Apparatus, method and computer program

Abstract

There is provided an apparatus comprising means for receiving, at the apparatus, a measurement configuration to record measurements in a recording window based on a trigger; means for recording one or more measurements in a recording window based on a measurement configuration; means for determining, based on a condition, that the recorded measurements are reported after the recording window; and means for reporting the logged measurements based on the determination.

Description

TECHNICAL FIELD

[0001] The present application relates to a method, apparatus and computer program, and in particular, but not exclusively, to measurement reporting suspension. BACKGROUND

[0002] A communication system can be seen as a facility that enables communication sessions between two or more entities such as user terminals, base stations and / or other nodes by providing carriers which are connected to the entities involved in a communication session. A communication system can be provided for one particular telecommunication system or for several telecommunication systems. A communication system can also be seen as a facility that provides access to one or more services for communication sessions. A communication system can be implemented as a wired or wireless system or as a combination of both. A wired system can use, for example, copper, cable, optical or other wires to connect the nodes involved in a communication session. A wireless system can use, for example, wireless networks, mobile telecommunication systems, satellite systems or a combination of these or other systems. A communication system can be, for example, a public switched telephone network, the Internet, a local area network, a wide area network, a metropolitan area network, a cable network, a fiber optic network, a satellite network or any combination thereof. A communication system can be implemented using hardware components or a combination of hardware and software components.

[0003] In a wireless communication system at least a part of the communication sessions between at least two stations occurs over a wireless link. Examples of wireless systems include public land mobile networks (PLMN), satellite based communication systems and different wireless local networks, such as wireless local area networks (WLAN). Some wireless systems can be divided into cells, and are therefore often referred to as cellular systems.

[0004] A user can access the communication system through appropriate communication equipment or terminal. The user's communication equipment can be referred to as user equipment (UE) or user equipment. The communication equipment is provided with appropriate signal receiving and transmitting devices for enabling communication, for example for enabling access to a communication network or for directly communicating with other users. The communication equipment can access the carriers provided by stations, such as base stations of a cell, and transmit and / or receive communication on the carriers.

[0005] The communication system and associated devices typically operate in accordance with a given standard or specification which sets out what the various entities associated with the system are allowed to do and how that should be achieved. The communication protocols and / or parameters used for the connection are also typically defined. An example of a communication system is the Universal Mobile Telecommunication System (UMTS) Terrestrial Radio Access Network (UTRAN) (3G radio). Other examples of communication systems are the Long Term Evolution (LTE) of the Universal Mobile Telecommunication System (UMTS) radio access technology and the so-called 5G or New Radio (NR) networks. NR is being standardized via the Third Generation Partnership Project (3GPP). Other examples of communication systems include Advanced 5G (NR Rel-18 and beyond) and 6G. SUMMARY

[0006] In a first aspect, an apparatus is provided, comprising: means for receiving, at the apparatus, a measurement configuration to record measurements in a recording window based on a trigger; means for recording one or more measurements in the recording window based on the measurement configuration; means for determining to report the recorded measurements after the recording window based on a condition; and means for reporting the recorded measurements based on the determination.

[0007] The apparatus can comprise: means for receiving, at the apparatus, an indication from a network to suspend measurement reporting for at least one of a given cell or beam for a time period, wherein the trigger comprises the indication and means for suspending measurement reporting based on the indication.

[0008] The indication to suspend measurement reporting can comprise a validity timer.

[0009] The validity timer can comprise at least one of: a time period, or a start time and a stop time.

[0010] The apparatus can comprise: means for suspending measurement reporting upon receiving the indication to suspend measurement reporting or based on a subsequent event trigger if the validity timer comprises a time period.

[0011] The measurement configuration can be for at least one beam or cell for which measurement reporting has been suspended.

[0012] The measurement configuration can further comprise at least one beam or cell for which measurement reporting has not been suspended.

[0013] The recording window can be a function of the validity timer.

[0014] The apparatus can comprise: means for determining a prediction of an event, and means for determining to record measurements during the recording window based on the prediction of the event.

[0015] The apparatus can comprise: means for determining, at a user equipment, a prediction of an event using a machine learning model, the prediction having an associated confidence value, the confidence value indicating a confidence level of the machine learning model used for the prediction.

[0016] The apparatus can comprise: means for receiving, from a network, an indication of a predicted event, the prediction having an associated confidence value, the confidence value indicating a confidence level of the machine learning model used for the prediction.

[0017] The confidence value can be below a given threshold.

[0018] The periodicity of the measurements can depend on the confidence value.

[0019] The apparatus can comprise: means for determining to report the recorded measurements if the predicted event does not occur.

[0020] The apparatus can comprise means for determining, without prediction, that an event has occurred, and means for reporting the logged measurements from the user equipment to the network based on the determining.

[0021] In a second aspect, there is provided an apparatus comprising means for providing a measurement configuration from a network to a user equipment to log measurements in a logging window based on a trigger, and means for receiving logged measurements from the user equipment.

[0022] The apparatus can comprise means for determining, based on a first machine learning model, to suspend measurement reporting for at least one given cell or beam for a first time period, and means for providing an indication to the user equipment to suspend measurement reporting for at least one of the given cells or beams, wherein the trigger comprises the indication.

[0023] The indication to suspend measurement reporting can comprise a validity timer.

[0024] The logging window can be a function of the validity timer.

[0025] The validity timer can comprise at least one of: a time period, or a start time and a stop time.

[0026] The measurement configuration can be for at least one beam or cell for which measurement reporting has been suspended.

[0027] The measurement configuration can further comprise at least one beam or cell for which measurement reporting has not been suspended.

[0028] The apparatus can comprise means for determining, at the network, a prediction of an event, and means for providing an indication of the prediction of the event from the network to a further apparatus for determining to log measurements.

[0029] The apparatus can comprise means for determining, using a second machine learning model, a prediction of an event, the prediction having an associated confidence value, the confidence value indicating a level of confidence of the machine learning model used for the prediction.

[0030] The confidence value can be below a given threshold.

[0031] The periodicity of the measurements can depend on the confidence value.

[0032] In a third aspect, there is provided a method comprising: receiving, at an apparatus, a measurement configuration to log measurements in a logging window based on a trigger; logging one or more measurements in the logging window based on the measurement configuration; determining, based on a condition, to report the logged measurements after the logging window; and reporting the logged measurements based on the determining.

[0033] The method can comprise receiving, at the apparatus, an indication from the network to suspend measurement reporting for at least one of the given cells or beams for a time period, wherein the trigger comprises the indication and suspending the measurement reporting based on the indication.

[0034] The indication to suspend the measurement reporting can comprise a validity timer.

[0035] The validity timer can comprise at least one of: a time period, or a start time and a stop time.

[0036] The method can comprise suspending the measurement reporting upon receiving the indication to suspend the measurement reporting or based on a subsequent event trigger if the validity timer comprises a time period.

[0037] The measurement configuration can be for at least one beam or cell for which measurement reporting has been suspended.

