Apparatus, user equipment and methods for a network-sided model for mobility enhancements

Abstract

A user equipment of a wireless communication network according to an embodiment is provided. The user equipment is configured for obtaining and processing at least one command and / or a configuration to maintain a connectivity with the network, wherein the at least one command and / or the at least one configuration depends on one or more measurement predictions or event predictions.

Description

[0001] Apparatus, User Equipment and Methods for a Network-Sided Model for Mobility Enhancements

[0002] Description

[0003] The present invention relates to the field of wireless communication systems or networks, more specifically to an apparatus, to a user equipment and to methods for a Network-Sided Model for Mobility Enhancements

[0004] BACKGROUND OF THE INVENTION

[0005] Fig. 1 is a schematic representation of an example of a terrestrial wireless network 100 including, as is shown in Fig. 1(a), the core network and one or more radio access networks RANi, RAN2, ... RANN (RAN = Radio Access Network). Fig. 1(b) is a schematic representation of an example of a radio access network RANnthat may include one or more base stations gNBi to gNBs (gNB = next generation Node B), each serving a specific area surrounding the base station schematically represented by respective cells IO61 to IO65. The base stations are provided to serve users within a cell. The one or more base stations may serve users in licensed and / or unlicensed bands. The term base station, BS, refers to a gNB in 5G networks, an eNB in UMTS / LTE / LTE-A / LTE-A Pro, or just a BS in other mobile communication standards. A user may be a stationary device or a mobile device. The wireless communication system may also be accessed by mobile or stationary loT (Internet of Things) devices which connect to a base station or to a user. The mobile devices or the loT devices may include physical devices, ground based vehicles, such as robots or cars, aerial vehicles, such as manned or unmanned aerial vehicles, UAVs, the latter also referred to as drones, buildings and other items or devices having embedded therein electronics, software, sensors, actuators, or the like as well as network connectivity that enables these devices to collect and exchange data across an existing network infrastructure. Fig. 1 (b) shows an exemplary view of five cells, however, the RANnmay include more or less such cells, and RANnmay also include only one base station. Fig. 1(b) shows two users UE1 and UE2, (UE = User Equipment) also referred to as user equipment, UE, that are in cell 1062and that are served by base station gNB2. Another user UE3is shown in cell 1064which is served by base station gNB4. The arrows IO81, 1082and IO83 schematically represent uplink / downlink connections for transmitting data from a user UE1, UE2and UE3 to the base stations gNB2, gNB4or for transmitting data from the base stations gNB2, gNB4to the users UE1, UE2, UE3. This may be realized on licensed bands or on unlicensed bands. Further, Fig. 1(b) shows two loT devices 110i and HO2 in cell IO64, which may be stationary or mobile devices. The loT device 110i accesses the wireless communication system via the base station gNB4 to receive and transmit data as schematically represented by arrow 112i . The loT device HO2 accesses the wireless communication system via the user UE3 as is schematically represented by arrow 1122. The respective base stations gNBi to gNB5may be connected to the core network 102, e.g. via the S1 interface, via respective backhaul links 114i to 114s, which are schematically represented in Fig. 1(b) by the arrows pointing to “core”. The core network 102 may be connected to one or more external networks. The external network may be the Internet or a private network, such as an intranet or any other type of campus networks, e.g. a private WiFi or 4G or 5G mobile communication system. Further, some or all of the respective base stations gNBi to gNBs may be connected, e.g. via the S1 or X2 interface or the XN interface in NR (New Radio), with each other via respective backhaul links 1161 to 1165, which are schematically represented in Fig. 1(b) by the arrows pointing to “gNBs”. A sidelink channel allows direct communication between UEs, also referred to as device-to-device, D2D (Device to Device), communication. The sidelink interface in 3GPP (3G Partnership Project) is named PC5 (Proximity-based Communication 5).

[0006] For data transmission a physical resource grid may be used. The physical resource grid may comprise a set of resource elements to which various physical channels and physical signals are mapped. For example, the physical channels may include the physical downlink, uplink and sidelink shared channels, PDSCH (Physical Downlink Shared CHannel), PLISCH (Physical Uplink Shared Channel), PSSCH (Physical Sidelink Shared Channel), carrying user specific data, also referred to as downlink, uplink and sidelink payload data, the physical broadcast channel, PBCH (Physical Broadcast Channel), carrying for example a master information block, MIB, and one or more of a system information block, SIB, one or more sidelink information blocks, SLIBs, if supported, the physical downlink, uplink and sidelink control channels, PDCCH (Physical Downlink Control Channel), PUCCH (Physical Uplink Control CHannel), PSCCH (Physical Sidelink Control Channel), the downlink control information, DCI, the uplink control information, UCI, and the sidelink control information, SCI, and physical sidelink feedback channels, PSFCH (Physical sidelink feedback channel), carrying PC5 feedback responses. Note, the sidelink interface may support a 2-stage SCI (Speech Call Items). This refers to a first control region comprising some parts of the SCI, and, optionally, a second control region, which comprises a second part of control information. For the uplink, the physical channels may further include the physical random-access channel, PRACH (Packet Random Access Channel) or RACH (Random Access Channel), used by UEs for accessing the network once a UE synchronized and obtained the Ml B and SIB. The physical signals may comprise reference signals or symbols, RS, synchronization signals and the like. The resource grid may comprise a frame or radio frame having a certain duration in the time domain and having a given bandwidth in the frequency domain. The frame may have a certain number of subframes of a predefined length, e.g. 1ms. Each subframe may include one or more slots of 12 or 14 OFDM symbols (OFDM = Orthogonal Frequency-Division Multiplexing) depending on the cyclic prefix, CP, length. A frame may also include of a smaller number of OFDM symbols, e.g. when utilizing a shortened transmission time interval, sTTI (slot or subslot transmission time interval), or a mini- slot / non-slot-based frame structure comprising just a few OFDM symbols.

[0007] The wireless communication system may be any single-tone or multicarrier system using frequency-division multiplexing, like orthogonal frequency-division multiplexing, OFDM, or orthogonal frequency-division multiple access, OFDMA (Orthogonal frequency-division multiple access), or any other IFFT-based signal (IFFT = Inverse Fast Fourier Transformation) with or without CP, e.g. DFT-s-OFDM (DFT = discrete Fourier transform). Other waveforms, like non-orthogonal waveforms for multiple access, e.g. filter-bank multicarrier, FBMC, generalized frequency division multiplexing, GFDM, or universal filtered multi carrier, LIFMC, may be used. The wireless communication system may operate, e.g., in accordance with the LTE-Advanced pro standard, or the 5G or NR, New Radio, standard, or the NR-U, New Radio Unlicensed, standard.

[0008] The wireless network or communication system depicted in Fig. 1 may be a heterogeneous network having distinct overlaid networks, e.g., a network of macro cells with each macro cell including a macro base station, like base stations gNBi to gNBs, and a network of small cell base stations, not shown in Fig. 1 , like femto or pico base stations. In addition to the above described terrestrial wireless network also non-terrestrial wireless communication networks, NTN, exist including spaceborne transceivers, like satellites, and / or airborne transceivers, like unmanned aircraft systems. The non-terrestrial wireless communication network or system may operate in a similar way as the terrestrial system described above with reference to Fig. 1 , for example in accordance with the LTE-Advanced Pro standard or the 5G or NR, new radio, standard. In mobile communication networks, for example in a network like that described above with reference to Fig. 1 , like an LTE or 5G / NR network, there may be UEs that communicate directly with each other over one or more sidelink, SL, channels, e.g., using the PC5 / PC3 interface or WiFi direct. UEs that communicate directly with each other over the sidelink may include vehicles communicating directly with other vehicles, V2V communication, vehicles communicating with other entities of the wireless communication network, V2X communication, for example roadside units, RSUs, or roadside entities, like traffic lights, traffic signs, or pedestrians. An RSU may have a functionality of a BS or of a UE, depending on the specific network configuration. Other UEs may not be vehicular related UEs and may comprise any of the above-mentioned devices. Such devices may also communicate directly with each other, D2D communication, using the SL channels.

[0009] In a wireless communication network, like the one depicted in Fig. 1 , it may be desired to locate a UE with a certain accuracy, e.g., determine a position of the UE in a cell. Several positioning approaches are known, like satellite-based positioning approaches, e.g., autonomous and assisted global navigation satellite systems, A-GNSS, such as GPS, mobile radio cellular positioning approaches, e.g., observed time difference of arrival, OTDOA, and enhanced cell ID, E-CID, or combinations thereof.

[0010] It is noted that the information in the above section is only for enhancing the understanding of the background of the invention and, therefore, it may comprise information that does not form prior art that is already known to a person of ordinary skill in the art.

[0011] Starting from the above, there may be a need for improvements or enhancements for a wireless communication system or network and its components.

[0012] SUMMARY

[0013] An apparatus of a wireless communication network according to an embodiment is provided. The apparatus is configured for:

[0014] Obtaining information on one or more measurements and / or one or more measurement estimates, wherein the one or more measurements and / or the one or more measurement estimates depend on a radio condition between a user equipment and a second entity of the wireless communication network, wherein the second entity is a network entity or is a further user equipment of the wireless communication network.

[0015] Making one or more predictions for one or more future time instants and / or one or more different frequency layers, wherein the one or more predictions are one or more measurement predictions and / or one or more event predictions and / or one or more predictions of network configurations for one or more future time instants and / or for one or more different frequency layers, wherein making the one or more measurement predictions or event predictions is conducted depending on the information on the one or more measurements and / or one or more measurement estimates.

[0016] Providing, depending on the one or more predictions, at least one command and / or a configuration or a set of configurations for the user equipment to maintain a connectivity with the network.

[0017] Moreover, a user equipment of a wireless communication network according to an embodiment is provided. The user equipment is configured for obtaining and processing at least one command and / or a configuration to maintain a connectivity with the network, wherein the at least one command and / or the at least one configuration depends on one or more measurement predictions or event predictions.

[0018] Radio link failure (RLF) occurs when connectivity is compromised for any reason. This may happen for a multitude of reasons such as when the RSRP of received signal is too low, PDCCH or PDSCH cannot be decoded due to low RSRP or RSRQ, lower SINR from UE compared to what the gNB configured for the UE, SRS power is lower than what configured for UE, gNB does not see NACK or ACKs for the PDSCH). A RLF usually happens when one or more of the impairing observation are made for at least two times within a configured interval. In particular, from UE’s perspective, a RLF may be declared if certain time has expired after a radio problem is indicated from the physical layer (such as failure to decode certain channels like PDCCH or PDSCH with certain repetitions or persistency) or degraded SINR, RSRP or RSRQ or radio failure, or measurement failure, failure with shared spectrum access operation, etc.).

