Measurement repetition

Abstract

Example embodiments of the present disclosure relate to methods, devices, apparatuses and computer readable storage medium of measurement repetition. In a method, a first apparatus receives, from a second apparatus, a request for a measurement repetition associated with a model functionality. In response to receiving the request, the first apparatus repeats measurement associated with the model functionality. The first apparatus transmits information related to the repeated measurements to the second apparatus.

Description

MEASUREMENT REPETITIONCROSS-REFERENCE TO RELATED APPLICATION

[0001] The present application claims priority from US Provisional Application No. 63 / 514946, filed on July 21, 2023, the contents of which are hereby incorporated by reference in their entirety.FIELDS

[0002] Various example embodiments of the present disclosure generally relate to the field of telecommunication and in particular, to methods, devices, apparatuses and computer readable storage medium of measurement repetition.BACKGROUND

[0003] In some communication systems such as the next cellular systems, artificial intelligence (Al) and / or machine learning (ML) technology is proposed to be used in order to improve the communication performance. An AI / ML model may be applied in the new radio (NR) radio interface to assist model functionalities or communication-related functions, such as, channel state information (CSI) overhead reduction, beam management (BM), positioning, and the like. For example, the AI / ML-based beam management targets spatial and / or time beam prediction for overhead and latency reduction. The AI / ML based functions such as air-interface functions need to be enhanced.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 request for a measurement repetition associated with a model functionality, in response to receiving the request, repeat measurements associated with the model functionality; and transmit information related to the repeated measurements to the second apparatus.

[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 apparatusat least to: transmit, to at least one first apparatus, at least one request for at least one measurement repetition associated with a model functionality; and receive, from the at least one first apparatus, at least one information related to repeated measurements performed by the at least one first apparatus.

[0006] In a third aspect of the present disclosure, there is provided a method. The method comprises: receiving, at a first apparatus from a second apparatus, a request for a measurement repetition associated with a model functionality, in response to receiving the request, repeating measurements associated with the model functionality; and transmitting information related to the repeated measurements to the second apparatus.

[0007] In a fourth aspect of the present disclosure, there is provided a method. The method comprises: transmitting, at a second apparatus to at least one first apparatus, at least one request for at least one measurement repetition associated with a model functionality; and receiving, from the at least one first apparatus, at least one information related to repeated measurements performed by the at least one first apparatus.

[0008] In a fifth aspect of the present disclosure, there is provided an apparatus. The first apparatus comprises means for receiving, from a second apparatus, a request for a measurement repetition associated with a model functionality; means for in response to receiving the request, repeating measurements associated with the model functionality; and means for transmitting information related to the repeated measurements to the second apparatus.

[0009] In a sixth aspect of the present disclosure, there is provided an apparatus. The first apparatus comprises means for transmitting, to at least one first apparatus, at least one request for at least one measurement repetition associated with a model functionality; and means for receiving, from the at least one first apparatus, at least one information related to repeated measurements performed by the at least one first apparatus.

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

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

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

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

[0014] FIG. 2 illustrates a signaling diagram for measurement repetition according to some example embodiments of the present disclosure;

[0015] FIG. 3 illustrates another signaling diagram for measurement repetition according to some example embodiments of the present disclosure;

[0016] FIG. 4 illustrates a flowchart of a process for measurement repetition determination according to some example embodiments of the present disclosure;

[0017] FIG. 5 illustrates another signaling diagram for measurement repetition according to some example embodiments of the present disclosure;

[0018] FIG. 6 illustrates a diagram illustrating the updating of a model according to some example embodiments of the present disclosure;

[0019] FIG. 7 illustrates a diagram illustrating the updating of a model according to some example embodiments of the present disclosure;

[0020] FIG. 8 illustrates a flowchart of a method implemented at a first apparatus according to some example embodiments of the present disclosure;

[0021] FIG. 9 illustrates a flowchart of a method implemented at a second apparatus according to some example embodiments of the present disclosure;

[0022] FIG. 10 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0023] FIG. 11 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0024] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION

[0025] Principle 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.

[0026] 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.

[0027] 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.

[0028] It shall be understood that although the terms “first,” “second” 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. 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.

[0029] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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 processorintegrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0034] 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-IoT) and so on. Furthermore, the communications between a terminal 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 (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G) communication protocols, 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. 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.

[0035] As used herein, the term “network device” or “network access device” refers to a node in a communication network via which a terminal 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 header (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.

[0036] The term “terminal device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a SubscriberStation (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). The terminal 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 terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customerpremises 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 terminal 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 “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0037] As used herein, the term “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer to any resource for performing a communication, for example, a communication between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0038] As used herein, the term “model” is referred to as an association between an input and an output learned from training data, and thus a corresponding output may be generated for a given input after the training. The generation of the model may be based on a ML technique. The ML techniques may also be referred to as Al techniques. In general, a ML model can be built, which receives input information and makes predictions based on the input information. As used herein, a model is equivalent to an AI / ML model,or a data-driven / data processing algorithm / procedure.

[0039] As described above, an AI / ML model may be applied in the NR radio interface to assist model functionalities or communication-related functions, such as, Channel State Information (CSI) feedback overhead reduction, beam management, enhanced positioning, and the like. For example, the AI / ML-based beam management targets spatial and / or time beam prediction for overhead and latency reduction. To support those functions, a common AI / ML framework including functional requirements of AI / ML architecture is desired to be identified. For example, it is proposed to identify areas where AI / ML may improve the performance of air-interface functions. Specification impact may be assessed to improve the overall understanding of what would be required to enable AI / ML techniques for the air interface.

[0040] In some mechanisms, the model’s generalization performance may be assessed in different ways. In a mechanism, the model generalization capability is assessed towards new data generated with the same configuration / scenario. For example, the AI / ML model is trained based on training dataset from one Scenario# A / Configuration#A, and then the AI / ML model performs inference or test on a dataset from the same Scenario#A / Configuration#A. In this option, the configuration used for training the ML model remains unchanged during the ML model inference. Nevertheless, for practical reasons, a single ML model may be used for inference in different configurations or scenarios, implying that the ML model should accurately predict the beam even for unseen configurations / scenarios during the training operation.

[0041] In another mechanism, the ML model is tested with a configuration or in a scenario that is not included in the training data. For example, the AI / ML model is trained based on training dataset from one Scenario#A / Configuration#A, and then the AI / ML model performs inference or test on a different dataset than Scenario# A / Configuration#A, such as Scenario#B / Configuration#B, Scenario# A / Configuration#B, or the like. In this case, the ML model performance is generally poor, since changing the configuration may lead to different data distributions and characteristics.

[0042] In some mechanisms, the model for deriving the outcome of the model functionality may be site-specific, panel-specific or considering other fixed assumptions. For a site-specific model, the model may be trained for a specific cell. For instance, a gNB deploys an ML model #A trained in the sector #A. A neighbour gNB may use the MLmodel #A trained for sector #A. Although, neighbour gNBs may employ the same beam pattern and benefit from spatial correlation, the propagation environment may change, and prediction results may change from sector #A to sector #B, making it not possible to use model #A in sector #B.

[0043] In another example, the ML model may be specific to the Tx beam pattern. In general, the ML model is trained with a mix of data collected from multiple sectors. For instance, the ML model may be trained with the data collected from sector #A and sector #B, all with same Tx beam patterns. At some point, the gNB in sector #A may switch off one or more of its antenna panels to save energy. This implicitly changes the Tx beam pattern. Therefore, the ML model #A may generalize well in sector #B but cannot generalize toward the different antenna and Tx pattern configurations adopted by gNB in sector #A.

[0044] In a further example, the ML model may be specific to one or more Rx beam patterns: In DL Tx beam prediction, for reporting the measurements for different Tx beams the UE device may use a fixed Rx beam (e.g., pointing towards the boresight Rx beam panel direction) or an optimal Rx beam. Therefore, the ML model trained with a mix of data collected from multiple UE may generalize well for different devices with similar Rx beam pattern. However, the ML model may not support a new UE device, which uses a new antenna design enabling for instance narrow beams to enhance coverage and / or reducing blockages.

[0045] In a further mechanism, it is assumed training the ML model with a mix of data collected with multiple configurations / scenarios. The scenarios may be various deployment scenarios, various outdoor / indoor UE distributions, or various UE mobility. The configuration may be various UE parameters, various gNB settings or various Set B of beams or beam pairs. For example, the AI / ML model is trained based on training dataset constructed by mixing datasets from multiple scenarios / configurations including Scenario#A / Configuration#A and a different dataset than Scenario# A / Configuration#A, e.g., Scenario#B / Configuration#B, Scenario# A / Configuration#B. Then the AI / ML model performs inference or test on a dataset from a single Scenario / Configuration from the multiple scenarios / configurations, e.g., Scenario#A / Configuration#A, Scenario#B / Configuration#B, Scenario# A / Configuration#B. The ratio for dataset mixing may be reported. The number of the multiple scenarios / configurations may be larger than two. In this mechanism, a single ML model should adapt to the changes of theconfigurations / scenarios, without significant impact on performance.