[0038] The measurement configuration can further comprise at least one beam or cell for which measurement reporting has not been suspended.

[0039] The logging window can be a function of the validity timer.

[0040] The method can comprise determining a prediction of the event and determining to log the measurements during the logging window based on the prediction of the event.

[0041] The method can comprise determining, at the user equipment, a prediction of the event using a machine learning model, the prediction having an associated confidence value, the confidence value indicating a level of confidence of the machine learning model used for the prediction.

[0042] The method can comprise receiving, from the network, an indication of a predicted event, the prediction having an associated confidence value, the confidence value indicating a level of confidence of the machine learning model used for the prediction.

[0043] The confidence value can be below a given threshold.

[0044] The periodicity of the measurements can depend on the confidence value.

[0045] The method can comprise determining to report the logged measurements if the predicted event does not occur.

[0046] The method can comprise determining, without a prediction, that the event has occurred and reporting the logged measurements from the user equipment to the network based on the determination.

[0047] In a fourth aspect, there is provided a method comprising: providing, from a network to a user equipment, a measurement configuration to log measurements in a logging window based on a trigger, and receiving, at the network from the user equipment, the logged measurements.

[0048] The method may include: determining, based on a first machine learning model, to suspend measurement reports for at least one given cell or beam during a first time period, and providing an instruction to a user equipment to suspend measurement reports for at least one of the given cells or beams, wherein the trigger includes the instruction.

[0049] Instructions to pause measurement reports may include validity timers.

[0050] The logging window can function as a validity timer.

[0051] A validity timer may include at least one of the following: a time period, or a start time and a stop time.

[0052] The measurement configuration can be used for at least one beam or cell whose measurement reports have been suspended.

[0053] The measurement configuration may also include at least one beam or cell that has not yet been suspended.

[0054] The method may include: determining the prediction of an event at the network, and providing an indication of the event prediction from the network to another device for determining recorded measurements.

[0055] The method may include: using a second machine learning model to determine a prediction of the event, the prediction having an associated confidence value that indicates the confidence level of the machine learning model used for the prediction.

[0056] The confidence value can be lower than a given threshold.

[0057] The periodicity of the measurement can depend on the confidence value.

[0058] In a fifth aspect, an apparatus is provided, comprising: at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the apparatus to at least: receive a measurement configuration at the apparatus for recording a measurement in a recording window based on a trigger; record one or more measurements in the recording window based on the measurement configuration; determine, based on a condition, to report the recorded measurement after the recording window; and report the recorded measurement based on the determination.

[0059] The device can be configured to: receive at the device an instruction from the network to suspend measurement reports for at least one of a given cell or beam during a time period, wherein triggering includes the instruction and suspending the measurement reports based on the instruction.

[0060] Instructions to pause measurement reports may include validity timers.

[0061] A validity timer may include at least one of the following: a time period, or a start time or a stop time.

[0062] The apparatus can be caused to suspend the measurement reporting upon receiving the indication to suspend the measurement reporting or based on a subsequent event trigger if the validity timer comprises a time period.

[0063] The measurement configuration can be for at least one beam or cell for which measurement reporting has been suspended.

[0064] The measurement configuration can further comprise at least one beam or cell for which measurement reporting has not been suspended.

[0065] The logging window can be a function of the validity timer.

[0066] The apparatus can be caused to determine a prediction of the event and determine to log the measurements during the logging window based on the prediction of the event.

[0067] The apparatus can be caused to determine, at the user equipment, a prediction of the event using a machine learning model, the prediction having an associated confidence value, the confidence value indicating a confidence level of the machine learning model used for the prediction.

[0068] The apparatus can be caused to receive, from the network, an indication of a prediction of the event, the prediction having an associated confidence value, the confidence value indicating a confidence level of the machine learning model used for the prediction.

[0069] The confidence value can be below a given threshold.

[0070] The periodicity of the measurements can depend on the confidence value.

[0071] The apparatus can be caused to determine to report the logged measurements if the predicted event does not occur.

[0072] The apparatus can be caused to determine, without the prediction, that the event has occurred and report the logged measurements from the user equipment to the network based on the determination.

[0073] In a sixth aspect, there is provided 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 provide, by the apparatus, a measurement configuration to a user equipment to log measurements in a logging window based on a trigger and receive, at the apparatus, logged measurements from the user equipment.

[0074] The apparatus can be caused to determine, based on a first machine learning model, to suspend measurement reporting for at least one given cell or beam for a first time period and means for providing, by the apparatus, an indication to the user equipment to suspend measurement reporting for at least one of the given cells or beams, wherein the trigger comprises the indication.

[0075] The indication to suspend the measurement reporting can comprise a validity timer.

[0076] The logging window can be a function of the validity timer.

[0077] The validity timer can comprise at least one of: a time period, or a start time and a stop time.

[0078] The measurement configuration can be for at least one beam or cell for which measurement reporting has been suspended.

[0079] The measurement configuration can further comprise at least one beam or cell for which measurement reporting has not been suspended.

[0080] The apparatus can be caused to: determine, at the network, a prediction of the event, and provide, from the network to the further apparatus, an indication of the prediction of the event for use in determining to log the measurements.

[0081] The apparatus can be caused to: determine, using a second machine learning model, a prediction of the event, the prediction having an associated confidence value, the confidence value indicating a confidence level of the machine learning model for the measurement.

[0082] The confidence value can be below a given threshold.

[0083] The periodicity of the measurements can depend on the confidence value.

[0084] In a seventh aspect, there is provided a computer readable medium comprising instructions that, when executed by an apparatus, cause the apparatus to perform at least the following: receive, at the apparatus, a measurement configuration to log measurements in a logging window based on a trigger; log one or more measurements in the logging window based on the measurement configuration; determine to report the logged measurements after the logging window based on a condition; and report the logged measurements based on the determination.

[0085] The apparatus can be caused to receive, at the apparatus, an indication from the network to suspend measurement reporting for at least one of the given cells or beams for a time period, wherein the trigger comprises the indication and suspending the measurement reporting based on the indication.

[0086] The indication to suspend the measurement reporting can comprise a validity timer.

[0087] The validity timer can comprise at least one of: a time period, or a start time and a stop time.

[0088] The apparatus can be caused to perform: if the validity timer comprises a time period, suspending the measurement reporting upon receiving the indication to suspend the measurement reporting or based on a subsequent event trigger.

[0089] The measurement configuration can be for at least one beam or cell for which measurement reporting has been suspended.

[0090] The measurement configuration can further comprise at least one beam or cell for which measurement reporting has not been suspended.

[0091] The logging window can be a function of the validity timer.

[0092] The apparatus can be caused to perform determining a prediction of the event, and determining to log measurements during the logging window based on the prediction of the event.

[0093] The apparatus can be caused to perform determining, at the user equipment, a prediction of the event using a machine learning model, the prediction having an associated confidence value indicating a confidence level of the machine learning model used for the prediction.

[0094] The apparatus can be caused to perform receiving, from the network, an indication of a predicted event, the prediction having an associated confidence value indicating a confidence level of the machine learning model used for the prediction.