[0019] Furthermore, a user equipment of a wireless communication network according to another embodiment is provided. The user equipment comprises an Artificial Intelligence / Machine Learning model. The user equipment is configured to conduct one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network. The Artificial Intelligence / Machine Learning model is configured to conduct one or more measurement estimates, which depend on the radio condition between the user equipment and said network entity of the wireless communication network. The user equipment is configured to transmit information on the one or more measurement estimates to the network entity or to a second user equipment or to another network entity of the wireless communications network.

[0020] A method for a wireless communication network according to an embodiment is provided. The method comprises:

[0021] Obtaining, by an apparatus of the wireless communication network, information on one or more measurements and / or one or more measurement estimates, wherein the one or more measurements and / or the one or more measurement estimates depend on a radio condition between a user equipment and a second entity of the wireless communication network, wherein the second entity is a network entity or is a further user equipment of the wireless communication network.

[0022] Making, by the apparatus, one or more predictions for one or more future time instants, wherein the one or more predictions are one or more measurement predictions and / or one or more event predictions and / or one or more predictions of network configurations for one or more future time instants, wherein making the one or more measurement predictions or event predictions is conducted depending on the information on the one or more measurements and / or one or more measurement estimates.

[0023] Providing, by the apparatus, depending on the one or more predictions, at least one command and / or a configuration or a set of configurations for the user equipment to maintain a connectivity with the network.

[0024] Moreover, a method for a wireless communication network according to an embodiment is provided. The method comprises obtaining and processing, by a user equipment of the wireless communication system, at least one command and / or a configuration to maintain a connectivity with the network, wherein the at least one command and / or the at least one configuration depends on one or more measurement predictions or event predictions. Furthermore, a method for a wireless communication network according to an embodiment is provided. The method comprises:

[0025] Conducting, by a user equipment of the wireless communication network, one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network.

[0026] Conducting, by an Artificial Intelligence / Machine Learning model of the user equipment, one or more measurement estimates, which depend on the radio condition between the user equipment and said network entity of the wireless communication network. And:

[0027] Transmitting, by the user equipment, information on the one or more measurement estimates to the network entity or to a second user equipment or to another network entity of the wireless communications network.

[0028] Moreover, computer programs according to embodiments are provided for implementing one of the above-described methods, when the computer program is implemented by a computer or signal processor.

[0029] Further particular embodiments are provided in the dependent claims.

[0030] BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Fig. 1 illustrates a schematic representation of an example of a terrestrial wireless network.

[0032] Fig. 2 illustrates mobility in NR.

[0033] Fig. 3 depicts the state-of-the-art procedures for handover of a UE between the source gNB and a target gNB, in a scenario where neither AMF nor UPF changes.

[0034] Fig. 4 illustrates a prediction of inter-frequency measurements. Fig. 5 illustrates a prediction measurement at different time instants based on measurement and / or additional information according to embodiments.

[0035] Fig. 6 illustrates an embodiment, where the AI / ML model may be able to predict events, such as measurement events ahead of time

[0036] Fig. 7 illustrates a hierarchical network.

[0037] Fig. 8 illustrates a collection of measurements from RAN nodes to determine RRC connection parameters by serving node.

[0038] Fig. 9 illustrates gNBs, TRPs and UEs in a wireless communication network according to an embodiment.

[0039] Fig. 10 illustrates an example of a computer system on which units or modules as well as the steps of the methods described in accordance with the inventive approach may execute.

[0040] DETAILED DESCRIPTION OF THE INVENTION

[0041] Embodiments of the present invention are now described in more detail with reference to the accompanying drawings, in which the same or similar elements have the same reference signs assigned.

[0042] An apparatus of a wireless communication network according to an embodiment is provided. The apparatus is configured for:

[0043] Obtaining information on one or more measurements and / or one or more measurement estimates, wherein the one or more measurements and / or the one or more measurement estimates depend on a radio condition between a user equipment and a second entity of the wireless communication network, wherein the second entity is a network entity or is a further user equipment of the wireless communication network. Making one or more predictions for one or more future time instants and / or one or more different frequency layers, wherein the one or more predictions are one or more measurement predictions and / or one or more event predictions and / or one or more predictions of network configurations for one or more future time instants and / or for one or more different frequency layers, wherein making the one or more measurement predictions or event predictions is conducted depending on the information on the one or more measurements and / or one or more measurement estimates.

[0044] Providing, depending on the one or more predictions, at least one command and / or a configuration or a set of configurations for the user equipment to maintain a connectivity with the network.

[0045] According to an embodiment, the information on the one or more measurements and / or the one or more measurement estimates may, e.g., comprise information on one or more measurements or measurement estimates of the user equipment and / or information on one or more measurements or measurement estimates of the apparatus or of another network entity of the wireless communication system, wherein said other network entity is different from the user equipment and is different from the apparatus and is different from or equal to the second entity.

[0046] In an embodiment, the apparatus may, e.g., be configured to use the information on the one or more measurements and / or the one or more measurement estimates to train an Artificial Intelligence / Machine Learning model. The apparatus may, e.g., be configured to make the one or more predictions depending on the Artificial Intelligence / Machine Learning model.

[0047] According to an embodiment, the apparatus may, e.g., be configured to provide input data to the Artificial Intelligence / Machine Learning model, and, wherein the input data may, e.g., comprise information on at least one of the one or more measurements or measurement estimates from the user equipment and / or from the apparatus and / or from a network node. The apparatus may, e.g., be configured to receive output data from the Artificial Intelligence / Machine Learning model, wherein the output data may, e.g., comprise the one or more predictions or may, e.g., comprise information for conducting the one or more predictions. In an embodiment, the apparatus may, e.g., comprise the Artificial Intelligence / Machine Learning model.

[0048] According to an embodiment, the apparatus may, e.g., be configured to request a measurement or measurement estimate on a measurement object from the user equipment. The apparatus may, e.g., be configured to receive the measurement or measurement estimate from the user equipment. Moreover, the apparatus may, e.g., be configured to validate and / or provide information to a network entity to validate the Artificial Intelligence / Machine Learning model using the measurement or the measurement estimate.

[0049] In an embodiment, the apparatus may, e.g., be configured to request the user equipment to provide the measurement on the measurement object instead of providing a measurement estimate.

[0050] According to an embodiment, the apparatus may, e.g., be configured to receive the measurement estimate from the user equipment. The apparatus may, e.g., be configured to validate the Artificial Intelligence / Machine Learning model using the measurement estimate.

[0051] In an embodiment, depending on at least one of the one or more measurements or measurement estimates and depending on at least one of the one or more measurement predictions or event predictions, the apparatus may, e.g., be configured to indicate to the user equipment to temporarily disable to provide the one or more measurements or measurement predictions.

[0052] According to an embodiment, the apparatus may, e.g., be configured to indicate to the user equipment to temporarily disable to provide the one or more measurements or measurement predictions, if a difference between at least one of the one or more measurements or measurement estimates and at least one of the one or more measurement predictions is within a predefined interval.

[0053] In an embodiment, the apparatus may, e.g., be configured to indicate to the user equipment to temporarily disable a measurement gap configuration depending on at least one of the one or more measurements or measurement estimates and depending on at least one of the one or more measurement predictions or event predictions. According to an embodiment, the measurement gap configuration may, e.g., be provided by network layer signalling (e.g., RRC) so that the measurement gap is aligned between one or more network entities of the wireless communication network and the user equipment. An activation or deactivation of the measurement gap configuration is conducted by MAC-CE signaling or physical layer signalling (such as DCI or SCI), (e.g., so as to enable fast skipping or activation of gaps configured).

[0054] In an embodiment, apparatus may, e.g., be configured to provide input data to the Artificial Intelligence / Machine Learning model comprising additional information in addition to the information on said at least one of the one or more measurements or measurement estimates.

[0055] According to an embodiment, the additional information may, e.g., comprise statistics provided by network data analytics. In some examples, the RAN node may be a subscriber to the network analytics provided by the NWDAF or O&M. In other examples, where the O- RAN architecture is deployed, the statistics and / or analytics may additionally or alternatively be provided by Non-Real time RIC, Near Real time RIC (e.g. xAPP).

[0056] In an embodiment, the additional information may, e.g., comprise information about a location of the user equipment and / or of another user equipment and / or of a network node of the wireless communication network.

[0057] According to an embodiment, the location may, e.g., be a preconfigured location of the user equipment (e.g., a fixed user equipment) or of a fixed network node (e.g., BS). Or, the location may, e.g., be a mobile location of a mobile user equipment, whose location may, e.g., be determined with GNSS and / or multi-RTT and / or DL-TDOA and / or DL-AoD and / or using multi-RTT with LEO satellites and / or UL-TDOA. Or, the location may, e.g., be a location of a moving network node, such as a satellite (e.g., a LEO or a MEO or a GSO satellite). Or, the location may, e.g., be a location of a non-terrestrial network node or of a mobile IAB node.

[0058] According to an embodiment, the output of the Artificial Intelligence / Machine Learning model may, e.g., comprise at least one of a RSRP, a RSRQ, a SINR, a network event (e.g., a radio link failure), a prediction of a configuration or a set of configuration of network nodes for handling connection to and / or from the user equipment. In an embodiment, the apparatus may, e.g., be configured to provide the information on the one or more measurements and / or the one or more measurement estimates to a network entity of the wireless communication network (e.g., a NWDAF or, e.g., an O&M entity), wherein said network entity is different from the apparatus. The apparatus may, e.g., be configured to receive from said network entity one or more measurements and / or one or more predicted events.

[0059] According to an embodiment, the apparatus may, e.g., be configured to receive statistics or analytics from a network entity of the wireless communication network (e.g., a NWDAF or, e.g., an O&M entity), wherein said network entity may, e.g., be different from the apparatus. The apparatus may, e.g., be configured to transmit the statistics or the analytics to the user equipment, or wherein, depending on the statistics or the analytics, the apparatus may, e.g., be configured to generate and to transmit a configuration to the user equipment.

[0060] In an embodiment, the apparatus may, e.g., be configured to obtain information on the one or more measurement estimates from the user equipment, wherein the one or more measurement estimates are provided by an Artificial Intelligence / Machine Learning model of the user equipment.

[0061] According to an embodiment, the one or more measurements or measurement estimates comprise one or more of the following: one or more measurements or measurement estimates on a radio condition between the user equipment and the network entity, one or more measurements or measurement estimates on a radio condition between the user equipment and another network entity, one or more measurements or measurement estimates on a radio condition between another user equipment and the network entity, one or more measurements or measurement estimates on a radio condition between another user equipment and another network entity, one or more measurements or measurement estimates on a radio condition between the user equipment and another user equipment, one or more measurements or measurement estimates on a radio condition between the network entity and another network entity.

[0062] In an embodiment, at least one of the one or more measurements or measurement estimates may, e.g., be a measurement or measurement estimate for a first frequency layer or for a first carrier frequency. At least one of the one or more measurement predictions or or more event predictions may, e.g., be a measurement prediction or an event prediction for said first frequency layer or for said first carrier frequency.

