Devices, methods, apparatuses and media for radio resource management prediction timing configuration update

Abstract

Embodiments of the present disclosure relate to devices, methods, apparatuses and medium for radio resource management (RRM) prediction timing configuration update. In an aspect, a terminal device transmits, to a network device, a RRM measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, the configuration information indicates at least one of an observation window length or a prediction window length, the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. The terminal device receives, from the network device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling, wherein the updated configuration information is updated based on the RRM measurement prediction report.

Description

DEVICES, METHODS, APPARATUSES AND MEDIA FOR RADIO RESOURCE MANAGEMENT PREDICTION TIMING CONFIGURATION UPDATEFIELD

[0001] Various example embodiments generally relate to the field of communication, and in particular, to devices, terminal devices, network devices, methods, apparatuses and computer readable storage media related to radio resource management (RRM) prediction timing configuration update.BACKGROUND

[0002] A communication network can be seen as a facility that enables communications between two or more communication devices, or provides communication devices access to a data network. A mobile or wireless communication network is one example of a communication network.

[0003] Such communication networks operate in accordance with standards, such as those promulgated by 3GPP (Third Generation Partnership Project) or ETSI (European Telecommunications Standards Institute). Examples of such standards include the so-called 5G (5th Generation) standard or other standards promulgated by 3GPP.SUMMARY

[0004] In general, example embodiments of the present disclosure provide devices, terminal devices, network devices, methods, apparatuses and computer readable storage media for communication, for example, for RRM prediction timing configuration update, especially for update of RRM observation windows and prediction windows.BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0006] FIG. 1 illustrates an example of an application scenario in which some example embodiments of the present disclosure may be implemented;

[0007] FIG. 2 illustrates an example simplified block diagram of a device that is suitable for implementing RRM prediction timing configuration update according to some embodiments of the present disclosure;

[0008] FIG. 3 illustrates an example signaling process for RRM prediction timing configuration update between a terminal device and a network device according to some embodiments of the present disclosure;

[0009] FIG. 4 illustrates an example signaling process for RRM prediction timing configuration update between a terminal device and a network device according to some other embodiments of the present disclosure;

[0010] FIG. 5 illustrates an example signaling process for static / semi-static RRM prediction timing configuration update between a user equipment (UE) and a gNB according to some embodiments of the present disclosure;

[0011] FIG. 6 illustrates an example signaling process for dynamic RRM prediction timing configuration update between a UE and a gNB according to some embodiments of the present disclosure;

[0012] FIG. 7 illustrates an example signaling process for UE autonomous RRM prediction timing configuration update between a UE and a gNB according to some embodiments of the present disclosure;

[0013] FIG. 8 illustrates a static solution for RRM prediction timing configuration update loop according to some embodiments of the present disclosure;

[0014] FIG. 9 illustrates a heuristic solution for RRM prediction timing configuration update loop according to some embodiments of the present disclosure;

[0015] FIG. 10 illustrates a reinforcement learning (RL) solution for RRM prediction timing configuration update loop according to some embodiments of the present disclosure;

[0016] FIG. 11 illustrates an example diagram for observation and prediction windows selection according to some embodiments of the present disclosure;

[0017] FIG. 12A illustrates an example diagram of cumulative distribution function (CDF) of mean absolute error (MAE) for three different solutions for RRM prediction timing configuration update according to some embodiments of the present disclosure;

[0018] FIG. 12B illustrates an example diagram of mean MAE for three different solutions for RRM prediction timing configuration update according to some embodiments of the present disclosure;

[0019] FIG. 13 illustrates a flowchart of an example method implemented at a terminal device in accordance with some embodiments of the present disclosure;

[0020] FIG. 14 illustrates a flowchart of an example method implemented at a network device in accordance with some embodiments of the present disclosure;

[0021] FIG. 15 illustrates a flowchart of an example method implemented at a terminal device in accordance with some other embodiments of the present disclosure;

[0022] FIG. 16 illustrates a flowchart of an example method implemented at a network device in accordance with some other embodiments of the present disclosure;

[0023] FIG. 17 illustrates an example simplified block diagram of a device that is suitable for implementing embodiments of the present disclosure; and

[0024] FIG. 18 illustrates an example block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0025] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION

[0026] Principles of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. The disclosure described herein may be implemented in various manners other than the ones described below.

[0027] 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 the present disclosure belongs.

[0028] 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.

[0029] It may be understood that although the terms “first”, “second”, “third”, “fourth” etc. 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.

[0030] 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. 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.

[0031] 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.

[0032] 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 basebandintegrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0033] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as new radio (NR), long term evolution (LTE), LTE-advanced (LTE-A), wideband code division multiple access (WCDMA), high-speed packet access (HSPA), narrow band Internet of things (NB-loT) and so on. Furthermore, the communications between a 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 third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G) communication protocols, the sixth generation (6G) communication protocols, and / or beyond. 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.

[0034] As used herein, the term “network 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), a NR NB (also referred to as a gNB), a transmit-receive point (TRP), a remote radio unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, a low power node such as afemto, a pico, an Integrated Access and Backhaul (I AB) node, 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.

[0035] 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 subscriber station (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 customer-premises equipment (CPE), an Internet of things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial, a relay node, an integrated access and backhaul (IAB) node, and / or industrial wireless networks, and the like. In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0036] As used herein, the term “resource”, “transmission resource”, “resource block”, “physical resource block” (PRB), “uplink (UL) resource” or “downlink (DL) 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, a resource in a combination of more than one domain or any other resource enabling a communication, and the like. In the following, a resource in time domain (such as, a subframe) 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.

[0037] In a communication technology, the third generation partnership project (3GPP) discusses two RRM measurement prediction cases in the temporal domain (i.e., Case A and Case B) for artificial intelligence / machine learning (AI / ML) mobility, which adopts observation windows and prediction windows. The observation windows are used for gathering RRM measurement results, which are used for predicting RRM measurements results for the prediction windows. The choice of window length for both observation and prediction would significantly impact the performance of AI / ML model for the temporal RRM measurement prediction. For observation windows, increasing the observation window length can offer more data points for the model to learn from, potentially leading to improved accuracy. However, once the observation window length exceeds a certain threshold, further increasing the observation window length would not yield significant benefits. For prediction windows, larger windows will increase prediction errors, resulting decreased prediction accuracy. Therefore, employing a constant window length for observation windows and / or prediction windows is suboptimal for dynamic mobility and radio environments, as it fails to achieve an optimal balance between artificialintelligence / machine learning (AI / ML) performance and measurement reduction gain. However, how to configure and update the observation window and prediction window lengths needs to be studied.

[0038] Therefore, some example embodiments of the present disclosure provide a solution for update of RRM observation windows and prediction windows. According to these embodiments of the present disclosure, a device (e.g., a UE or a gNB) obtains configuration information related to radio resource management (RRM) measurement prediction. The configuration information indicates at least one of an observation window length or a prediction window length. The observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. Afterwards, the device updates the configuration information based on predicted RRM measurement results.

[0039] It is understood that the above procedure steps may work together, in a flow of operations as described below, partly together or independently of each other. By implementing these embodiments of the present disclosure, the device (e.g., a UE or a gNB) could update the configuration information related to radio RRM measurement prediction based on the predicted RRM measurement results predicated based on an initial observation window length and / or a prediction window length, thereby providing dynamic and adaptable configuration update and achieving a robust time domain RRM measurement prediction configuration update solution.

[0040] Furthermore, some other example embodiments of the present disclosure provide a solution for update of RRM observation windows and prediction windows by the network device. According to these embodiments of the present disclosure, a terminal device (e.g., a UE) transmits, to a network device (e.g., a gNB), a radio resource management (RRM) measurement prediction report. The RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction. The configuration information indicates at least one of an observation window length or a prediction window length. The observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. Then, the network device updates the configuration information based on the RRM measurement prediction report. The updated configuration information comprises at least one of an updated observation window length and an updated prediction window length. In turn, the terminal device receives, from the network device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling.

[0041] It is understood that the above procedure steps may work together, in a flow of operations as described below, partly together or independently of each other. By implementing these embodiments of the present disclosure, the network device (e.g., a gNB) could update the configuration information related to radio RRM measurement prediction based on the predicted RRM measurement results predicated based on an initial observation window length and / or a prediction window length, thereby providing dynamic and adaptable configuration update and achieving a robust time domain RRM measurement prediction configuration update solution.