[0046] In some mechanisms, generalization verification is proposed. In such mechanisms, the AI / ML model is trained based on training dataset from one Scenario#A / Configuration#A, and then the AI / ML model is updated based on a fine- tuning dataset different than Scenario#A / Configuration#A, e.g., Scenario#B / Configuration#B, Scenario# A / Configuration#B. After that, the AI / ML model is tested on a different dataset than Scenario# A / Configuration#A, e.g., subject to Scenario#B / Configuration#B, Scenario# A / Configuration#B. In some cases, the fine- tuning dataset setting such as the size of dataset and the improvement of performance may be reported.

[0047] In some mechanisms, further analysis on the reasonable scenarios or configurations for each use cases (e.g., beam management cases) and / or AI / ML training, inference location (e.g., UE-side / network (NW)-side models) and monitoring location (e.g., UE-side / NW-side monitoring) is provided. However, the model cannot maintain good performance such as good beam prediction accuracy in different reasonable scenarios or situations. More importantly, is not clear how to trigger a model updating, how to collect data for model updating and how to update the model by the network or by the UE.

[0048] In order to solve at least part of the above problems or other potential problems, a solution on measurement repetition is proposed. According to example embodiments, a second apparatus (for example, a network device) transmits, to at least one first apparatus (for example, at least one terminal device), at least one request for a measurement repetition associated with a model functionality. For example, the model functionality may be an AI / ML based function such as beam prediction. In response to receiving the request, the at least one first apparatus repeats measurements associated with the model functionality. The at least one first apparatus transmits information related to the repeated measurements to the second apparatus.

[0049] In this manner, a plurality of repeated measurements is performed by the first apparatus. Based on the repeated measurement results, the model functionality can be improved. For example, a model for deriving an outcome of the model functionality may be updated based on the repeated measurements. Accordingly, a more accurate outcome of the model functionality can be achieved. The performance of the model functionalitycan thus be enhanced.

[0050] Principle and implementations of the present disclosure will be described in detail below with reference to FIGS. 1-11.

[0051] FIG. 1 illustrates an example communication environment 100 in which example embodiments of the present disclosure can be implemented. In the communication environment 100, a plurality of communication devices, including a first apparatus 110- 1, a first apparatus 110-2, > , a first apparatus 110-N and a second apparatus 120, can communicate with each other. For ease of discussion, the first apparatus 110-1, first apparatus 110-2, > , and first apparatus 110-N may be collectively referred to as “first apparatuses 110” or individually referred to as a “first apparatus 110”.

[0052] In the example of FIG. 1, the second apparatus 120 has a certain coverage range, which may be called as a serving area or a cell (not shown). The first apparatuses 110 are located in the cell covered by the second apparatus 120. In the communication environment 100, the second apparatus 120 may communicate data and control information to the first apparatus(es) 110 and the first apparatus(es) 110 may also communication data and control information to the second apparatus 120.

[0053] In some example embodiments, a model functionality such as an AI / ML based functionality may be provided for the first apparatus 110. For example, the second apparatus 120 may provide a plurality of beams for the first apparatuses 110. The model functionality may be a beam prediction which predicts a beam for a corresponding first apparatus 110. In some example embodiments, a model may derive an outcome such as the predicted beam of the model functionality. The model may be implemented at the first apparatus 110, or the second apparatus 120, or both. For purpose of illustration, some example embodiments hereinafter will be described with the beam prediction as the model functionality. It is to be understood that the model functionality may also be any other suitable functions, including but not limited to CSI prediction, positioning prediction, or the like. Scope of the present disclosure is not limited in this regard.

[0054] It is to be understood that the number 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 of apparatuses configured to implementing example embodiments of the present disclosure.

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

[0056] In some example embodiments, if the first apparatus 110 is a terminal device and the second apparatus 120 is a network device, a link from the second apparatus 120 to the first apparatus 110 is referred to as a downlink (DL), while a link from the first apparatus 110 to the second apparatus 120 is referred to as an uplink (UL). In DL, the second apparatus 120 is a transmitting (TX) device (or a transmitter) and the first apparatus 110 is a receiving (RX) device (or a receiver). In UL, the first apparatus 110 is a TX device (or a transmitter) and the second apparatus 120 is a RX device (or a receiver).

[0057] Communications in the communication environment 100 may be implemented according to any proper communication protocol(s), comprising, but not limited to, cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), the fifth generation (5G), the sixth generation (6G), and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols currently known or to be developed in the future. 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.

[0058] As briefly mentioned above, to improve a model functionality, measurement repetition is requested. FIG. 2 illustrates a signaling diagram 200 for measurement repetition according to some example embodiments. The signaling diagram 200 involves the plurality of first apparatuses 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling diagram 200 will be described with respect to FIG. 1.

[0059] It is to be understood that although there is the plurality of first apparatuses 110 shown in FIG. 2, in some example embodiments, there may be a single first apparatus 110 in the signaling diagram 200. For purpose of discussion, some example embodiments are described where the first apparatus 110 is implemented as a terminal device and the second apparatus 120 is implemented as a network device.

[0060] As shown in FIG. 2, the second apparatus 120 transmits (220) to at least one first apparatus such as the plurality of first apparatuses 110, a plurality of requests for a plurality of measurement repetitions associated with a model functionality. The first apparatuses 110 receive (230) the requests, respectively. As used herein, the term “model functionality” or “model function” may refer to a functionality or service related to the communication network or related to communications between apparatuses. The model functionality may be implemented by one or more models such as one or more AI / ML models.

[0061] In some example embodiments, the model functionality may be an AI / ML based function, such as AI / ML based beam management, or any other suitable functions. The AI / ML based beam management may be spatial and / or time domain beam prediction. The spatial beam prediction (also referred to as BM-Casel) is to predict one or more best Tx beams or Tx-Rx beam pairs or corresponding reference signal received power (RSRP) values in different spatial locations. The time-domain beam predictions (also referred to as BM-Case2) aim to predict the best Tx beams or Tx-Rx beam pairs to use for next time instants, e.g., beam prediction in the spatial domain (BM-Casel) for next time instants. For purpose of illustration, some example embodiments are described where the model functionality is the spatial and / or time domain beam prediction.

[0062] In response to receiving (230) the request, the first apparatuses 110 repeat (240) the measurements, respectively. In some example embodiments, a first apparatus 110 of the first apparatuses 110 may receive a configuration for one or more reference signals (RSs) associated with the measurement repetition from the second apparatus 120. The first apparatus 110 may repeat (240) the measurements for the one or more RSs based on the configuration.

[0063] The one or more RSs may be determined by the second apparatus 120. In an example, the second apparatus 120 may determine a monitoring result of the model functionality based on a measurement result from the first apparatus 110. The one or moreRSs may be determined by the second apparatus 120 based on the monitoring result of the model functionality. Taking the model functionality being the beam prediction as an example, the monitoring result may be a monitoring result of a predicted beam for the first apparatus 110. The beam prediction or the predicted beam may be from one or models.

[0064] The first apparatuses 110 transmit (250) information related to repeated measurements to the second apparatus 120, respectively. The second apparatus 120 receives (260) the information.

[0065] In some example embodiments, the information related to the repeated measurements may include a result of the repeated measurements. Alternatively, or in addition, the information related to the repeated measurements may include an outcome of the model functionality.

[0066] In this manner, a plurality of repeated measurements is performed by the first apparatuses 110. Based on the repeated measurement results, the model functionality can be improved. For example, one or more models for deriving an outcome of the model functionality may be updated based on the repeated measurements. Accordingly, a more accurate outcome of the model functionality can be achieved. The performance of the model functionality can thus be enhanced.

[0067] In some example embodiments, a model for deriving the outcome of the model functionality may be site-specific, panel-specific or considering other fixed assumptions. The model may be implemented at the first apparatus 110 and / or the second apparatus 120.

[0068] In some example embodiments, the second apparatus 120 may transmit (220) the request(s) based on at least one condition for measurement repetition. For example, if the second apparatus 120 determines that an outcome of the model functionality is not accurate, the second apparatus 120 may transmits (220) the request(s) to the first apparatus 110. Several example conditions regarding the transmission (220) of the request for measurement repetition will be described with respect to FIG. 3 to FIG. 4.

[0069] FIG. 3 illustrates another signaling diagram 300 for measurement repetition according to some example embodiments of the present disclosure. The signaling diagram 300 involves the plurality of first apparatuses 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling diagram 300 will be described with respect to FIG. 1.

