Measurement gap configuration

Abstract

Example embodiments of the present disclosure relate to methods, apparatuses, and computer readable medium for measurement gap configuration. In a method, a terminal device receives a management configuration for measurement gap management based on a machine learning model from a network device. Based on the machine learning model, the terminal device obtains predicted mobility information of the apparatus within a time window. The terminal device manages one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

Description

MEASUREMENT GAP CONFIGURATION FIELDS

[0001] Various example embodiments of the present disclosure generally relate to the field of telecommunication and in particular, to methods, devices, apparatuses and computer readable storage medium for measurement gap management. BACKGROUND

[0002] A Mobile device has to measure the neighboring cell signal and other carrier components. The mobile device may be equipped with a single radio frequency (RF) module to control the manufacturing cost and form factor, and thus the mobile device has to perform all this measurements, transmission (Tx) and reception (Rx) of data using the single RF module. As such, the mobile device may measure the neighboring cell signal transmitting on the same frequency easily while simultaneously transmitting and receiving data from the serving cell.

[0003] However, in the case of measuring a cell operating at a different frequency (such as an inter-frequency neighboring cell) or other radio access technology (RAT), the mobile device has to suspend communication (such as Tx / Rx) with the serving cell and needs to tune the RF module to configured frequencies (such as configured measurement objects). The mobile device may resume communication with the serving cell after the suspended duration. The time duration during which the mobile device suspends its communication with a serving cell to measure an inter frequency neighboring cell or other RAT neighboring cell is known as the measurement gap, which is also abbreviated as Meas Gap. However, the measurement gap may affect the throughput in both downlink (DL) and uplink (UL). SUMMARY

[0004] In a first aspect of the present disclosure, there is provided an apparatus. The apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network device, a management configuration for measurement gap management based on a machine learning model; obtain, based on the machine learning model,predicted mobility information of the apparatus within a time window; and manage one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

[0005] In a second aspect of the present disclosure, there is provided an apparatus. The apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine a management configuration for measurement gap management based on a machine learning model; and transmit the management configuration to a terminal device.

[0006] In a third aspect of the present disclosure, there is provided a method. The method comprises: receiving, at an apparatus from a network device, a management configuration for measurement gap management based on a machine learning model; obtaining, based on the machine learning model, predicted mobility information of the apparatus within a time window; and managing one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

[0007] In a fourth aspect of the present disclosure, there is provided a method. The method comprises: determining, at an apparatus, a management configuration for measurement gap management based on a machine learning model; and transmitting the management configuration to a terminal device.

[0008] In a fifth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the third aspect.

[0009] In a sixth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the fourth aspect.

[0010] It is to be understood that the Summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Some example embodiments will now be described with reference to theaccompanying drawings, where:

[0012] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;

[0013] FIG.2 illustrates a signaling diagram of an example process for L1 / L2-triggered mobility (LTM) in accordance with some example embodiments of the present disclosure;

[0014] FIG. 3A illustrates simulation results of the relationship between DL user throughput and different measurement gap length (MGL) values;

[0015] FIG. 3B illustrates simulation results of the relationship between UL user throughput and different MGL values;

[0016] FIG. 4A illustrates simulation results of the relationship between radio link problem and different MGL values;

[0017] FIG.4B illustrates simulation results of the relationship between mean Time out Outage (ToO) and different MGL values;

[0018] FIG. 5 illustrates a signaling diagram for an example communication process in the communication environment according to some example embodiments of the present disclosure.

[0019] FIG. 6 illustrates an example diagram of managing reporting signal format in accordance with some embodiments of the present disclosure;

[0020] FIG. 7 illustrates an example time instance in accordance with some embodiments of the present disclosure;

[0021] FIG. 8 illustrates a signaling diagram for an example communication process in the communication environment according to some example embodiments of the present disclosure;

[0022] FIG. 9 illustrates a signaling diagram for an example communication process in the communication environment according to some example embodiments of the present disclosure;

[0023] FIG. 10 illustrates an example structure of the machine learning (ML) model in accordance with some example embodiments of the present disclosure;

[0024] FIG. 11 illustrates an example plot of a prediction window in accordance withthe embodiments of the present disclosure;

[0025] FIG. 12 illustrates a flowchart of a method implemented at a first device according to some example embodiments of the present disclosure;

[0026] FIG. 13 illustrates a flowchart of a method implemented at a second device according to some example embodiments of the present disclosure;

[0027] FIG. 14 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0028] FIG.15 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0029] Throughout the drawings, the same or similar reference numerals represent the same or similar element. DETAILED DESCRIPTION

[0030] Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

[0031] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0032] 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.

[0033] It shall be understood that although the terms “first,” “second,”…, etc. in front of noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0034] 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.

[0035] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0036] 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.

[0037] 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 tocause 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.

[0038] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0039] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), the sixth generation (6G) communication protocols, and / or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0040] 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), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a Centralized Unit (CU) and a Distributed Unit (DU) at an IAB donor node. An IAB node comprises a Mobile Terminal (IAB-MT) part that behaves like a UE toward the parent node, and a DU part of an IAB node behaves like a base station toward the next-hop IAB node.

[0041] 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 (IoT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. The terminal device may also correspond to a Mobile Termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0042] As used herein, the term “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer toany resource for performing a communication, for example, a communication between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other combination of the time, frequency, space and / or code domain resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0043] As used herein, the terms “ML model”, “artificial intelligence (AI) model” or “AI / ML model” may refer to a data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. In the context of the present disclosure, the term “ML model” may be interchangeably with the terms “model”, “ML prediction model”, “AI model” and “AI / ML model”.

[0044] FIG.1 illustrates an example communication environment 100 in which example embodiments of the present disclosure can be implemented. In the communication environment 100, a terminal device 110 and a network device 120 can communicate with each other. In some example embodiments, the terminal device 110, for example, may be a UE. The network device 120, for example, may be a gNB.

[0045] In some example embodiments, a link from the network device 120 to the terminal device 110 is referred to as a downlink (DL), while a link from the terminal device 110 to the network device 120 is referred to as an uplink (UL). In DL, the network device 120 is a transmitting (TX) device (or a transmitter) and the terminal device 110 is a receiving (RX) device (or a receiver). In UL, the terminal device 110 is a TX device (or a transmitter) and the network device 120 is a RX device (or a receiver).

[0046] Communications in the communication environment 100 may be implemented according to any proper communication protocol(s), comprising, but not limited to, cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), the fifth generation (5G), the sixth generation (6G), and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols currently known or to be developed in the future. Moreover, thecommunication may utilize any proper wireless communication technology, comprising but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s-OFDM) and / or any other technologies currently known or to be developed in the future.

[0047] It is to be understood that the number of devices and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication environment 100 may include any suitable number of devices configured to implement example embodiments of the present disclosure.

[0048] In the communication environment 100, during a measurement gap, the terminal device 110 may suspend its communication with a serving cell to measure an inter frequency neighboring cell or other RAT neighboring cell. To this end, the network device 120 may transmit to the terminal device 110 measurement gap configuration, which may include various suitable parameters.

[0049] The measurement gap configuration may include a measurement gap length (MGL). In some example embodiments, for example in an LTE system, the MGL is fixed, such that at least one synchronization signal, such as primary synchronization signal (PSS), or secondary synchronization signal (SSS), is included within one gap. LTE sync signals are transmitted at 5 milliseconds (ms) periodicity, so the MGL in LTE is 6 ms, allowing 0.5 ms for RF module re-tuning at the beginning and end of the measurement gap. The terminal device may detect the synchronization signals within the measurement gap, identify the physical cell ID (PCI) and reception timing, and thereafter the terminal device may perform measurements with cell-specific reference signals (CRS). In some example embodiments, for example in new radio (NR), MGL typically is: 1.5 ms, 3 ms, 3.5 ms, 4 ms, 5.5 ms and 6 ms. Another parameter ---Measurement Gap Repetition Period (MGRP) typically is: 20 ms, 40 ms, 80 ms and 160 ms.

[0050] In 5G NR, there are three different measurement gap configurations, gapFR1, gapFR2, and gapUE. The gapFR1 configuration may only be applied to frequency range 1 (FR1). The gapFR1 measurement gap cannot be configured together with the gapUE measurement gap. For example, if UE is in radio resource control (RRC) connected modestate with EUTRA-NR dual connection (EN-DC) attach and FR1 frequency needs to be measured, then gNB will configure either gapFR1 or gapUE.