[0042] Still furthermore, yet other example embodiments of the present disclosure provide a solution for update of RRM observation windows and prediction windows by the terminal device. According to these embodiments of the present disclosure, a terminal device (e.g., a UE) receives, from a network device (e.g., a gNB), configuration information related to radio resource management (RRM) measurement prediction. The configuration information indicates at least one of an observation window length or a prediction window length. The observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. Then, the terminal device updates the configuration information related to RRM measurement prediction based on predicted RRM measurement results.

[0043] It is understood that the above procedure steps may work together, in a flow of operations as described below, partly together or independently of each other. By implementing these embodiments of the present disclosure, the terminal device (e.g., a UE) could autonomously update the configuration information related to radio RRM measurement prediction based on the predicted RRM measurement results predicated based on an initial observation window length and / or a prediction window length, thereby providing dynamic and adaptable configuration update and achieving a robust time domain RRM measurement prediction configuration update solution.

[0044] For illustrative purposes, principles and example embodiments of the present disclosure of update of RRM observation windows and prediction windows will be described below with reference to FIG. 1 through FIG. 18. However, it is to be noted that these embodiments are given to enable the skilled in the art to understand inventive concepts of the present disclosure and implement the solution as proposed herein, and not intended to limit scope of the present application in any way.

[0045] FIG. 1 illustrates an example of an application scenario 100 in which some example embodiments of the present disclosure may be implemented. The network environment 100, which may be a part of a communication network, includes a terminal device 102 and a network device 104.

[0046] As illustrated in FIG. 1, the terminal device 102 may also be referred to as a user equipment 102 or a UE 102. The network device 104 may also be referred to as a gNB 104. The terminal device 102 and the network device 104-1 can communicate with each other. The network device 104 could provide a cell for serving the terminal device 102. The terminal device may gather RRM measurement results during observation windows and predict RRM measurement results for following prediction windows based on the previously gathered RRM measurement results. Although FIG. 1 only shows one terminal device 102 and one network device 104, it should be understood that this is only for illustration, not limitation. FIG. 1 may comprise more terminal devices and network devices.

[0047] FIG. 2 illustrates an example simplified block diagram 200 of a device (for example, a terminal device or a network device) that is suitable for implementing RRM prediction timing configuration update according to some embodiments of the present disclosure. FIG. 2 may be performed by the terminal device 102 or the network device 104 in FIG. 1.

[0048] At 210, the device may obtain configuration information related to radio resource management (RRM) measurement prediction. The configuration information may indicate at least one of an observation window length or a prediction window length. The observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. The configuration information may be initial configuration information. Prediction of RRM measurement results may be performed iteratively based on an AI / ML model. By term “obtain” it is meant that the device may e.g. determine such configuration or receive such configuration from another device.

[0049] In some example embodiments, the observation window length and the prediction window length may be in a unit of millisecond (ms). The observation window may define a number of samples used as input for the AL / ML model that is used to predict the RRM measurement results, such as reference signal receiving power (RSRP), for the duration of the prediction window, thus controlling an amount of data a UE actually measures and uses as the input. For example, the initial observation window length might be aligned with a periodicity of sounding reference signals (SRSs) or channel state information-reference signals (CSI-RSs). Alternatively, the initial observation window length may be aligned with a periodicity of synchronization block (SSB) to measure. The prediction window may determine a number of samples that an AI / ML model outputs as predicted RRM measurements. A larger prediction window generally provides more insights for decision-making. However, factors like UE speed and accuracy may impact effectiveness of decision-making. Therefore, a careful design is required to determine an optimal observation window length and / or an optimal prediction window length,so as to balance ML accuracy with a desired timing margin for decision-making such as handover or failure handling.

[0050] In some example embodiments, the configuration information may further comprise prediction triggering information, causing periodic triggering, aperiodic triggering, or event-based triggering. As one example, when the periodic triggering is caused, the prediction triggering information may comprise prediction periodicity (e.g., in ms) and prediction steps / frequency (in number of samples). As another example, when the aperiodic triggering is caused, the prediction triggering information may comprise the time for performing prediction. As yet another example, when the event-based triggering is caused, the prediction triggering information may comprise measurement event triggering conditions, such as A2, A3 or A5 conditions if inter-frequency measurements are configured, or the start of T310 timer for radio link failure (RLF) prediction. In addition, the network may configure a dedicated threshold to trigger the prediction.

[0051] Alternatively or additionally, the configuration information may further comprise prediction reporting configuration, indicating at least one of: a reporting criterion, at least one reporting content type, or a reporting format. The reporting criterion may comprise periodic reporting, a periodic reporting, or event-based reporting. As one example, when the periodic reporting is caused, the prediction reporting information may comprise reporting periodicity (e.g., in ms), which may be aligned with prediction periodicity. As another example, when the aperiodic reporting is caused, the prediction reporting information may comprise the time for reporting. As yet another example, when the eventbased reporting is caused, the prediction reporting information may comprise event reporting conditions, such as A2, A3 or A5 conditions if inter-frequency measurements are configured, or the start of T310 timer for radio link failure (RLF) prediction. In addition, the network may configure semi-persistent reporting. The reporting content type may be predicted measurements with accuracy (e.g., in percentage), which may be used to update the configuration information. The policies for updating the configuration information may also be included in the reporting contents. The reporting format may be a continuous reporting or a quantized reporting. Based on the prediction reporting configuration, the terminal device may report e.g. the prediction results to the network.

[0052] In some example embodiments, the device may obtain (e.g. determine or receive) capability information. The capability information may comprise information indicating that the device supports an update of the configuration information. Alternatively or additionally, the capability information may indicate a supported update solution type for updating the configuration information. The update solution type may be one of: a static solution, a heuristic solution, and a reinforcement learning (RL) solution. That is, the update solution type may indicate which type or types of AI / ML assisted update ofthe configuration information the device is capable to perform. Alternatively or additionally, the capability information may indicate supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

[0053] In some example embodiments, the device may obtain (e.g. determine or receive) at least one performance indicator (e.g., key performance indicator (KPI)) related to potential update of the configuration information. The at least one performance indicator may indicate measurement errors between the predicted RRM measurement results and measured RRM measurement results. These measured RRM measurement results may be obtained by performing measurements during the prediction window, so as to determine whether the predicted values correspond to the measured values. Alternatively or additionally, the at least one performance indicator may indicate artificial intelligence / machine learning (AI / ML) related reliability prediction metrics, such as prediction accuracy or confidence in percentage (e.g., confidence in percentage that is estimated by the last layer of neural network such as signoid or softmax activation function), mean absolute error (MSE), mean squared logarithmic error (MSLE), mean absolute percentage error (MAPE), etc. Alternatively or additionally, the at least one performance indicator may indicate radio stability and mobility related metrics, such as mean time of staying outage (e.g., in ms), accumulated negative handover or beam management counters (e.g., handover failure, radio link failure, beam failure recovery), reduced capability (RedCap) UE like stationary conditions (e.g., low speed, cell edge, etc.), UE instantaneous signal to interference plus noise ratio (SINR)Zthroughput stability, other RRM related metrics (e.g., packet delay budget, XR UE happiness ratio), etc. Alternatively or additionally, the at least one performance indicator may indicate joint evaluation of both AI / ML metrics and radio stability and mobility related metrics.

[0054] In some example embodiments, the device may obtain (e.g. determine or receive) a RRM measurement prediction report. The RRM measurement prediction report may comprise the predicted RRM measurement results. The RRM measurement prediction report may be used for updating the configuration information.

[0055] In some example embodiments, the device may determine to update the configuration information related to RRM measurement prediction based on the predicted RRM measurement results. The device may determine to update the configuration information based on a static solution, a heuristic solution or a reinforcement learning (RL) solution.

[0056] When a static solution is adopted, the device may determine to update the configuration information in response to expiry of a validity time period for the configuration information. In other words, when the current prediction timing configuration information becomes outdated, the device would update the configuration information.