[0063] According to an embodiment, at least one of the one or more measurements or measurement estimates may, e.g., be a measurement or measurement estimate for a first frequency layer or for a first carrier frequency. At least one of the one or more measurement predictions and / or of the one or more event predictions may, e.g., be a measurement prediction or an event prediction for a second frequency layer being different from the first frequency layer, or for a second carrier frequency being different from the first carrier frequency.

[0064] In an embodiment, the measurement or measurement estimate for the first frequency layer or for the first carrier frequency may, e.g., be a measurement made on a terrestrial TRP. The measurement prediction or the event prediction for the second frequency layer or for the second carrier frequency may, e.g., be a measurement prediction or an event prediction for a non-terrestrial TRP (e.g., for an NTN satellite).

[0065] According to an embodiment, at least one of the one or more measurements or measurement estimates may, e.g., be a measurement or measurement estimate for a first signal. At least one of the one or more measurement predictions or event predictions may, e.g., be a measurement prediction or an event prediction for a second signal being collocated with the first signal.

[0066] In an embodiment, at least one of the one or more measurements or measurement estimates may, e.g., comprise a measurement or a measurement estimate on an uplink reference signal. According to an embodiment, the uplink reference signal may, e.g., be an SRS or a PRACH or a DMRS or an UL-PTRS.

[0067] In an embodiment, the apparatus may, e.g., be configured to make a prediction of one or more channel parameters for a channel between the user equipment and the second entity as the one or more measurement predictions or event predictions for one or more future time instants.

[0068] According to an embodiment, the one or more predictions comprise one or more of the following: a spatial prediction of a beam measurements, a temporal prediction of a beam measurement, a spatial and temporal prediction of a beam measurement, an inter-frequency prediction of a beam measurement, one or more cell-measurements beams of TRPs and / or group of TRPs, a dwell time in target cell, an anticipated RLF, an uplink synchronization, such as timing advance in the new cell, a carrier frequency offset, a transmit power, a pathloss reference, a UE-beam, a carrier frequency offset, a time difference between a propagation path between a user equipment and at least two network nodes (e.g., between a user equipment and two NTN nodes, or, e.g., between a user equipment and an NTN node and a terrestrial node, or, e.g., between two terrestrial nodes), a configuration of parameters to be applied by a user equipment, when handover occurs (e.g. TA values, CA parameters, such as primary cell and secondary cell configurations, etc), a configuration of parameters to be applied by a user equipment, when a conditional handover occurs (e.g., TA values, CA parameters, such as primary cell and secondary cell configurations, etc).

[0069] In an embodiment, the apparatus may, e.g., be configured to provide at least one of one or more measurement predictions to the user equipment. The apparatus may, e.g., be configured to receive information on a difference between said at least one of the one or more measurement predictions and at least one actual measurement from the user equipment.

[0070] According to an embodiment, the apparatus may, e.g., be configured to fine-tune or to calibrate or to switch an Artificial Intelligence / Machine Learning model depending on the one or more measurements or measurement estimates.

[0071] In an embodiment, the apparatus may, e.g., be configured to generate or update a configuration of an uplink reference signal and / or a sidelink reference signal as the configuration for the user equipment depending on the one or more measurement predictions or event predictions, and may, e.g., be configured to provide the configuration to the user equipment.

[0072] According to an embodiment, the apparatus may, e.g., be configured to initiate a handover of the user equipment from one cell to another cell of the wireless communication network depending on the one or more measurement predictions or event predictions.

[0073] In an embodiment, to obtain the one or more measurements, the apparatus may, e.g., be configured to request one or more measurements from a TRP of the wireless communication network, and wherein the apparatus may, e.g., be configured to receive the one or more measurements from the TRP.

[0074] According to an embodiment, the appatus may, e.g., be a network entity of the wireless communication network being different from the user equipment.

[0075] In an embodiment, the one or more measurements comprise one or more of the following: one or more measurements on signal power and / or signal quality and / or timing per SS / PBCH block, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least two SS / PBCH blocks; one or more measurements on signal power and / or signal quality and / or timing per cell based on SS / PBCH block(s), one or more measurements on signal power and / or signal quality and / or timing or timing diffrences between two cells based on SS / PBCH block(s), one or more measurements to detect SS / PBCH block(s) indexes and / or measured above a threshold, one or more measurements on signal power and / or signal quality and / or timing per CSI-RS resource, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least CSI-RS resource and a SS / PBCH block, at least two CSI-RS resources or a combination, one or more measurements on signal power and / or signal quality and / or timing per cell between at least CSI-RS resource and a SS / PBCH block, at least two CSI-RS resources or a combination, one or more measurements measuring CSI-RS resource measurement identifiers, one or more measurements on signal power and / or signal quality and / or timing, or timing differences above further consolidated using certain filtering or averaging, one or more measurements on signal power and / or signal quality and / or timing, or timing differences above further consolidated or predicted using certain AI / ML algorithms, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least DL-PRS resource and a SS / PBCH block, at least two DL-PRS resrouces or a combination, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least two LIL-SRS resources, one or more measurements on phase or phase differences between at least two signals.

[0076] According to an embodiment, the one or more measurements comprise one or more measurements on a frequency layer or different frequency layers or different network layers (e.g. terrestrial and non-terrestrial).

[0077] In an embodiment, the apparatus may, e.g., be configured to make said one or more predictions of network configurations, which relate to the network settings to be used by the network and / or by the user equipment. The one or more predictions of network configurations indicate a likely candidate where a handover may be carried out, so that packets from a user plane may be pre-buffered at a new network node in anticipation that the handover will happen and the data can be transferred with lower latency, since the new network node does not need to wait for the old network node to forward its buffer.

[0078] According to an embodiment, the apparatus may, e.g., be configured to make said one or more predictions of network configurations to be used by the user equipment, wherein the one or more predictions of network configurations indicate a set of parameters to be used by the user equipment, for example, TA, primary and secondary cells, multi-TRP configurations, TAG group, QCL information, initial BWP, BWPs etc. According to some examples, a user equipment may, e.g., maintain connectivity with two network nodes. In such a scenario, the first network node may, e.g., provide and / or release a configuration for measurement and reporting for secondary nodes. In an embodiment, the apparatus may, e.g., be configured to provide the at least one command for the user equipment, such that the at least one command may, e.g., comprise a handover command instructing the user equipment to initiate connection at a target cell, or a redirection command where the network instructs the UE to move to RRCJDLE and initiate connection in target cell or frequency, or L1 / L2 initiated mobility, wherein the connection is changed based on preconfigured parameters based on MAC-CE or DCI trigger.

[0079] According to an embodiment, the apparatus may, e.g., be configured to provide the at least one command for the user equipment, such that the at least one command may, e.g., comprise an instruction whether to store the measurement and / or predictions at the UE. The apparatus may, e.g., further indicate whether the UE should release or retain the logged measurement when the UE performs handover to a different cell. Likewise, the UE may, e.g., further be indicated by a gNB whether or not to log measurements pertaining to the downlink reference signals in deactivated BWP, dormant BWP (e.g., the initial BWP after the UE has switched to another BWP) or deactivated secondary cells.

[0080] In an embodiment, the apparatus may, e.g., be configured to provide the UE with at least two configurations for the UE to execute, wherein the two configurations are associated with conditions under which they are executed, for example, the CHO configurations. In addition, the at least two configurations may, e.g., be associated with the same parameter for selection (such as measurement or event trigger), but the two configurations may, e.g., be associated with a parameter that influences which set of parameter is executed preferentially by the UE. For example, the two configurations may, e.g., be associated with a probability of selection value, wherein the first configuration may be selected with probability p1 , second with probability p2 and so forth. The UE may, in addition, provide KPIs associated with the performance of one configuration over the other, for example, dwell time in the cell, handover success / failure, RSRP, RSRQ, SINR, ping-pong rate, throughput on user plane, end-to-end throughput from application layer, ... , etc. The UE may provide instantaneous KPI associated with the measurement or an aggregate KPI associated with the configuration or KPIs describing accuracy, precision, recall or F1- score. As an example, the UE may, e.g., predict an event (e.g., a RLF) occurring at a certain time or a time window. The UE may later determine whether the event has (true prediction) I has not (false prediction) occurred. It may also be the case that an event may occur where the UE didn’t predict the event to occur (missed prediction). Information indicating the true event detection, false event detection or missed event detection may, e.g., be provided to the network. The aggregated KPI may, for example, be provided when the network provides reconfiguration and / or at regular intervals. The network entity may, e.g., be able to use the KPIs to fine-tune the configuration or the set of configurations provided to a UE or a group of UEs.

[0081] Unlike the current CHO configuration, the proposed CHO has same execution conditions for two configuration, but may, e.g., differ in the probability with which they are selected by the UE. Furthermore, the current CHO configurations are based on past measurements, but with this approach, the CHO configuration may be selected based on past and / or future measurements or event predictions.

[0082] At least one configuration may be indicated as a fallback configuration or a safe configuration. The UE may not choose / select the second configuration for a certain time period after receiving an indication to use the fallback configuration or safe configuration. This may be used by the network, when for example, the network observes handover failures over a certain rate.

[0083] The information provided by the UE may optionally be used by the network to perform reinforcement learning over two or more configurations. The environment then the current configuration used by the UE, and the actions are selection of one or more configurations, the KPI are the rewards. The probability with which one configuration is selected over the other configuration(s) is adjusted based on the KPI and signalled to the UE.

[0084] The apparatus may, e.g., be configured to provide the at least one command for the user equipment, wherein the command may be carried by RRC signalling, LPP signalling, NAS signalling, MAC-CE signalling or DCI signalling, wherein the command may instruct the UE to do any one of the following:

[0085] Modify at least one measurement gap parameters, including gap-offset indicating the time location of the start of the measurement gap with respect to a certain frame, slot or symbol boundary and / or periodicity.

[0086] Instructing at least one measurement and / or measurement within at least one measurement gap to be either skipped or performed by the UE, based on measurement or measurement gap configured to the UE by earlier signalling (e.g. RRC).

[0087] Indicating the UE to adjust at least one parameter of the measurement configuration provided to the UE, in response to a status report or indication provided by the UE (e.g. battery power, buffer status report, power headroom report).

[0088] Indicating the UE to transmit at least one reference signal according to a configurationor a set of configurations provided to the UE (e.g. via preconfiguration, system information, RRC configuration), in response to a status report or indication provided by the UE (e.g. battery power, buffer status report, power headroom report) or capability or UE assistance information (UAI).

[0089] Sending information regarding the battery status of the UE, wherein the battery status may indicate the remaining battery power, the projected battery life, indication regarding remaining battery power remaining at a certain reference time (for example, the time when the battery would typically be connected to charging point) or reference times (last charge, next anticipated charge, etc), indication regarding change in remaining battery power.