[0095] The confidence value can be below a given threshold.

[0096] The periodicity of the measurements can depend on the confidence value.

[0097] The apparatus can be caused to perform determining to report the logged measurements if the predicted event does not occur.

[0098] The apparatus can be caused to perform determining, without the prediction, that the event has occurred, and means for reporting the logged measurements from the user equipment to the network based on the determination.

[0099] In an eighth aspect, there is provided a computer readable medium comprising instructions that, when executed by an apparatus, cause the apparatus to perform at least the following: providing, by the apparatus, a measurement configuration to a user equipment to log measurements in a logging window based on a trigger; and receiving, at the apparatus, logged measurements from a further user equipment.

[0100] The apparatus can be caused to perform determining, based on a first machine learning model, to suspend measurement reporting for at least one given cell or beam for a first time period; and providing, from the network, an indication to suspend measurement reporting for at least one of the given cells or beams to a further apparatus, wherein the trigger comprises the indication.

[0101] The indication to suspend measurement reporting can comprise a validity timer.

[0102] The logging window can be a function of the validity timer.

[0103] The validity timer can comprise at least one of: a time period, or a start time and a stop time.

[0104] The measurement configuration can be for at least one beam or cell for which measurement reporting has been suspended.

[0105] The measurement configuration can further comprise at least one beam or cell that has not been suspended.

[0106] The apparatus can be caused to perform determining, at the network, a prediction of the event, and providing, from the network to the further apparatus, an indication of the prediction of the event for use in determining to record the measurement.

[0107] The apparatus can be caused to perform determining, using a second machine learning model, a prediction of the event, the prediction having an associated confidence value, the confidence value being indicative of a confidence level of the machine learning model used for the prediction.

[0108] The confidence value can be below a given threshold.

[0109] The periodicity of the measurement can depend on the confidence value.

[0110] In a ninth aspect, there is provided a non-transitory computer readable medium comprising program instructions for causing an apparatus to perform at least the method according to the third aspect or the fourth aspect.

[0111] In the foregoing, a number of different embodiments have been described. It will be appreciated that further embodiments can be provided by a combination of any two or more of the embodiments described above. BRIEF DESCRIPTION OF DRAWINGS

[0112] Embodiments will now be described, by way of example only, with reference to the accompanying drawings in which:

[0113] Figure 1 A schematic diagram illustrating an example 5GS communication system is shown;

[0114] Figure 2 A schematic diagram illustrating an example mobile communication device is shown;

[0115] Figure 3 A schematic diagram illustrating an example control apparatus is shown;

[0116] Figure 4 A plot of RSRP against time for an A3 event is shown;

[0117] Figure 5 A schematic illustration of an ML model setting a suspension state of a UE is shown;

[0118] Figure 6a A timeline of operation of a suspension state is shown;

[0119] Figure 6b A timeline of operation of a suspension state is shown;

[0120] Figure 7 A flow diagram of a method according to an example embodiment is shown;

[0121] Figure 8 A flow diagram of a method according to example embodiments is shown;

[0122] Figure 9 A schematic diagram of a timer for de-configuring a suspended state according to example embodiments is shown;

[0123] Figure 10 A timeline for the setting of a suspended state according to example embodiments is shown;

[0124] Figure 11a A flow diagram of a method for mobility event triggered data collection according to example embodiments is shown;

[0125] Figure 11b A flow diagram of a method for suspension event triggered data collection according to example embodiments is shown;

[0126] Figure 12 A timeline for logging and reporting measurements triggered by a predicted mobility event is shown;

[0127] Figure 13 A timeline for logging and reporting measurements triggered by a suspension event is shown;

[0128] Figure 14 A signalling diagram between a UE and a gNB according to example embodiments is shown;

[0129] Figure 15 A signalling diagram between a UE and a gNB according to example embodiments is shown;

[0130] Figure 16 A signalling diagram between a UE and a gNB according to example embodiments is shown. DETAILED DESCRIPTION

[0131] Before the examples are explained in detail, reference is made to Figure 1 , Figure 2 and Figure 3 to explain certain general principles of wireless communication systems and mobile communication systems, to help understand the technology upon which the described examples are based.

[0132] An example of a suitable communications system is the 5G or NR concept. The network architecture in NR can be similar to that of LTE-Advanced. The base stations of the NR system can be referred to as next generation NodeBs (gNBs). Changes to the network architecture can depend on the need to support various radio technologies as well as finer quality of service (QoS) support, and on-demand basis for QoS levels to support, for example, quality of experience (QoE) for users. In addition, network-aware services and applications, as well as services- and application-aware networks, can bring changes to the architecture. These are related to information-centric networking (ICN) and user-centric content delivery network (UC-CDN) approaches. NR can use multiple-input multiple-output (MIMO) antennas, many more base stations or nodes than LTE (the so-called small cell concept), including macro sites operating in co-operation with smaller stations and possibly also employing a variety of radio technologies for better coverage and enhanced data rates.

[0133] Future networks can utilize network function virtualization (NFV), which is a network architecture concept that proposes virtualizing network node functions into "building blocks" or entities that can be operationally linked or chained together to provide services. A virtualized network function (VNF) can comprise one or more virtual machines using standard or generic type servers instead of customized hardware to run computer program codes. Cloud computing or data storage can also be utilized. In wireless communication, this can mean that node operations are performed at least partly in servers, hosts, or nodes that are operationally coupled with remote radio heads. Node operations can also be distributed among a plurality of servers, nodes, or hosts. It should be understood that the distribution of labor between core network operations and base station operations can be different from that of the LTE or even absent.

[0134] Figure 1 A schematic representation of a 5G system (5GS) 100 is shown. The 5GS can comprise a user equipment (UE) 102 (also referred to as a communication device or terminal), a 5G radio access network (5G RAN) 104, a 5G core network (5G CN) 106, one or more internal or external application functions (AF) 108, and one or more data networks (DN) 110.

[0135] An example 5G core network (CN) includes functional entities. The 5G CN 106 can include one or more access and mobility management functions (AMF) 112, one or more session management functions (SMF) 114, an authentication server function (AUSF) 116, a unified data management (UDM) 118, one or more user plane functions (UPF) 120, a unified data repository (UDR) 122, and / or a network exposure function (NEF) 124. The UPF is controlled by the SMF (session management function), which receives policies from the PCF (policy control function).

[0136] The CN is connected via a radio access network (RAN) to the UE. The 5G RAN can include one or more gNodeB (gNB) distributed unit (DU) functions connected to one or more gNodeB (gNB) centralized unit (CU) functions. The RAN can include one or more access nodes.

[0137] A user plane function (UPF), referred to as a PDU session anchor (PSA), can be responsible for forwarding frames to and from a UE exchanging traffic with a DN back and forth between the DN and a tunnel established over 5G.