[0051] Furthermore, the gapFR2 configuration may only be applied to frequency range 2 (FR2). Similar to gapFR1, gapFR2 measurement gap cannot be configured together with gapUE measurement gap. For example, if UE is in RRC connected mode with EN-DC attach and FR2 needs to be measured, then gNB will configure either gapFR2 measurement gap or gapUE measurement gap. In addition, gapUE configuration may be applied to all frequencies (such as FR1 and FR2). If the gapUE measurement gap is configured, then neither gapFR1 measurement gap nor gapFR2 measurement gap can be configured. With this measurement gap configuration, UE may measure FR1, FR2, and non-NR RAT.

[0052] Future standards such as 6G may support other frequency ranges, such as FR3, 7GHz-15GHz, or other frequency ranges. Measurement gaps may be configured to measure signals in those frequency ranges as well.

[0053] Similar to LTE, in 5G NR, RRC signaling is responsible for providing the measurement gap configuration to UE. For example, the measurement gap configuration may be provided using MeasGapConfig information element (IE) within the MeasConfig IE and may be carried by the RRC reconfiguration message. The MeasGapConfig IE has two parts, the first part specifies control setup / release of the measurement gap, and the second part specifies measurement gap configuration and controls setup / release. An example MeasGapConfig IE is shown as below. -- ASN1START -- TAG-MEASGAPCONFIG-STARTMeasGapConfig ::= SEQUENCE {gapFR2 SetupRelease { GapConfig } OPTIONAL, -- Need M ..., [[ gapFR1 SetupRelease { GapConfig } OPTIONAL, -- Need M gapUE SetupRelease { GapConfig } OPTIONAL -- Need M ]], [[ gapToAddModList-r17 SEQUENCE (SIZE (1..maxNrofGapId-r17)) OF GapConfig-r17 OPTIONAL, -- Need N gapToReleaseList-r17 SEQUENCE (SIZE (1..maxNrofGapId-r17)) OF MeasGapId-r17 OPTIONAL, -- Need N posMeasGapPreConfigToAddModList-r17 PosMeasGapPreConfigToAddModList-r17 OPTIONAL, -- Need N posMeasGapPreConfigToReleaseList-r17 PosMeasGapPreConfigToReleaseList-r17OPTIONAL -- Need N]] } GapConfig ::= SEQUENCE { gapOffset INTEGER (0..159),mgl ENUMERATED {ms1dot5, ms3, ms3dot5, ms4, ms5dot5, ms6}, mgrp ENUMERATED {ms20, ms40, ms80, ms160}, mgta ENUMERATED {ms0, ms0dot25, ms0dot5}, ..., [[refServCellIndicator ENUMERATED {pCell, pSCell, mcg-FR2} OPTIONAL -- Cond NEDCorNRDC ]], [[ refFR2ServCellAsyncCA-r16 ServCellIndex OPTIONAL, -- Cond AsyncCA mgl-r16 ENUMERATED {ms10, ms20} OPTIONAL -- Cond PRS ]]}GapConfig-r17 ::= SEQUENCE { measGapId-r17 MeasGapId-r17, gapType-r17 ENUMERATED {perUE, perFR1, perFR2}, gapOffset-r17 INTEGER (0..159),mgl-r17 ENUMERATED {ms1, ms1dot5, ms2, ms3, ms3dot5, ms4, ms5, ms5dot5, ms6, ms10, ms20}, mgrp-r17 ENUMERATED {ms20, ms40, ms80, ms160}, mgta-r17 ENUMERATED {ms0, ms0dot25, ms0dot5, ms0dot75}, refServCellIndicator-r17 ENUMERATED {pCell, pSCell, mcg-FR2}OPTIONAL, -- Cond NEDCorNRDC refFR2-ServCellAsyncCA-r17 ServCellIndex OPTIONAL, -- Cond AsyncCA preConfigInd-r17 ENUMERATED {true} OPTIONAL, -- Need R ncsgInd-r17 ENUMERATED {true} OPTIONAL, -- Need R gapAssociationPRS-r17 ENUMERATED {true} OPTIONAL, -- Need R gapSharing-r17 MeasGapSharingSchemeOPTIONAL, -- Need R gapPriority-r17 GapPriority-r17 OPTIONAL, -- Need R ... } PosMeasGapPreConfigToAddModList-r17 ::= SEQUENCE (SIZE (1..maxNrofPreConfigPosGapId-r17)) OF PosGapConfig-r17PosGapConfig-r17 ::= SEQUENCE { measPosPreConfigGapId-r17 MeasPosPreConfigGapId-r17, gapOffset-r17 INTEGER (0..159),mgl-r17 ENUMERATED {ms1dot5, ms3, ms3dot5, ms4, ms5dot5, ms6, ms10, ms20}, mgrp-r17 ENUMERATED {ms20, ms40, ms80, ms160}, mgta-r17 ENUMERATED {ms0, ms0dot25, ms0dot5}, gapType-r17 ENUMERATED {perUE, perFR1, perFR2}, ... } MeasPosPreConfigGapId-r17 ::= INTEGER (1..maxNrofPreConfigPosGapId-r17) -- TAG-MEASGAPCONFIG-STOP -- ASN1STOP

[0054] Some example parameters of the measurement gap configuration are described now. As shown in the above MeasGapConfig IE, the parameter “gapOffset” represents measurement gap offset and may be defined as the offset of the measurement gap pattern.There are about 160 offset values, and not all values are applicable for all periodicities. The offset values point to the starting subframe within the period, and the value range of the offset is from 0 to MGRP-1. For example, if the periodicity is 20 ms, the offset may range from 0 to 19.

[0055] The parameter “MGL” is the length of the measurement gap in ms which may be 1.5, 3, 3.5, 4, 5.5, or 6 ms. The parameter MGRP of the MeasGapConfig IE may define the periodicity (in ms) at which the measurement gap repeats. MGRP may be configured as 20, 40, 80, and 160 ms. The parameter Measurement Gap Timing Advance (MGTA) of the MeasGapConfig IE may indicate that measurement shall be started in advance of the subframe when the gap starts. If the MGTA is configured, the measurement may be started by MGTA (in ms) before the gap subframe occurrence. For example, the measurement gap starts at time MGTA (in ms) advanced to the end of the latest subframe occurring immediately before the measurement gap. The value of MGTA may be 0.25 ms for FR2 or 0.5 ms for FR1.

[0056] Example parameters of the measurement gap configuration are given above as examples without any limitation to the protection scope. In example embodiments of the present disclosure, other suitable parameters are possible.

[0057] There may exist some mobility scenarios, for example, baseline handover (BHO), conditional handover (CHO) or LTM. Taking LTM as an example, FIG. 2 illustrates a signaling diagram of an example process 200 for LTM from a serving cell in a DU 202 to a target cell in a DU 204 according to some example embodiments of the present disclosure. In the process 200, UE 201 may be considered as an example of the terminal device 110.

[0058] The process 200 may be applied to an inter-DU intra-CU scenario and intra-DU intra-CU scenario. In the case of intra-DU intra-CU cell change, the DU 202 would be the same as the DU 204. In contrast to layer 3 (L3) based-mobility procedures where the handover between two cells is decided by RRC layer and terminated at the CU 203, LTM is performed by the medium access control (MAC) layer terminated in the DU 202 or the DU 204.

[0059] As shown in FIG. 2, in the preparation phase of the LTM performed between 225 and 265, the network may decide to configure the potential target cells for LTM based on the measurement report received from the UE 201. At 225, the UE 201 may transmita measurement report to the DU 202. At 230, the DU 202 may forward the measurement report to the CU 203. At 235, the CU 203 may transmit a UE context setup request to the DU 202. At 240, the DU 202 may transmit a UE context setup response to the CU 203, which may be included in a DU to DU container. At 245, the CU 203 may transmit a UE context setup request to the DU 204. At 250, the DU 204 may transmit a UE context setup response to the CU 203, which may be included in a DU to CU container. At 255, the CU 203 may generate a RRC reconfiguration including a measurement reporting configuration for L1 cell change and configurations of a prepared cell. At 260, the CU 203 may transmit the RRC reconfiguration (such as the configuration for LTM) to the UE 201. At 265, the UE 201 may transmit an RRC reconfiguration complete message to the CU 203.

[0060] At 270, after confirming the RRC reconfiguration to the network, the UE 201 may transmit an L1 measurement report to the DU 202. In an example, the UE 201 may start to report periodically the L1 beam measurements of serving and candidate target cells to the DU 202. At 275, the DU 202 may transmit a MAC control element (CE) command to the UE 201. In an example, upon determining that there is a target candidate cell having a better radio link beam measurement than the serving cell, for example, L1-reference signal received power (RSRP) of target beam measurement > L1-RSRP of serving beam measurement + Off for e.g., Time -to-Trigger (TTT) time, the serving cell may send the MAC CE or an L1 message to trigger the cell change to the target cell. At 280, a cell change may occur, for example, the handover from serving cell to the target cell may be executed by the UE 201.