[0090] Sending an indication to the network if the remaining battery power or projected battery power or remaining battery time or remaining projected battery power or remaining projected battery power subject to reduced or increased operation (e.g. measurements) falls below respective threshold value(s).

[0091] Performing at least one operation, such as adjusting measurement and / or measurement reporting parameters, indicating the NW its reduced capability to do certain operation (e.g. inter-frequency measurements / predictions) or start / stop transmission of certain reference signals (e.g. UL-SRS, positioning reference signals, scheduling request) in response to change in battery status (e.g. remaining battery power or projected battery power or remaining battery time or remaining projected battery power or remaining projected battery power).

[0092] Providing at least one information, describing the UE configuration or parameters, such as UE beams, UE orientation, Antenna orientation and / or location, UE dimensions etc.

[0093] Providing information pertaining to location (e.g. LCS or cell-ID) and / or motion of the UE (e.g. motion state, measurements from motion sensor)

[0094] Indicating the UE to transmit its measurement estimate, immediately, at a future time instant, on over an interval. Indicating the UE to transmit its event prediction within a certain time interval (e.g. RLF within a certain window), wherein the interval may be configured to the UE by earlier configuration (e.g. RRC_configuration or indicated dynamically (e.g. using MAC-CE signalling or DCI signalling).

[0095] Indicating the configuration of the interval where the UE is expected to perform measurements (e.g. measurement window) and / or the interval where the UE is expected to perform predictions (e.g. prediction window). The measurement window and prediction window may be adjacent to each other or may be separated by configured gap, alternatively the two windows may be signalled to the UE. In some examples, the windows may be fixed and alternating and in other examples, the windows may be configured as sliding windows.

[0096] Filtering coefficient for averaging raw measurement or L1 predicted measurements and / or indication to AI / ML model (e.g. using identifier signalled to the NW by the UE or from the UE to the NW) to use for prediction.

[0097] Indication of QCL information to the UE informing the UE whether two signals are similar in terms of at least one of the following parameters: Doppler spread, average delay, delay spread, spatial Rx parameter. The at least two signals may be SSB on FR1 and SSB on FR2, SSB on FR1 and CSI-RS on FR1. DL-PRS on FR1 and SSB on FR2, SSB on FR2 and DL-PRS on FR1. In summary, any combination of DL signal on first band with any combination of DL signal on the second band.

[0098] In some embodiments, the measurement window may, e.g., be implementation dependent and only the prediction window may be signalled to the UE.

[0099] According to an embodiment, apparatus may, e.g., be configured to provide the configuration or the set of configurations for the user equipment, such that the configuration or the set of configurations comprising a conditional handover, where the handover may, e.g., be performed where where the condition associated with the configuration are fulfilled, or comprising a configuration of a connection after performing the handover or adjustment of at least one connection parameter (such as a group of serving cells, timing adjustments, configuration for enabling swift connection restore, such as contention free-handover setting, etc). Moreover, a user equipment of a wireless communication network according to an embodiment is provided. The user equipment is configured for obtaining and processing at least one command and / or a configuration to maintain a connectivity with the network, wherein the at least one command and / or the at least one configuration depends on one or more measurement predictions or event predictions.

[0100] According to an embodiment, the at least one command and / or the at least one configuration may, e.g., depend on the one or more measurement predictions or event predictions, which depend on information on the one or more measurements or on information on one or more measurement estimates. The one or more measurements or the one or more measurement estimates may, e.g., depend on a radio condition between the user equipment and a network entity of the wireless communication network.

[0101] In an embodiment, the user equipment may, e.g., be configured to conduct one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network. The one or more measurement predictions or event predictions may, e.g., depend on information on the one or more measurements.

[0102] According to an embodiment, the user equipment may, e.g., be configured to receive information on one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network. The one or more measurement predictions or event predictions may, e.g., depend on the information on the one or more measurements.

[0103] In an embodiment, the user equipment may, e.g., be configured to receive the information on the one or more measurements from said network entity.

[0104] According to an embodiment, the user equipment may, e.g., be configured to receive the information on the one or more measurements from another network entity of the wireless communication system.

[0105] In an embodiment, the user equipment may, e.g., be configured to receive the information on the one or more measurements from another user equipment of the wireless communication system. According to an embodiment, the user equipment may, e.g., be configured to transmit the information on the one or more measurements to a network entity of the wireless communication network. The user equipment may, e.g., be configured to receive the at least one command and / or the configuration, which depends on the information on the one or more measurements transmitted to the network entity.

[0106] In an embodiment, the user equipment may, e.g., be configured to determine one or more measurement estimates depending on the information on the one or more measurements. The user equipment may, e.g., be configured to transmit the information on the one or more measurement estimates to a network entity of the wireless communication network. Moreover, the user equipment may, e.g., be configured to receive the at least one command and / or the configuration, which depends on the information on the one or more measurement estimates.

[0107] According to an embodiment, the user equipment comprises an Artificial Intelligence / Machine Learning model. The user equipment may, e.g., be configured to conduct the one or more measurement estimates using the Artificial Intelligence / Machine Learning model. Moreover, the user equipment may, e.g., be configured to transmit information on the one or more measurement estimates to the network entity or to another network entity of the wireless communications network.

[0108] Furthermore, a user equipment of a wireless communication network according to another embodiment is provided. The user equipment comprises an Artificial Intelligence / Machine Learning model. The user equipment is configured to conduct one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network. The Artificial Intelligence / Machine Learning model is configured to conduct one or more measurement estimates, which depend on the radio condition between the user equipment and said network entity of the wireless communication network. The user equipment is configured to transmit information on the one or more measurement estimates to the network entity or to a second user equipment or to another network entity of the wireless communications network.

[0109] According to an embodiment, the user equipment may, e.g., be configured to receive a request for a measurement or a measurement estimate on a measurement object from an entity of the wireless communication network. The user equipment may, e.g., be configured to conduct a measurement estimate using the Artificial Intelligence / Machine Learning model using the measurement or the measurement estimate. The user equipment may, e.g., be configured to transmit information on the measurement estimate to said entity of the wireless communication network.

[0110] In an embodiment, the user equipment may, e.g., be configured to receive a request to provide a measurement on the measurement object instead of providing a measurement estimate. On receiving the request, the user equipment may, e.g., be configured to conduct the measurement on the measurement object.

[0111] According to an embodiment, the user equipment may, e.g., be configured to receive an indication to temporarily disable to provide the one or more measurements or measurement predictions. In response to the indication, the user equipment may, e.g., be configured to not transmit any measurement or measurement prediction for a predetermined time period.

[0112] A user equipment may, e.g., be configured to provide a measurement report either with its own measurement or using predicted measurement (e.g. using AI / ML model). The UE may, e.g., perform prediction of measurement at a future time or time interval or in a different band. A UE may, e.g., be configured a threshold or a set of thresholds for different KPIs which must be achieved before the UE is allowed to signal its capability to perform measurement prediction or its capability to use its AI / ML model to perform certain actions (such as predicting measurement or events). A UE may, e.g., be required to achieve certain KPIs such as accuracy, recall, precision, F1 -score or have prediction with a certain quality. e.g certain spread measurement and prediction within certain threshold values etc. before the UE indicates the NW its capability to use AI / ML based operations. The parameters may, e.g., be signalled to the UE when the UE indicates its availability to use such functionality.

[0113] The UE may, e.g., initially report its capability to the network to use AI / ML model for certain operation (e.g. measurement and / or event and / or parameter prediction). In some examples, the network may, e.g., allow the UE to immediately use such capabilities. In other examples, the network may need to (dynamically) validate the model before the UE is allowed to use the functionality. The network may then provide the UE with certain fixed configuration (e.g. measurement objects). The UE may, e.g., perform prediction(s) and / or measurement(s). The network may, e.g., provide KPIs the UE need to fulfill before the capability of the UE may be activated or used. For example, the UE may, e.g., indicate the network that it has an AI / ML model to predict inter-frequency measurements. The network may configure the UE to perform certain measurements and give the KPI values. If the AI / ML model prediction fulfills the KPI values indicated by the network, then the UE may request the NW to activate or request a grant to allow the UE to use the AI / ML based functionality. The UE may, e.g., report the KPI values and the network may reconfigure the UE (e.g. reconfigure measurement gaps).

[0114] Likewise, the UE may, e.g., indicate unavailability of AI / ML functionality on not fulfilling KPI within an observation window. The UE may, e.g., further request configuration for fallback operation or the NW may provide such fallback configuration when the UE indicates the unavailability of AI / ML functionality.

[0115] The verification of AI / ML functionality may, e.g., be done dynamically (e.g. at cell-level, TA- level or RAN-level) or semi-statically (e.g. in a registration area). A UE may have a running timer allowing the UE to use the AI / ML functionality within a certain time. Alternatively, the UE may, e.g., be configured with a validity area, where the UE may continue to use such AI / ML model. A UE may indicate the change in capabilities when the UE leaves the area or the timer expires. A UE may perform revalidation of the model before the expiration of the validity timer corresponding to the AI / ML model validated by the network.

[0116] The network may provide indication to the UE on validating the AI / ML model or functionality at the UE for measurement or connectivity purposes. The indication may be sent to the higher layer (e.g. application layer), wherein in response to receiving an indication from the network that AI / ML based functionality for connectivity is accepted for the UE from the network, the UE displays a status indication indicating activation of AI / MI based features.

[0117] In an embodiment, the user equipment may, e.g., be configured to receive an indication to temporarily disable to provide the one or more measurements or measurement predictions, if a difference between at least one of the one or more measurements or measurement estimates and at least one of one or more measurement predictions of said network entity or of said other network entity is within a predefined interval.

[0118] According to an embodiment, the user equipment may, e.g., be configured to receive an indication to temporarily disable a measurement gap configuration depending on at least one of the one or more measurements or measurement estimates and depending on at least one of one or more measurement predictions or event predictions of said network entity or of said other network entity. The user equipment may, e.g., be configured to temporarily disable the measurement gap configuration in response to receiving the indication.

[0119] In an embodiment, user equipment may, e.g., be configured to provide input data to the Artificial Intelligence / Machine Learning model comprising information on one or more measurements or measurement estimates, which depend on the radio condition between the user equipment and a network entity of the wireless communication network.

[0120] According to an embodiment, the user equipment may, e.g., be configured to provide the input data to the Artificial Intelligence / Machine Learning model, which further may, e.g., comprise additional information in addition to the information on said at least one of the one or more measurements or measurement estimates.

[0121] In an embodiment, the additional information may, e.g., comprise statistics provided by network data analytics. In some examples, the RAN node may be a subscriber to the network analytics provided by the NWDAF or O&M. In other examples, where the O-RAN architecture is deployed, the statistics and / or analytics may additionally or alternatively be provided by Non-Real time RIC, Near Real time RIC (e.g. xAPP).