[0057] Alternatively, when a heuristic solution is adopted, the device may determine to update the configuration information in response to at least one predetermined condition being satisfied. The at least one condition comprises at least one of: measurement error performance (e.g., MAE in dB) falls below a pre-defined threshold; prediction error(s) exceed a prediction error threshold; mean absolute errors (MAEs) of predicted measurements exceed a MAE threshold; accumulated beam failure instances exceed an accumulated beam failure threshold; radio link failure (RLF) instances exceed a RLF threshold; ping-pong instances exceed a ping-pong threshold; out of specification (OOS) indications exceed an OOS threshold. The at least one predetermined condition and the thresholds may be configured by the network. Alternatively or additionally, multiple thresholds may be configured to map different prediction error tolerance levels to different delta values for window update / adaptation. This allows for more granular control over the window update process based on the severity of the prediction error. Alternatively or additionally, the device may determine to update the configuration information in response to a weighting factor of AI / ML metrics and radio / mobility related metrics is satisfied, so as to balance desired performance indication from both AI / ML and radio / mobility perspectives. This allows for a more holistic assessment of performance.

[0058] Alternatively, when a RL solution is adopted, the device may determine to update the configuration information using a RL policy. The network may configure RL specific parameters. The RL policy may use a neural network (e.g., Q-network) to learn an optimal window size by maximizing a reward function.

[0059] At 220, the device may update the configuration information based on predicted RRM measurement results. The updated configuration information may comprise at least one of an updated observation window length and an updated prediction window length. That is, due to the updating, at least one of the observation window length and prediction window length changes from the length(s) that was / were initially configured (e.g. based on the configuration information obtained in step 210 of FIG. 2). The device may transmit, to another device, at least one of: the updated observation window length, or the updated prediction window length. The device may be a terminal device and the another device may be a network device. Alternatively, the device may be a network device and the another device may be a terminal device.

[0060] In some example embodiments, the configuration information may comprise updating policy related parameters for the configuration information, which may be called as RRM prediction timing configuration (RPTC) updating policy related parameters. The updating policy related parameters for the configuration information may comprise an update solution type flag indicating a static solution, a heuristic solution or a reinforcement learning solution. Additionally, the updating policy relatedparameters for the configuration information may comprise the at least one predetermined condition for triggering the update of the configuration information. E.g. the network device may configure the terminal device to perform the update with one of the AI / ML assisted solutions and the network device may also determine when to perform the update (via the at least one predetermined condition for triggering).

[0061] In some example embodiments, the device may update the configuration information based on the update solution type flag, the predicted RRM measurement results and the at least one performance indicator. For example, if the update solution type flag indicates the heuristic solution, the device will update the configuration information based on the heuristic solution.

[0062] FIG. 3 illustrates an example signaling process 300 for RRM prediction timing configuration update between a terminal device (for example, a terminal device 302 or a UE 302) and a network device (for example, a TRP 304 or a gNB 304) according to some embodiments of the present disclosure. The terminal device 302 may refer to the terminal device 102 in FIG. 1 and the network device 304 may refer to the network device 104 in FIG. 1 .

[0063] At 310, the terminal device 302 may transmit, to the network device 304, a radio resource management (RRM) measurement prediction report. In a reverse direction, the network device 304 may receive, from the terminal device 302, the RRM measurement prediction report. The RRM measurement prediction report may comprise predicted RRM measurement results predicted based on RRM measurements gathered during the observation window, as configured in the configuration information related to RRM measurement prediction. The configuration information may indicate at least one of an observation window length or a prediction window length. The observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. Prediction of RRM measurement results may be performed iteratively based on an AI / ML model.

[0064] In some example embodiments, the terminal device 302 may receive, from the network device 304, the configuration information. In a reverse direction, the network device 304 may transmit, to the terminal device 302, the configuration information. The configuration information may be initial configuration information. The configuration information may be received via a RRC signaling in a static or semi-static manner.

[0065] In some example embodiments, the terminal device 302 may predict RRM measurement results based on the configuration information. For example, the terminal device 302 may predict RRMmeasurement results utilizing the observation window and / or prediction window derived based on the configuration information.

[0066] In some example embodiments, the terminal device 302 may transmit, to the network device 304, capability information. In a reverse direction, the network device 304 may receive, from the terminal device 302, the capability information. The capability information may comprise information indicating that the device supports an update of the configuration information. Alternatively or additionally, the capability information may indicate a supported update solution type for updating the configuration information. The update solution type may be one of: a static solution, a heuristic solution, and a reinforcement learning (RL) solution. Alternatively or additionally, the capability information may indicate supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

[0067] In some example embodiments, the terminal device 302 may collect at least one performance indicator (e.g., key performance indicator (KPI)) related to potential update of the configuration information. The at least one performance indicator may comprise the same contents as those described with reference to FIG. 2. The RRM measurement prediction report may further comprise the at least one performance indicator.

[0068] In some example embodiments, the network device 304 may determine to update the configuration information related to RRM measurement prediction based on the RRM measurement prediction report. The network device 304 may determine to update the configuration information based on a static solution, a heuristic solution or a reinforcement learning (RL) solution. Details regarding updating the configuration information based on different solutions described with reference to FIG. 2 also apply for FIG. 3.

[0069] At 320, the terminal device 302 may receive, from the network device 304, updated configuration information related to RRM measurement prediction via a radio resource control (RRC) signaling. In a reverse direction, the network device 304 may update the configuration information based on the RRM measurement prediction report, and transmit, to the terminal device 302, updated configuration information related to RRM measurement prediction via the RRC signaling. The updated configuration information may comprise at least one of an updated observation window length and an updated prediction window length. The RRC signaling may be a RRC reconfiguration message. In this way, the network device 304 could reconfigure the configuration information related to RRM measurement prediction to the terminal device 302 in a static or semi-static manner. In some example embodiments, the network device 304 may configure multiple concurrent window lengths for the terminal device 302 to choose based on its radio condition and AI / ML model performance.

[0070] Alternatively, the terminal device 302 may receive, from the network device 304, updated configuration information related to RRM measurement prediction via a layer-1 (L1) signaling or a layer- 2 (L2) signaling. In a reverse direction, the network device 304 may update the configuration information based on the RRM measurement prediction report, and transmit, to the terminal device 302, updated configuration information related to RRM measurement prediction via the L1 signaling or the L2 signaling. The L1 signaling may be a downlink control information (DCI) command. The L2 signaling may be a media access control (MAC) control element (CE) message. In this way, the network device 304 could reconfigure the configuration information related to RRM measurement prediction to the terminal device 302 in a dynamic manner.

[0071] In some example embodiments, the RRM measurement prediction report may be received via a radio resource control (RRC) signaling. Alternatively or additionally, the RRM measurement prediction report may be received via a layer-1 (L1) signaling or a layer-2 (L2) signaling.

[0072] It should be noted that those embodiments described with reference FIG. 2 also apply for or could be combined with the embodiments described with reference FIG. 3 in a replaced or mixed manner, explanations of terms with reference to FIG. 2 also apply for FIG. 3, so the same contents apply for both FIG. 2 and FIG. 3 are not repeated here for brevity.

[0073] FIG. 4 illustrates an example signaling process 400 for RRM prediction timing configuration update between a terminal device (for example, a terminal device 402 or a UE 402) and a network device (for example, a TRP 404 or a gNB 404) according to some embodiments of the present disclosure. The terminal device 402 may refer to the terminal device 102 in FIG. 1 and the network device 404 may refer to the network device 104 in FIG. 1 .

[0074] At 410, the terminal device 402 may receive, from the network device 404, configuration information related to radio resource management (RRM) measurement prediction. In a reverse direction, the network device 404 may transmit, to the terminal device 402, configuration information related to radio resource management (RRM) measurement prediction. The configuration information may indicate at least one of an observation window length or a prediction window length. The observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. The configuration information may be initial configuration information. The configuration information may be received via a RRC signaling in a static or semi-static manner. Prediction of RRM measurement results may be performed iteratively based on an AI / ML model.

[0075] In some example embodiments, the terminal device 402 may predict RRM measurement results based on RRM measurements gathered during the observation window, as configured in the configuration information. For example, the terminal device 402 may predict RRM measurement results utilizing the observation window and / or prediction window derived based on the configuration information.