[0061] The main benefit of LTM compared to baseline handover and conditional handover is that the interruption during the handover execution can be reduced substantially as the terminal device does not need to perform higher layer (such as RRC, packet data convergence protocol (PDCP)) reconfiguration and for some scenarios the terminal device may perform random access channel-less (RACHless) to connect the target cell.

[0062] For a given mobility scenario, for example, BHO, CHO or LTM, UE can measure the neighboring cell signal transmitting on the same frequency very easily while simultaneously transmitting and receiving data from the serving cell. However, when it comes to the case of measuring inter-frequency neighboring cell or inter-RAT mobility cases, the measurement gap occurs, which can cause some problems.

[0063] For example, owing to the existence of the measurement gap, the communication link via data channel is suspended within the gap, which affects the user throughput in both DL and UL. For another example, there are unnecessary measurement activities conducted during the measurement gap if the candidate target cells are predictable or inter-frequency measurements can be inferred through intra-frequency measurements with AI assistance. For a further example, no signaling mechanism, control algorithm, and feedback loops are available in the art to trigger the skipping of unnecessary measurement gaps or the switching between different measurement gaps by taking into account the tradeoff between throughput and mobility performance.

[0064] To further highlight the above problems due to the existence of measurement gap, some example system-level simulations are discussed below with reference to FIG. 3A to FIG. 4B. In these examples, the system-level simulation results that account for various system key performance indicators (KPIs) vs different measurement gap configurations, i.e., MGL (in ms) are presented. The measurement gap repetition period is 20ms in the simulation.

[0065] Reference is first made to FIG. 3A which illustrates an example plot of the relationship between DL user throughput and different MGL values. As shown in FIG. 3A, under the same charging data function (CDF), the larger the MGL (such as GapLength_ in FIG. 3A) values, the lower the DL user throughput. For example, when the CDF is 0.7, with the increase in the MGL, the DL user throughput decreases.

[0066] FIG. 3B illustrates an example plot of the relationship between UL user throughput and different MGL values. As shown in FIG. 3B, similar to FIG. 3A, under the same CDF, the larger the MGL values, the lower the UL user throughput. For example, when the CDF is 0.7, with the increase in the MGL, the UL user throughput decreases.

[0067] It can be observed from FIG. 3A and 3B that for a certain measurement gap repetition period, the increase of the value of MGL may negatively affect the user throughput in both DL and UL. This may be mainly because the UE may prioritize the measurement activities in the configured gap duration while suspending the data transmission of the serving cell.

[0068] Then reference is made to FIG. 4A which illustrates an example histogram of the relationship between radio link problem and different MGL values. As shown in FIG. 4A, it can be observed that there is a considerable drop of radio link problem when theMGL (such as GapLength_ in the figure) is 10ms as compared with the case of 6ms. FIG. 4B illustrates an example histogram of the relationship between mean ToO and different MGL values. As shown in FIG. 4B, it can be observed that the ToO is decreased if the MGL value is increased to 10 ms. Therefore, the longer MGL may lead to more accurate measurement activities for handover and mobility management.

[0069] As can be seen from FIG.3A to FIG.4B, it may be concluded that without robust control mechanism, the mobility performance in terms of ToO and user throughput may be affected.

[0070] Problems or limitations of the measurement gaps are described above. In another aspect, AI / ML for NR air interface has been studied in Release (Rel)-18. Use cases of AI / ML for air interface include channel state information (CSI) feedback enhancement, for example, overhead reduction, improved accuracy, and prediction. Use cases of AI / ML for air interface further include beam management, for example, beam prediction in time, and / or spatial domain for overhead and latency reduction, beam selection accuracy improvement. Use cases of AI / ML for air interface further comprise positioning accuracy enhancements for different scenarios including, for example, those with heavy non-line-of-sight (NLOS) conditions. Representative sub use cases for each use case for characterization and baseline performance evaluations are finalized. The AI / ML approaches for the selected sub use cases need to be diverse enough to support various requirements on the gNB-UE collaboration levels.

[0071] There are some terminologies and descriptions to identify common and specific characteristics for framework investigations in AI / ML models. Model generation, for example, model training (including input / output, pre- / post-process, online / offline as applicable), model validation, model testing, as applicable, and inference operation, for example, input / output, pre- / post-process, as applicable, characterize the defining stages of AI / ML related algorithms and associated complexity.

[0072] Various levels of collaboration between UE and gNB pertinent to the selected use cases are identified, for example, no collaboration representing implementation-based only AI / ML algorithms without information exchange (such as for comparison purposes), and various levels of UE / gNB collaboration targeting at separate or joint ML operation. Lifecycle management of AI / ML model is characterized, for example, model training, model deployment, model inference, model managing, model updating.

[0073] In addition, AI / ML terminologies and descriptions may further include dataset(s) for training, validation, testing, and inference. Some objectives of AI / ML for NR air interface may include identifying common notation and terminology for AI / ML-related functions, procedures, and interfaces. It is to be noted that the work done for FS_NR_ENDC_data_collect should be considered when appropriate.

[0074] There are some use cases under consideration, and potential specification impact is accessed, specifically for the agreed use cases in the final representative set and for a common framework. For physical (PHY) layer aspects (such as radio access network (RAN)1), aspects related to, for example, the potential specification of the AI model lifecycle management, and dataset construction for training, validation, and testing for the selected use cases are considered. Use case and collaboration level-specific specification impact, such as new signaling, means for training and validation data assistance, assistance information, measurement, and feedback.

[0075] In addition, for protocol aspects (such as RAN2), RAN2 only starts the work after there is sufficient progress on the use case studied in RAN1. Aspects related to, for example, capability indication, configuration and control procedures (such as training / inference), and management of data and AI / ML model, per RAN1 input are considered. Collaboration level-specific specification impacts each use case.

[0076] For UE-part / UE-side models in NR Release 18, the mechanisms for ML life cycle management (LCM) procedures are studied based on two approaches including model-ID based and functionality-based approaches, and model managing may be part of the study.

[0077] In view of the above, the ML model can be used to assist in handling or managing the measurement gaps. To this end, example embodiments of the present disclosure propose a measurement gap management scheme. With this scheme, a management configuration for measurement gap management based on a ML model may be transmitted from the network device to the terminal device. The terminal device may obtain predicted mobility information within a time window based on the ML model. Then, the terminal device may manage one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

[0078] In the embodiments of the present disclosure, the terminal device is allowed to perform proactive measurement gap management or handling with aid of ML predictionin a foreseen time window. By enabling the proposed ML-based solution, it is expected that the terminal device can perform proactive measurement gap adaptation to maintain the reliable data transmission while at the same time mobility performance is not impaired. In this way, dynamic measurement gap configuration can be realized, which is beneficial to balance the measurement accuracy and throughput enhancement in mobility.

[0079] In various example embodiments, a configuration which is also referred to as management configuration is used for measurement gap management. In particular, a dynamic measurement gap configuration managing framework with aid of ML-based methodologies that includes new signaling messages between the network device 120 and the terminal device 110 is proposed. Some example implementations will be discussed in detail below with reference to FIGS. 5 to 11. In the following, the measurement gap configuration as described above may be referred to as legacy configuration without any limitation.

[0080] FIG. 5 illustrates a signaling diagram for an example communication process 500 in the communication environment 100 according to some example embodiments of the present disclosure. As shown in FIG.5, in the process 500, the network device 120 may determine (505) a management configuration for measurement gap management based on an ML model (also refers to as ML prediction model). In example embodiments, measurement gap management and managing the measurement gap may means any suitable aspect of handling or monitoring a measurement gap or measurement gap configuration. In the following, measurement gap management may be also referred to as measurement gap monitoring or handling.

[0081] The management configuration may include any suitable information or parameters for dynamic handling of measurement gaps. In some example embodiments, the management configuration may comprise an indication of whether the measurement gap management is performed autonomously by the terminal device 110 or under control of the network device 120, which is also referred to as managing modes. In other words, the network device 120 may configure the terminal device 110 how to control the measurement gap management based on the ML model on top of the legacy configuration messages. In some example embodiments, the indication is to perform the measurement gap management under control of the network device 120. In other words, the network device 120 may configure the terminal device 110 to monitor the legacy measurement gap configuration under the instruction and feedback from the network device 120.Alternatively, in some example embodiments, the indication is to perform the measurement gap management autonomously by the terminal device 110. In other words, the terminal device 110 may be granted to autonomously handling the legacy measurement gap configuration without control from the network device 120.