[0070] It is to be understood that although there is the plurality of first apparatuses 110 shown in FIG. 3, in some example embodiments, there may be a single first apparatus 110 in the signaling diagram 300. For purpose of discussion, some example embodiments are described where the first apparatus 110 is implemented as a terminal device and the second apparatus 120 is implemented as a network device. For purpose of illustration, it is assumed that in some example embodiments of FIG. 3, the model functionality is the spatial and / or time domain beam prediction from one or more models.

[0071] As shown in FIG. 3, the second apparatus 120 may transmit (310) at least one configuration for reference signal (RS) to at least one first apparatus 110. For example, the second apparatus 120 may transmit (310) a plurality of configurations for RSs to the plurality of first apparatuses 110. The plurality of first apparatuses 110 may receive (310) the plurality of configurations for RSs, respectively. The RS(s) may be channel state information (CSI)-RS(s) or any other suitable RS(s). In an example, the configurations may configure measurements for a set of beams (also referred to as beams in Set A).

[0072] The second apparatus 120 may transmit (330) a plurality of transmission (Tx) beams in Set A to the plurality of first apparatuses 110. The transmission beams correspond to the RSs. The first apparatuses 110 may receive (340) the transmission beams in Set A, respectively. The first apparatus 110 may perform beam measurements on the transmission beams in Set A. For example, the first apparatus 110 may perform RSRP measurement or any other suitable measurement on the transmission beams in Set A.

[0073] The first apparatuses 110 may transmit (350) beam measurement(s) to the second apparatus 120, respectively. For example, the second apparatus 120 may receive (360) the beam measurement(s) such as reported RSRP measurements or measurements for any other suitable parameter from the plurality of first apparatuses 110.

[0074] In some example embodiments, the plurality of first apparatuses 110 or the at least one first apparatus 110 may be a fixed number of first apparatuses 110. The fixed number may be predefined. Alternatively, the plurality of first apparatuses 110 or the at least one first apparatus 110 may be all the first apparatuses 110 served by the model functionality.

[0075] In the example of FIG. 3, it is assumed that a model implemented at the second apparatus 120 may derive an outcome of the model functionality. That is, the secondapparatus 120 may perform (370) the beam prediction inference. In the beam prediction example with the model at the second apparatus 120 (also referred to as network (NW) side model), the second apparatus 120 performs (370) the beam prediction.

[0076] In an example, for a certain first apparatus 110 of the plurality of first apparatuses 110 such as a k-th first apparatus 110, model input or model output for the certain first apparatus 110 may be described as follows.

[0077] The input of the model is the set of RSRP measurements for another set of beams (for example, Set B beams) which may be a subset of Set A beams, or different from Set A beams. The model input vectormay be expressed as= [Po ( < Pi ( > ■■■ > PN(£)]’ where N represents the size of Set B beams, k denotes an index for the first apparatus 110, and t denotes the time. The output of the model may be the best predicted beam index k^ =Hi), given by a prediction function / (■) obtained with training parametersand input vector Pw(0 for time t.

[0078] The second apparatus 120 may determine (380) whether to transmit a request for a measurement repetition to the first apparatus(es) 110. For example, the second apparatus 120 may determine (380) to transmit the request based on at least one condition for measurement repetition. As used herein, the term “at least one condition for measurement repetition” may be referred as “at least one condition”.

[0079] In some example embodiments, the at least one condition for measurement repetition may be based on at least one monitoring result of the model functionality. The at least one monitoring result is associated with at least one measurement result from the at least one first apparatus 110. Alternatively, or in addition, the at least one condition for measurement repetition may be based on at least one outcome of the model functionality. The at least one outcome is associated with the at least one first apparatus 110.

[0080] Alternatively, or in addition, the at least one condition for measurement repetition may be based on a model assertion for monitoring an outcome or performance of the model functionality. If a predicted outcome of the model functionality mismatches with a reference outcome such as a ground truth, the model assertion is detected. For example, for a first apparatus 110 such as a k-th first apparatus 110, if the predicted best beam k^ is different from the ground truth best beam k , the model assertion formonitoring the performance may be considered as being detected or failing. A detected model assertion indicates that the model functionality is not capable to provide sufficiently accurate prediction outcomes. If any model assertions are detected for a certain first apparatus 110, the certain first apparatus 110 may be referred to as a first apparatus 110 not passing the model monitoring assertion results.

[0081] Otherwise, if the predicted outcome of the model functionality matches with the reference outcome or the ground truth, the model assertion is undetected. For example, if the predicted best beamis same with or similar to the ground truth best beam k^ , the model assertion for monitoring the performance may be considered as being undetected or passing. In other words, if the predicted outcome indicates the model assertion is passed, the predicted outcome may be considered as passing model assertions during monitoring. If all the model assertions are undetected for a certain first apparatus 110, the certain first apparatus 110 may be referred to as a first apparatus 110 passing the model monitoring assertion results. As used herein, the term “model assertion for monitoring the performance of the model functionality” may be used to indicate “model monitoring assertion(s)”, “model monitoring assertion result(s)” or “model assertion(s)”.

[0082] In an example, a first condition for measurement repetition may be that the number of reliable monitoring results of the at least one monitoring result is less than or equal to a first threshold number. For example, for a monitoring result associated with a first apparatus 110 of the plurality of first apparatuses 110, the second apparatus 120 may determine whether the monitoring result is reliable based on at least one of: a distribution of measurement results from the first apparatus 110 (such as a measurement report of the first apparatus 110), a variation of conditions of the first apparatus 110 (such as a mobility of the second apparatus 120 or a capability of the second apparatus 120), or a change of confidence errors associated with the first apparatus 110, or any other suitable aspect. As used herein, the reliable monitoring results may be referred to as reliable set of model performances, or filtered model performances. If the number of reliable monitoring results is less than or equal to the first threshold number, the second apparatus 120 may determine (380) to transmit the request(s).

[0083] In another example, a second condition for measurement repetition may be that the number of the at least one monitoring result with a monitoring performance value being less than a threshold value is equal to or greater than a second threshold number. Ifthe number of the at least one monitoring result with a monitoring performance value being less than a threshold value is equal to or greater than a second threshold number, the second apparatus 120 may determine (380) to transmit the request(s). For example, the monitoring performance value may be a key performance indicator (KPI) such as model performance KPIs e.g., beam prediction accuracy, difference between RSRP of best predicted beam and RSPR of best ground-truth beam, etc., or system performance KPIs like signal to noise and interference ratio (SINR), RSRP or reference signal received quality (RSRQ), or the like.

[0084] In a further example, a third condition for measurement repetition may be that the number of failure events of the model functionality within a monitoring time interval is equal to or greater than a third threshold number. If the number of failure events of the model functionality within a monitoring time interval is equal to or greater than the third threshold number, the second apparatus 120 may determine (380) to transmit the request(s).

[0085] In a still further example, a fourth condition for measurement repetition may be that the number of at least one outcome of the model functionality mismatching with a reference outcome is equal to or greater than a fourth threshold number. For example, if for k-th first apparatus 110, the predicted best beam k^ is different from the reference outcome such as the ground truth best beam k^, it indicates that the model functionality is not capable to provide sufficiently accurate predictions given the input vector p^ together with parameters. If the number of the outcomes of the model functionality mismatching with the reference outcome is equal to or greater than the fourth threshold number, the second apparatus 120 may determine (380) to transmit the request(s).

[0086] In a yet further example, a fifth condition for measurement repetition may be based on the model assertion. For example, the fifth condition may be that an outcome of the model functionality associated with a first apparatus 110 of the at least one first apparatus 110 mismatches with a reference outcome (such as a ground truth). In the example where the model functionality is the beam prediction, the reference outcome may be the ground truth best beam k for k-th first apparatus 110. That is, if the predicted at least one beam k^ is different from the reference outcome such as the ground truth best beam / Cf , it indicates that the outcome of the model functionality is not correct. If the outcome of the model functionality for a certain first apparatus 110 or any other firstapparatus 110 is not correct, the second apparatus 120 may determine (380) to transmit the request(s) for a measurement repetition to the certain first apparatus 110 or to the other first apparatus 110.

[0087] It is to be understood that in some example embodiments, these conditions and any other suitable conditions may be applied in any suitable combination, or be used separately. For example, if the fifth condition is satisfied and at least one of the first, second, third or fourth condition is satisfied, the request for measurement repetition may be transmitted. FIG. 4 illustrates a flowchart of a process 400 for measurement repetition determination according to some example embodiments of the present disclosure. The process 400 may be implemented by the second apparatus 120.

[0088] As illustrated, the second apparatus 120 may monitor the model performance on a plurality of first apparatuses 110 at blocks 412, 414, > and 416. For example, the first apparatuses 110 may perform parallel monitoring of the model performance, including the determination of the KPIs (e.g., beam prediction accuracy and / or RSRP error, or the like). The second apparatus 120 may obtain the monitoring results of the first apparatuses 110. The model performances may be denoted by Mi, M2, ..., MN, which correspond to the model performances (measured with a KPI such as model prediction accuracy, Ll-RSRP difference, etc.) of the plurality of first apparatuses 110 served by the second apparatus 120.