[0076] In some example embodiments, the terminal device 402 may transmit, to the network device 404, capability information. In a reverse direction, the network device 404 may receive, from the terminal device 402, the capability information. The capability information may comprise information indicating that the device supports an update of the configuration information. Alternatively or additionally, the capability information may indicate a supported update solution type for updating the configuration information. The update solution type may be one of: a static solution, a heuristic solution, and a reinforcement learning (RL) solution. Alternatively or additionally, the capability information may indicate supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

[0077] In some example embodiments, the terminal device 402 may collect at least one performance indicator (e.g., key performance indicator (KPI)) related to potential update of the configuration information. The at least one performance indicator may comprise the same contents as those described with reference to FIG. 2. The RRM measurement prediction report may further indicate the at least one performance indicator.

[0078] In some example embodiments, the terminal device 402 may determine to update the configuration information related to RRM measurement prediction based on the predicted RRM measurement results. The terminal device 402 may determine to update the configuration information based on a static solution, a heuristic solution or a reinforcement learning (RL) solution. Details regarding updating the configuration information based on different solutions described with reference to FIG. 2 also apply for FIG. 4.

[0079] In some example embodiments, the configuration information may further comprise updating policy related parameters for the configuration information. The updating policy related parameters may indicate an update solution type flag indicating e.g. a heuristic solution or a reinforcement learning solution. In this way, the terminal device 402 could know to update the configuration information based on which solution as indicated by the update solution type flag.

[0080] At 420, the terminal device 402 may update the configuration information related to RRM measurement prediction based on predicted RRM measurement results. The updated configurationinformation may comprise at least one of an updated observation window length and an updated prediction window length. In this way, the terminal device 402 could update the configuration information related to RRM measurement prediction in an autonomous manner.

[0081] In some example embodiments, the terminal device 402 may transmit, to the network device 404, a RRM measurement prediction report. In a reverse direction, the network device 404 may receive, from the terminal device 402, the RRM measurement prediction report. The RRM measurement prediction report may indicate at least one of: the predicted RRM measurement results, at least one performance indicator, the updated observation window, or the updated prediction window length. The RRM measurement prediction report may be transmitted via at least one of: a radio resource control (RRC) signaling; a layer-1 (L1) signaling; or a layer-2 (L2) signaling. Alternatively, the RRM measurement prediction report may be transmitted as part of L1 and or layer-3 (L3) measurement report.

[0082] It should be noted that those embodiments described with reference FIG. 2 also apply for or could be combined with the embodiments described with reference FIG. 4 in a replaced or mixed manner, explanations of terms with reference to FIG. 2 also apply for FIG. 4, so the same contents apply for both FIG. 2 and FIG. 4 are not repeated here for brevity.

[0083] FIG. 5 illustrates an example signaling process 500 for static / semi-static RRM prediction timing configuration update between a UE (for example, a terminal device 502 or a UE 502) and a gNB (for example, a network device 504 or a gNB 504) according to some embodiments of the present disclosure. The UE 502 may refer to the terminal device 102 in FIG. 1 or the terminal device 302 in FIG.3, and the gNB 504 may refer to the network device 104 in FIG. 1 or the network device 304 in FIG. 3.

[0084] At 510, the UE 502 and the gNB 504 perform radio transmission and AI / ML related capability signaling exchange therebetween. This may include UE capability enquiry and response about RRM measurement prediction related configurations. Capability information of the UE 502 may be exchanged between the UE 502 and the gNB 504.

[0085] At 515, the gNB 504 sends the temporal domain configuration information related to RRM measurement prediction, namely RRM prediction timing configuration (RPTC), to the UE 502. These parameters may be defined in a RRM RPTC subsection. The new RPTC parameters may be conveyed in a RRC signaling, e.g., a RRC re-configuration message. The RPTC parameters may include at least one of: 1) prediction timing horizons: an observation window length (e.g., in ms) and a prediction window length (e.g., in ms), 2) prediction triggering information, or 3) prediction reporting configuration.The prediction reporting configuration may include at least one of: 1) reporting criteria, e.g., periodic, aperiodic, semi-persistent or event-triggered reporting, 2) reporting content types of predicted RRM measurements, e.g., a measurement accuracy (in X% or X dB), a prediction reliability such as a prediction confidence, and radio stability and mobility state information, etc. The reporting contents will be used for the gNB 504 to evaluate the window monitoring conditions.

[0086] In this case, the UE 502 shall only be configured to perform prediction and reporting. The RPTC parameters update is done at the network side.

[0087] At 520, the UE 502 performs L1 / L3 radio measurement procedures and collects the measurement data for measurement prediction. At 525, the UE 502 performs temporal RRM measurement prediction using the network configured RPTC parameters. For example, the UE 502 gathers RRM measurement results (e.g. by performing RRM measurements) during configured observation window and then predicts RRM measurement results for the time period of prediction window. The UE 502 may e.g. at the end of the observation window and before the prediction window starts, predict one or more RRM measurement results for the time period of the prediction window. At 530, the UE 502 collects the RPTC configuration update related KPIs as requested by the gNB 504 in order to monitor the window updating criteria. The KPI may comprise measurement errors between the predicted RRM measurement results and measured RRM measurement results, AI / ML related reliability prediction metrics, radio stability and mobility related metrics, etc.

[0088] At 535, the UE 502 sends a RRM measurement prediction report to the gNB 504. This report may indicate the RRM measurement prediction results and KPIs. The RRM measurement prediction results may comprise a time series of predicted future RRM measurements results in a configured prediction time window. The KPIs may depend on the RRM measurement prediction related configurations. The KPIs may be AI / ML related reliability metrics such as prediction accuracy, confidence, MAE, etc., or instantaneous radio specific metrics such as mobility state information, Redcap-like UE stability conditions, etc. The format of the RRM measurement prediction report may be continuous values or quantized bitmap, e.g., similar as L1 reference signal receiving power (RSRP) report. The signaling channels for the RRM measurement prediction report may be a new dedicated RRC message, or an L1 / L2 signaling such as uplink control information (UCI) command or a MAC CE message.

[0089] At 540, the gNB 504 continuously monitors various criteria to determine if the RPTC parameters update for the observation and / or prediction window (may also include other timing configurations such as prediction periodicity and steps) is necessary based on the RRM measurement prediction report sent by the UE 502. When a static solution is adopted, the gNB 504 may determineto update the RPTC parameters in response to expiry of a validity time period for the RPTC parameters. Alternatively, when a heuristic solution is adopted, the gNB 504 monitors one or more conditions and applies the corresponding actions to adjust the current window settings. The detailed conditions and associated thresholds could be same as those described with reference to FIG. 2. As indicated by 545, the monitoring may be repeated until the monitored conditions are satisfied. Alternatively, when a RL solution is adopted, the implementation details are likely to be network specific. As such, the gNB 504 may not need to configure RL specific parameters. The gNB 504 may update the configuration information using a RL policy. The RL policy may use a neural network (e.g., Q-network) to learn an optimal window size by maximizing a reward function.

[0090] At 550, the gNB 504 prepares the new RPTC parameters after the performance monitoring outcome, and repeat the RRC reconfiguration procedure to send the updated RPTC parameters to the UE 502. At 560, the gNB 504 sends the RRC reconfiguration message to the UE 502, which includes the updated new RPTC parameters for the UE 502 to apply. After the new RPTC parameters are received by the UE 502, 520 to 560 could be repeated and the RPTC parameter may be further updated iteratively.

[0091] By implementing these embodiments described with reference to FIG. 5, the gNB 504 could update the RPTC parameters based on the predicted RRM measurement results predicated based on a previous observation window length and / or a previous prediction window length in a static or semistatic manner.

[0092] It should be noted that those embodiments described with reference FIG. 2 and FIG. 3 also apply for or could be combined with the embodiments described with reference FIG. 5 in a replaced or mixed manner, explanations of terms with reference to FIG. 2 and FIG. 3 also apply for FIG. 5, so the same contents apply for both FIG. 2 / FIG. 3 and FIG. 5 are not repeated here for brevity.

[0093] FIG. 6 illustrates an example signaling process 600 for dynamic RRM prediction timing configuration update between a UE (for example, a terminal device 602 or a UE 602) and a gNB (for example, a network device 604 or a gNB 604) according to some embodiments of the present disclosure. The UE 602 may refer to the terminal device 102 in FIG. 1 or the terminal device 302 in FIG.3, and the gNB 604 may refer to the network device 104 in FIG. 1 or the network device 304 in FIG. 3.