[0122] According to an embodiment, the one or more measurements or measurement estimates comprise one or more of the following: one or more measurements or measurement estimates on a radio condition between the user equipment and the network entity, one or more measurements or measurement estimates on a radio condition between the user equipment and another network entity, one or more measurements or measurement estimates on a radio condition between another user equipment and the network entity, one or more measurements or measurement estimates on a radio condition between another user equipment and another network entity, one or more measurements or measurement estimates on a radio condition between the user equipment and another user equipment, one or more measurements or measurement estimates on a radio condition between the network entity and another network entity.

[0123] The one or more measurement may be raw measurement made by the physical layer and filtered, resulting in L1 measurements (RSRP, RSRQ, SINR) or they may be the filtered measurement resulting in averaged measurements such as the L3 measurements.

[0124] The measurement estimates may be based on the measurement performed by the UE. For example, a L1-RSRP for a given beam in a particular cell may be predicted using L1-RSRP for at least one beam on the same cell, or using at least one beam on a different cell or a combination of both. Likewise, a L1 or L3-RSRP for a given beam in a particular cell may be predicted using L1 or L3-RSRP or at least one beam on the same cell, or using at least one beam on a different cell or a combination of both.

[0125] Likewise, the average cell measurement estimates may be based on a L1 or L3-RSRP for a given beam in a particular cell may be predicted using L1 or L3-RSRP or at least one beam on the same cell, or using at least one beam on a different cell or a combination of above. Alternatively, different combination of cells and beams in one or more cell may be made to perform predictions above.

[0126] A UE may report to the network the relationship between measurement on one cell to at least one another cell (e.g. covariance between two measurements) to the network. For example, a UE may observe a cell to suddenly drop in measurement (e.g. due to an obstacle) but measurement to other cells may be relatively stable. For example, there may be more frequent measurement on the cell that has suddenly dropped to make estimation better. The network may configure a UE to alter its measurement and / or its measurement reporting in response to a sudden change in measurements observed in at least one cell.

[0127] In an embodiment, the user equipment may, e.g., be configured to conduct the one or more measurement estimates depending on the one or more measurements.

[0128] According to an embodiment, the user equipment may, e.g., be configured to employ one or more of the one or more measurements to train the Artificial Intelligence / Machine Learning model. In an embodiment, the user equipment may, e.g., be configured to feed at least one of the one or more measurements as input data into the Artificial Intelligence / Machine Learning model.

[0129] The UE may, e.g., perform future predictions of the measurement on the same reference signals made and / or the same cells and / or same beams and / or between two reference signals having a certain QCL relation. Alternatively, the UE may perform prediction of measurement of cells on different carrier frequency, references signals having different QCL relation. The ability of UE to perform temporal and / or spatial and / or inter-frequency predictions is a UE capability, and may be indicated to the network using UE signalling, such as UE assistance information carried over RRC_signalling from the UE to the network. The UE capability may be dynamic and may depend on the model configured or available at the UE. In some examples, the model may be valid only within a certain area or a certain period of time. If the UE model becomes valid in a new area or becomes invalid when entering a new area or an updated model becomes available at the UE to handle one or more type of prediction, then the UE may send an updated UAI to the network informing the changes in capabilities. This enables the NW to configure or enable the UE to perform certain prediction or disable certain measurement and / or reporting and / or measurement and / or reporting configurations.

[0130] According to an embodiment, the user equipment may, e.g., be configured to receive the Artificial Intelligence / Machine Learning model from a network entity or from an OTT server of the wireless communication network. The user equipment may, e.g., be configured to refine and / or update the Artificial Intelligence / Machine Learning model by training the Artificial Intelligence / Machine Learning model using the at least one of the one or more measurements.

[0131] In an embodiment, at least one of the one or more measurements is a measurement for a first frequency layer or for a first carrier frequency. At least one of the one or more measurement estimates is a measurement for said first frequency layer or for said first carrier frequency.

[0132] According to an embodiment, at least one of the one or more measurements is a measurement for a first frequency layer or for a first carrier frequency. At least one of the one or more measurement estimnates is a measurement estimate for a second frequency layer being different from the first frequency layer, or for a second carrier frequency being different from the first carrier frequency.

[0133] In an embodiment, at least one of the one or more measurements is a measurement for a first signal. At least one of the one or more measurement estimates is a measurement estimate for a second signal being collocated with the first signal.

[0134] According to an embodiment, at least one of the one or more measurements or measurement estimates may, e.g., comprise a measurement or a measurement estimate on an uplink reference signal.

[0135] In an embodiment, the uplink reference signal may, e.g., be an SRS or a PRACH or a DMRS or an UL-PTRS or a signal based on an orthogonal sequence (e.g., a Zadoff-Chu sequence or a Gold code sequence) transmitted by the user equipment or by another user equipment of the wireless communication network.

[0136] According to an embodiment, the user equipment may, e.g., be configured to conduct one or more measurement estimates of channel parameters for a channel between the user equipment and the network entity.

[0137] In an embodiment, the one or more measurement estimates comprise one or more of the following: a spatial prediction of a beam measurements, a temporal prediction of a beam measurement, a spatial and temporal prediction of a beam measurement, an inter-frequency prediction of a beam measurement, one or more cell-measurements beams of TRPs and / or group of TRPs, a dwell time in target cell, an anticipated RLF, an uplink synchronization, such as timing advance in the new cell, a carrier frequency offset, a transmit power, a pathloss reference, a UE-beam, a carrier frequency offset.

[0138] According to an embodiment, the user equipment may, e.g., be configured to receive a configuration or an updated configuration for an uplink reference signal and / or for a sidelink reference signal depending on the information on the one or more measurements or measurement estimates transmitted.

[0139] In an embodiment, the user equipment may, e.g., be configured to take part in a handover of the user equipment from one cell to another cell of the wireless communication network depending on the information on the one or more measurements or measurement estimates transmitted.

[0140] According to an embodiment, the user equipment may, e.g., be configured to decide whether to conduct a measurement or whether to conduct a measurement estimate.

[0141] In an embodiment, the user equipment may, e.g., be configured to decide whether to conduct a measurement or whether to conduct a measurement estimate depending on a state of a battery power of a battery of the user equipment.

[0142] According to an embodiment, the user equipment may, e.g., be configured to decide whether to conduct a measurement or whether to conduct a measurement estimate depending on a processing load and / or depending on a buffer state, (e.g. buffer size at the user equipment or network, or, e.g., a packet delay budget, or, e.g., an expiration deadline of packets in a buffer). In an embodiment, the user equipment may, e.g., be configured to provide an indication to a network node of the wireless communication network that it has skipped a measurement and / or that it has skipped reporting a measurement.

[0143] According to an embodiment, the user equipment may, e.g., be configured to provide an indication to the network node indicating a cause why the UE skipped measurement and / or reporting (e.g., by providing a value).

[0144] In an embodiment, the one or more measurements comprise one or more of the following: one or more measurements on signal power and / or signal quality and / or timing per SS / PBCH block, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least two SS / PBCH blocks; one or more measurements on signal power and / or signal quality and / or timing per cell based on SS / PBCH block(s), one or more measurements on signal power and / or signal quality and / or timing or timing diffrences between two cells based on SS / PBCH block(s), one or more measurements to detect SS / PBCH block(s) indexes and / or measured above a threshold, one or more measurements on signal power and / or signal quality and / or timing per CSI-RS resource, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least CSI-RS resource and a SS / PBCH block, at least two CSI-RS resources or a combination, one or more measurements on signal power and / or signal quality and / or timing per cell between at least CSI-RS resource and a SS / PBCH block, at least two CSI-RS resources or a combination, one or more measurements measuring CSI-RS resource measurement identifiers, one or more measurements on signal power and / or signal quality and / or timing, or timing differences above further consolidated using certain filtering or averaging, one or more measurements on signal power and / or signal quality and / or timing, or timing differences above further consolidated or predicted using certain AI / ML algorithms, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least DL-PRS resource and a SS / PBCH block, at least two DL-PRS resrouces or a combination, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least two LIL-SRS resources, one or more measurements on phase or phase differences between at least two signals.

[0145] According to an embodiment, the one or more measurements comprise one or more measurements on a frequency layer or different frequency layers or different network layers (e.g. terrestrial and non-terrestrial).

[0146] Moreover, a system according to an embodiment is provided. The system comprises comprising an apparatus according to one of the above-described embodiments, and a user equipment according to one of the above-described embodiments.

[0147] In the following, particular embodiments are described in detail.

[0148] At first, a problem formulation is provided.

[0149] In 3GPP networks, mobility is controlled by the network node, which until Rel. 18 is of reactive nature. The major problem with the existing mechanisms is that:

[0150] 1) The existing handover mechanism are based on measurement made by the UE in the past, which may not reflect the conditions in the future. 2) Measurement reporting by the UE for different network layers (e.g. different RAT technologies, different type of access (e.g. terrestrial or non-terrestrial access) causes processing and / or signaling overhead.

[0151] 3) To collect measurements from different RAT technologies or from a different frequency layer (e.g. inter-frequency measurements), measurement gaps need to be configured. Depending on the mobility state of the UE, the measurements may need to be performed more often. During the measurement gap, the UE may not transmit and / or receive radio signals on the carrier frequency or BWP where the UE is connected to the network. The pauses its regular data transmission and reception, switches its receiver to a configured target frequency to perform measurement on, and performs measurements on parameters such as signal strength, quality, and interference levels. This may be determined by the configuration of the reference signals that the UE is expected to perform measurement on. This may be one of the measurement objects, or a configuration of DL-PRS assistance data for positioning. Once the measurements are completed, the UE resumes normal operations on its serving frequency. Finally, the measured data is processed and reported back to the network, which utilizes this information for mobility management, handover decisions, and radio resource management. Consequently, this makes addressing the requirements of services having one or more stringent requirements, such as high throughput, low jitter, low latency, etc.

[0152] With the reactive approach, the UE may not be able to exploit knowledge of the environment, such as existence of obstacles and / or reflectors in the surroundings that the UE may encounter in future. This may cause short term radio link failures and / or short dwell time in a cell.

[0153] To address these problems, 3GPP is currently studying various mechanisms to be able to predict future measurements (such as RSRP, RSRQ, SINR values, Radio link failure), etc to handle mobility of current and future generations of mobile communications.

[0154] Some embodiments target reducing the number of measurements and / or reporting to be performed by the UE. Furthermore, this reduces the number of measurement gap needed by the UE, thereby ensuring continuity of transmission and reception.