[0138] A possible mobile communication device will now be described in more detail with reference to the accompanying drawings. Figure 2 Figure 2 ​A schematic partial cross-section of a communication device 200 is shown. Such a communication device is often referred to as user equipment (UE) or terminal. A suitable mobile communication device can be provided by any device capable of sending and receiving radio signals. Non-limiting examples include: a mobile station (MS) or mobile device such as a mobile phone or a mobile device known as a'smart phone', a computer provided with a wireless interface card or other wireless interface facility (e.g., USB dongle), a personal data assistant (PDA) or a tablet provided with wireless communication capabilities, a voice over IP (VoIP) phone, a portable computer, a desktop computer, an image capture terminal device such as a digital camera, a game terminal device, a music storage and playback appliance, a vehicular wireless terminal device, a wireless endpoint, a mobile station, a laptop embedded equipment (LEE), a laptop mounted equipment (LME), a smart device, a wireless customer-premises equipment (CPE), or any combination of these or the like. For example, a mobile communication device can provide communication for carrying communications such as voice, electronic mail (email), text message, multimedia, and so on. Thus, a user of a communication device can be offered and provided numerous services via the communication device. Non-limiting examples of these devices include two-way or multi-way calling, data communication or multimedia services, or simply access to data communication network systems such as the Internet. A user can also be provided broadcast or multicast data. Non-limiting examples of content include downloads, television and radio programs, videos, advertisements, various alerts, and other information.

[0139] A communication device is typically provided with at least one data processing entity 201, at least one memory 202, and other possible components 203 for use in software and hardware aided execution of tasks it is designed to perform, including control of access to and communications with access systems and other communication devices. Data processing, storage, and other related control devices can be provided on appropriate circuit boards and / or in chipsets. This feature is denoted by reference 204. A user can control the operation of the mobile device by means of a suitable user interface such as key pad 205, voice commands, touch sensitive screen or touchpad, combinations thereof or the like. A display 208, a speaker, and a microphone can also be provided. Furthermore, the mobile communication device can comprise appropriate connectors (either wired or wireless) to other devices and / or for connecting external accessories, for example hands-free equipment, to it.

[0140] The mobile device 200 can receive signals over the air interface or radio interface 207, on which signals are conveyed, via appropriate apparatus for receiving the signals and can transmit signals via appropriate apparatus for transmitting the signals. The mobile device 200 can further comprise appropriate power supply means for supplying power to the mobile device 200, at least during its use. Figure 2In some embodiments, the transceiver arrangement is schematically represented by a block 206. The transceiver arrangement 206 can be provided, for example, by a radio part and an associated antenna arrangement. The antenna arrangement can be arranged internally or externally to the mobile device.

[0141] Figure 3 An example of a control apparatus 300 for a communication system is shown, e.g. coupled with a station of an access system and / or for controlling a station of an access system, such as a RAN node (e.g. a base station, eNB or gNB), a relay node or a core network node (such as an MME or a Serving Gateway (S-GW) or a Packet Data Network Gateway (P-GW)), or a core network function (such as an AMF / SMF), or a server or a host. The method can be implemented in a single control apparatus, or across more than one control apparatus. The control apparatus can be integrated with a node or module of a core network or RAN, or external to a node or module of a core network or RAN. In some embodiments, a base station comprises a separate control apparatus unit or module. In other embodiments, the control apparatus can be another network element, such as a radio network controller or a spectrum controller. In some embodiments, each base station can have such a control apparatus as well as a control apparatus provided in a radio network controller. The control apparatus 300 can be arranged to provide control of communications in a service area of the system. The control apparatus 300 comprises at least one memory 301, at least one data processing unit 302, 303, and an input / output interface 304. Via the interface, the control apparatus can be coupled with a receiver and a transmitter of a base station. The receiver and / or transmitter can be implemented as a radio front-end or a remote radio head.

[0142] The following relates to measurement reporting savings. Existing mechanisms for UE measurement reporting configuration involve, for example, reporting configuration for baseline handover (BHO).

[0143] For non-low layer triggered mobility (LTM) (e.g. BHO, conditional handover (CHO), etc.), measurement reporting is sent as an RRC message. The triggering of those reports and related mechanisms are described in 3GPP specifications.

[0144] A UE can be configured by the network to report measurements for up to N measurement IDs, where N is an integer value and N is decided based on UE capabilities. For example, a list of "measldToAddMod" is configured to the UE, where each entry in the list links a measurement ID (measld) to a measurement object ID (measObjld) and a reporting configuration ID (reportConfigld). Thus, for a given measurement ID, the UE performs measurements on the measurement object it refers to and applies the criteria provided in the corresponding reporting configuration.

[0145] Each reportConfig describes the way in which a report should occur, e.g. periodically, or event triggered, such as by the A3 event typically used by the network to perform a handover of the UE from a source cell to a target cell (i.e. primary / PCell change).

[0146] Figure 4 An example scenario is illustrated of how the A3 event works when the RSRP changes over time. In A3, after the triggering condition (e.g. neighbor RSRP better compensated (offset) than serving RSRP) is met, and after the time-to-trigger (TTT) has passed while the condition is still true, a measurement report is sent (according to the reporting configuration with the given reporting interval). The network is responsible for reacting to these measurement reports, e.g. by following up with baseline HO commands (Rel-15) or initiating preparation for conditional HO (according to Rel-16). A3 includes an exit condition that also triggers a measurement report by the UE.

[0147] A3 is triggered for a specific cell or beam, and the reporting procedure adds to the UE variable varMeasReport for that beam or cell the data that will be sent as a report. Multiple cells can be reported for the same ReportConfig.

[0148] In LTM, the L1 measurement reports are sent in a periodic (or semi-static or aperiodic) manner on the MAC protocol layer. The configuration for these reports is delivered to the UE via the RRC message “CSI-ReportConfig”.

[0149] The IE CSI-ReportConfig is used to configure periodic or semi-persistent reporting sent on PUCCH on the cell where the CSI-ReportConfig is included, or to configure semi-persistent or aperiodic reporting sent on PUSCH triggered by a DCI received on the cell where the CSI-ReportConfig is included (in which case the cell on which the report is sent is determined by the received DCI). The IE CSI-ReportConfigId is used to identify one CSI-ReportConfig (e.g. section 5.2.1 of TS 38.214 and CSI-reportConfig IE of TS 38.331).

[0150] Figure 5A method measurement using a pause state to report pauses is illustrated. The pause state can be attached to the reporting of a cell or beam. The beam / cell pause state can be set or unset at the UE by an ML model prediction (e.g., that the reporting will become non-necessary) or by other events such as the serving cell falling below an absolute threshold. The pause state is evaluated at the latest at the time of sending the measurement report to the network.

[0151] The pause mechanism works with triggers and external setting / unsetting actors. In this context, the actors can be ML models in the UE, or the network signaling the UE, or trigger configurations in the UE linked to the pause state (i.e., rule-based mechanisms). In several cases, the pause state inherently has a duration. However, the current pause state solution cancels the pause reporting when the observed cell / beam goes out of range.