[0089] In some example embodiments, at block 420, the second apparatus 120 may filter of model performance for the plurality of first apparatuses 110. That is, the second apparatus 120 may perform some filtering of the first apparatus-specific model performance results. Filtering may be applied over time, over space location, or for any other network KPIs such as SINR, RSRP and RSRQ. For example, after filtering, M2, M3... MN-I correspond to the reliable model performances set.

[0090] At block 440, the second apparatus 120 may determine at least one of the first, second, third or fourth threshold number associated with the at least one condition. For example, the second apparatus 120 may determine a threshold limit (such as the second threshold number or the third threshold number) that defines the max number of model failure first apparatuses 110 not attaining the minimum required model performance KPIs, and / or the max number of model failure events. As used herein, if a monitoring result associated with a certain first apparatus 110 is not satisfied the minimum required modelperformance KPIs, or the certain apparatus 110 is associated with a model failure event, the certain first apparatus 110 may be referred to as a first apparatus 110 not passing model assertions during monitoring.

[0091] In some example embodiments, the second apparatus 120 may determine at least one of the first, second, third or fourth threshold number based on at least one of: the monitoring time interval, or the monitoring performance value associated with a predetermined number of failure events of the model functionality. For example, the threshold limit (such as the second threshold number or the third threshold number) may be adjusted accordingly to the monitoring time interval, or the average RSRP error corresponding to a maximum number of failing events or a combination of one or more criteria. A confidence interval around the threshold limit may be provided to check if an estimated model performance metric errors are included in the calculated model performance metric minus / plus the error.

[0092] At block 450, the second apparatus 120 may optionally determine radio network conditions. Any suitable radio network conditions may be applied. At block 430, the second apparatus 120 may evaluate the overall status of the model performance. As used herein, the block 430 may be referred to as a decision block. For example, if the number of first apparatuses 110 and / or the number of events not passing model assertions during monitoring is above the threshold limit determined at block 440, the model is considered to be updated. That is, the request for measurement repetition is needed. In one example, if the first threshold is K, if K >= count (M2, M3...MN-1) the model may be declared to be as “update needed”.

[0093] In some example embodiments, the second apparatus 120 may output the list of first apparatus 110 not passing model assertions during monitoring. For example, the second apparatus 120 may use extra information such as the mobility of the first apparatus 110 to weigh each failure event associated with the first apparatus 110 for the overall model performance evaluation.

[0094] At block 460, the second apparatus 120 may trigger the measurement repetition request. For example, if the model monitoring assertions are detected for a k-th first apparatus 110, the second apparatus 120 may determine that one or more measurement repetitions are required to obtain a second or more measurement reports, including the set of RSRP measurements p^(t + 1) for time t+1.

[0095] In some example embodiments, if the second apparatus 120 may trigger the measurement repetition request, the second apparatus 120 may transmit the request for measurement repetition to at least one first apparatus 110. By using the process 400, the second apparatus 120 may use a parallel approach where the model performances observed for different first apparatuses 110 are firstly filtered based on conditions of the first apparatuses 110 (weighting which first apparatuses 110 are providing reliable model performance results). Then, a decision for the measurement repetition may be determined for instance based on a threshold limit. The threshold limit may be the max number model failure first apparatuses 110 or any other threshold limit or threshold number mentioned above. The decision may be determined at block 430. The decision may be applied to trigger the model update. Other indications such as the indications which first apparatuses 110 configure for reporting additional measurements and which model parameters may be transferred during the update are also provided for the determination of the measurement repetitions.

[0096] Referring back to FIG. 3, the second apparatus 120 transmits (220) at least one request for at least one measurement repetition associated with the model functionality to at least one first apparatus 110 such as the plurality of first apparatuses 110. The at least one first apparatus 110 receives (230) the at least one request, respectively.

[0097] In some example embodiments, the request may indicate the first apparatus 110 to repeat the measurements and to report the measurements back to the second apparatus 120. In an example, the request may indicate the first apparatus 110 to repeat the measurements on the set of RSs such as the set of CSI-RSs corresponding to the beams in Set A indicated by the transmitted (310) configuration.

[0098] Alternatively, or in addition, in some example embodiments, the second apparatus 120 may further transmit a plurality of configurations for RSs associated with the measurement repetition to the plurality of first apparatuses 110. The plurality of first apparatuses 110 may receive the plurality of configurations for RSs, respectively. For example, for a certain first apparatus 110 of the plurality of first apparatuses 110, the certain first apparatus 110 may receive a configuration for one or more RSs associated with the measurement repetition of the certain first apparatus 110. The second apparatus 120 may determine a monitoring result of the model functionality based on a measurement result from the certain first apparatus 110. The second apparatus 120 may determine the one or more RSs based on the monitoring result of the model functionality.

[0099] In some example embodiments, the second apparatus 120 may obtain at least one predicted beam for the first apparatus 110. The at least one predicted beam is provided by the model functionality. For example, the at least one predicted beam may be Top-K (K being an integer) beams provided by the model functionality. The second apparatus 120 may determine at least one serving beam based on the measurement result from the first apparatus 110. The at least one serving beam may be Top-K genie-aided beams or Top-K strongest beams. For example, the Top-K strongest beams may be provided by ranking the strongest layer one (Ll)-RSRP values determined from beam measurements. The second apparatus 120 may determine the one or more RSs based on the at least one predicted beam and the at least one serving beam.

[0100] In an example, the set or subset of CSI-RS for repeating measurements may be determined based on Top-K (K being an integer) beams provided by the model functionality and the Top-K genie-aided beams, for instance provided by ranking the strongest layer one (Ll)-RSRP values determined from beam measurements.

[0101] Alternatively, or in addition, in some example embodiments, the second apparatus 120 may determine a plurality of candidate beams for the first apparatus 110. For example, the plurality of candidate beams may be the transmission beams in Set A. The second apparatus 120 may determine the one or more RSs based on one or more candidate beams in the plurality of candidate beams. The one or more candidate beams may be randomly selected. In an example, the set or subset of CSI-RS for repeating measurements may be determined randomly from Set A beams at each repetition request. Such determination of RSs may be used in a case with monitoring results indicating equally unreliable outcomes of model functionality.

[0102] The at least one first apparatus 110 repeats (240) the measurements based on the received (230) request. The at least one first apparatus 110 transmits (250) at least one information related to the repeated measurements to the second apparatus 120. The second apparatus 120 receives (260) the at least one information. The at least one information may include at least one result of repeated measurements.

[0103] The second apparatus 120 may update (390) the model based on the received (260) at least one information such as the at least one result of the repeated measurements. For example, the second apparatus 120 may trigger the update, re-training or fine-tuning of the model at the second apparatus 120 and determines a new set of training parametersn2at time t+1 to use for the model functionality. The model training at the second apparatus 120 may use a dataset that includes both the sets of RSRP measurements obtained at time t, namely Pw(t), and the one obtained at time t + 1, namely p^(t + 1), in addition to any other RSRP measurements report obtained from measurement repetition requests. The model functionality may be updated accordingly. It is to be understood that in some example embodiments, a plurality of models may be used to generate the outcome of the model functionality, at least a part of the plurality of models may be updated in a similar way as described above.

[0104] In some example embodiments, the second apparatus 120 may determine (395) a further decision regarding the measurement repetition. For example, the second apparatus 120 may determine (395) whether the model is to be further updated or whether to transmit a further request for the measurement repetition. For example, the second apparatus 120 may determine whether the at least one condition for measurement repetition is satisfied based on the at least one information.

[0105] If the at least one condition for measurement repetition is still satisfied, the second apparatus 120 may determine to further update the model. In some example embodiments, the second apparatus 120 may transmit at least one further request for at least one measurement repetition associated with the model functionality to the at least one first apparatus 110. For example, the second apparatus 120 may apply the updated model functionality such as the new prediction function for performing network-side model monitoring. The second apparatus 120 may initiate a new set of measurement repetition requests in case of detected model monitoring assertions.

[0106] If the at least one condition for measurement repetition is not satisfied, the second apparatus 120 may cause termination of updating of the model for deriving the outcome of the model functionality. That is, the second apparatus 120 may apply the updated model functionality such as the new prediction function for performing networkside model monitoring and may terminate the transmission of measurement repetition requests in case of undetected model monitoring assertions.

[0107] In an example, the second apparatus 120 may perform a second beam prediction inference and obtain the best predicted beam index for at time t + 1. The best predicted beam index for at time t + 1 may be expressed aswhich is given by training parameters fl2and for input vector p^(t + 1). The second apparatus 120 maythus perform a second model monitoring assessments. At time t + 1, the predicted best beam k^+1matches with the ground truth best beam k^+1, indicating that the prediction function provides accurate predictions when used with the set of input vectortogether with parameters fl2. Therefore, the model monitoring assertions are not detected. No further measurement repetition requests are transmitted.