[0155] Some background considerations are now made:

[0156] A UE may be capable of using one or more radio access technologies to establish connection with a wireless network. Example of radio access technologies include LTE, new radio, or future radio interface, such as the radio interface of the 6G radio. The wireless network may provide coverage to the mobile devices using a combination of different radio access technologies, such as 2G systems (like GPRS), 4G systems (like LTE), NR and so on. As the UE moves along in the network, it may need to move between different radio access technologies, different frequencies, different cells depending on several requirements and constraints. Examples of requirements may be data rate, latency requirement, reliability of data transmission, packet loss rate, bit error rate and so on. The constraints may be, power consumption (e.g. processing), transmit power, UE capability, hardware (e.g. number of antenna), size of the device, etc. Likewise, constraints may also come from network priority, radio resource management at the network side, and so on. For example, even if a UE may have good channel condition to a cell served in NR, but the NR cell may be overloaded due to higher priority traffic, the network may need to handover the UE to a different LTE cell for load balancing purposes.

[0157] Mobility in LTE (4G) or NR (5G) radio systems by establishing signalling connection to the core network via an access network. The access network level mobility in 5G NR is depicted in Fig. 2, as defined in TS38.300 (Ver 18.0.0). In particular, Fig. 2 illustrates mobility in NR.

[0158] A UE in RRCJDLE mode or RRCJNACTIVE mode camps on a cell, listening to paging from the core network or NG-RAN network. Furthermore, the UE may receive small data transmission and / or reception using SDT mechanism, wherein small amount of data is transmitted without going into the RRC_CONNECTED mode.

[0159] Mobility is achieved by initial selection or reselection of camped cell, where the UE does not need to inform the network where exactly the UE is as long as it is within one of the cells configured within the respective notification area (e.g. RAN-notification area (RNA) for RRCJNACTIVE or tracking area for RRCJDLE and RRCJNACTIVE). A UE in RRC_CONNECTED state needs to ensure mobility by means of handover from a source cell to a target cell.

[0160] Fig. 3 depicts the state-of-the-art procedures for handover of a UE between the source gNB and a target gNB, in a scenario where neither AMF nor UPF changes. In particular, Fig. 3 depicts a state-of-the-art Handover procedures according to TS 38.300, V18.1 .0. There may be scenarios where either AMF or UPF or both may need to change. Furthermore, there may be scenarios where the source gNB need provides redirection towards target cell, e.g. the source gNB orders the UE to idle mode providing information about the target cell, where the UE should attempt connection. This could, for example, happen when there is no interface (known as N26 interface) between MME of EPC and AMF of 5GC to support 5GC- to-EPC handover. Common to all scenarios, the state of the art requires the UE to perform measurement and report to the source gNB. The source gNB takes handover decision and sends a HANDOVER REQEST to the target gNB (e.g. over the XN interface). The target gNB performs admission control, which may be internal implementation of the UE (and may take into account load in the current cell or priority or network slice etc) and respond to the source gNB whether it accepts the handover request, by sending a HANDOVER REQUEST ACKNOWLEDGE. The source gNB sends a RRCReconfiguration message, indicating at least cell ID and information required to access the target cell without having to read the system information in the target cell. Furthermore, the information required for contentionbased and contention-free random access may also be provided in RRC_Reconfiguration message. There may also be beam-specific information provided to the UE.

[0161] Likewise, there may be inter-gNB handover. This is also referred to as beam-level mobility and there may be no RRC_Handover, but simply beam management. This may pertain to multi-TRP scenario, where the gNB-CU may be the same, but the gNB-DU may be different or the TRP may be broadcasting different cell identifiers (PCI). This scenario, also known as beam level mobility, or inter-cell beam coordination, requires no RRC layer awareness of active beam and can be based on CD-SSB.

[0162] This mean a UE may use a TRP associated with a different Physical Cell Identity (PCI) than the serving cell's PCI for dedicated channels / signals, whereas UE-specific channel or signals are transmitted and / or received via a TRP with the same PCI as the serving cell. The gNB provides RRC signalling to the UE, which includes measurement configurations for SSB and CSI resources, and conditions for triggering and / or reporting measurements. Especially in scenarios involving different TRPs, the configuration for measurement may include resources with SSB associated with different PCI than the serving cell.

[0163] Common to all scenario is that the UE receives the configuration from the network to perform measurement and / or reporting on. This means, the UE reports the measurement to the source gNB, which takes handover decision based on this information.

[0164] In NR standards, the following handover mechanisms are supported:

[0165] 1) Handover mechanism defined in Rel. 15 (primary handover mechanism):

[0166] The source gNB configures the UE with measurement objects to specify the cells and frequencies and the type of resources (SSB / CSI position (e.g. time / frequency location), subcarrier index, etc etc) to monitor. Likewise, the source gNB also specifies reporting configuration to the UE (e.g. periodic, event-triggered, CGI reporting, how many cells to report, how many beams to report, whether beam measurements are to be included etc. etc). Furthermore, a measurement ID links the measurement and reporting configuration. For example, an event A3 informs the source gNB that the neighbouring cell has become stronger than current cell. The source gNB based on UE- measurements, determines when a handover is necessary and initiates handover request to the target gNB. The target gNB performs admission control, which may comprise of reserving resources for the said UE and responds back to the source gNB. The source gNB sends a handover command to the UE by means of RRC_RECONFIGURATION. The UE detaches from the source cell, performs random access with the target cell, and reconfigures based on the target gNB's information. Once synchronization and reconfiguration are complete, the target gNB notifies the source gNB, which then releases the resources. A new routing path is created between UPF and target gNB for routing the said UEs packet, and existing packets are forwarded to the target gNB.

[0167] 2) Conditional handover mechanism defined in Rel. 16:

[0168] The gNB provides a UE with a configuration of candidate cells and the conditions for executing the handover to the cell. The configuration of candidate cell come from the target gNB and the source gNB provides the condition which when satisfied starts the handover process. There may be one or two trigger conditions (CHO events A3 / A5) and the CHO is based on single RS type and two trigger quantities (e.g. RSRP and RSRP or RSRP and SI NR) may be monitored as a evaluation condition for handover towards a single candidate cell.

[0169] As conditional handover is provided to UE while the UE is still in good channel condition, the RRCReconfiguration containing CHO configuration can be assumed to be received by the UE before Radio link failure occurs, which was one of the main problems with the primary handover mechanism.)

[0170] 3) L1 / L2 triggered mobility defined in Rel. 18:

[0171] A L1 / L2 triggered mobility is a mechanism enabled in Rel. 18 to allow the gNB to switch the serving cell for a UE by a cell-switch command signalled using a MAC-CE. The gNB would have previously configured a candidate cell using RRC-signalling and upon receiving a MAC-CE from the source cell, the UE switches to the indicated target cell. This mechanism was introduced to reduce latency. 1) The existing handover mechanism are based on measurement made by the UE in the past, which may not reflect the conditions in the future.

[0172] 2) Measurement reporting by the UE for different network layers (e.g. different RAT technologies, different type of access (e.g. terrestrial or non-terrestrial access) causes processing and / or signaling overhead.

[0173] 3) The UE may not be able to exploit knowledge of the environment, such as existence of obstacles and / or reflectors in the surroundings. This may cause short term radio link failures and / or short dwell time in a cell.

[0174] This invention aims to utilize the measurements performed on the signals that are already transmitted and / or received by the UE for further measurements by the network to predict the parameters for mobility. In particular, if an AI / ML model for mobility management is deployed at the NW side, this reduces the overhead the UE has to spend on performing inter-frequency measurements. Likewise, it also utilizes the existing uplink reference signal transmitted to predict the suitable parameters for transmission.

[0175] Further particular embodiments are now described in detail:

[0176] Existing solution relies on UE performing measurement, and either reporting the measurement back to the serving gNB, which may be used by the serving gNB to provide a handover command and / or handover configuration (e.g. CHO) to the UE. The UE then attaches itself with the new cell as indicated by the network. In the state-of-the-art, the handover is based on UE measurements on downlink reference signal transmitted by the network node, such as CSI-RS or SSBs.

[0177] In an RRC_CONNECTED mode, there are also reference signals transmitted by the UE. The measurement made by network nodes on these reference signals can also be utilized by the network node for handling mobility of the UE. On large scale, the parameters of channel transmission are generally correlated between uplink and downlink. On smaller scale, there may, however, be smaller differences between the channel parameters of the uplink and downlink, depending on hardware components (e.g. for TDD) and / or frequency separation (e.g. for FDD) or separation between BWP used in uplink vs BWP used in downlink. The network node may use the uplink measurements to perform mobility decisions, either alone, or in combination with the measurement performed and reported by the UE. In general, mobility decisions are taken by averaging the physical layer measuremets to average out errors (for example due to noise), which is generally referred to as L1-filtering. These filtering effects are implementation specific. Then certain beams are selected and processed further to determine the aggregate cell-level measurements, which is further smoothened with L3-filtering coefficients which are provided to the UE to obtain smooth measurements.

[0178] The invention described in this document enables the network node to utilize the measurement made by one or more network node, in addition to, or instead of the measurements performed and reported by the UE.

[0179] In some examples, the mobility of the UE may be handled by data driven statistics, for example, where the existing data collected by the UE and the network node are used to train a model, either at the UE side, or at the network side, or both. Such data driven statistics, may be used to train a AI / ML model, where the AI / ML model may be used to predict at least a measurement pertaining to mobility of the UE and / or an event describing the RRC_CONNECTION status or its performance (e.g. RLC failure).

[0180] In some examples, the uplink measurements made by the network node may be used to validate and / or to calibrate the measurements reported by the UE. This may be needed, when the UE is also running data driven algorithms (e.g. UE-sided AI / ML model), and the performance needs to be checked by the network to ensure that the reported statistics are valid. In addition or as an alternative, the uplink measurement can be utilized by the network to relax the measurement and / or measurement reporting and / or event reporting from the UE. Especially in TDD systems, the use of the channel reciprocity property can be utilized to deduce measurement on downlink reference signals performed by the UE based on uplink measurement made by one or more network nodes. For this, the reference signals transmtted by the UE (e.g. SRS) may be utilized or the UE may be configured to transmit the reference signals with a different configuration or different type of uplink reference signals.

[0181] To enable a robust handover mechanism, according to an embodiment:

[0182] A method performed by a network entity (e.g. gNB) for managing connectivity between the UE and the cellular network, wherein the network entity,

[0183] 1) Receives measurements corresponding to the radio condition between the network entity and the UE on a first carrier frequency / first frequency layer. 2) Predicts measurements and / or events corresponding to radio condition between at least one component of network (e.g. a TRP) one of more future time instants and / or one or more frequency layers.

[0184] 3) Based on predicted measurement or events, provides at least one command and / or configuration to the UE to maintain the connectivity with the network.

[0185] For predicting the measurement and / or events, the network entity may have an associated AI / ML model, which predicts measurement or channel conditions between one or more network components and the UE, at one or more time instants.

[0186] The radio channel conditions predicted may be based on measurement performed by the UE and / or reported to the network based on selection and filtering according to the conditions provided by the network.

[0187] Alternatively, or in addition to the measurement performed by the UE, the radio channel conditions prediction may be based on the measurement performed by at least one network component (e.g. TRP), based on at least one uplink reference signal transmitted by the UE and received by at least one network component (e.g. the serving cell).