[0082] Alternatively, or in addition, in some example embodiments, the management configuration may comprise action information about one or more actions (also refer to as managing options or optional actions) available for the measurement gap management. The action information may include indications of the managing options and relevant parameters of each managing option for use by the terminal device 110.

[0083] The managing options may include any suitable actions to be performed on a measurement gap. As examples without any limitation, the one or more actions may comprise at least one of: measurement gap skipping (which is also referred to as skipping option), measurement gap reservation (which is also referred to as reserving option), a measurement gap reconfiguration (which is also referred to as reconfiguration option), an adjustment to a measurement gap configuration (which is also referred to as adjusting option), an adaptation of a measurement gap configuration, early termination of a measurement gap, or postponing of a measurement gap.

[0084] In the skipping option, the next measurement gap or the next ^ ( ^ ≥ 1 ) measurement gaps may be skipped to prioritize the data transmission. In the reserving option, the next measurement gap or the next ^ (^ ≥ 1 ) measurement gaps may be reserved to prioritize measurement activities. For the skipping and reserving options, the parameter maxNrofMonitoredGaps ^^^^may be configured, which indicates the max number of consecutive gaps to be managed or monitored such that 1 ≤ ^ ≤ ^^^^.

[0085] In the reconfiguration option, the RRC reconfiguration of the new measurement gap parameters may be requested by the terminal device 110 if the current parameters are not functioning properly. For example, the legacy configured measurement gap parameters may be altered.

[0086] In the adjusting option, the legacy measurement gap configuration may be altered by the terminal device 110. Any suitable parameters of the measurement gap configuration (for example, one or more of parameters as configured in the MeasGapConfig IE) may be candidate for this option. The network device 120 may configure which parameter(s) can be altered. As examples without any limitation, thecandidate parameters may include a measurement gap length, a measurement gap repetition period, a measurement gap timing advance, or a measurement gap offset. Accordingly, the action information may include updates to these parameters.

[0087] The update to a parameter may be in any suitable manner. In some example embodiments, the update may include scaling down or up the parameter. As an example, the action information may comprise a scaling factor of the measurement gap length, for example, measGapLengthMonitoringScalingFactor which serves as a float value to scale the measurement gap length. As another example, the action information may comprise a scaling factor of the measurement gap repetition period, for example, measGapRepetitionPeriodMonitoringScalingFactor which represents a float value to scale the measurement gap repetition period. In some example embodiments, the update may include an offset of the parameter. As example, the action information may further comprise an offset to the measurement gap length, for example, measGapLengthMonitoringOffset which denotes a constant value to adjust the legacy measurement gap length in ms.

[0088] It is to be understood that the above parameters are given as examples. Any parameters of the measurement gap configuration may be altered.

[0089] Alternatively, or in addition, in some example embodiments, the management configuration may comprise a signaling format for reporting the measurement gap management to the network device 120, which is also referred to as “managing reporting signal format”. Accordingly, the terminal device 110 may transmit a request for measurement gap management (as will be described with reference to FIG.8) or a request of measurement gap management (as will be described with reference to FIG. 9) to the network device 120 by using the signaling format. As an example, without any limitation, the signaling format may be configured by the network device 120 to the terminal device 110, so that the terminal device 110 may report the managing request or the result of the measurement gap management to the network device 120 in a compound Q-bits format.

[0090] FIG.6 illustrates an example diagram of a managing reporting signal format in accordance with some embodiments of the present disclosure. In this example, managing reporting signal format is shown in a compound Q-bits format. As shown in FIG. 6, the first two bits 610 represents the use of different managing options. For example, the skipping option (which is denoted as option 1 in FIG. 6) may be represented by 00 whichmeans that the first two bits 610 are both zeros. As examples, the reserving option may be represented by 01, the reconfiguration option may be represented to be 10, and the adjusting option may be represented to be 11. The remaining Q-2 bits 615 represent whether the consecutive N measurement gaps 620 are going to be managed in the option indicated by the first two bits. If the skipping or reserving option is not applied, the remaining Q-2 bits 615 may be set as zeros for other options.

[0091] Alternatively, or in addition, in some example embodiments, the management configuration may comprise a timing to use the ML model for the measurement gap management. For example, the network device 120 may configure one or more triggers in the time domain for running ML prediction models with respect to the legacy measurement gap configurations.

[0092] To this end, in some example embodiments, a time domain variable, namely TimeToTrigger_ML-MG, may be applied when the measurement gap is configured periodically, and the value of MGRP may be known. Thus, the use of the ML model can be triggered periodically. As an example, the time domain variable TimeToTrigger_ML- MG may be defined as a reference time instance to the configured MGRP. FIG. 7 illustrates an example time instance in accordance with some embodiments of the present disclosure. In this example, as shown in the FIG. 7, the length of the measurement gap 720 is 4ms. The measurement gap 720 comprises an actual measurement window 710 of 3 ms and RF retuning time 705 of 1ms. TimeToTrigger_ML-MG may be defined as ^^715 in advance of each measurement gap occurrence / periodicity. In some example embodiments, the value of TimeToTrigger_ML-MG may be configured to be higher than MGRP such that multiple follow-up gaps can be skipped. Some operations 725, for example, prediction output, feature extraction, and trigger the update, may be completed before ^^715 in advance of each measurement gap occurrence / periodicity.

[0093] In some example embodiments, a set of timers may be defined as the timing to use the ML model. The start of the set of timers may be triggered by the network device 120.

[0094] Alternatively, or in addition, in some example embodiments, the management configuration may include model information about the ML model to be used. In other words, ML model related parameters and settings may be configured by the network device 120. The ML prediction model related parameters and settings may include butnot limited to an identifier (ID) of the ML model, the model structure of time series prediction, the model input, the model output, and prediction window related configuration, etc.

[0095] The network device 120 may transmit (515) the management configuration to the terminal device 110. Accordingly, the terminal device 110 may receive the management configuration from the network device 120 for follow-up ML-based dynamic measurement gap management. Through the management configuration, the network device 120 may control or enforce the transition between different ML-based managing modes. For example, by controlling or enforcing the transition between different ML- based managing modes by the network device 120, the measurement gap management may be performed autonomously by the terminal device 110 or controlled by the network device 120. The management configuration may be transmitted in any suitable signaling channel or protocol layer, for example, RRC or MAC.

[0096] In some example embodiments, the management configuration may be transmitted in response to a request from the terminal device 110. As shown in FIG. 5, the terminal device 110 may transmit (510) a first request to configure the measurement gap management to the network device 120. In other words, the terminal device 110 may request ML based dynamic measurement gap configuration(s) from the network device 120. For example, the terminal device 110 may transmit the first request to request the measurement configuration from the network device 120 to be used for the execution of one or more ML-based dynamic measurement gap related procedures. The requested management configuration may include but not limited to one or more configuration parameters as described above with respect to act 505. As an example, the terminal device 110 may request selection of the managing modes, whether under control of the network device 120 or not. As another example, the terminal device 110 may request time instances to trigger the operation of the ML models (such as TimeToTrigger_ML-MG). As a further example, the terminal device 110 may request a set of new parameters that correspond to different managing options, such as measGapLengthMonitoringScalingFactor described above. As a yet further example, the terminal device 110 may request the managing reporting signal format. In some example embodiments, the requested parameters of the management configuration may constitute new capability information of the terminal device 110.

[0097] In some example embodiments, the terminal device 110 may request ML modelID or ML-related algorithm ID. This might be optional if the terminal device 110 is equipped with ML-based functionalities. It is to be noted that embodiments of the present disclosure are not limited in this regard.

[0098] The first request may be transmitted in any suitable signaling channel or protocol layer, for example, RRC or MAC. In some example embodiments, the signaling channel or protocol layer, for example, RRC or MAC, may be selected depending on the time constrains of the prediction window update and optimization related evaluation execution, data collection, and feedback indication, etc.

[0099] In these example embodiments, the management configuration is transmitted (515) as a first response to the first request. The management configuration may be transmitted via the same or different signaling channel or protocol layer as the first request.

[0100] Continuing with the process 500, the terminal device 110 receives the management configuration from the network device 120. In some example embodiments, the terminal device 110 may use the ML model for the measurement gap management according to the management configuration. For example, if the management configuration includes the triggers in time domain as described above, the terminal device 110 may use the prediction from ML model according to the time instance indicated by the triggers. For example, the value of TimeToTrigger_ML-MG (in ms) may be determined by various input variables, such as prediction window length, measurement gap repetition period, etc.