[0108] Several example embodiments regarding the measurement repetition request and the model updating based on the repeated measurements have been described with respect to FIG. 3 and FIG. 4. In the example of FIG. 3, the model for deriving an outcome of the model functionality is implemented at the second apparatus 120. In some example embodiments, the model for deriving the outcome of the model functionality may be implemented at the first apparatus 110. FIG. 5 illustrates another signaling diagram 500 for measurement repetition according to some example embodiments of the present disclosure. In the example of FIG. 5, it is assumed that the model for deriving an outcome of the model functionality is implemented at the first apparatus 110.

[0109] The signaling diagram 500 involves the plurality of first apparatuses 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling diagram 500 will be described with respect to FIG. 1. It is to be understood that although there is the plurality of first apparatuses 110 shown in FIG. 5, in some example embodiments, there may be a single first apparatus 110 in the signaling diagram 500. For purpose of discussion, some example embodiments are described where the first apparatus 110 is implemented as a terminal device and the second apparatus 120 is implemented as a network device. For purpose of illustration, it is assumed that in some example embodiments of FIG. 5, the model functionality is the spatial and / or time domain beam prediction.

[0110] Similar to the signaling diagram 300, in the signaling diagram 500, the second apparatus 120 may transmit (310) at least one configuration for reference signal (RS) to at least one first apparatus 110. For example, the second apparatus 120 may transmit (310) a plurality of configurations for RSs to the plurality of first apparatuses 110. The plurality of first apparatuses 110 may receive (310) the plurality of configurations for RSs, respectively. The RS(s) may be channel state information (CSI)-RS(s) or any other suitable RS(s). In an example, the configurations may configure measurements for a set of beams (also referred to as beams in Set A).

[0111] The second apparatus 120 may transmit (330) a plurality of transmission (Tx) beams in Set A to the plurality of first apparatuses 110. The transmission beams correspond to the RSs. The first apparatuses 110 may receive (340) the transmissions beams in Set A, respectively. The first apparatus 110 may perform beam measurements on the transmission beams in Set A. For example, the first apparatus 110 may perform RSRP measurement or any other suitable measurement on the transmission beams in Set A.

[0112] The first apparatuses 110 may transmit (350) beam measurement to the second apparatus 120, respectively. For example, the second apparatus 120 may receive (360) the beam measurement such as reported reference signal received power (RSRP) measurements or measurements for any other suitable parameter from the plurality of first apparatuses 110.

[0113] In some example embodiments, the plurality of first apparatuses 110 or the at least one first apparatus 110 may be a fixed number of first apparatuses 110. The fixed number may be predefined. Alternatively, the plurality of first apparatuses 110 or the at least one first apparatus 110 may be all the first apparatuses 110 with a model. The second apparatus 120 may be configured to model monitoring the first apparatuses 110.

[0114] The first apparatuses 110 may transmit (350) beam measurement to the second apparatus 120, respectively. For example, the second apparatus 120 may receive (360) the beam measurement such as reported reference signal received power (RSRP) measurements or measurements for any other suitable parameter from the plurality of first apparatuses 110.

[0115] Different with the signaling diagram 300, in the signaling diagram 500, it is assumed that a model implemented at the first apparatus(es) 110 may derive an outcome of the model functionality. That is, the first apparatus(es) 110 may perform (510) the beam prediction inference.

[0116] In an example, for a certain first apparatus 110 of the plurality of first apparatuses 110 such as a k-th first apparatus 110, model input or model output for the certain first apparatus 110 may be described as follows. The input of the model is the set of RSRP measurements for another set of beams (for example, Set B beams) which may be a subset of Set A beams, or different from Set A beams. The model input vector p^ may be expressed asN represents the size of Set Bbeams, k denotes an index for the first apparatus 110, and t denotes the time. The output of the model may be the best predicted beam indexfit), given by a prediction function (■) obtained with training parametersand input vectorfor time t.

[0117] In some example embodiments, the at least one first apparatus 110 may transmit (520) at least one beam measurement or the beam prediction to the second apparatus 120. For example, the at least one beam measurement may be reported RSRP measurements or other measured values.

[0118] The second apparatus 120 may determine (540) whether to transmit a request for a measurement repetition to the first apparatus(es) 110. For example, the second apparatus 120 may determine (540) to transmit the request based on at least one condition for measurement repetition. In some example embodiments, the at least one condition for measurement repetition may be based on at least one monitoring result of the model functionality and / or at least one outcome of the model functionality. The at least one monitoring result is associated with at least one measurement result from the at least one first apparatus 110. The at least one outcome is associated with the at least one first apparatus 110.

[0119] In an example, the second apparatus 120 may perform model monitoring. If model monitoring assertions are detected for k-th first apparatus 110 where the predicted best beam k^ is different from the ground truth best beam / Cj, it may indicate that the model functionality is not providing accurate predictions given the input vectortogether with parameters IL In such situation, the second apparatus 120 may determine (540) that one or more measurement repetitions are required to obtain a second measurements / prediction report.

[0120] In some example embodiments, if any condition described with respect to FIG. 3 is satisfied, the second apparatus 120 may determine (540) that one or more measurement repetitions are require. That is, the second apparatus 120 may determine (540) to transmit the request for measurement repetition. Likewise, the second apparatus 120 may perform the process 400 to determine (540) whether the request for measurement repetition is required.

[0121] In some example embodiments, the request may indicate the first apparatus 110 to repeat the measurements and to report the measurements back to the second apparatus120. In an example, the request may indicate the first apparatus 110 to repeat the measurements on the set of RSs such as the set of CSI-RSs corresponding to the beams in Set A indicated by the transmitted (310) configuration.

[0122] Alternatively, or in addition, in some example embodiments, the second apparatus 120 may further transmit a plurality of configurations for RSs associated with the measurement repetition to the plurality of first apparatuses 110. The plurality of first apparatuses 110 may receive the plurality of configurations for RSs, respectively. For example, for a certain first apparatus 110 of the plurality of first apparatuses 110, the certain first apparatus 110 may receive a configuration for one or more RSs associated with the measurement repetition of the certain first apparatus 110. The second apparatus 120 may determine a monitoring result of the model functionality based on a measurement result from the certain first apparatus 110. The second apparatus 120 may determine the one or more RSs based on the monitoring result of the model functionality.

[0123] In a first example, the set or subset of CSI-RS for repeating measurements may be determined based on Top-K (K being an integer) beams provided by the model functionality and the Top-K genie-aided beams, for instance provided by ranking the strongest Ll-RSRP values determined from beam measurements. In a second example, the set or subset of CSI-RS for repeating measurements may be determined randomly from Set A beams at each repetition request (case with monitoring results indicating equally unreliable outcomes of model functionality).

[0124] The at least one first apparatus 110 repeats (240) the measurements based on the received (230) request. The at least one first apparatus 110 transmits (250) at least one information related to the repeated measurements to the second apparatus 120. The second apparatus 120 receives (260) the at least one information. The at least one information may include at least one result of repeated measurements.

[0125] The at least one first apparatus 110 may update (390) the model based on the at least one result of the repeated measurements. For example, first apparatus 110 may trigger the update, re-training or fine-tuning of the model and determines a new set of training parameters fl2at time t+1 to use for the model functionality. The model training at first apparatus 110 may use a dataset that includes both the sets of RSRP measurements obtained at time t, namelyand the one obtained at time t + 1, namely pjy(t + 1), in addition to any other RSRP measurements report obtained from measurement repetitionrequests. The model functionality may be updated accordingly.

[0126] In one example, the first apparatus 110 itself may update (390) the model based on the result of the repeated measurements. In another example, the first apparatus 110 may cause another device or apparatus communicatively connected with the first apparatus 110 to update the model. For example, the first apparatus 110 may cause a server to update the model based on the result of the repeated measurements. The first apparatus 110 may manage such model update. In example embodiments where the first apparatus 110 is UE, the server may be a UE server.

[0127] It is to be understood that in some example embodiments, a plurality of models may be implemented at the first apparatus 110 or at a server of the first apparatus 110 to generate the outcome of the model functionality, at least a part of the plurality of models may be updated in a similar way as described above.

[0128] In some example embodiments, the at least one first apparatus 110 may perform a second beam prediction inference and obtain the best predicted beam index for at time t + 1. The second beam prediction inference may be performed by the updated model.

[0129] The at least one first apparatus 110 transmits (250) at least one information related to the repeated measurements to the second apparatus 120. The second apparatus 120 receives (260) the at least one information. The at least one information may include at least one outcome of the model functionality. For example, the at least one information may include at least one outcome derived from the updated model. In some example embodiments, the at least one information may further include at least one result of repeated measurements. That is, the measurements or predictions may be reported back to the second apparatus, including the set of RSRP measurements+ l) and corresponding predicted best beam k^+1or time t + 1.