[0094] The main difference between FIG. 5 and FIG. 6 is that the updated RPTC parameters are transmitted in FIG. 6 by a lower layer (e.g., L1 / L2) signaling, such as a DCI command or MAC CEmessage, in a dynamic manner. 610 to 645 are basically same as 510-545 in FIG. 5, thus the description of 610 to 645 are not repeated here.

[0095] At 650, the gNB 604 prepares the requested lower layer signaling information to be transmitted to the UE 602. At 660, the gNB 604 sends the L1 / L2 signaling to the UE 602 to update the RPTC parameters, which may include the updated observation and / or prediction windows. The L1 signaling may be a DCI command. The L2 signaling may be a MAC CE message. The design of the DCI command may be similar as a structure of the transmission power control (TPC) command, where different field values may map to distinct delta values (e.g., in ms) for adjusting the current window settings. After the new RPTC parameters are received by the UE 602, 620 to 660 could be repeated and the RPTC parameter may be further updated iteratively.

[0096] By implementing these embodiments described with reference to FIG. 6, the gNB 604 could update the RPTC parameters based on the predicted RRM measurement results predicated based on a pervious observation window length and / or a previous prediction window length in a dynamic manner.

[0097] It should be noted that those embodiments described with reference FIG. 2 and FIG. 3 also apply for or could be combined with the embodiments described with reference FIG. 6 in a replaced or mixed manner, explanations of terms with reference to FIG. 2 and FIG. 3 also apply for FIG. 6, so the same contents apply for both FIG. 2 / FIG. 3 and FIG. 6 are not repeated here for brevity.

[0098] FIG. 7 illustrates an example signaling process 700 for UE autonomous RRM prediction timing configuration update between a UE (for example, a terminal device 702 or a UE 702) and a gNB (for example, a network device 704 or a gNB 704) according to some embodiments of the present disclosure. The UE 702 may refer to the terminal device 102 in FIG. 1 or the terminal device 402 in FIG.4, and the gNB 704 may refer to the network device 104 in FIG. 1 or the network device 404 in FIG. 4.

[0099] The main difference between FIG. 7 and FIG. 5 / FIG. 6 is that in this case, the UE 702 is not only configured to perform prediction and reporting, but also perform the update of the RPTC parameters autonomously. 710 to 730 are basically same as 510-530 in FIG. 5, thus the description of 710 to 730 are not repeated here.

[0100] At 740, the UE 702 continuously monitors various criteria to determine if the RPTC parameters update for the observation and / or prediction window (may also include other timing configurations such as prediction periodicity and steps) is necessary. The RPTC parameters sent in 715 may further comprise RPTC updating policy related parameters. At 740, the network configured RPTC updating policy related parameters will be used, with specific parameters depending on the typeof prediction algorithm (e.g., a heuristic solution or a RL solution) employed. For the heuristic solution, the gNB 704 needs to configure one or more conditions and actions that allows either the UE 702 to adjust the current window settings. As indicated by 745, the monitoring may be repeated until the monitored conditions are satisfied. For the RL solution, the implementation details are likely to be UE 702 or network specific. As such, the gNB 704 may not need to configure RL specific parameters.

[0101] At 750, once the configured update condition is met, the UE 702 adjusts the observation and / or prediction window lengths based on the configured RPTC updating policy related parameters. At 760, the UE 702 sends a RRM measurement prediction report to the gNB 704, which may indicate the RRM measurement prediction results and monitoring KPIs. In addition, the updated RPTC parameters may also be included in the RRM measurement prediction report. The RRM measurement prediction results may be a time series of future predicted RRM measurements results in a configured prediction time window. The KPIs may depend on the RRM measurement prediction related configurations. The KPIs may be AI / ML related reliability metrics such as prediction accuracy, confidence, MAE, etc., or instantaneous radio specific metrics such as mobility state information, Redcap-like UE stability conditions, etc. The format of the RRM measurement prediction report may be continuous values or quantized bitmap, e.g., similar as L1 reference signal receiving power (RSRP) report. The signaling channels for the RRM measurement prediction report may be a new dedicated RRC message, or an L1 / L2 signaling such as uplink control information (UCI) command or a MAC CE message. After the new RPTC parameters are generated, 720 to 760 could be repeated and the RPTC parameter may be further updated iteratively.

[0102] By implementing these embodiments described with reference to FIG. 7, the UE 702 could update the RPTC parameters based on the predicted RRM measurement results predicated based on a pervious observation window length and / or a previous prediction window length in an autonomous manner.

[0103] It should be noted that those embodiments described with reference FIG. 2 and FIG. 4 also apply for or could be combined with the embodiments described with reference FIG. 7 in a replaced or mixed manner, explanations of terms with reference to FIG. 2 and FIG. 4 also apply for FIG. 7, so the same contents apply for both FIG. 2 / FIG. 4 and FIG. 7 are not repeated here for brevity.

[0104] FIG. 8 illustrates a static solution 800 for RRM prediction timing configuration update loop according to some embodiments of the present disclosure. The static solution 800 may be performed at the network device (for example, the network device 104, 304, or the gNB 504, 604) side.

[0105] At initialization step of 810, the network device may initialize the RPTC values including observation and prediction window lengths to a fixed value (e.g., 100 ms). Data preparation is performed, that is, converting the fixed window size to samples based on the sampling period and creating observation and prediction windows from the data using the fixed window size.

[0106] At 822, the terminal device may perform a time series prediction with an AI / ML model by using the windowed data. At 824, the model performance (e.g., using mean absolute error, MAE) and / or radio performance for a given use case is evaluated.

[0107] At 830, in response to the time to update the window length(s) is reached, the network device triggers the configuration update by using RRC reconfiguration message to convey the new RPTC parameters. Otherwise, at 840, the output related to the current RPTC parameters (including e.g., RRM measurement predication results, window length(s) and MAE CDF) is delivered.

[0108] FIG. 9 illustrates a heuristic solution 900 for RRM prediction timing configuration update loop according to some embodiments of the present disclosure. The heuristic solution 900 may be performed at the network device (for example, the network device 104, 304, or the gNB 504, 604) side or the terminal device (for example, the terminal device 102, 402, or the gNB 702) side.

[0109] At initialization step of 910, the RPTC values including observation and prediction window lengths may be initialized to a fixed value (e.g., 100 ms). An adjustment step (delta) to increase or decrease the window size (e.g., in ms) may also be defined. Decision policy related thresholds, e.g., a MAE threshold that determines when to adjust the window size, may also be set. Data preparation may be performed, that is, converting the fixed window size to samples based on the sampling period and creating observation and prediction windows from the data using the fixed window size.

[0110] At 922, a time series prediction with an AI / ML model by using the windowed data will be performed. At 924, the model performance (e.g., using mean absolute error, MAE) and / or radio performance for a given use case is evaluated.

[0111] At 930, it is determined whether the time to update the window length(s) is reached. In response to the time to update the window length(s) is reached, at 940, the metrics (or KPIs) for evaluation is aggregated. At 950, if the aggregated metrics (or KPIs) is less than the threshold, the window size is increased by a delta value (e.g., in ms). Otherwise, the window size is decreased by a delta value (e.g., in ms). Alternatively, at 930, if it is determined that the time to update the window length(s) is not reached, the process will go back to 922.

[0112] At 960, it is determined whether a maximum iteration number is reached is. If the maximum iteration number is not reached, the updated RPTC parameters, e.g., window sizes used in eachiteration for later analysis, will be tracked. Otherwise, if the maximum iteration number is reached, at 970, the output related to the best RPTC parameters (including e.g., RRM measurement predication results, window length(s) and MAE CDF) is delivered.

[0113] FIG. 10 illustrates a reinforcement learning (RL) 1000 for RRM prediction timing configuration update loop according to some embodiments of the present disclosure. The RL solution 1000 may be performed at the network device (for example, the network device 104, 304, or the gNB 504, 604) side or the terminal device (for example, the terminal device 102, 402, or the gNB 702) side. The RL solution may use Q-learning with a neural network (Q-network) to learn the optimal window size by maximizing a reward function. The RL solution aims to adaptively choose the best window size over multiple episodes.