[0101] In some example embodiments, use of the ML model for the measurement gap management may be triggered by the network device 120. As shown in FIG. 5, the network device 120 may transmit (520) to the terminal device 110 an indication to trigger the use of the ML model for the measurement gap management. In other words, the network device 120 may trigger the terminal device 110 to start the ML-based functionalities for mobility management.

[0102] According to the triggers as defined in the management configuration or in response to the indication from the network device 120, the terminal device 110 may obtain (525) predicted mobility information of the terminal device 110 within a time window based on the ML model. The predicted mobility information may include any suitable information about mobility of the terminal device 110, for example, measurement results, parameters, mobility related features and events. The predicted mobilityinformation may be a result output by the ML model or obtained by post-processing the result output by the ML model.

[0103] In some example embodiments, the ML inference may be performed by another entity and the terminal device 110 may request the result of the ML model from that entity. In some example embodiments, the ML inference may be performed at the terminal device 110. Embodiments of the present disclosure are not limited in this regard.

[0104] In some example embodiments, the terminal device 110 may perform the ML inference to output a sequence of prediction samples, for example, a sequence of RSRP values from serving and neighboring cells / beam, in a future time window. As an example, a time series prediction model, such as long-short-term-memory (LSTM), recurrent neural network (RNN), is hosted and executed for the defined use cases at the terminal device 110 side. It is to be noted that data collection, labeling, model training, and model transfer procedures are not limited in embodiments of the present disclosure. In some example embodiments, the terminal device 110 may be capable of hosting and performing ML related functionalities.

[0105] Then, the terminal device 110 may derive the mobility related features and events from the prediction time window. For example, to perform feature extraction and analysis from the prediction window, the terminal device 110 may collect top N RSRP statistics including both serving and neighboring cells / beams, and collect / calculate the average prediction accuracy with respect to each prediction sample in the given prediction time window and analyze the potential HO execution time instances, etc.

[0106] Continuing with the process 300, the terminal device 110 may manage (530) one or more measurement gaps within the time window based on the management configuration and the predicted mobility information. Depending on the predicted mobility information, a managing option as described above may be performed. For example, the next measurement gap or the next N (N≥1) measurement gaps within the prediction time window may be skipped or may be reserved. For another example, the terminal device 110 may request the network device 120 to reconfigure a measurement gap within the prediction time window given the current parameters are not functioning properly. For a further example, a measurement gap configuration may be adjusted. In other words, one or more parameters of a measurement gap within the prediction time window may be updated.

[0107] In some example embodiments, if the terminal device 110 is configured to perform the measurement gap management autonomously and the management configuration indicates one or more actions available for the measurement gap management, the terminal device 110 may select an action from the one or more actions based on the predicted mobility information. Then, the terminal device 110 may perform the selected action. Such example embodiments will be described below with reference to FIG. 9.

[0108] In some example embodiments, if the terminal device 110 is configured to perform the measurement gap management under control of the network device 120, the terminal device 110 may transmit to the network device 120 a second request to manage the one or more measurement gaps. The second request at least comprise the predicted mobility information. The network device 120 may transmit to the terminal device 110 a second response indicating an action for managing the one or more measurement gaps. Accordingly, the terminal device 110 may perform the indicated action.

[0109] Reference is now made to FIG.8 to described example process for such example embodiments. FIG. 8 illustrates a signaling diagram for an example communication process 800 in the communication environment 100 according to some example embodiments of the present disclosure. In the process 800, the network device 120 may control the measurement gap managing procedures executed by the terminal device 110 with the indication signaling request and response. It is to be noted that the process 800 is given as an example and some acts of the process 800 may be omitted.

[0110] At 805 and 810, the capability exchange between the terminal device 110 and the network device 120 is performed via RRC (re)configuration. Specifically, at 805, the terminal device 110 may request ML-based functionalities from the network device 120 to support a target use case (such as LTM, HO, etc.). At 810, the legacy measurement gap configuration is transmitted from the network device 120 to the terminal device 110. For example, legacy measurement gap related parameters and constraints may be signaled through RRC (re)configuration.

[0111] At 815, the terminal device 110 may request the ML-based measurement gap configuration from the network device 120. In other words, the first request as described above may be transmitted to the network device 120. It is to be noted that, this step (815) is similar to the aforementioned act 510 in FIG. 5, therefore the details are not repeatedhere.

[0112] At 820, the network device 120 may send an ML-based measurement gap configuration response to the terminal device 110. That is, the network device 120 may transmit the management configuration to the terminal device 110. It is to be noted that, this step (820) is similar to the aforementioned act 515 in FIG.5, therefore the details are not repeated here.

[0113] At 825, the terminal device 110 may exploit the initial / legacy measurement gap configuration to execute the inter-RAT or inter-frequency measurement activities for the present use case. The initial / legacy measurement gap configuration may comprise parameters received at 810 from the network device 120, such as measurement gap length, etc.

[0114] At 830, the network device 120 may trigger ML functionality with regard to the measurement gap periodicity. It is to be noted that, this step (830) is similar to the aforementioned act 520 in FIG. 5, therefore the details are not repeated here.

[0115] Then, the terminal device 110 may obtain the predicted mobility information based on the ML model. As shown in FIG. 8 as an example, at 835, the terminal device 110 may perform the ML inference to output a sequence of prediction samples, for example, beam / cell RSRP values, in a future time window. At 840, the terminal device 110 may perform post-processing and feature extraction. The terminal device 110 may derive the mobility related features and events within the prediction time window. For example, to perform feature extraction and analysis from the prediction window, the terminal device 110 may collect top N RSRP statistics including both serving and neighboring cells / beams, and collect / calculate the average prediction accuracy with respect to each prediction sample in the given prediction time window and analyze the potential HO execution time instances, etc.

[0116] At 845, the terminal device 110 may transmit a second request to manage the one or more measurement gaps to the network device 120. The second request may at least comprise the predicted mobility information, for example, information about the mobility related features and events within the prediction time window. As an example, the second request may be a measurement gap managing request, and the terminal device 110 may transmit the measurement gap managing request to the network device 120 with the mobility related feature extraction results, for example, handover events, target cell / beamIDs, handover time instances, etc. The second request may follow the reporting signaling format indicated in the management configuration, as described above with reference to FIG. 5.

[0117] In some example embodiments, the second request may include a selected managing option to be performed. As an example, the reporting signaling format may be formulated as a compound Q-bits that include the selection of managing options from the RRC configuration transmitted at 820. In some example embodiments, depending on the timing constraints, the second request at 845 may be conveyed via the independent L1 / L2 signaling channel, such as being embedded in MAC CE format.

[0118] Accordingly, the network device 120 may receive the second request from the terminal device 110. At 850, the network device 120 may perform feature analysis and evaluation based on the second request, for example the predicted mobility information. In some example embodiments, the network device 120 may select the desired managing options. For example, the network device 120 may evaluate the managing request received from the terminal device 110 and verify the one or more managing options for the terminal device 110 to use. In some example embodiments, if the second request includes an indication of the managing option selected by the terminal device 110, the network device 120 may determine to confirm the selected managing option or reselect another managing option.

[0119] At 855, the network device 120 may transmit to the terminal device 110 a second response indicating an action for managing the one or more measurement gaps. In some embodiments, the second response may include an indication of the managing option selected by the network device 120. In some example embodiments, if the second request includes the indication of the managing option selected by the terminal device 110, the second response may include an acknowledge to the selected managing option or a selection of another managing option. For example, the network device 120 may send the indication message ACK to the terminal device 110 to trigger the measurement gap managing procedure with the managing option preferred by the terminal device 110.

[0120] The second response may be conveyed in any suitable signaling. In some example embodiments, the L1 / L2 fast indication will be applied to trigger the follow-up process. In some example embodiments, for the case that NACK is indicated, the legacy measurement configuration will still be applied.

[0121] Accordingly, the terminal device 110 may receive the second response from the network device 120. At 860, the terminal device 110 may manage the measurement gap by performing the managing option indicated by the network device 120. It is to be noted that, this step (860) is similar to the aforementioned act 530 in FIG.5, therefore the details are not repeated here.

[0122] At 865, the terminal device 110 may transmit a result of performing the indicated action to the network device 120. Accordingly, the network device 120 may receive the result of performing the indicated action from the terminal device 110. For example, the result of performing the indicated action may be a managing outcome indication. In some example embodiments, step 865 is only necessary if the network device 120 needs to store the outcome of the managing, resulting measurement gap configurations for the following processing loop.