[0130] In some example embodiments, the second apparatus 120 may determine (560) a further decision regarding the measurement repetition. For example, the second apparatus 120 may determine (560) whether the model is to be further updated or whether to transmit a further request for the measurement repetition. For example, the second apparatus 120 may determine whether the at least one condition for measurement repetition is satisfied based on the at least one information such as the at least one outcome derived from the updated model.

[0131] If the at least one condition for measurement repetition is still satisfied, the second apparatus 120 may determine to further update the model. In some example embodiments, the second apparatus 120 may transmit at least one further request for at least one measurement repetition associated with the model functionality to the at least one first apparatus 110. For example, the second apparatus 120 may initiate a new set of measurement repetition requests in case of detected model monitoring assertions. In this way, the second apparatus 120 may determine the first apparatus-side model predictions performance while performing second apparatus-side model monitoring and may initiate a new set of measurement repetition requests in case of detected model monitoring assertions.

[0132] If the at least one condition for measurement repetition is not satisfied, the second apparatus 120 may cause termination of updating of the model for deriving the outcome of the model functionality. For example, if at time t + 1, the predicted best beam ^t+i matches with the ground truth best beam / Cj+1, it may indicate that the prediction function is capable to provide accurate predictions. In other words, the model monitoring assertions are not detected. In such cases, no further measurement repetition requests may be transmitted by the second apparatus 120.

[0133] Alternatively, or in addition, in some example embodiments, the second apparatus 120 may transmit at least one indication to the at least one first apparatus 110. In an example, an indication transmitted to a certain first apparatus 110 may indicate that a monitoring of the model functionality or a monitoring of the model is passed. For example, the indication may indicate that the model assertion is passed or undetected during monitoring. The first apparatus 110 may determine, based on the received indication, that the model is not to be further updated. In another example, the at least one indication may indicate that the model for deriving an outcome of the model functionality is not to be further updated.

[0134] In this way, the second apparatus 120 may determine the model predictions performance at the first apparatus 110 while performing model monitoring at the second apparatus 120 and may terminate the transmission of measurement repetition requests in case of undetected model monitoring assertions.

[0135] With the signaling diagram 500, the model implemented at the first apparatus 110 may be updated based on the repeated measurements. The repeated measurementsmay improve the data collection for training and updating the model for the model functionality.

[0136] Example embodiments regarding measurement repetition and model functionality updating based on the repeated measurements have been described. In some example embodiments, the second apparatus 120 or the first apparatus 110 may train a new version of the model by transferring the parameters of the source model to a second model. The second apparatus 120 or the first apparatus 110 may determine the parameters to transfer based on the model monitoring assertions results. For purpose of illustration, in the following example embodiments, the updating of the model will be implemented by the second apparatus 120.

[0137] In an example, if monitoring results fail for most of the first apparatuses that are served with the model, the second apparatus 120 may transfer pre-trained model parameters considering a backup version of the model created before asserting the changes of the model monitoring performance, or by considering a model trained in another sector, or trained by the network from multiple sectors that may include or not include the sector of the second apparatus 120, or trained from any entities including digital versions of the second apparatus 120.

[0138] In another example, if failing for one or a few more first apparatuses 110 that are served with the model, the second apparatus 120 may transfer pre-trained model parameters that relate to first apparatuses 110 not failing the model monitoring assertions.

[0139] The second apparatus 120 may train, re-train and / or fine-tune the new version of the model including non-trained model parameters based on the input and / or output data corresponding to the first apparatuses 110 failing model monitoring assertions.

[0140] In some example embodiments, data may be collected from the same sector, or acquired by the network in another sector, or acquired by the network from multiple sectors that may include or not include the sector of the second apparatus 120, or synthetically generated by a digital version of the network. Non-trained model parameters may be added to the model and trained with such data. Pre-trained and non-trained model parameters may be fine-tuned with such data by adopting a low learning rate.

[0141] FIG. 6 illustrates a diagram 600 illustrating the updating of a model according to some example embodiments of the present disclosure. It is assumed that in the exampleof FIG. 6, the updating of the model is implemented by the second apparatus 120. In the example of diagram 600, a model 610 may be updated to a model 620. In the example of FIG. 6, model parameters transferred from a previously trained model of a same sector may be used. For example, the updating of the model may use updated data from the first apparatuses 110 failing monitoring. The parameters from layers 1, 2, 3 may be transferred from a previously trained model 610 of the same sector and kept frozen (non-trainable) during training, whereas new layers are added and trained with the updated data.

[0142] FIG. 7 illustrates another diagram 700 illustrating the updating of a model according to some example embodiments of the present disclosure. It is assumed that in the example of FIG. 7, the updating of the model is implemented by the second apparatus 120. In the example of diagram 700, a model 710 may be updated to a model 720. In the example of FIG. 7, model parameters transferred from a trained model of another sector may be used. For example, the model monitoring at the second apparatus 120 such as a NW node B may fail for most first apparatuses 110. In this case, the second apparatus 120 may transfer pre-trained model parameters considering a model trained in another sector, e.g., served with NW node A. The parameters from layers 1, 2, 3 may be transferred from NW node A to NW node B. Then all layers may be trained with the updated data from NW node B .

[0143] In some example embodiments, the second apparatus 120 may change the configuration of transferred layers as trainable or non-trainable (kept frozen) during the ML model update operation depending on the model updating results.

[0144] In an example, if the size of the beam set is different from the size of the beam set defined in the initial configuration, the number of units in the output layer of the ML model B may be adapted to the size of the beam set in the target configuration.

[0145] In another example, the subset of beams measured for the ML model input may be fixed or selected randomly from the entire set of beams to predict. The maximum number of measurements used as the ML model input and may be equal to the size of the output layer, nevertheless the input of the non-measured beams may be forced to zeros.

[0146] Several example embodiments regarding updating the model at the second apparatus 120 have been described. It is to be understood that the model may be updated at the first apparatus 110, or at a device or server communicatively connected with the first apparatus 110 in a similar manner. For example, the updating of the model may beimplemented by a server for the first apparatus 110, and managed by the first apparatus 110. In this way, the update of the model can be carried out based on the transfer learning approach. The dataset used to update the model may be defined considering the model monitoring assertion results.

[0147] It would be appreciated that some example specifications and embodiments are provided above, and the detailed description may be varied. It is to be understood that these signaling diagrams 200, 300 and 500, the process 400, and the diagrams 600 and 700 for updating the model can be used in any suitable combinations. In this manner, a plurality of repeated measurements is request by the second apparatus 120 and performed by the first apparatuses 110. Based on the repeated measurement results, the model functionality can be improved. For example, the model for deriving an outcome of the model functionality may be updated based on the repeated measurements. Accordingly, a more accurate outcome of the model functionality can be achieved. The performance of the model functionality can thus be enhanced.

[0148] FIG. 8 shows a flowchart of an example method 800 implemented at a first apparatus, such as a terminal device, in accordance with some example embodiments. For purpose of discussion, the method 800 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0149] At block 810, the first apparatus 110 receives, from a second apparatus such as the second apparatus 120, a request for a measurement repetition associated with a model functionality.

[0150] At block 820, in response to receiving the request, the first apparatus 110 repeats measurements associated with the model functionality.

[0151] At block 830, the first apparatus 110 transmits information related to the repeated measurements to the second apparatus.

[0152] In some example embodiments, the first apparatus 110 is further caused to: receive, from the second apparatus, a configuration for one or more reference signals associated with the measurement repetition; and repeat the measurements for the one or more reference signals based on the configuration.

[0153] In some example embodiments, the first apparatus is further caused to: update, based on a result of the repeated measurements, a model for deriving an outcome of themodel functionality; obtain the outcome of the model functionality with the updated model; and transmit, to the second apparatus, the information including the outcome of the model functionality.

[0154] In some example embodiments, the first apparatus is further caused to: receive, from the second apparatus, an indication indicating at least one of: a monitoring of the model functionality being passed, or a model for deriving an outcome of the model functionality being not to be updated.

[0155] In some example embodiments, the first apparatus is further caused to: transmit, to the second apparatus, the information including a result of the repeated measurements.

[0156] In some example embodiments, the model functionality comprises beam prediction from a model.

[0157] FIG. 9 shows a flowchart of an example method 900 implemented at a second apparatus, such as a network device, in accordance with some example embodiments. For purpose of discussion, the method 900 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0158] At block 910, the second apparatus 120 transmits, to at least one first apparatus such as at least one first apparatus 110, at least one request for at least one measurement repetition associated with a model functionality.

[0159] At block 920, the second apparatus 120 receives, from the at least one first apparatus, at least one information related to repeated measurements performed by the at least one first apparatus.

[0160] In some example embodiments, the second apparatus is further caused to: for a first apparatus of the at least one first apparatus, transmit, to the first apparatus, a configuration for one or more reference signals associated with the measurement repetition of the first apparatus.