[0114] At initialization step of 1010, the RL related configuration and parameter (e.g., state, action, reward, Q-values) are defined. The state parameters may comprise at least one of: a normalized window size, that is, a current window size divided by a maximum window size; a previous MAE, that is, the MAE from a previous episode; a RSRP mean, that is, average RSRP values in a current observation window; or a RSRP variance, that is, a variance of RSRP values in the observation window. The action parameters may comprise at least one of: increasing the window size by a fixed amount (e.g., 10 ms); decreasing the window size by a fixed amount (e.g., 10 ms); and maintaining the current window size. The RL related parameter may also comprise an exploration probability, a discounting factor, or an algorithm updating period (e.g., in ms), etc. A Q-network may be initialized, that is, a neural network that takes the state as input and outputs Q-values for each action is initialized. The Q-network should have an input size corresponding to the state parameters (e.g., previous 4 kinds of state parameters) and an output size equal to a number of actions (e.g., 3).

[0115] Then, at 1020 and 1030, the RL agent for the RL solution is trained over multiple episodes. For example, windowed data is created by using current RPTC including observation and prediction windows, RSRP statistics (e.g., mean and variance statistics) are calculated and a state is constructed using the previous 4 kinds of state parameters, an action is selected using epsilon-greedy policy, and the selected action is applied to update the window size.

[0116] At 1042, a time series prediction with an AI / ML model by using the windowed data will be performed. At 1044, the model performance (e.g., using mean absolute error, MAE) and / or radio performance for a given use case is evaluated.

[0117] At 1050, it is determined whether it is the time to perform a next RL iteration. In response to determining it is the time to perform the next RL iteration, at 1060, a reward function is calculated. Thereward function may be related to at least one of: a MAE improvement, rewarding for reducing MAE; stability penalty, penalizing large fluctuations in MAE; or a RSRP accuracy, penalizing large differences between predicted and actual RSRP.

[0118] At 1070, the Q-network is updated by updating a Q table with the reward. At 1080, the state parameters are updated. The updated state parameters may comprise at least one of: a current window size; a recent MAE; a change in MAE, that is, differences between a current MAE and a previous MAE. In the end, the best window size and a corresponding MAE is returned. FIG. 11 illustrates an example diagram 1100 for observation and prediction windows selection according to some embodiments of the present disclosure. As shown in FIG. 11 , initial values for both observation and prediction may be set as 100ms for a case of a low- UE speed 1 (such as 30 km / h). When the speed of the UE increases, it is better to increase the observation window and shorten the prediction window to ensure the same level accuracy (e.g. 2 dB upper bound prediction error). For example, the observation window may be increased to 200ms while the prediction window may be shortened as 50ms for a case a high UE speed 2 (such as 120 km / h). The observation and prediction windows may be updated separately with different delta.

[0119] To validate and demonstrate performances of the three solutions, a comparative analysis of three solutions in a temporal domain RRM prediction use case, specifically Case A. The simulation environment was configured as follows:• Scenario: Frequency range 2 (FR2) with 7 sites (i.e., 21 cells) and intra-frequency SSB based measurements. 14 grid of beams are assumed at each gNB.• UE speed: 120 km / h.• Measurement collection: measurements were collected every 20ms (i.e., a sampling period). L1 and L3 filters are applied.• Initial window settings: both the observation window and prediction window were initialized to 100ms.

[0120] Specific parameters for the heuristic and RL solutions are also defined as follows:• Heuristic solution: an error threshold of 5dB was employed, with a delta value of 10ms for window adjustments. Maximum number of iterations is set as 10.• RL solution: deep Q-network (DQN) based solution, a total number of episodes for training the RL agent is set as 50. Epsilon decaying is applied for exploration. Discounting factor is set as 0.9. The state, action, and reward parameters are defined as follows:o State:■ A normalized window size: The current window size divided by the maximum allowed window size (e.g., 20, 40, 60, 80, 100, 200).■ A previous MAE: The MAE from the previous prediction episode.■ A RSRP mean: Average RSRP values within the current observation window.■ A RSRP variance: Variance of RSRP values within the observation window. o Action: Three possible actions were available:■ Increasing window size: Increasing the window size by a fixed amount, delta = 10ms.■ Decreasing window size: Decreasing the window size by a fixed amount, delta = 10ms.■ Maintaining window size: Keeping the current window size unchanged. o Reward Function: The reward function was designed to incentivize performance improvements and penalize instability and prediction errors■ MAE Improvement: A reward was provided for reducing the MAE, weighted by 0.2.■ Stability Penalty: A penalty was applied for significant fluctuations in MAE, weighted by 0.5.■ RSRP Accuracy: A penalty was applied for large discrepancies between predicted and actual RSRP values, weighted by 0.3. o Q-network: 3 hidden layers with 1000 replay buffer size. Input and output features are specified by state and action.

[0121] The above comprehensive simulation setup allows for a thorough evaluation of the three solutions, comparing their performance and effectiveness in the context of temporal domain RRM prediction. The simulation results are shown in FIG. 12Aand FIG. 12B. FIG. 12A illustrates an example diagram of cumulative distribution function (CDF) of mean absolute error (MAE) for three different solutions for RRM prediction timing configuration update according to some embodiments of the present disclosure. As shown in FIG. 12A, the simulation results show that CDF of MAE for the heuristic and RL solutions are better than that of the static solution, demonstrating the advantages of employing intelligent, iterative solutions to enhance error performance compared to the static solution. FIG. 12Billustrates an example diagram of mean MAE for three different solutions for RRM prediction timing configuration update according to some embodiments of the present disclosure. As shown in FIG. 12B, the simulation results show that the mean MAE for the heuristic and RL solutions are lower than that of the static solution, also demonstrating the advantages of employing intelligent, iterative solutions to enhance error performance compared to the static solution.

[0122] FIG. 13 illustrates a flowchart of an example method 1300 implemented at a terminal device (for example, a terminal device 102 or 302, or a UE 502 or 602) in accordance with some embodiments of the present disclosure. For ease of understanding, the method 1300 will be described from the perspective of the terminal device 302 with reference to FIG. 3.

[0123] At block 1310, the terminal device 302 transmits, to a network device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. At block 1320, the terminal device 302 receives, from the network device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling, wherein the updated configuration information is updated based on the RRM measurement prediction report.

[0124] In some example embodiments, the terminal device 302 is further caused to: receive, from the network device, the configuration information.

[0125] In some example embodiments, the configuration information further comprises at least one of: prediction triggering information, causing periodic triggering, aperiodic triggering or event-based triggering; or prediction reporting configuration, indicating at least one of: a reporting criterion, at least one reporting content type, or a reporting format.

[0126] In some example embodiments, the terminal device 302 is further caused to: predict RRM measurement results based on the configuration information.

[0127] In some example embodiments, the terminal device 302 is further caused to: transmit, to the network device, capability information comprising at least one of: information indicating that the terminal device 302 supports an update of the configuration information; a supported update solution type for updating the configuration information; or supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

[0128] In some example embodiments, the terminal device 302 is further caused to: collect at least one performance indicator related to potential update of the configuration information, wherein the at least one performance indicator comprises at least one of: measurement errors between the predicted RRM measurement results and measured RRM measurement results; artificial intelligence / machine learning (AI / ML) related reliability prediction metrics; radio stability and mobility related metrics; or joint evaluation of both AI / ML metrics and radio stability and mobility related metrics.

[0129] In some example embodiments, the RRM measurement prediction report further comprises the at least one performance indicator.

[0130] In some example embodiments, the updated configuration information comprises at least one of an updated observation window length and an updated prediction window length.

[0131] In some example embodiments, the RRM measurement prediction report is transmitted via at least one of: a radio resource control (RRC) signaling; a layer-1 (L1) signaling; or a layer-2 (L2) signaling.

[0132] In some example embodiments, the updated configuration information is received via at least one of: a RRC reconfiguration message; a downlink control information (DCI) command; or a media access control (MAC) control element (CE) message.

[0133] In some example embodiments, prediction of RRM measurement results is performed iteratively based on an AI / ML model.

[0134] FIG. 14 illustrates a flowchart of an example method 1400 implemented at a network device (for example, a network device 104 or 304, or a gNB 504 or 604) in accordance with some embodiments of the present disclosure. For ease of understanding, the method 1400 will be described from the perspective of the network device 304 with reference to FIG. 3.

[0135] At block 1410, the network device 304 receives, from a terminal device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. At 1420, the network device 304 updates the configuration information based on the RRM measurement prediction report. At 1430, the network device 304 transmits, to the terminal device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling.

[0136] In some example embodiments, the network device 304 is further caused to: transmit, to the terminal device, the configuration information.