[0152] In case of A3, the event and thus the pause state ends when the maximum number of configured reports being sent exists. Alternatively, or additionally, the configured A3 leaving condition can be fulfilled. Either of these can lead to the removal of the observed cell from the varMeasReportList, i.e., the un-pause. In case of HO, the (RRCreconfig) measurement report end will end the pause state.

[0153] Figure 6a The operation of the pause state is shown. At point A, the pause state is set by an event or model. At B, a measurement report is triggered. At point C and point D, the pause state is cleared by the end of the report. The end of the report will correspond to the maximum number of reports reached, an event leaving condition encountered, or an RRC reconfiguration message.

[0154] Other mechanisms to un-pause the measurement can be appropriate, such as a measurement trigger linked to un-pause the pause state variable.

[0155] The current solution does not consider the prediction range as the basis for the ML model based pause state setting. When a prediction pauses the measurement reporting for a cell, but in fact the measurement reporting is never triggered, the actor responsible for the setting needs to recognize that the prediction did not materialize and clear the pause state. Otherwise, the pause state can still be set for a measurement reporting trigger, for which the prediction did not refer to this measurement reporting trigger. This creates problems in terms of robustness and complexity.

[0156] Figure 6b The operation of the pause state is shown, where the measurement report is not triggered at point B. If the pause state is not cleared, future reports can be paused even when they are needed.

[0157] The suspend mechanism does not report suspend setting events in advance, as the purpose of the mechanism is to save signaling. However, the network can benefit from knowledge about the usage of the suspend mechanism and the content of the suspended measurement reports. For example, if the model monitoring relies on regular reports, but these reports are suspended, the model monitoring is negatively affected.

[0158] In addition, beyond the suspend mechanism, for network side event prediction models, the training or fine-tuning or performance monitoring of the model would benefit from the measurements, especially in case the prediction is wrong. However, setting a low reporting trigger criteria can create excessive signaling load instead of targeting the moments when the measurements are really needed. There is a need to design a mechanism to provide the network with training data for the suspend events or prediction models, where the associated signaling should not offset the reporting saving gain or create heavy signaling load.

[0159] When the suspend mechanism is applied to the LTM, the network is able to act and signal fast on lower layers. The network can also predict and detect the suspend situation.

[0160] Figure 7 A flowchart of a method according to an example embodiment is shown. The method can be performed at an apparatus, such as a UE.

[0161] In 701, the method comprises receiving, at the apparatus, a measurement configuration to record measurements in a recording window based on a trigger.

[0162] In 702, the method comprises recording one or more measurements in the recording window based on the measurement configuration.

[0163] In 703, the method comprises determining, based on a condition, to report the recorded measurements after the recording window.

[0164] In 704, the method comprises reporting the recorded measurements based on the determination.

[0165] Figure 8 A flowchart of a method according to an example embodiment is shown. The method can be performed, for example, at a network node.

[0166] In 801, the method comprises providing, from the network, a measurement configuration to a user equipment to record measurements in a recording window based on a trigger.

[0167] In 802, the method comprises receiving, at the network, recorded measurements from the user equipment.

[0168] The UE can be configured to log measurements triggered by setting a suspend state or by an event prediction. The event prediction can be a mobility event prediction. The logged measurements will include the cell / beam for which the suspend state has been set, and optionally other cells / beams. The network can query the logged measurements when convenient, e.g. when the UE is in a cell center.

[0169] When the network trains and adjusts the network-side prediction model or suspend decision rules (for the network, or for UE deployment), the purpose becomes apparent.

[0170] Note that by continuously logging, the logging can start earlier than the trigger occurs, and the logging is discarded when the trigger does not occur later.

[0171] The method at the UE can comprise receiving at the apparatus from the network an indication to suspend measurement reporting for at least one of a given cell or beam for a time period, wherein the trigger comprises the indication and suspending measurement reporting based on the indication.

[0172] The indication to suspend measurement reporting can comprise a validity timer. The validity timer can comprise at least one of: a time period, or a start time and a stop time.

[0173] In an example embodiment, when a suspend is set, an attach time validity range is indicated to the setting. This is an example of a validity timer. The validity range determines the latest time at which the suspend is de-set.

[0174] Figure 9 A diagram is shown for a timer to de-set a suspend state, which is initialized with a time validity range of the setting mechanism. In this example embodiment, the validity range is implemented by a timer. Other example validity range settings can include a start time and a stop time.

[0175] When the validity timer comprises a time period, the method can comprise suspending measurement reporting upon receiving the indication to suspend measurement reporting or based on a subsequent event trigger.

[0176] In an example embodiment, when a suspend state is set for a cell or beam, it is also configured with a time validity range. In its simplest form, the validity range can be implemented as a maximum duration from the point of setting. When the duration has been exceeded, the state is de-set. Other range definitions can also use a starting point in the future and a duration for the setting. Other range definitions can bind the start to a measurement reporting trigger. This is an example of a subsequent event trigger. Once the suspend state validity range expires, the suspend state is set to false.

[0177] The measurement configuration can be for at least one beam or cell for which the measurement reporting has been suspended. The measurement configuration also includes at least one beam or cell for which the suspension has not been set. That is, the logged measurements will include the cells / beams for which the suspension status has been set, and optionally other cells / beams.

[0178] The validity range can be determined by the actor that sets the suspension status.

[0179] For example, if the ML model uses a prediction window of length L, and makes a prediction that results in determining that no measurements are needed for beam b within that window, the ML model can set the suspension status for measurement reporting for beam b, and set a validity range corresponding to the prediction window length. The ML model can be at the network, or at the UE. For example, a method at the network can comprise determining, based on a first machine learning model, to suspend measurement reporting for at least one given cell or beam for a time period; and providing, from the network to a user equipment, an indication to suspend measurement reporting for at least one of the given cells or beams, wherein the trigger comprises the indication.

[0180] The logging window can be a function of the validity timer (e.g. the validity range plus some margin before and after the range).

[0181] In Figure 10 In the middle, two possibilities are shown for the case where the suspension status validity range is implemented as a timer with a maximum duration. At point A, the timer is started, and it ends at point C. At point C, the suspension status is cleared. In the example, this results in the measurement reporting being resumed at point C, as shown in the left-hand figure. The measurement reporting will end at point D, e.g. because the maximum number of reports has been reached. In the right-hand figure, the suspension status is set, but in fact no report happens to be triggered. The suspension status will therefore remain set. This will result in the suspension of the report that is triggered at a later point in time, at another point B2, no longer being relevant to the prediction that set the suspension status. However, with the new validity range mechanism, the suspension status will be automatically cleared.

[0182] A method can comprise determining a prediction of an event and logging measurements during a logging window based on the prediction of the event. The logging can be triggered by a prediction event that does not match an observed event. The event prediction can be performed at the network and signaled to the UE. The event prediction can be a mobility event prediction. The event prediction can also be that a beam ID will be the strongest or that a beam strength will be within a certain range. The event prediction can also specify a sub-time window within a prediction window in which the event can occur.