[0161] In some example embodiments, the second apparatus is further caused to: determine a monitoring result of the model functionality based on a measurement result from the first apparatus; and determine the one or more reference signals associated with the measurement repetition based on the monitoring result of the model functionality.

[0162] In some example embodiments, the second apparatus is further caused to: obtainat least one predicted beam for the first apparatus, the at least one predicted beam being provided by the model functionality; determine at least one serving beam based on the measurement result from the first apparatus; and determine the one or more reference signals based on the at least one predicted beam and the at least one serving beam.

[0163] In some example embodiments, the second apparatus is further caused to: determine a plurality of candidate beams for the first apparatus; and determine the one or more reference signals associated with the measurement repetition based on one or more candidate beams in the plurality of candidate beams.

[0164] In some example embodiments, the second apparatus is further caused to: receive, from the at least one first apparatus, the at least one information including at least one result of repeated measurements; and update, based on the at least one result of the repeated measurements, a model for deriving an outcome of the model functionality.

[0165] In some example embodiments, the second apparatus is further caused to: receive, from the at least one first apparatus, the at least one information including at least one outcome of the model functionality.

[0166] In some example embodiments, the second apparatus is further caused to: transmit the at least one request for the at least one measurement repetition based on at least one condition for measurement repetition being satisfied, the at least one condition for measurement repetition being associated with at least one of: at least one monitoring result of the model functionality, the at least monitoring result being associated with at least one measurement result from the at least one first apparatus, at least one outcome of the model functionality, the at least one outcome being associated with the at least one first apparatus, or a model assertion for monitoring an outcome of the model functionality.

[0167] In some example embodiments, the at least one condition for measurement repetition comprises at least one of: a first condition that the number of reliable monitoring results of the at least one monitoring result is less than or equal to a first threshold number, a second condition that the number of the at least one monitoring result with a monitoring performance value being less than a threshold value is equal to or greater than a second threshold number, a third condition that the number of failure events of the model functionality within a monitoring time interval is equal to or greater than a third threshold number, a fourth condition that the number of at least one outcome of the model functionality mismatching with a reference outcome is equal to or greater than a fourththreshold number, or a fifth condition that an outcome of the model functionality associated with a first apparatus of the at least one first apparatus mismatches with a reference outcome.

[0168] In some example embodiments, the second apparatus is further caused to: for a monitoring result associated with a first apparatus of the at least one first apparatus, determine whether the monitoring result is reliable based on at least one of: a distribution of measurement results from the first apparatus, a variation of conditions of the first apparatus, or a change of confidence errors associated with the first apparatus.

[0169] In some example embodiments, the second apparatus is further caused to: determine at least one of the first, second, third or fourth threshold number based on at least one of: the monitoring time interval, or the monitoring performance value associated with a predetermined number of failure events of the model functionality.

[0170] In some example embodiments, the second apparatus is further caused to: determine, based on the at least one information, whether the at least one condition for measurement repetition is satisfied; and in accordance with a determination that the at least one condition is not satisfied, cause termination of updating of a model for deriving an outcome of the model functionality.

[0171] In some example embodiments, the second apparatus is further caused to: in accordance with a determination that the at least one condition for measurement repetition is not satisfied, transmit, to the at least one first apparatus, at least one indication indicating at least one of: a monitoring of the model functionality being passed, or a model for deriving an outcome of the model functionality being not to be updated.

[0172] In some example embodiments, the second apparatus is further caused to: determine, based on the at least one information, whether the at least one condition for measurement repetition is satisfied; and in accordance with a determination that the at least one condition for measurement repetition is satisfied, transmit at least one further request for the at least one measurement repetition associated with the model functionality.

[0173] In some example embodiments, the model functionality comprises beam prediction.

[0174] In some example embodiments, a first apparatus configured to perform any of the method 800 (e.g., the first apparatus 110 in FIG. 1) may comprise means forperforming 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.

[0175] In some example embodiments, the first apparatus comprises means for receiving, from a second apparatus such as the second apparatus 120, a request for a measurement repetition associated with a model functionality; means for in response to receiving the request, repeating measurements associated with the model functionality; and means for transmitting information related to the repeated measurements to the second apparatus.

[0176] In some example embodiments, the first apparatus further comprises means for receiving from the second apparatus, a configuration for one or more reference signals associated with the measurement repetition; and means for repeating the measurements for the one or more reference signals based on the configuration.

[0177] In some example embodiments, the first apparatus further comprises means for updating, based on a result of the repeated measurements, a model for deriving an outcome of the model functionality; means for obtaining the outcome of the model functionality with the updated model; and means for transmitting, to the second apparatus, the information including the outcome of the model functionality.

[0178] In some example embodiments, the first apparatus further comprises means for receiving, from the second apparatus, an indication indicating at least one of: a monitoring of the model functionality being passed, or a model for deriving an outcome of the model functionality being not to be updated.

[0179] In some example embodiments, the first apparatus further comprises means for transmitting, to the second apparatus, the information including a result of the repeated measurements.

[0180] In some example embodiments, the model functionality comprises beam prediction from a model.

[0181] In some example embodiments, the first apparatus further comprises means for performing other operations in some example embodiments of the method 800 or the first apparatus 110. In some example embodiments, the means comprises at least one processor;and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the first apparatus.

[0182] In some example embodiments, a second apparatus configured to perform any of the method 900 (e.g., the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 900. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0183] In some example embodiments, the second apparatus comprises means for transmitting, to at least one first apparatus such as at least one first apparatus 110, at least one request for at least one measurement repetition associated with a model functionality; and means for receiving, from the at least one first apparatus, at least one information related to repeated measurements performed by the at least one first apparatus.

[0184] In some example embodiments, the second apparatus further includes means for transmitting, to a first apparatus of the at least one first apparatus, a configuration for one or more reference signals associated with the measurement repetition of the first apparatus.

[0185] In some example embodiments, the second apparatus further includes means for determining a monitoring result of the model functionality based on a measurement result from the first apparatus; and means for determining the one or more reference signals associated with the measurement repetition based on the monitoring result of the model functionality.

[0186] In some example embodiments, the second apparatus further includes means for obtaining at least one predicted beam for the first apparatus, the at least one predicted beam being provided by the model functionality; means for determining at least one serving beam based on the measurement result from the first apparatus; and means for determining the one or more reference signals based on the at least one predicted beam and the at least one serving beam.

[0187] In some example embodiments, the second apparatus further includes means for determining a plurality of candidate beams for the first apparatus; and means for determining the one or more reference signals associated with the measurement repetition based on one or more candidate beams in the plurality of candidate beams.

[0188] In some example embodiments, the second apparatus further includes means for receiving, from the at least one first apparatus, the at least one information including at least one result of repeated measurements; and means for updating, based on the at least one result of the repeated measurements, a model for deriving an outcome of the model functionality.

[0189] In some example embodiments, the second apparatus further includes means for receiving, from the at least one first apparatus, the at least one information including at least one outcome of the model functionality.

[0190] In some example embodiments, the second apparatus further includes means for transmitting the at least one request for the at least one measurement repetition based on at least one condition for measurement repetition being satisfied, the at least one condition for measurement repetition being associated with at least one of: at least one monitoring result of the model functionality, the at least monitoring result being associated with at least one measurement result from the at least one first apparatus, at least one outcome of the model functionality, the at least one outcome being associated with the at least one first apparatus, or a model assertion for monitoring an outcome of the model functionality.

[0191] In some example embodiments, the at least one condition for measurement repetition comprises at least one of: a first condition that the number of reliable monitoring results of the at least one monitoring result is less than or equal to a first threshold number, a second condition that the number of the at least one monitoring result with a monitoring performance value being less than a threshold value is equal to or greater than a second threshold number, a third condition that the number of failure events of the model functionality within a monitoring time interval is equal to or greater than a third threshold number, or a fourth condition that the number of at least one outcome of the model functionality mismatching with a reference outcome is equal to or greater than a fourth threshold number, or a fifth condition that an outcome of the model functionality associated with a first apparatus of the at least one first apparatus mismatches with a reference outcome.

[0192] In some example embodiments, the second apparatus further includes means for determining, for a monitoring result associated with a first apparatus of the at least one first apparatus, whether the monitoring result is reliable based on at least one of: a distribution of measurement results from the first apparatus, a variation of conditions ofthe first apparatus, or a change of confidence errors associated with the first apparatus.

[0193] In some example embodiments, the second apparatus further includes means for determining at least one of the first, second, third or fourth threshold number based on at least one of: the monitoring time interval, or the monitoring performance value associated with a predetermined number of failure events of the model functionality.

[0194] In some example embodiments, the second apparatus further includes means for determining, based on the at least one information, whether the at least one condition for measurement repetition is satisfied; and means for in accordance with a determination that the at least one condition for measurement repetition is not satisfied, causing termination of updating of a model for deriving an outcome of the model functionality.