[0188] The prediction of radio channel conditions may be performed for the frequency layer (flnf = fMeas), or the prediction may be performed for a different frequency layer (flnf not equal to fMeas).

[0189] Fig. 4 illustrates a prediction of inter-frequency measurements. The f1 to which the UE is connected may and f2 may be between two different TRPs. But there may be another NW- node (e.g. TRP-2 handling f 1 , which may be collocated with the TRP handling f2)

[0190] In some examples, the network may comprise of hierarchical networks, wherein the microcells may be operating on carrier frequency (f 1 ), and the macro-cells may be operating on carrier frequency (f2). Based on measurement performed in frequency layer A (FL_A), where FL_A corresponds to carrier frequency of f 1 , the prediction may be made for frequency layer B (FL_B), where FL_B corresponds to carrier on frequency f_2.

[0191] In some examples, the network elements transmitting signals according to FL_A and FL_B may or may not be collocated. The AI / ML model may receive information on the co-location state of the network elements that are transmitting the signals in FL_A or FL_B, so that the radio channel condition between the transmitter and the receiver and vice versa can be predicted.

[0192] Fig. 5 illustrates a prediction measurement at different time instants based on measurement and / or additional information according to embodiments. The different measurements predicted in time may have different quality associated with them. The quality of the prediction may be used to relax measurements at the UE side or complement with the NW side model predictions and / or measurement at the NW side to handle RRC_CONNECTION of the UE.

[0193] Fig. 6 illustrates an embodiment, where the AI / ML model may be able to predict events, such as measurement events ahead of time. The predicted event from either NW node and / or UE may be used to provide an early indication of impending condition.

[0194] Fig. 7 illustrates a hierarchical network. The NW may be able to predict the inter-frequency measurements with the measurement performed by the UE and / or NW node on the frequency associated with the RRC_CONNECTION.

[0195] The network entity may predict at least a channel parameter (e.g. RSRP, RSRQ, SINR etc) between a network component (TRP) and the UE, using an AI / ML model. The network entity may configure the UE to perform measurement and / or report measurement, wherein the measurement performed and / or reported by the UE corresponds to the predicted channel parameter.

[0196] The network entity may further indicate the UE to perform measurement on the configured measurement object and indicate restriction to the UE in using a prediction made by the UE. The network entity may validate the model running at the network, with the ground truth collected from the UE by mandating the UE to perform measurements, rather than use AI / ML model for measurement prediction.

[0197] Alternatively, the NW may leave it up to the UE on how it provides the measurement. The second version may be useful for aligning the models at the NW and UE side.

[0198] In one variant, the UE may report the measurement to the network as configured. The network may compare the predicted measurement with the actual measurement and determine whether the measurement and measurement reporting at the UE can be relaxed. For example, if the predicted measurement and the reported measurement are within a certain interval, then the NW may be able to determine that the AI / ML model matches the UE measurement. The NW may indicate to the UE that at least one preconfigured measurement gap configuration may be disabled temporarily.

[0199] In another variant, the network may provide one or more predicted measurement and / or confidence in predicted measurement to the UE. The measurement may be predicted for one or more frequency layers and / or spatial layers and / or at one or more time instants. A UE may compare the received measurement and compare the received measurement against the performed measurement and indicate the difference between the real measurement to the network. Alternatively, the UE may be configured with a threshold, wherein if the mismatch between prediction and measurement exceeds a threshold, then the UE may be triggered to report measurement to the network.

[0200] In some examples, the UE may be equipped with an AI / ML model (for example, the UE- sided model). The UE-sided model may be trained to generalize over a wider area. Likewise, the network may be equipped with an AI / ML model (for example, the NW-sided model), wherein the network sided model may have been trained to deliver a good performance in the local area. The network side measurement and / or a prediction from the network-sided model may be used to trigger one or more LCM phases at the UE:

[0201] 1) Data collection by the UE.

[0202] 2) Monitoring of the LCM at the UE side (for example, a UE indicated to perform real measurement and compare to the AI / ML model).

[0203] 3) Switch to the fallback mode.

[0204] In some examples, the NW may configure the UE to perform measurements and ask the UE to report one or more measurement. The UE may be indicated to report additional conditions, such as an identifier to denote the UE-sided beamforming, which it used to perform the measurement. The reported measurement may be used by the network side to fine-tune, calibrate or switch models at the network side.

[0205] In the following, the details of interactions are described to achieve the above effects in further detail.

[0206] A network node (e.g. the serving gNB) provides at least one configuration of uplink reference signal and / or sidelink reference signal to at least one UE and / or a group of UEs. The UE transmits the reference signal according to the configuration provided to the UE. The reference signal may be used by the network node serving the UE to determine and / or adjust at least one parameter of transmission to the UE. For example, the measurement on the sounding reference signal (SRS) made by the serving network node (e.g. TRP transmitting the CD-SSB corresponding to the PCI of the serving cell) for antenna selection or for scheduling. In current state-of-the-art, the neighbouring network nodes (e.g. TRPs transmitting CD-SSBs that are different from the CD-SSB of the serving cell) are generally agnostic to the transmission from the UE. Hence, the transmission from the said UE appears as interference to measurement performed by other cells if the same resources are reused by the neighbouring nodes too.

[0207] The solution is to enable the network node, which has established RRC_CONNECTION or the network which last established the RRC_CONNECTION to the UE (also denoted as serving cell, RAN node, serving gNB, serving TRP or similar), to provide the configuration the UE is configured to transmit to at least a second network entity (e.g. a neighbouring RAN node, a neighbouring cell), so that the second network entity can perform measurement on the reference signal transmitted by the UE.

[0208] Some embodiments provide uplink resource assignment coordination.

[0209] Fig. 8 illustrates a collection of measurements from RAN nodes to determine RRC connection parameters by serving node.

[0210] The at least one second network entity performs measurement on the uplink reference signal transmitted by the UE, and provides measurement report back to the serving network node.

[0211] The at least one TRP associated with the first network entity performs measurement on the uplink reference signal transmitted by the UE. The first network entity (example, the source gNB) may request and receive one further measurement from a second TRP associated with the first network entity (e.g. a TRP associated with a different PCI to the PCI of the cell serving the UE). Furthermore, the first network entity may send a measurement request to a second network entity (e.g. a target gNB), wherein the entity may indicate at least one network entity (e.g. TRP ID, or CGI ID), which should perform the measurement.

[0212] The source node may be able to predict one or more measurement and / or parameters and / or event based on at least one measurement performed by the network entity and / or measurement reported by the UE. Fig. 9 illustrates gNBs, TRPs and UEs in a wireless communication network according to an embodiment.

[0213] In some cases, the at least second network entity performing the measurement is TRP connected within the same gNB (e.g. a different DU or the same DU). The gNB then signals the DU (e.g. using F1AP interface) to perform measurement and provide measurement report.

[0214] In some cases, the at least second network entity receiving the configuration and / or reporting the configuration is a different gNB. The gNB may further signal at least one TRP controlled by the gNB to perform measurement. The gNB then receives measurements from at least one network entity controlled by the gNB and provides the measurement to the first network node.

[0215] In some embodiments, the UE may transmit the reference signal immediately upon configuration. For example, the UE may be configured with a periodic reference signal, such as periodic SRS reference signal. In some cases, the UE may transmit the reference signal dependent on the assigned resource blocks (e.g. DM RS for uplink), which are located within the assigned resource blocks. Yet in other cases, the dedicated reference signal, such as sounding reference signal, or other uplink or sidelink reference signals may be transmitted only based on trigger. For example, the UE may be triggered by a downlink MAC-CE to transmit configuration of reference signal already provided to the UE by higher layer (e.g. RRC or LPP or NAS).

[0216] In the following, inference aspects are considered:

[0217] An AI / ML model may be used at a UE and / or a network node, to predict at least one parameter, which may be used by at least one entity (UE or gNB) to adjust at least one parameter of radio connectivity between the network node and the UE.

[0218] In one example, a network entity (e.g. the gNB) comprises an integrated processing logic, which may be an AI / ML model configured to predict at least one parameter pertaining to radio conditions (e.g. RSRP, RSRQ, SINR) between the UE and at least one network entity (e.g. target gNB), or at least one configuration pertaining to the RRC_CONNECTION between the UE and the NW. Based on the predicted parameter or configuration, the network entity may issue at least one command to the UE and / or at least one request to a second network entity. The network entity may acquire measurement from at least one network entity and / or receive at least one measurement reported by the UE, as input to obtain the aforesaid predicted parameter or the aforesaid configuration.

[0219] To acquire such measurement, the network entity may send a request to a second network entity, to perform measurement on certain uplink reference signal transmitted by the said UE.

[0220] The input to the model is at least one of the measurement performed by the UE and / or at least one network node. The at least one network node may be the network node hosted by the same gNB (e.g. the TRP connected to the same source gNB, or the gNB-DU connected to the same source gNB-CU) or it may be hosted by a different gNB (e.g. the TRP connected to a ‘potential’ target gNB). The measurement from the network may be based on at least one uplink reference signal (e.g. SRS, PRACH, DMRS, UL-PTRS and so on). Likewise, the model may also take into account the measurement performed by the UE. Furthermore, the model may also be subscriber to the statistics provided by the network data analytics (e.g. NWDAF, O&M), and the model may take the processed statistics from a group of UE (for example, a group of UEs from a certain OEM, a group of UEs at a certain location), etc.

[0221] As a predicted output, the artificial intelligence / machine learning (AI / ML) model is configured to predict network-related parameters, including but not limited to Reference Signal Received Power (RSRP) and Reference Signal Received Quality (RSRQ), Signal to interference and noise ratio (SI NR) as well as network events such as radio link failures.

[0222] Such predicted parameter may be at least one of the following:

[0223] 1) Beam measurements: a. Spatial prediction, wherein the measurement at one or more location in the wireless coverage area is determined based on measurement at a different location. For example, the measurement on panel ‘a’ in a multi-panel antenna may be predicted based on panel ‘b’. b. Temporal prediction, wherein the measurement at one or more time instants [t1 ...tN] may be predicted based on the input data provided at time instance t. c. Spatial and temporal prediction, wherein prediction may be made for one or more location at one or more time intervals. For example, the model may utilize potential location and measurement simultaneously. d. Inter-frequency prediction, wherein based on measurement made in frequency f 1 , prediction for measurement made in frequency f2 may be made. In line with this example, the TRP transmitting and / or receiving on f2 may or may not be located at the same location. Information about what may be assumed between the measurement on f1 and f2 based on location of the network elements transmitting and / or receiving at these frequencies may be provided to the UE and / or the network node. An example of such assistance information may be the quasi-colocation of the UE. ) Cell measurements a. The cell-measurements are generated based on selection and consolidation parameters provided by the network. In some examples, the selection and consolidation parameters are provided by the network. In other examples, the AI / ML model itself predicts the selection and consolidation parameters. The AI / ML model predicting the selection and consolidation parameters may be based on the outcome of the prediction (for example, whether the prediction led to better outcome or worse outcome). ) Beams and / or group of TRPs suitable for serving a cell at different point in future. The measurements made by the network nodes and / or reported by the UE may be used to predict one or more group of cells, wherein the first group of the cells may be the PCell. There may be additional group of cells, wherein the second group of the cells may be the SCell. Alternatively or in addition, different TRPs may be selected to transmit data and / or control signal to the UE simultaneously or in a time- multiplexed manner. One or more parameters of UE-transmission (e.g. timing advance, carrier frequency offset, beam index, pathloss, transmit power) may be predicted by the model to perform a coherent transmission or joint scheduling of data to the UE from multiple TRPs. ) Dwell time in target cell.