[0183] The method can include determining, using a machine learning model, a prediction of the event, the prediction having an associated confidence value, the confidence value indicating a confidence level of the machine learning model used for the prediction. The prediction of the event can be determined at the UE or at the network. When the prediction of the event is determined at the network, the network can provide an indication of the predicted event to the UE. Determining the logged measurement can include determining that the predicted event does not match the observed event, or can include determining that the prediction confidence value can be below a given threshold.

[0184] The UE can also report the measurement based on a condition (e.g., a reporting configuration, receiving a query from the network, or a data store of the UE reaching a threshold).

[0185] As mentioned, an advantage is that the UE reporting is selective for cases of interest to the network. In addition, the UE reporting can include utilizing regular reporting to make available measurements that would not have been available, e.g., because regular measurement and reporting configuration would select lower measurement intervals, or higher thresholds, or more restrictions on the number of reported beams.

[0186] Figure 11a A flowchart is shown in accordance with an example embodiment.

[0187] In this example embodiment, the UE is instructed to log measurements, which will serve the purpose of later improving the prediction or monitoring the performance of the mobility model. The logging is started and adjusted when the actioner (network or UE ML model) predicts a mobility event. For example, the mobility event can be a predicted A3 event. For high confidence level of the prediction, no logging of measurements needs to be performed.

[0188] Thus, measurement logging can be made for data relevant to improving the prediction.

[0189] Alternatively, as shown in the example embodiment of Figure 11b The logging action is configured by the network at an earlier time and linked to the dynamic setting of the paused state, as shown in the example embodiment of

[0190] In the example embodiment shown in Figure 11b The logging is triggered by the paused state setting. There is no additional signaling for logging events of interest. Logging non-paused events requires separate signaling (network side event prediction) or configuration (UE side event prediction).

[0191] Figure 12 An example timeline of logging and reporting of training data is shown in accordance with the first example embodiment.

[0192] The ML model predicts a mobility event for point B. It can be assumed here that the model is in the UE. (If the model is in the network, the network can signal the predicted event to the UE, e.g. in the form of a record window, and the type of predicted event expected in the window). In this example, the predicted event does not occur, and thus the UE retains the record for later reporting to the network at point E.

[0193] Figure 13 A timeline of the record is shown for the second example embodiment. The data record occurs around the validity range of the suspended state (A...C). The data record is also conditioned on the predicted event not occurring (B). Thus, the record is retained and sent to the network at later point E.

[0194] In both of the example embodiments discussed above, the UE measurements can not be limited to the predicted beam / cell ID. The UE measurements can also be collected as described when the signal level is below the mobility event reporting threshold used for the event prediction.

[0195] A separate "record measurement configuration" can be defined by the network detailing, e.g., the minimum signal level required for a record. The measurement record can indicate that the configured beam / cell can not be identified, i.e., the minimum signal level is not observed.

[0196] The periodicity of the measurements can depend on the confidence value. For example, sparse measurements can be configured that optimize the sampling rate for the desired purpose of training the model. The level of sparsity of the data collection can be adjusted to the confidence level or the accuracy of the prediction observed. That is, instead of a binary decision that no data collection is needed, there can also be multiple thresholds for the confidence level if it exceeds a certain threshold τ (e.g., 90%). For example and without loss of generality, full scheme data collection is needed if it is below a threshold τ1. Sparse data collection would be more appropriate if it is between τ1 and τ2, and no data collection can be needed if it is above a threshold τ2. The number of threshold regions and their corresponding values can be fixed or dynamically set, in the latter case it becomes a problem of optimization task only, which can be implemented heuristically or through various available statistical learning methods.

[0197] The data reporting can be conditioned on the prediction of a mobility event. The data reporting can be conditioned on the prediction of an event, such as the beam ID being the strongest. The data reporting can be conditioned on the prediction of the beam strength, e.g., RSRP measured to have a value in the configured range.

[0198] The method can comprise determining to report the logged measurements if the predicted event did not occur. In an example embodiment, if the predicted event did not occur (false prediction or “false positive”), the measurement logging is retained. This is intended to collect training or fine-tuning data by collecting data as ground truth for false predictions, for improving the prediction mechanism. It helps with root cause analysis of prediction failures. This applies to UE-side models as well as network-side models. In the context of being able to suspend measurement reporting, one advantage is that the logged data covers the event that would have caused the measurement to be suspended.

[0199] The method can comprise determining that the event has occurred without prediction, and means for reporting the logged measurements from the user equipment to the network based on the determination. For example, if a mobility event occurs but the prediction is not known (“false negative”), the measurement logging is retained. This variant requires the UE to retain the logging data even if no event was predicted. This applies to UE-side models, or to network-side models in combination with signaling where the UE is informed about the predicted event (or period without predicted event).

[0200] If the UE has a limit on the number of records, the logging can occur in a circular fashion (older records are discarded), making the latest measurements available. Alternatively, the data logging can be disabled when the buffer is full (serving energy saving), so that older measurements are retained, and no new measurements are logged when the buffer is full.

[0201] The network can query the logged measurements when convenient (e.g. when the UE is in the cell center). This has the advantage that the measurements can be relayed to the network with higher spectral efficiency compared to cell edge reporting. Alternatively, the UE can send the logged measurements based on configured triggers such as “serving cell exceeds threshold” or data buffer threshold is exceeded.

[0202] Signaling is introduced where the network can set a suspension state of reporting, temporarily disabling reporting for selected beams (as opposed to the actioner in the UE, such as the ML model in the UE, setting the suspension state). This has the advantage of minimizing the reporting load without performing RRC reconfiguration. For L1 / L2 reporting, it allows emulating aperiodic beam reporting, but with the finer granularity of suspending specific beams.

[0203] In one embodiment variant, the network stops sending dedicated reference signals (DMRS) to the UE for a period where it indicates that measurement reporting is to be suspended. This is efficient in the case that the UE-side measurement logging is disabled, and no back-off clear of the suspension state at the UE is expected to occur. The advantage is in saving DL transmission resources.

[0204] Figure 14A signaling diagram according to example embodiments is shown.

[0205] In step 0 (not shown), the NW configures reportConfig to the UE.

[0206] In step 1, the UE sends to the NW measurements (e.g. RRM measurements) that are not suspended.

[0207] In step 2, the prediction of the event in the future window is performed in the NW. Since, the network knows that reportConfig has been configured to the UE, the network can infer that reporting for some beams / cells can be triggered, but not necessarily. The network can anticipate when the suspension of reporting will start. The suspension state will refer to the measld that the ReportConfig belongs to.

[0208] In step 3, the prediction of the event yields a time range in which the prediction can be considered accurate. This time range will be used to set the suspension duration. For example, the time range can be determined as the window length that still yields a 90% confidence of accurate prediction.

[0209] In step 4, the suspension of the cell / beam is signaled together with the maximum suspension duration. The suspension duration can include the anticipated start time of the suspension.

[0210] In alternative embodiments, steps 2, 3, 4 can be performed in the UE.