[0123] At 870, the network device 120 may store the managing outcome to enable the network device 120 to assess whether current approach is beneficial to be continued or it is better to be reverted to the legacy configurations.

[0124] In these example embodiments, the network device 120 can control the behavior of the terminal device 110 in managing, handling or monitoring the measurement gaps.

[0125] As mentioned above, in some example embodiments, the terminal device 110 may be configured to manage or handle the measurement gaps autonomously. Reference is now made to FIG. 9 to described example process for such example embodiments.

[0126] FIG. 9 illustrates a signaling diagram for an example communication process 900 in the communication environment 100 according to some example embodiments of the present disclosure. In the process 900, the terminal device is granted to autonomously manage the measurement gap configurations without the indication signaling request and response. In the process 900, steps with the same reference number as FIG. 8 are similar with those described above with reference to FIG.8, therefore the details are not repeated here.

[0127] The management configuration received at 820 may indicate one or more actions available for the measurement gap management. At 945, the terminal device 110 may select an action from the one or more actions based on the predicted mobility information. For example, the terminal device 110 may derive the mobility related features and eventsfrom the prediction window. For example, the terminal device 110 may perform feature extraction and analysis from the prediction window including the following: 1) collecting top N RSRP statistics including both serving and neighboring cells / beams, 2) collecting / calculating the average prediction accuracy with respect to each prediction sample in a given prediction window, 3) analyzing the potential handover execution time instances, etc. Then, the terminal device 110 may select the preferred action.

[0128] At 950, the terminal device 110 may perform the selected action on the one or more measurement gap. It is to be noted that, step 950 is similar to the aforementioned act 530 in FIG. 5, therefore the details are not repeated here.

[0129] At 955, the terminal device 110 may transmit an indication of the selected action and a result of performing the selected action to the network device 120. For example, the terminal device 110 may send an outcome indication to the network device 120 that explicitly reflects the managing actions and the resulting configurations. Accordingly, the network device 120 may receive a result of performing the selected action from the terminal device. The signal at 955 may follow the reporting signaling format in the management configuration.

[0130] In some example embodiments, the reporting signaling format may be formulated as a compound Q-bits that include the selection of managing options from the RRC configuration. Depending on the timing constraints, this signal at 955 may be conveyed via the independent L1 / L2 signaling channel, such as being embedded in MAC CE format.

[0131] At 960, the network device 120 may store the managing outcome to assess whether current approach is beneficial to be continued or it is better to be reverted to the legacy configurations.

[0132] In these example embodiments, the measurement gap management can be performed autonomously by the terminal device 110. In this way, the measurement gap can be managed in a time and signaling saving way.

[0133] An implementation example on ML prediction model under the purpose of inter- frequency mobility management and handover decision making will be illustrated below. Further, how measurement gap configuration may be managed based on the prediction outcome will be described. However, it is to be noted that the model shown in FIG.10 isgiven as an example without any limitation.

[0134] FIG. 10 illustrates an example structure of the ML prediction model in accordance with some example embodiments of the present disclosure. As shown in FIG. 10, the input frame of the model structure may be sequence of L2-RSRP and / or sequence of beam IDs. These two inputs may be concatenated in a concatenated layer 1010 before feeding into ML model 1030. The example here using L2-RSRP input values from 294 beams (14 beams from 21 gNBs) within 3 seconds. It is to be noted that the network device 120 may measure SSB every 20 ms, the measurement is for 150 samples, and the total input length is 3 seconds. Furthermore, the input frame, such as L2-RSRP + Beam IDs and fed into ML model 1030, such as LSTM, RNN, to obtain time sequence output. The output of the model may be any of predicted L2-RSRP values, or key markers, for example handover indicator metric / predicted handover events within the prediction window. The main benefit of current model is that it allows to deliver an additional information in terms of beam / cell selection on top of the legacy mobility management framework in L1 / L2 and / or L3.

[0135] In some example embodiments, the input sequence of the ML model 1030 at time t is denoted as (^^^^, … , ^^^^). Each sample ^ is a tuple of: ^ ={^, ^}= {{^^, ^^, … , ^^^^},{^^, ^^, … , ^^^^}} where ^ ={^^, ^^, … , ^^^^}is the input RSRP vector measured from from 294 beams (14 beams from 21 network devices), that is ^ = {^^, ^^, … , ^^^^}. The input frame is measured from past N ms that contains q past samples for each measurement or beam ID. In this example, gNB measures SSB every 20 ms, q=150 measurement samples are collected within the total input length N=3000 ms. So the input data is thus a 150 × 588 matrix.

[0136] In some example embodiments, the labeled data used to train the model is the sequence of RSRP samples in a given prediction window ^ ms that contains ^ past samples for each measurement or beam ID. In this example, the prediction output is the RSRP measured from from 294 beams (14 beams from 21 gNBs) in ^ = 100 ms that include ^ = 5 samples for each index. The label data is thus a 294 × 5 matrix of (^^^^, … ^^^^).

[0137] In some example embodiments, a time series prediction model is implemented to learn the dependencies of historical RSRP plus each beam index (^^^^, … , ^^^^) overthe future RSRP values (^^^^, … ^^^^). LSTM has been proven as an effective approach to tackle the long-range dependencies problem, which is used in our model design in Fig. 10. The present model comprises a set of parameters ^(^,^), associated with each input ^^. The earlier are multiplied with a weight and added to the later one, to capture the time series dependencies. The output layeris associated with each label ^^. A loss function is defined to evaluate the error between the model predicted ^^and detected ^, for example:

[0138] In the training process, optimization algorithm like stochastic gradient descend (SGD) can be applied to tune each, such that the average prediction error of samples collected from the terminal device can be minimized. The model reliability evaluation and assessment are conducted when training steps are completed.

[0139] Several different managing options that allow the terminal device or the network device vendors to design their preferred monitoring algorithms based on the output from an ML prediction model. FIG. 11 illustrates example plots of a prediction window in accordance with the embodiments of the present disclosure. The plot 1105 represents the RSRP of the strongest neighbor beam and the plot 1110 represents the RSRP of the severing beam. As shown in FIG. 11A, before handover time ^^^1115, the RSRP of the severing beam is higher than the RSRP of the strongest neighbor beam. However, after the handover time ^^^1115, the RSRP of the severing beam 1110 is lower than the RSRP of the strongest neighbor beam. Based on such prediction, the measurement gaps 1120, 1121, and 1122 which are after handover time ^^^1115, may be skipped. The generated monitoring reporting signal format 1130 is also presented.

[0140] In example embodiments of the present disclosure, superiorities in terms of time- robustness in dynamic measurement gap configuration as compared to the static legacy measurement gap configuration that require time-cost RRC reconfigurations can be provided. Solutions for dynamic measurement gap configuration are possible by using ML, with the consideration of performance tradeoff between measurement accuracy and throughput enhancement in mobility.

[0141] Moreover, potential UE power saving enhancements by reducing theunnecessary inter-frequency or inter-RAT measurement activities can be achieve by the proposed solution. A relatively low complexity signaling solution for operation of UE specific fast adaptation within RAN is provided. Interoperability between and across different vendors in NR helps intelligent algorithms formulate a shared understanding and helps make other AI and ML models across vendors more flexible.

[0142] FIG. 12 shows a flowchart of an example method 1200 implemented at a terminal device in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1200 will be described from the perspective of the terminal device 110 in FIG. 1.

[0143] At block 1210, the terminal device 110 receives, from a network device 120, a management configuration for measurement gap management based on a machine learning model.

[0144] At block 1220, the terminal device 110 obtains, based on the machine learning model, predicted mobility information of the apparatus within a time window.

[0145] At block 1230, the terminal device 110 manages one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

[0146] In some example embodiments, the management configuration comprises at least one of: an indication of whether the measurement gap management is performed autonomously by the apparatus or under control of the network device, a timing to use the machine learning model for the measurement gap management, actioning information about one or more actions available for the measurement gap management, or a signaling format for reporting the measurement gap management to the network device.

[0147] In some example embodiments, the one or more actions comprise at least one of: measurement gap skipping, measurement gap reservation, a measurement gap reconfiguration, an adjustment to a measurement gap configuration, an adaptation of a measurement gap configuration, early termination of a measurement gap, or postponing of a measurement gap.

[0148] In some example embodiments, for the adjustment to the measurement gap configuration, the action information comprises at least one of: an update to a measurement gap length, an update to a measurement gap repetition period, an update toa measurement gap timing advance, or an update to a measurement gap offset.