[0195] In some example embodiments, the second apparatus further includes means for in accordance with a determination that the at least one condition for measurement repetition is not satisfied, transmitting, to the at least one first apparatus, at least one indication indicating at least one of: a monitoring of the model functionality being passed, or a model for deriving an outcome of the model functionality being not to be updated.

[0196] In some example embodiments, the second apparatus further includes means for determining, based on the at least one information, whether the at least one condition for measurement repetition is satisfied; and means for in accordance with a determination that the at least one condition for measurement repetition is satisfied, transmitting at least one further request for the at least one measurement repetition associated with the model functionality.

[0197] In some example embodiments, the model functionality comprises beam prediction from a model.

[0198] In some example embodiments, the second apparatus further comprises means for performing other operations in some example embodiments of the method 900 or the second apparatus 120. In some example embodiments, the means comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the second apparatus.

[0199] FIG. 10 is a simplified block diagram of a device 1000 that is configured to implement some example embodiments described herein. The device 1000 may be provided to implement a communication device, for example, the first apparatus 110 orthe second apparatus 120 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.

[0200] 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 utilized for communication with other network elements. In some example embodiments, the communication module 1040 may include at least one antenna.

[0201] 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.

[0202] 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.

[0203] 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. 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.

[0204] The example embodiments 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. 2 to FIG. 9. The example embodiments may also be implemented byhardware or by a combination of software and hardware.

[0205] 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 (e.g., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0206] 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.

[0207] Various example embodiments may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of the example embodiments 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.

[0208] Some example embodiments 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. Program modules may include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for programmodules 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.

[0209] Program code for carrying out methods 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.

[0210] In the context, 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.

[0211] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0212] 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 example embodiments, but rather as descriptions of features that may be specific to particular example embodiments. Unless explicitly stated, certain features that aredescribed in the context of separate example embodiments may also be implemented in combination in a single example embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single example embodiment may also be implemented in a plurality of example embodiments separately or in any suitable sub-combination.

[0213] Although various example embodiments of the subject disclosure have been described in language specific to structural features and / or methodological acts, it is to be understood that the various example embodiments of the subject disclosure are not 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 various example embodiments of the subject disclosure.

Claims

WHAT IS CLAIMED IS:

1. A first apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus to: receive, from a second apparatus, a request for a measurement repetition associated with a model functionality; in response to receiving the request, repeat measurements associated with the model functionality; and transmit information related to the repeated measurements to the second apparatus.

2. The first apparatus of claim 1, wherein the first apparatus is further caused to: receive, from the second apparatus, a configuration for one or more reference signals associated with the measurement repetition; and repeat the measurements for the one or more reference signals based on the configuration.

3. The first apparatus of claim 1 or claim 2, wherein the first apparatus is further caused to: update, based on a result of the repeated measurements, a model for deriving an outcome of the model functionality; obtain the outcome of the model functionality with the updated model; and transmit, to the second apparatus, the information including the outcome of the model functionality.

4. The first apparatus of claim 3, wherein the first apparatus is further caused to: receive, from the second apparatus, an indication indicating at least one of: a monitoring of the model functionality being passed, or a model for deriving an outcome of the model functionality being not to be updated.

5. The first apparatus of claim 1 or claim 2, wherein the first apparatus is further caused to: transmit, to the second apparatus, the information including a result of the repeated measurements.

6. The first apparatus of any of claims 1-5, wherein the model functionality comprises beam prediction from a model.

7. A second apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus to: transmit, to at least one first apparatus, at least one request for at least one measurement repetition associated with a model functionality; and receive, from the at least one first apparatus, at least one information related to repeated measurements performed by the at least one first apparatus.

8. The second apparatus of claim 7, wherein the second apparatus is further caused to: for a first apparatus of the at least one first apparatus, transmit, to the first apparatus, a configuration for one or more reference signals associated with the measurement repetition of the first apparatus.

9. The second apparatus of claim 8, wherein the second apparatus is further caused to: determine a monitoring result of the model functionality based on a measurement result from the first apparatus; and determine the one or more reference signals associated with the measurement repetition based on the monitoring result of the model functionality.

10. The second apparatus of claim 8, wherein the second apparatus is further caused to: obtain at least one predicted beam for the first apparatus, the at least one predicted beam being provided by the model functionality; determine at least one serving beam based on the measurement result from the first apparatus; anddetermine the one or more reference signals associated with the measurement repetition based on the at least one predicted beam and the at least one serving beam.

11. The second apparatus of claim 8, wherein the second apparatus is further caused to: determine a plurality of candidate beams for the first apparatus; and determine the one or more reference signals associated with the measurement repetition based on one or more candidate beams of the plurality of candidate beams.

12. The second apparatus of any of claims 7-11, wherein the second apparatus is further caused to: receive, from the at least one first apparatus, the at least one information including at least one result of repeated measurements; and update, based on the at least one result of the repeated measurements, a model for deriving an outcome of the model functionality.

13. The second apparatus of any of claims 7-11, wherein the second apparatus is further caused to: receive, from the at least one first apparatus, the at least one information including at least one outcome of the model functionality.

14. The second apparatus of any of claims 7-13, wherein the second apparatus is further caused to: transmit the at least one request for the at least one measurement repetition based on at least one condition for measurement repetition being satisfied, the at least one condition for measurement repetition being associated with at least one of: at least one monitoring result of the model functionality, the at least monitoring result being associated with at least one measurement result from the at least one first apparatus, or at least one outcome of the model functionality, the at least one outcome being associated with the at least one first apparatus, or a model assertion for monitoring an outcome of the model functionality.

15. The second apparatus of claim 14, wherein the at least one condition for measurement repetition comprises at least one of:a first condition that the number of reliable monitoring results of the at least one monitoring result is less than or equal to a first threshold number, a second condition that the number of the at least one monitoring result with a monitoring performance value being less than a threshold value is equal to or greater than a second threshold number, a third condition that the number of failure events of the model functionality within a monitoring time interval is equal to or greater than a third threshold number, a fourth condition that the number of at least one outcome of the model functionality mismatching with a reference outcome is equal to or greater than a fourth threshold number, or a fifth condition that an outcome of the model functionality associated with a first apparatus of the at least one first apparatus mismatches with a reference outcome.

16. The second apparatus of claim 15, wherein the second apparatus is further caused to: for a monitoring result associated with a first apparatus of the at least one first apparatus, determine whether the monitoring result is reliable based on at least one of: a distribution of measurement results from the first apparatus, a variation of conditions of the first apparatus, or a change of confidence errors associated with the first apparatus.

17. The second apparatus of claim 15 or claim 16, wherein the second apparatus is further caused to: determine at least one of the first, second, third or fourth threshold number based on at least one of: the monitoring time interval, or the monitoring performance value associated with a predetermined number of failure events of the model functionality.

18. The second apparatus of any of claims 15-17, wherein the second apparatus is further caused to: determine, based on the at least one information, whether the at least one condition for measurement repetition is satisfied; and in accordance with a determination that the at least one condition is not satisfied, cause termination of updating of a model for deriving an outcome of the model functionality.

19. The second apparatus of claim 18, wherein the second apparatus is further caused to: in accordance with a determination that the at least one condition for measurement repetition is not satisfied, transmit, to the at least one first apparatus, at least one indication indicating at least one of: a monitoring of the model functionality being passed, or a model for deriving an outcome of the model functionality being not to be updated.

20. The second apparatus of any of claims 15-19, wherein the second apparatus is further caused to: determine, based on the at least one information, whether the at least one condition for measurement repetition is satisfied; and in accordance with a determination that the at least one condition is satisfied, transmit at least one further request for the at least one measurement repetition associated with the model functionality.

21. The second apparatus of any of claims 7-20, wherein the model functionality comprises beam prediction from a model.

22. A method comprising: receiving, at a first apparatus from a second apparatus, a request for a measurement repetition associated with a model functionality; in response to receiving the request, repeating measurements associated with the model functionality; and transmitting information related to the repeated measurements to the second apparatus.

23. A method comprising: transmitting, at a second apparatus to at least one first apparatus, at least one request for at least one measurement repetition associated with a model functionality; and receiving, from the at least one first apparatus, at least one information related to repeated measurements performed by the at least one first apparatus.

24. An apparatus comprising:means for receiving, from a second apparatus, a request for a measurement repetition associated with a model functionality; means for in response to receiving the request, repeating measurements associated with the model functionality; and means for transmitting information related to the repeated measurements to the second apparatus.

25. An apparatus comprising: means for transmitting, to at least one first apparatus, at least one request for at least one measurement repetition associated with a model functionality; and means for receiving, from the at least one first apparatus, at least one information related to repeated measurements performed by the at least one first apparatus.

26. A computer readable medium comprising instructions stored thereon for causing an apparatus at least to perform the method of claim 22 or the method of claim 23.

Images