[0211] In step 5, the network configures the UE: whether the suspension action should trigger the measurement logging. There are different methods to perform this operation: a) statically: this step can be performed statically during the configuration of the UE with the reportConfig in step 1, and b) dynamically: for example, if the model prediction in step 2 yields low confidence, and the network aims to improve the model performance for the current settings, this operation can be performed dynamically as step 5.

[0212] In step 6, the UE sets the suspension state for the measld with (optional: the anticipated start time and) the maximum suspension duration for the indicated cell / beam. The suspension state is cleared when the timer for measld + beam / cell is up.

[0213] In step 7, the UE logs the measurements, which can be the reports that have been suspended, if configured. The duration of the logging can be the duration of the suspension state validity timer. In alternative embodiments, additional measurements are logged, spanning a duration, e.g. twice the suspension validity timer.

[0214] In step 8, the method can continue with step 1 or step 9, depending on, for example, whether the UE is still in a cell edge area where HO events are prevalent or not.

[0215] In step 9, the network polls the logged suspend reports once the UE is no longer in a HO situation or is able to easily report the logged suspend reports.

[0216] In step 10, the network uses the suspend reports to verify and improve its step 2 prediction algorithm.

[0217] Figure 15 A sequence of steps is shown for an example embodiment where the prediction of the event occurs at the network side.

[0218] In step 1, the NW configures conditions to log data in the UE. The configuration can also contain configuration for what beams and cells to log for.

[0219] In steps 2 and 3, the network performs a prediction and determines if it wants the UE to collect data for these. For example, the network can predict an A3 event but predict that it has low confidence. Or the network can want to collect more training data for this current situation but only for situations where its prediction is not met, or for situations where the event occurs but it did not make a prediction.

[0220] In step 4, the network indicates the prediction to the UE. For example, the network can indicate that there will be an A3 event between two cells in a future time window. The indication of the prediction can also indicate the time range for each prediction occurrence.

[0221] In step 5, the UE logs measurements (e.g., beam RSRP) according to the configured. The UE can also log observed events (e.g., A3). The UE also evaluates the configured conditions, matches the prediction to the observation (e.g., did A3 occur). The UE retains the measurements for later reporting according to its evaluation.

[0222] In step 6, the logging is reported.

[0223] The steps described above are valid not only for mobility events but also for simpler predictions. For example, a prediction of the K strongest beams in a future window, or a prediction of the RSRP of a beam. The K value can be an integer number of 1, 2, etc.

[0224] Figure 16 A signaling diagram is shown for an embodiment where there is UE side prediction but network side suspension.

[0225] In step 1, the UE performs a prediction.

[0226] In step 2, the UE provides an indication of the predicted event for the beam and / or cell (including reference Figure 14 to the time range of step 3) to the gNB.

[0227] Then, the gNB provides a suspend command for the beam / cell to the UE in step 3 based on the indication received from the UE.

[0228] In step 4, the UE performs suspend / cancel suspend of measurement reporting according to the suspend command.

[0229] In this embodiment, the suspend validity range setting and logging setting can be controlled by the UE or by the network.

[0230] The embodiments can ensure that the logging of measurements is cleared before a new suspend event occurs.

[0231] By logging and reporting in an efficient way, training data relevant for mobility event prediction models is made available.

[0232] The apparatus can comprise means for receiving, at the apparatus, a measurement configuration to log measurements in a logging window based on a trigger; means for logging one or more measurements in the logging window based on the measurement configuration; means for determining to report the logged measurements after the logging window based on a condition; and means for reporting the logged measurements based on the determination.

[0233] The apparatus can comprise a user equipment (such as a mobile phone), be a user equipment, or be comprised in a user equipment or a chipset for performing at least some actions of / for a user equipment.

[0234] Alternatively, the apparatus can comprise means for providing a measurement configuration to a user equipment to log measurements in a logging window based on a trigger; and means for receiving logged measurements from the user equipment.

[0235] The apparatus can comprise a network node, be a network node, or be comprised in a network node or a chipset for performing at least some actions of / for a network node.

[0236] It should be understood that the apparatus can comprise or be coupled with other units or modules etc. (such as a radio part or radio head) used in or for transmission and / or reception. Although the apparatus has been described as one entity, different modules and memories can be implemented in one or more physical or logical entities.

[0237] Note that although some embodiments have been described with respect to a 5G network, similar principles can be applied with respect to other networks and communication systems, such as a 6G network or an advanced 5G network. Thus, although certain embodiments were described above by way of example with reference to certain example architectures for wireless networks, technologies and standards, embodiments can be applied to any other suitable form of communications system than those illustrated and described herein.

[0238] Note also that, although example embodiments were described above, several changes and modifications to the disclosed solutions can be made without departing from the scope thereof.

[0239] As used herein, “at least one of ” and “one or more of ,” and the like, wherein the list of two or more elements is

[0240] In general, the various embodiments can be implemented in hardware or special-purpose circuits, software, logic or any combination thereof. Some aspects of the disclosure can be implemented in hardware, whereas other aspects can be implemented in firmware or software which can be executed by a controller, microprocessor or other computing device, although the disclosure is not limited thereto. While various aspects of the disclosure can be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein can be implemented in hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controler or other computing devices, or some combination thereof.

[0241] As used in this application, the term “circuitry” can refer to one or more or all of the following: (a) hardware-only circuitry such as amongst others an implementation in 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 processors); software, such as mainframe applications, enterprise software, mobile software, web software, mobile applets, and the like, and memory that work together to cause an apparatus, such as a mobile phone, server, or computer, to perform various functions and (c) hardware circuit(s) and / or processor(s), such as a microprocessor(s) or a portion of microprocessor(s), for need for software (e.g., firmware) for operation, but that does not require software to be present.

[0242] 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 that includes one or more processors and / or a processor(s) working in conjunction with a software module and / or other circuitry to cause an apparatus, such as a mobile device or server, to carry out a function. As a further example, as used in this application, the term circuitry also covers an implementation that includes one or more processors and / or a processor(s) working in conjunction with a software module and / or other circuitry to cause an apparatus, such as a mobile device or server, to carry out a function.

[0243] Embodiments of the disclosure can be implemented by computer software (such as in a processor entity), or by hardware, or by a combination of software and hardware. Computer software or program, also called program product, including software routines, applets and / or macros, can be stored in any apparatus-readable data storage medium and they include program instructions that, when executed by computer processing apparatus, cause the functions of the embodiments to be implemented. The computer program product can comprise one or more computer-executable components that, when the program is run, are configured to carry out embodiments. The one or more computer-executable components can be at least one software code or a part of it.

[0244] Further, it should be noted that any boxes in the logical flow that represents a step in the process, or that represent a portion of the logic flow, can represent any type of logical flow, such as a state machine, flowchart logical flow, flowchart, or correlation chart. Software can be stored in physical media such as memory chips or device hard disks (e.g., solid state drives or magnetic hard disk drives), optical media (e.g., DVD or CD), and memory blocks implemented within the processor. The physical media is non-transitory media. As used herein, the term non-transitory is to limit the type of media (i.e., tangible, not a signal), not the duration of the data storage (e.g., RAM vs. ROM).