[0137] In some example embodiments, the configuration information further comprises at least one of: prediction triggering information, causing periodic triggering, aperiodic triggering or event-based triggering; or prediction reporting configuration, indicating at least one of: a reporting criterion, at least one reporting content type, or a reporting format.

[0138] In some example embodiments, the network device 304 is further caused to: receive, from the terminal device, capability information comprising at least one of: information indicating that the terminal device supports an update of the configuration information; a supported update solution type for updating the configuration information; or supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

[0139] In some example embodiments, the RRM measurement prediction report further comprises at least one performance indicator related to update of the configuration information, wherein the at least one performance indicator comprises at least one of: measurement errors between the predicted RRM measurement results and measured RRM measurement results; artificial intelligence / machine learning (AI / ML) related reliability prediction metrics; radio stability and mobility related metrics; or joint evaluation of both AI / ML metrics and radio stability and mobility related metrics.

[0140] In some example embodiments, the network device 304 is further caused to: determine to update the configuration information related to RRM measurement prediction based on the RRM measurement prediction report.

[0141] In some example embodiments, the update of the configuration information comprises: determining to update the configuration information in response to expiry of a validity time period for the configuration information.

[0142] In some example embodiments, the update of the configuration information comprises: determining to update the configuration information in response to at least one predetermined condition being satisfied.

[0143] In some example embodiments, the update of the configuration information comprises: determining to update the configuration information using a reinforcement learning policy.

[0144] In some example embodiments, the updated configuration information comprises at least one of an updated observation window length and an updated prediction window length.

[0145] In some example embodiments, the RRM measurement prediction report is received via at least one of: a radio resource control (RRC) signaling; a layer-1 (L1) signaling; or a layer-2 (L2) signaling.

[0146] In some example embodiments, the updated configuration information is transmitted via at least one of: a RRC reconfiguration message; a downlink control information (DCI) command; or a media access control (MAC) control element (CE) message.

[0147] In some example embodiments, prediction of RRM measurement results is performed iteratively based on an AI / ML model.

[0148] In some example embodiments, an apparatus (for example, the terminal device 302) capable of performing the method 1300 may comprise means for performing the respective steps of the method 1300. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[0149] In some example embodiments, the apparatus may comprise: means for transmitting, to a network device 304, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; and means for receiving, from the network device 304, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling, wherein the updated configuration information is updated based on the RRM measurement prediction report. In some example embodiments, the apparatus may comprise means for performing other embodiments described with reference to FIG. 13.

[0150] In some example embodiments, an apparatus (for example, the network device 304) capable of performing the method 1400 may comprise means for performing the respective steps of the method 1400. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[0151] In some example embodiments, the apparatus may comprise: means for receiving, from a terminal device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configurationinformation indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; means for updating the configuration information based on the RRM measurement prediction report; and means for transmitting, to the terminal device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling. In some example embodiments, the apparatus may comprise means for performing other embodiments described with reference to FIG. 14.

[0152] FIG. 15 illustrates a flowchart of an example method 1500 implemented at a terminal device (for example, a terminal device 102 or 402, or a UE 702) in accordance with some embodiments of the present disclosure. For ease of understanding, the method 1500 will be described from the perspective of the terminal device 402 with reference to FIG. 4.

[0153] At block 1510, the terminal device 402 receives, from a network device, configuration information related to radio resource management (RRM) measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window. At block 1520, the terminal device 402 updates the configuration information related to RRM measurement prediction based on predicted RRM measurement results.

[0154] In some example embodiments, the configuration information further comprises at least one of: prediction triggering information, causing periodic triggering, aperiodic triggering, or event-based triggering; or prediction reporting configuration, indicating at least one of: a reporting criterion, at least one reporting content type, or a reporting format.

[0155] In some example embodiments, the terminal device 402 is further caused to: transmit, to the network device, capability information comprising at least one of: information indicating that the terminal device 402 supports an update of the configuration information; a supported update solution type for updating the configuration information; or supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

[0156] In some example embodiments, the terminal device 402 is further caused to: collect at least one performance indicator related to update of the configuration information, wherein the at least one performance indicator comprises at least one of: measurement errors between the predicted measurement results and measured measurement results; artificial intelligence / machine learning(AI / ML) related reliability prediction metrics; radio stability and mobility related metrics; or joint evaluation of both AI / ML metrics and radio stability and mobility related metrics.

[0157] In some example embodiments, update of the configuration information comprises: determining to update the configuration information based on the predicted RRM measurement results.

[0158] In some example embodiments, the configuration information further comprises: updating policy related parameters for the configuration information, comprising an update solution type flag indicating a heuristic solution or a reinforcement learning solution.

[0159] In some example embodiments, the update of the configuration information comprises: determining to update the configuration information in response to at least one predetermined condition being satisfied.

[0160] In some example embodiments, the update of the configuration information related to RRM measurement prediction comprises: determining to update the configuration information using a reinforcement learning policy.

[0161] In some example embodiments, the updated configuration information comprises at least one of an updated observation window length and an updated prediction window length.

[0162] In some example embodiments, the terminal device 402 is further caused to: transmit, to the network device, a RRM measurement prediction report, wherein the RRM measurement prediction report comprises at least one of: the predicted RRM measurement results, at least one performance indicator, the updated observation window, or the updated prediction window length.

[0163] In some example embodiments, the RRM measurement prediction report is transmitted via at least one of: a radio resource control (RRC) signaling; a layer-1 (L1) signaling; or a layer-2 (L2) signaling.

[0164] In some example embodiments, prediction of RRM measurement results is performed iteratively based on an AI / ML model.

[0165] FIG. 16 illustrates a flowchart of an example method 1600 implemented at a network device (for example, a network device 104 or 404, or a gNB 704) in accordance with some embodiments of the present disclosure. For ease of understanding, the method 1600 will be described from the perspective of the network device 404 with reference to FIG. 4.

[0166] At block 1600, the network device 404 transmits, to a terminal device, configuration information related to radio resource management (RRM) measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction windowlength, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window, wherein the configuration information is updated based on predicted RRM measurement results.

[0167] In some example embodiments, the configuration information further comprises at least one of: prediction triggering information, causing periodic triggering, aperiodic triggering, or event-based triggering; or prediction reporting configuration, indicating at least one of: a reporting criterion, at least one reporting content type, or a reporting format.

[0168] In some example embodiments, the network device 404 is further caused to: receive, from the terminal device, capability information comprising at least one of: information indicating that the terminal device supports an update of the configuration information; a supported update solution type for updating the configuration information; or supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

[0169] In some example embodiments, the configuration information further comprises: updating policy related parameters for the configuration information, comprising an update solution type flag indicating a heuristic solution or a reinforcement learning solution.

[0170] In some example embodiments, the updated configuration information comprises at least one of an updated observation window length and an updated prediction window length.

[0171] In some example embodiments, the network device 404 is further caused to: receive, from the terminal device, a RRM measurement prediction report, wherein the RRM measurement prediction report comprises at least one of: the predicted RRM measurement results, at least one performance indicator related to update of the configuration information, the updated observation window, or the updated prediction window length.

[0172] In some example embodiments, the RRM measurement prediction report is received via at least one of: a radio resource control (RRC) signaling; a layer-1 (L1) signaling; or a layer-2 (L2) signaling.

[0173] In some example embodiments, prediction of RRM measurement results is performed iteratively based on an AI / ML model.

[0174] By implementing the embodiments described with reference to FIG. 1 to FIG. 16, the terminal device or the network device could update the configuration information related to radio RRM measurement prediction based on the predicted RRM measurement results predicated based on an initial observation window length and / or a prediction window length, thereby providing dynamic andadaptable configuration update and achieving a robust time domain RRM measurement prediction configuration update solution.

[0175] In some example embodiments, an apparatus (for example, the terminal device 402) capable of performing the method 1500 may comprise means for performing the respective steps of the method 1500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[0176] In some example embodiments, the apparatus may comprise: means for receiving, from a network device, configuration information related to radio resource management (RRM) measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; and means for updating the configuration information related to RRM measurement prediction based on predicted RRM measurement results. In some example embodiments, the apparatus may comprise means for performing other embodiments described with reference to FIG. 15.