[0149] In some example embodiments, the method 1200 further comprises: transmitting, to the network device, a first request to configure the measurement gap management, and wherein the management configuration is received as a first response to the first request.

[0150] In some example embodiments, the method 1200 further comprises: receiving, from the network device, an indication to trigger use of the machine learning model for the measurement gap management.

[0151] In some example embodiments, managing the one or more measurement gaps comprises: transmitting, to the network device, a second request to manage the one or more measurement gaps, the second request at least comprising the predicted mobility information; receiving, from the network device, a second response indicating an action for managing the one or more measurement gaps; and performing the indicated action on the one or more measurement gap.

[0152] In some example embodiments, the method 1200 further comprises: selecting an action from the one or more actions based on the predicted mobility information, and wherein the second request indicates the selected action, and the second response comprises an acknowledge to the selected optional action or a selection of another action from the one or more actions.

[0153] In some example embodiments, the method 1200 further comprises: transmitting, to the network device, a result of performing the indicated action.

[0154] In some example embodiments, managing the one or more measurement gaps comprises: selecting an action from the one or more actions based on the predicted mobility information; and performing the selected action on the one or more measurement gap.

[0155] In some example embodiments, the method 1200 further comprises: transmitting, to the network device, an indication of the selected action and a result of performing the selected action.

[0156] FIG.13 shows a flowchart of an example method 1300 implemented at a network device in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1300 will be described from the perspective of the network device 120 in FIG. 1.

[0157] At block 1310, the network device 120 determines a management configuration for measurement gap management based on a machine learning model.

[0158] At block 1320, the network device 120 transmits the management configuration to a terminal device.

[0159] In some example embodiments, the management configuration comprises at least one of: an indication of whether the measurement gap management is performed autonomously by the terminal device or under control of the apparatus, a timing to use the machine learning model for the measurement gap management, actioning information about one or more actions available for the measurement gap management, or a signaling format for reporting the measurement gap management to the apparatus.

[0160] In some example embodiments, the one or more actions comprise at least one of: measurement gap skipping, measurement gap reservation, a measurement gap reconfiguration, an adjustment to a measurement gap configuration, an adaptation of a measurement gap configuration, early termination of a measurement gap, or postponing of a measurement gap.

[0161] In some example embodiments, for the adjustment to the measurement gap configuration, the action information comprises at least one of: an update to a measurement gap length, an update to a measurement gap repetition period, or an update to a measurement gap timing advance, or an update to a measurement gap offset.

[0162] In some example embodiments, the method 1300 further comprises: receiving, from the terminal device, a first request to configure the measurement gap management, and wherein the management configuration is transmitted as a first response to the first request.

[0163] In some example embodiments, the method 1300 further comprises: transmitting, to the terminal device, an indication to trigger use of the machine learning model for the measurement gap management.

[0164] In some example embodiments, the method 1300 further comprises: receiving, from the terminal device, a second request to manage the one or more measurement gaps, the second request at least comprising predicted mobility information obtained based on the machine learning model; and transmitting, to the terminal device, a second response indicating an action for managing the one or more measurement gaps, wherein the actionis determined based on the predicted mobility information.

[0165] In some example embodiments, the management configuration indicates one or more actions available for the measurement gap management, and wherein the second request indicates an action selected from the one or more actions, and the second response comprises an acknowledge to the selected optional action or a selection of another action from the one or more actions.

[0166] In some example embodiments, the method 1300 further comprises: receiving, from the terminal device, a result of performing the indicated action.

[0167] In some example embodiments, the management configuration indicates one or more actions available for the measurement gap management, and receiving, from the terminal device, an indication of an action selected from the one or more actions and a result of performing the selected action.

[0168] In some example embodiments, an apparatus capable of performing any of the method 1200 (for example, the terminal device 110 in FIG. 1) may comprise means for performing the respective operations of the method 1200. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The apparatus may be implemented as or included in the terminal device 110 in FIG. 1.

[0169] In some example embodiments, the apparatus comprises means for receiving, from a network device, a management configuration for measurement gap management based on a machine learning model; means for obtaining, based on the machine learning model, predicted mobility information of the apparatus within a time window; and means for managing one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

[0170] In some example embodiments, the management configuration comprises at least one of: an indication of whether the measurement gap management is performed autonomously by the apparatus or under control of the network device, a timing to use the machine learning model for the measurement gap management, means for actioning information about one or more actions available for the measurement gap management, or a signaling format for reporting the measurement gap management to the network device.

[0171] In some example embodiments, the one or more actions comprise at least one of: means for measurement gap skipping, means for measurement gap reservation, a measurement gap reconfiguration, an adjustment to a measurement gap configuration, an adaptation of a measurement gap configuration, early termination of a measurement gap, or postponing of a measurement gap.

[0172] In some example embodiments, for the adjustment to the measurement gap configuration, the action information comprises at least one of: an update to a measurement gap length, an update to a measurement gap repetition period, an update to a measurement gap timing advance, or an update to a measurement gap offset.

[0173] In some example embodiments, the apparatus further comprises: means for transmitting, to the network device, a first request to configure the measurement gap management, and wherein the management configuration is received as a first response to the first request.

[0174] In some example embodiments, the apparatus further comprises: means for receiving, from the network device, an indication to trigger use of the machine learning model for the measurement gap management.

[0175] In some example embodiments, the means for managing one or more measurement gaps comprises: means for transmitting, to the network device, a second request to manage the one or more measurement gaps, the second request at least comprising the predicted mobility information; means for receiving, from the network device, a second response indicating an action for managing the one or more measurement gaps; and means for performing the indicated action on the one or more measurement gap.

[0176] In some example embodiments, the management configuration indicates one or more actions available for the measurement gap management, the apparatus further comprises: means for selecting an action from the one or more actions based on the predicted mobility information, and wherein the second request indicates the selected action, and the second response comprises an acknowledge to the selected optional action or a selection of another action from the one or more actions.

[0177] In some example embodiments, the apparatus further comprises: means for transmitting, to the network device, a result of performing the indicated action.

[0178] In some example embodiments, the management configuration indicates one ormore actions available for the measurement gap management, the means for managing one or more measurement gaps comprises: means for selecting an action from the one or more actions based on the predicted mobility information; and means for performing the selected action on the one or more measurement gap.

[0179] In some example embodiments, the apparatus further comprises: means for transmitting, to the network device, an indication of the selected action and a result of performing the selected action.

[0180] In some example embodiments, the apparatus further comprises means for performing other operations in some example embodiments of the method 1200 or the terminal device 110. In some example embodiments, the means comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the apparatus.

[0181] In some example embodiments, an apparatus capable of performing any of the method 1300 (for example, the network device 120 in FIG. 1) may comprise means for performing the respective operations 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. The apparatus may be implemented as or included in the network device 120 in FIG. 1.

[0182] In some example embodiments, the apparatus comprises means for determining a management configuration for measurement gap management based on a machine learning model; and means for transmitting the management configuration to a terminal device.

[0183] In some example embodiments, the management configuration comprises at least one of: an indication of whether the measurement gap management is performed autonomously by the terminal device or under control of the apparatus, a timing to use the machine learning model for the measurement gap management, means for actioning information about one or more actions available for the measurement gap management, or a signaling format for reporting the measurement gap management to the apparatus.

[0184] In some example embodiments, the one or more actions comprise at least one of: means for measurement gap skipping, means for measurement gap reservation, a measurement gap reconfiguration, an adjustment to a measurement gap configuration, anadaptation of a measurement gap configuration, early termination of a measurement gap, or postponing of a measurement gap.

[0185] In some example embodiments, for the adjustment to the measurement gap configuration, the action information comprises at least one of: an update to a measurement gap length, an update to a measurement gap repetition period, or an update to a measurement gap timing advance, or an update to a measurement gap offset.

[0186] In some example embodiments, the apparatus further comprises: means for receiving, from the terminal device, a first request to configure the measurement gap management, and wherein the management configuration is transmitted as a first response to the first request.

[0187] In some example embodiments, the apparatus further comprises: means for transmitting, to the terminal device, an indication to trigger use of the machine learning model for the measurement gap management.

[0188] In some example embodiments, the apparatus further comprises: means for receiving, from the terminal device, a second request to manage the one or more measurement gaps, the second request at least comprising predicted mobility information obtained based on the machine learning model; and means for transmitting, to the terminal device, a second response indicating an action for managing the one or more measurement gaps, wherein the action is determined based on the predicted mobility information.

[0189] In some example embodiments, the management configuration indicates one or more actions available for the measurement gap management, and wherein the second request indicates an action selected from the one or more actions, and the second response comprises an acknowledge to the selected optional action or a selection of another action from the one or more actions.