[0245] The memory can be of any type appropriate for the local technical environment and can be implemented using any appropriate data storage technology, such as semiconductor based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The data processor can be of any type suitable to the local technical environment, and can include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), FPGAs, gate level circuits and processors based on multi-core processor architectures, as non-limiting examples.

[0246] Embodiments of the disclosure can be practiced in various components such as integrated circuit modules. The design of integrated circuits is by nature highly automated. Complex and powerful software tools are available for converting a logic level design into a semiconductor circuit design ready to be fabricated on semiconductor chips. Various embodiments of the present disclosure, therefore, can be thought of as products or processes typically implemented on computers or processors. Accordingly, those skilled in the art will recognize that the mechanisms which

[0247] The scope of protection sought for embodiments of the present disclosure is set forth by the independent claims. Embodiments and features described in the specification that are not covered by the claims, if any, are to be interpreted as examples useful for understanding the disclosure of various embodiments of the present disclosure.

[0248] The foregoing description has provided by way of non-limiting examples of exemplary embodiments of the present disclosure. However, various modifications and adaptations can become apparent to those skilled in the relevant arts in view of the foregoing description, when read in conjunction with the accompanying drawings and the appended claims. However, all such and similar modifications of the teachings of this disclosure will still fall within the scope of the invention as defined by the appended claims. Indeed, there is a further embodiment comprising an embodiment of the present disclosure in combination with any other embodiment or portion thereof.

Claims

1. An apparatus comprising: A component for receiving measurement configuration at the device to record measurements in a recording window based on a trigger; A component used to record one or more measurements in the recording window based on the measurement configuration; Components for determining, based on conditions, the measurement to be reported after the recording window; as well as A component used to report the recorded measurements based on the determination.

2. The apparatus according to claim 1, comprising: Components for receiving, at the device, an indication from the network to suspend measurement reports for at least one of a given cell or beam over a time period, wherein the triggering includes the indication; and A component used to pause measurement reporting based on the indicated instruction.

3. The apparatus of claim 2, wherein the indication for pausing the measurement report includes a validity timer.

4. The apparatus of claim 3, wherein the validity timer includes at least one of the following: the time period, or the start time and the stop time.

5. The apparatus according to claim 4, comprising: A component for pausing a measurement report upon receiving an instruction to pause the measurement report or based on a subsequent event trigger, if the validity timer includes the time period.

6. The apparatus according to any one of claims 2 to 5, wherein the measurement configuration is for measuring reports for the at least one beam or cell that has been suspended.

7. The apparatus of claim 5 or claim 6, wherein the measurement configuration for recording measurements further includes at least one beam or cell that has not yet been paused.

8. The apparatus according to any one of claims 2 to 7, wherein the recording window is a function of the validity timer.

9. The apparatus according to any one of claims 1 to 8, comprising: Components for determining the prediction of an event, and components for determining the measurement to be recorded during the recording window based on the prediction of the event.

10. The apparatus according to claim 9, comprising: A component for: using a machine learning model at the user equipment to determine the prediction of the event, the prediction having an associated confidence value indicating the confidence level of the machine learning model used for the prediction.

11. The apparatus according to claim 9, comprising: Components for receiving indications of predicted events from the network, the predictions having associated confidence values ​​indicating the confidence level of the machine learning model used for the predictions.

12. The apparatus of claim 10 or claim 11, wherein the confidence value is below a given threshold.

13. The apparatus according to any one of claims 10 to 12, wherein the periodicity of the measurement depends on the confidence value.

14. The apparatus according to any one of claims 9 to 13, comprising: A component for determining the recorded measurement if the predicted event does not occur.

15. The apparatus according to any one of claims 1 to 14, comprising: Components for determining that an event has occurred without prediction, and components for reporting the recorded measurements from the user equipment to the network based on the determination.

16. An apparatus comprising components for: A component for providing measurement configuration to user equipment to record measurements in a recording window based on triggers; and A component for receiving recorded measurements from the user equipment.

17. The apparatus of claim 16, comprising: A component used to determine, based on a machine learning model, to pause measurement reports for at least one given cell or beam in the first time period; as well as The trigger includes an instruction to the user equipment to suspend measurement reporting for at least one of a given cell or beam.

18. The apparatus of claim 17, wherein the indication to pause the measurement report includes a validity timer.

19. The apparatus of claim 18, wherein the recording window is a function of the validity timer.

20. The apparatus of claim 18 or 19, wherein the validity timer comprises at least one of the following: a time period, or a start time and a stop time.

21. The apparatus according to any one of claims 16 to 20, wherein the measurement configuration is for measuring reports for the at least one beam or cell that has been suspended.

22. The apparatus of claim 21, wherein the measurement configuration further includes at least one beam or cell that has not been paused.

23. The apparatus according to any one of claims 16 to 22, comprising: Components for determining the prediction of an event at the network, and components for providing an indication of the event prediction from the network to the other device for determining the recorded measurement.

24. The apparatus of claim 23, comprising: Components for using a second machine learning model to determine the prediction of the event, the prediction having an associated confidence value indicating the confidence level of the machine learning model used for the prediction.

25. The apparatus of claim 24, wherein the confidence value is below a given threshold.

26. The apparatus of claim 24 or 25, wherein the periodicity of the measurement depends on the confidence value.

27. A method comprising: Receive measurement configuration at the device to record measurements in the recording window based on triggers; One or more measurements are recorded in the recording window based on the measurement configuration; Based on the conditions, determine that the recorded measurement will be reported after the recording window; as well as Based on the determination, the recorded measurements are reported.

28. A method comprising: Provide measurement configuration from the network to the user equipment to record measurements in the logging window based on triggers; as well as The recorded measurements are received from the user equipment at the network.

29. An apparatus comprising: At least one processor and at least one memory storing instructions, said instructions, when executed by said at least one processor, cause the means to at least: The device receives a measurement configuration for recording measurements in a recording window based on a trigger. One or more measurements are recorded in the recording window based on the measurement configuration; Based on the conditions, determine that the recorded measurement will be reported after the recording window; as well as Based on the determination, the recorded measurements are reported.

30. An apparatus comprising: At least one processor and at least one memory storing instructions, said instructions, when executed by said at least one processor, cause the means to at least: The device provides a measurement configuration to the user equipment for recording measurements in a recording window based on a trigger; and The recorded measurements are received from the user equipment at the device.

31. A computer-readable medium comprising instructions that, when executed by a means, cause the means to perform at least the following: The device receives a measurement configuration for recording measurements in a recording window based on a trigger. One or more measurements are recorded in the recording window based on the measurement configuration; Based on the conditions, determine that the recorded measurement will be reported after the recording window; as well as Based on the determination, the recorded measurements are reported.

32. A computer-readable medium comprising instructions that, when executed by a device, cause the device to perform at least the following: The device provides a measurement configuration to the user equipment for recording measurements in a recording window based on a trigger; and The recorded measurements are received from the user equipment at the device.

Images