[0177] In some example embodiments, an apparatus (for example, the network device 404) capable of performing the method 1600 may comprise means for performing the respective steps of the method 1600. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[0178] In some example embodiments, the apparatus may comprise: means for transmitting, to a terminal device, configuration information related to radio resource management (RRM) measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window, wherein the configuration information is updated based on predicted RRM measurement results. In some example embodiments, the apparatus may comprise means for performing other embodiments described with reference to FIG. 16.

[0179] FIG. 17 illustrates an example simplified block diagram of a device 1700 that is suitable for implementing embodiments of the present disclosure. The device 1700 may be provided to implement a communication device or a network element, for example, the terminal device 102 and the network device 104 as shown in FIG. 1. As shown, the device 1700 includes one or more processors 1710, one or more memories 1720 may couple to the processor 1710, and one or more communication modules 1740 may couple to the processor 1710.

[0180] The communication module 1740 is for bidirectional communications. The communication module 1740 has at least one antenna to facilitate communication. The communication interface may represent any interface that is necessary for communication with other network elements, for example the communication interface may be wireless or wireline to other network elements, or software based interface for communication.

[0181] The processor 1710 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 1700 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.

[0182] The memory 1720 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) 1724, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random access memory (RAM) 1722 and other volatile memories that will not last in the power-down duration.

[0183] A computer program 1730 includes computer executable instructions that are executed by the associated processor 1710. The program 1730 may be stored in the ROM 1724. The processor 1710 may perform any suitable actions and processing by loading the program 1730 into the RAM 1722.

[0184] The embodiments of the present disclosure may be implemented by means of the program so that the device 1700 may perform any process of the disclosure as discussed with reference to FIG. 1 or FIG. 16. The embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0185] In some example embodiments, the program 1730 may be tangibly contained in a computer readable medium which may be included in the device 1700 (such as in the memory 1720) or other storage devices that are accessible by the device 1700. The device 1700 may load the program 1730 from the computer readable medium to the RAM 1722 for execution. The computer readable medium may include any types of tangible non-volatile storage, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. FIG. 18 shows an example of the computer readable medium 1800 in form of CD or DVD. The computer readable medium has the program 1730 stored thereon.

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

[0187] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the methods 200 to 1000 and 1300 to 1600 as described above with reference to FIG. 2 to FIG. 10 and FIG. 13 to FIG. 16. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

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

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

[0190] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0191] Further, while 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, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.

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

Claims

WHAT IS CLAIMED IS:

1. A terminal device comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the terminal device at least to: transmit, to a network device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; and receive, from the network device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling, wherein the updated configuration information is updated based on the RRM measurement prediction report.

2. The terminal device of claim 1, wherein the terminal device is further caused to: receive, from the network device, the configuration information.

3. The terminal device of claim 1 or 2, wherein the configuration information further comprises at least one of: prediction triggering information, causing periodic triggering, aperiodic triggering or eventbased triggering; or prediction reporting configuration, indicating at least one of: a reporting criterion, at least one reporting content type, or a reporting format.

4. The terminal device of any of claims 1 to 3, wherein the terminal device is further caused to: predict RRM measurement results based on the configuration information.

5. The terminal device of any of claims 1 to 4, wherein the terminal device is further caused to: transmit, to the network device, capability information comprising at least one of:37information indicating that the terminal device supports an update of the configuration information; a supported update solution type for updating the configuration information; or supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

6. The terminal device of any of claims 1 to 5, wherein the terminal device is further caused to: collect at least one performance indicator related to potential update of the configuration information, wherein the at least one performance indicator comprises at least one of: measurement errors between the predicted RRM measurement results and gathered RRM measurement results; artificial intelligence / machine learning (AI / ML) related reliability prediction metrics; radio stability and mobility related metrics; or joint evaluation of both AI / ML metrics and radio stability and mobility related metrics.

7. The terminal device of claim 6, wherein the RRM measurement prediction report further comprises the at least one performance indicator.

8. The terminal device of any of claims 1 to 7, wherein the updated configuration information comprises at least one of an updated observation window length and an updated prediction window length.

9. The terminal device of any of claims 1 to 8, wherein the RRM measurement prediction report is transmitted via at least one of: a radio resource control (RRC) signaling; a layer-1 (L1) signaling; or a layer-2 (L2) signaling.

10. The terminal device of any of claims 1 to 9, wherein the updated configuration information is received via at least one of: a RRC reconfiguration message; a downlink control information (DCI) command; or a media access control (MAC) control element (CE) message.

11. The terminal device of any of claims 1 to 10, wherein prediction of RRM measurement results is performed iteratively based on an AI / ML model.

12. A network device comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the network device at least to: receive, from a terminal device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; update the configuration information based on the RRM measurement prediction report; and transmit, to the terminal device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling.

13. The network device of claim 12, wherein the network device is further caused to: transmit, to the terminal device, the configuration information.

14. The network device of claim 12 or 13, wherein the configuration information further comprises at least one of: prediction triggering information, causing periodic triggering, aperiodic triggering or eventbased triggering; or prediction reporting configuration, indicating at least one of: a reporting criterion, at least one reporting content type, or a reporting format.

15. The network device of any of claims 12 to 14, wherein the network device is further caused to: receive, from the terminal device, capability information comprising at least one of: information indicating that the terminal device supports an update of the configuration information;a supported update solution type for updating the configuration information; or supported upper bound and lower bound values of at least one of: an observation window, a prediction window, or a prediction step.

16. The network device of any of claims 12 to 15, wherein the RRM measurement prediction report further comprises at least one performance indicator related to update of the configuration information, wherein the at least one performance indicator comprises at least one of: measurement errors between the predicted RRM measurement results and gathered RRM measurement results; artificial intelligence / machine learning (AI / ML) related reliability prediction metrics; radio stability and mobility related metrics; or joint evaluation of both AI / ML metrics and radio stability and mobility related metrics.

17. The network device of any of claims 12 to 16, wherein the network device is further caused to: determine to update the configuration information related to RRM measurement prediction based on the RRM measurement prediction report.

18. The network device of any of claims 12 to 17, wherein the update of the configuration information comprises: determining to update the configuration information in response to expiry of a validity time period for the configuration information.

19. The network device of any of claims 12 to 17, wherein the update of the configuration information comprises: determining to update the configuration information in response to at least one predetermined condition being satisfied.

20. The network device of any of claims 12 to 17, wherein the update of the configuration information comprises: determining to update the configuration information using a reinforcement learning policy.21 . The terminal device of any of claims 12 to 20, wherein the updated configuration information comprises at least one of an updated observation window length and an updated prediction window length.

22. The network device of any of claims 12 to 21 , wherein the RRM measurement prediction report is received via at least one of: a radio resource control (RRC) signaling; a layer-1 (L1) signaling; or a layer-2 (L2) signaling.

23. The network device of any of claims 12 to 22, wherein the updated configuration information is transmitted via at least one of: a RRC reconfiguration message; a downlink control information (DCI) command; or a media access control (MAC) control element (CE) message.

24. The network device of any of claims 12 to 23, wherein prediction of RRM measurement results is performed iteratively based on an AI / ML model.

25. A method comprising: transmitting, to a network device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; and receiving, from the network device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling, wherein the updated configuration information is updated based on the RRM measurement prediction report.

26. A method comprising: receiving, from a terminal device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRMmeasurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; updating the configuration information based on the RRM measurement prediction report; and transmitting, to the terminal device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling.

27. An apparatus comprising: means for transmitting, to a network device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; and means for receiving, from the network device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling, wherein the updated configuration information is updated based on the RRM measurement prediction report.

28. An apparatus comprising: means for receiving, from a terminal device, a radio resource management (RRM) measurement prediction report, wherein the RRM measurement prediction report comprises predicted RRM measurement results predicted based on configuration information related to RRM measurement prediction, wherein the configuration information indicates at least one of an observation window length or a prediction window length, wherein the observation window is for gathering RRM measurement results which are used as a basis for predicting RRM measurement results for the prediction window; means for updating the configuration information based on the RRM measurement prediction report; andmeans for transmitting, to the terminal device, updated configuration information related to RRM measurement prediction via at least one of: a radio resource control (RRC) signaling, a layer-1 (L1) signaling, or a layer-2 (L2) signaling.

29. A non-transitory computer readable medium comprising program instructions stored thereon for performing the method of claim 25 or 26.43

Images