any of claims 22 to 25, wherein the third apparatus is further caused to:obtain at least one of measurement data of the first apparatus with respect to the performance monitoring, or a performance metric of the first machine learning model, wherein the at least one of the measurement data or the performance metric is responsive to the update of the monitoring configuration; andrefine the second machine learning model using the at least one of the measurement data or the performance metric.

27. The third apparatus of claim 26, wherein the third apparatus caused to obtain the at least one of the measurement data or the performance metric is caused to:receive the at least one of the measurement data or the performance metric from a second apparatus.

28. The third apparatus of claim 26 or 27, wherein the third apparatus is further caused to: determine a second recommendation for the adjustment of the monitoring configuration, by using the refined second machine learning model.

29. The third apparatus of claim 28, wherein the third apparatus is further caused to: send the second recommendation to a second apparatus.

30. The third apparatus of any of claims 22 to 29, wherein the first recommendation indicates an adjustment to at least one configuration parameter in the monitoring configuration, the at least one configuration parameter comprising at least one of:a measurement interval of channel state information (CSI) measurements for the performance monitoring,a measurement type of the CSI measurements,a reporting interval of CSI reporting for the performance monitoring, ora condition for triggering the CSI reporting.

31. The third apparatus of any of claims 22 to 30, wherein the first recommendation indicates whether a single channel state information (CSI) reporting procedure or two separate CSI reporting procedures are enabled for both performance monitoring and inference of the first machine learning model.

32. A method comprising:at a first apparatus,receiving, from a second apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; andreceiving, from the second apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

33. A method comprising:at a second apparatus,transmitting, to a first apparatus, a monitoring configuration related to a monitoring resource set, wherein the monitoring resource set is used for performance monitoring of a first machine learning model for resource management; andtransmitting, to the first apparatus, a monitoring configuration update message indicating an update to at least one configuration parameter in the monitoring configuration.

34. A method comprising:at a third apparatus,determining a prediction of a monitoring configuration related to performance monitoring of a first machine learning model, by using a second machine learning model, wherein the first machine learning model is used for resource management associated with a first apparatus; and determining a first recommendation for an adjustment of the monitoring configuration, based on the prediction.

Images