[0190] In some example embodiments, the apparatus further comprises: means for receiving, from the terminal device, a result of performing the indicated action.

[0191] In some example embodiments, the management configuration indicates one or more actions available for the measurement gap management, and means for receiving, from the terminal device, an indication of an action selected from the one or more actions and a result of performing the selected action.

[0192] In some example embodiments, the apparatus further comprises means forperforming other operations in some example embodiments of the method 1300 or the network device 120. In some example embodiments, the means comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the apparatus.

[0193] FIG. 14 is a simplified block diagram of a device 1400 that is suitable for implementing example embodiments of the present disclosure. The device 1400 may be provided to implement a communication device, for example, the terminal device 110 or the network device 120 as shown in FIG. 1. As shown, the device 1400 includes one or more processors 1410, one or more memories 1420 coupled to the processor 1410, and one or more communication modules 1440 coupled to the processor 1410.

[0194] The communication module 1440 is for bidirectional communications. The communication module 1440 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interfaces may represent any interface that is necessary for communication with other network elements. In some example embodiments, the communication module 1440 may include at least one antenna.

[0195] The processor 1410 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 1400 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.

[0196] The memory 1420 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) 1424, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random access memory (RAM) 1422 and other volatile memories that will not last in the power-down duration.

[0197] A computer program 1430 includes computer executable instructions that are executed by the associated processor 1410. The instructions of the program 1430 mayinclude instructions for performing operations / acts of some example embodiments of the present disclosure. The program 1430 may be stored in the memory, e.g., the ROM 1424. The processor 1410 may perform any suitable actions and processing by loading the program 1430 into the RAM 1422.

[0198] The example embodiments of the present disclosure may be implemented by means of the program 1430 so that the device 1400 may perform any process of the disclosure as discussed with reference to FIG.5 to FIG.13. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0199] In some example embodiments, the program 1430 may be tangibly contained in a computer readable medium which may be included in the device 1400 (such as in the memory 1420) or other storage devices that are accessible by the device 1400. The device 1400 may load the program 1430 from the computer readable medium to the RAM 1422 for execution. In some example embodiments, the computer readable medium may include any types of non-transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0200] FIG. 15 shows an example of the computer readable medium 1500 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 1500 has the program 1430 stored thereon.

[0201] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0202] Some example embodiments of the present disclosure also provide at least onecomputer program product tangibly stored on a computer readable medium, such as a non- transitory computer readable medium. The computer program product includes computer- executable instructions, such as those included in program modules, being executed in a device on a target physical or virtual processor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. 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.

[0203] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0204] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0205] 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.

[0206] Further, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable sub-combination.

[0207] 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. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network device, a management configuration for measurement gap management based on a machine learning model; obtain, based on the machine learning model, predicted mobility information of the apparatus within a time window; and manage one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

2. The apparatus of claim 1, wherein the management configuration comprises at least one of: an indication of whether the measurement gap management is performed autonomously by the apparatus or under control of the network device, a timing to use the machine learning model for the measurement gap management, action information about one or more actions available for the measurement gap management, or a signaling format for reporting the measurement gap management to the network device.

3. The apparatus of claim 2, wherein the one or more actions comprise at least one of: measurement gap skipping, measurement gap reservation, a measurement gap reconfiguration, an adjustment to a measurement gap configuration, an adaptation of a measurement gap configuration, early termination of a measurement gap, or postponing of a measurement gap.

4. The apparatus of claim 3, wherein for the adjustment to the measurement gap configuration, the action information comprises at least one of:an update to a measurement gap length, an update to a measurement gap repetition period, an update to a measurement gap timing advance, or an update to a measurement gap offset.

5. The apparatus of claim 1, wherein the instructions, when executed by the at least one processor, further cause the apparatus to: transmit, to the network device, a first request to configure the measurement gap management, and wherein the management configuration is received as a first response to the first request.

6. The apparatus of claim 1, wherein the instructions, when executed by the at least one processor, further cause the apparatus to: receive, from the network device, an indication to trigger use of the machine learning model for the measurement gap management.

7. The apparatus of claim 1, wherein the instructions, when executed by the at least one processor, cause the apparatus to: transmit, to the network device, a second request to manage the one or more measurement gaps, the second request at least comprising the predicted mobility information; receive, from the network device, a second response indicating an action for managing the one or more measurement gaps; and perform the indicated action on the one or more measurement gap.

8. The apparatus of claim 7, wherein the management configuration indicates one or more actions available for the measurement gap management, and the instructions, when executed by the at least one processor, further cause the apparatus to: select an action from the one or more actions based on the predicted mobility information, and wherein the second request indicates the selected action, and the second response comprises an acknowledge to the selected optional action or a selection of another action from the one or more actions.

9. The apparatus of claim 7, wherein the instructions, when executed by the at least one processor, further cause the apparatus to: transmit, to the network device, a result of performing the indicated action.

10. The apparatus of claim 1, wherein the management configuration indicates one or more actions available for the measurement gap management, and the instructions, when executed by the at least one processor, cause the apparatus to: select an action from the one or more actions based on the predicted mobility information; and perform the selected action on the one or more measurement gap.

11. The apparatus of claim 10, wherein the instructions, when executed by the at least one processor, further cause the apparatus to: transmit, to the network device, an indication of the selected action and a result of performing the selected action.

12. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine a management configuration for measurement gap management based on a machine learning model; and transmit the management configuration to a terminal device.

13. The apparatus of claim 12, wherein the management configuration comprises at least one of: an indication of whether the measurement gap management is performed autonomously by the terminal device or under control of the apparatus, a timing to use the machine learning model for the measurement gap management, action information about one or more actions available for the measurement gap management, or a signaling format for reporting the measurement gap management to the apparatus.

14. The apparatus of claim 13, wherein the one or more actions comprise at least oneof: measurement gap skipping, measurement gap reservation, a measurement gap reconfiguration, an adjustment to a measurement gap configuration, an adaptation of a measurement gap configuration, early termination of a measurement gap, or postponing of a measurement gap.

15. The apparatus of claim 14, wherein for the adjustment to the measurement gap configuration, the action information comprises at least one of: an update to a measurement gap length, an update to a measurement gap repetition period, or an update to a measurement gap timing advance, or an update to a measurement gap offset.

16. The apparatus of claim 12, wherein the instructions, when executed by the at least one processor, further cause the apparatus to: receive, from the terminal device, a first request to configure the measurement gap management, and wherein the management configuration is transmitted as a first response to the first request.

17. The apparatus of claim 12, wherein the instructions, when executed by the at least one processor, further cause the apparatus to: transmit, to the terminal device, an indication to trigger use of the machine learning model for the measurement gap management.

18. The apparatus of claim 12, wherein the instructions, when executed by the at least one processor, further cause the apparatus to: receive, from the terminal device, a second request to manage the one or more measurement gaps, the second request at least comprising predicted mobility information obtained based on the machine learning model; and transmit, to the terminal device, a second response indicating an action for managingthe one or more measurement gaps, wherein the action is determined based on the predicted mobility information.

19. The apparatus of claim 18, wherein the management configuration indicates one or more actions available for the measurement gap management, and wherein the second request indicates an action selected from the one or more actions, and the second response comprises an acknowledge to the selected optional action or a selection of another action from the one or more actions.

20. The apparatus of claim 19, wherein the instructions, when executed by the at least one processor, further cause the apparatus to: receive, from the terminal device, a result of performing the indicated action.

21. The apparatus of claim 12, wherein the management configuration indicates one or more actions available for the measurement gap management, and wherein the instructions, when executed by the at least one processor, further cause the apparatus to: receive, from the terminal device, an indication of an action selected from the one or more actions and a result of performing the selected action.

22. A method comprising: receiving, at an apparatus from a network device, a management configuration for measurement gap management based on a machine learning model; obtaining, based on the machine learning model, predicted mobility information of the apparatus within a time window; and managing one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

23. A method comprising: determining, at an apparatus, a management configuration for measurement gap management based on a machine learning model; and transmitting the management configuration to a terminal device.

24. A computer readable medium comprising instructions stored thereon for causingan apparatus at least to perform the method comprising: receiving, from a network device, a management configuration for measurement gap management based on a machine learning model; obtaining, based on the machine learning model, predicted mobility information of the apparatus within a time window; and managing one or more measurement gaps within the time window based on the management configuration and the predicted mobility information.

25. A computer readable medium comprising instructions stored thereon for causing an apparatus at least to perform the method comprising: determining a management configuration for measurement gap management based on a machine learning model; and transmitting the management configuration to a terminal device.

Images