[0224] The dwell time in one or more target cell, based on measurement in uplink and / or reporting from the UE may be predicted by the AI / ML model. The predicted dwell time, in addition to predicted measurements may be used to determine handover or a series of handover or beam-switchings to handle the traffic. 5) Events, such as anticipated, RLF.

[0225] In one example, the anticipated RLF may be predicted by UE based on the measurement and other information available at the UE. In another example, the network model may be able to predict anticipated RLF.

[0226] For handling an anticipated RLF condition, the UE may be provided with conditional handover parameters to use in case of an anticipated RLF. The network model may have been able to predict an anticipated RLF, and may have already reserved resources at other network nodes (e.g. target gNB) preemptively.

[0227] 6) Parameters for UE transmission, such as a. Uplink synchronization, such as timing advance in the new cell. b. Carrier frequency offset. c. Transmit power d. Pathloss reference e. UE-beam

[0228] 7) Parameters for UE reception, such as a. UE-beam b. Carrier frequency offset

[0229] The prediction of one or more measurement and / or event and / or transmission parameters based on AI / ML model may make it unnecessary for the UE to perform and / or report certain measurements or transmit certain information and / or reference signal to the network.

[0230] Likewise, the prediction on the UE side may make it redundant for the network to transmit certain reference signals. For example, if a UE is able to predict inter-frequency measurements based on measurement on the same frequency band (as the serving cell), then the measurement gaps at the UE side become redundant or they can be reduced. A UE may be able to indicate its capability to the network, and in response, the network may be able to configure some of the measurement gaps to be optional. The UE may also be able to request its preferred configuration to perform measurement on.

[0231] Likewise, prediction from the network node may make some of the reporting from the UE redundant. For example, the network may relax certain measurement for the UE, when the UE has indicated that the UE has low battery power, for example, signalling that the UE has battery power below the threshold, or when the UE has certain services that need certain uplink signal transmission anyway (for example, positioning) by performing certain prediction based on uplink reference signals that are anyway transmitted (such as SRS, DMRS, UL-PRS).

[0232] In some examples, at least one of the downlink and / or uplink may have packets with lower jitter or delay tolerance or higher importance. For example, the UE may be using demanding services like XR services or remote driving applications. There may be scenarios, where inter-frequency measurement may be desired but may be challenging to the network to schedule such MGAPS. In such scenarios, the MGAPS may be preconfigured by the network node, and activated on-demand. The on-demand activation may be initiated by the network side or by the UE-side. Either the network side or the UE side may perform interfrequency measurement prediction. Occasionally, the UE may perform the measurement or the NW side may trigger the UE to transmit a signal on a different carrier frequency (e.g. on the SUL carrier). If the difference predicted measurement by the UE and the measurement performed by the UE differ by more than a threshold value, then the UE may indidate the NW to activate at least one of the preconfigured measurement gap configuration. Likewise, if the NW would like to validate the model at the NW side, the NW may indicate the UE to activate the preconfigured MGAP configuration.

[0233] The network may also provide its predicted measurement for one or more time instants. The UE may skip some of the reception (for example, based on PDU set importance) and perform the measurement to validate the measurement by the network.

[0234] Alternatively, the UE may skip at least one of transmission at least at one instance when a preconfigured measurement gap is configured, and perfom measurement to obtain ground truth label to compare to the network.

[0235] By receiving prediction for one or more time instants, the UE can perfom measurement and indicate to the network the accuracy of prediction from network model as a function of time. This information may indicate the network with information on the multiplexing of predicted measurement vs. real measurement. Similarly, for the UE sided model, the UE may be able to provide information to the entity training the model (e.g. the NW-side or the OTT side), about the time validity of the prediction.

[0236] Now, a network indication to the UE according to embodiments is described.

[0237] A network node (e.g. source gNB) may configure the UE to perform measurement on certain measurement objects, and report according to some reporting configuration. In some examples, the UE may have capability of predicting the measurement based on some internal logic and / or AI / ML model running at the UE side. Thus, the UE may be capable of providing inter-freuqency measurements and / or inter-RAT measurements without needing to perform measurement for every instance of reporting. For example, for the case where a periodic reporting is configured with a periodicity of 50ms, the UE may only need to perform measurement every 500 ms and determine the rest of the measurement with the UE-based AI / ML model for predicting measurements. Likewise, the UE may be able to perform interfrequency measurements based on measurement on the carrier frequency on which the UE has maintained the RRC_CONNECTION with the serving gNB and / or based on sparse measurement in the target frequency to be reported. Thus, the UE may be able to skip some of the measurement gaps.

[0238] On the other hand, the network may wish to obtain the measurement reports from the UE for the purpose of validiating or training the NW sided model. Alternatively or in addition, the NW may wish to ensure consistency between estimation (e.g. AI / ML models) used by the UE and / or the network and / or the measurements reported by the UE or other UEs located in the area and / or other network entities. Therefore, the network may wish to receive the actual measurements made by the UE, rather than the measurement reported by the UE based on AI / ML models. The network may be able to indicate to the UE, the preferred or required type of measurement reported by the UE. The type of measurement report requested may include one or more of the following:

[0239] 1) Measurement required - e.g. the UE may report the measurement results based on (raw) measurement performed by the UE and selected and reported according to the criteria signalled to the UE by the network. This approach is similar to the existing legacy reporting mechanism.

[0240] 2) Measurement preferred: e.g. at least one measurement (raw or final) is predicted by the UE based on its internal AI / ML model.

[0241] 3) Predicted / Estimation preferred: e.g. the network may be able to indicate to the UE, that the UE may be able to skip some measurement gaps, in order to skip having to perform certain measurements. The UE may indicate to the network that some measurement gap configuration can be skipped by the UE, and the UE may be able to be scheduled during this period.

[0242] 4) U EDecision: The decision whether to report actual measurements and / or predicted measurement is up to the UE decision. The UE is not expected to decode or transmit during the measurement gaps configured to the UE, and the UE can flexibly select / choose, subject to its internal logic or implementation, whether it performs AI / ML based reporting or reporting based on real measurements.

[0243] In some examples, a pattern may be signalled to the UE, which indicates which of measurements reported by the UE are based on actual measurement and / or network configured filtering (e.g. the legacy procedures), and / or which of the measurement may or shall be based on UE-estimation / predictions (e.g. based on AI / ML model). For example, every nth measurement may be based on actual measurement and filtering, whereas the remaining may be based on estimation / prediction functionality (e.g. based on AI / ML model) supported by the UE subject to its capabilities. This may be done by signalling periodicity and offset values or bitmap patterns or a combination of both.

[0244] According to an aspect of embodiments, skipping measurement I reporting due to low battery power is implemented.

[0245] In one scenario, the UE may be running low on battery power. In this scenario, the UE may only wish to perform measurement pertaining to its own current mobility or perform inference operation for its own mobility. In other words, the UE may not want to participate at least one life cycle management (LCM) operation, such as data collection for training or monitoring, for example, for training the AI / ML model at the given instance. Likewise, the UE may be running down on remaining buffer for data collection. The UE can indicate to the network entity the availability of logged data and / or buffer status (e.g. full or above a threshold), so that the network entity can retrieve the logged data and / or start / stop the existing measurements or measurement reporting. This may be indicated (for example, in case of RRCReconfiguration with Synch) in the RRCReconfiguration message or another message between UE and the source / target base station. In case of handover, the source gNB sends a 1-bit indication to a target cell in HandoverPreparationlnformation message exchanged between the souce and target gNB. This 1-bit indication is included in HO command by the target cell in case the target cell wants to retrieve or keep the data from the UE. If the UE receives the indication, then the UE may keep the collected data from old cell otherwise the UE discards the collected / logged data upon successful handover.

[0246] In one example, the UE may be configured by at least one network entity to information regarding the battery status of the UE, wherein the battery status may indicate the remaining battery power, the projected battery life, indication regarding remaining battery power remaining at a certain reference time (for example, the time when the battery would typically be connected to charging point), indication regarding change in remaining battery power.

[0247] In one example, the UE may be configured by the network to send an indication to the network if the remaining battery power or projected battery power or remaining battery time or remaining projected battery power or remaining projected battery power subject to reduced or increased operation (e.g. measurements) falls below respective threshold value(s).

[0248] In one example, a UE may be configured by the network to perform at least one operation, such as adjusting measurement and / or measurement reporting parameters, indicating the NW its reduced capability to do certain operation (e.g. inter-frequency measurements / predictions) or start / stop transmission of certain reference signals (e.g. UL- SRS, positioning reference signals, scheduling request) in response to change in battery status (e.g. remaining battery power or projected battery power or remaining battery time or remaining projected battery power or remaining projected battery power).

[0249] In some implementations, the NW may indicate mandatory configurations and / or optional configurations for measurement and / or reporting. The UE must provide reporting according to mandatory configuration, and the optional configuration may be skipped by the UE, subject to UE implementation. In line with this example, the mandatory measurement and reporting configuration may correspond to the LCM pertaining to mobility for the own UE and / or the fallback method. The optional configurations may relate to the configuration, which may not immediately and specifically impact the given UE, for example, such configuration relate to data collection for training a AI / ML model and / or to validate an AI / ML model and / or to monitor the performance of AI / ML model.

[0250] In some implementations, the UE may, e.g., be configured with measurement objects and / or measurement gaps. The network may, e.g., signal the UE information enabling the UE to reduce number of beams or measurement instances. For example, it may, e.g., signal the UE the ratio between the skipped measurement time instances to total measurement time instances for a given prediction or a set of predictions. Likewise, the network entity can also signal the UE a ratio between the number of beams measured to the total number of beams that can be measured. The ratio or the maximum ratio that can be used by the UE may, e.g., be signalled by the network. The UE may, e.g., then choose to skip some of the measurements. Alternatively, the network could signal a pattern on which measurement the UE may skip. In some implementations, the UE may, e.g., be configured with one or more configurations of measurements. The UE may, e.g., perform one or more measurements on some configurations and use the measurement performed to obtain the measurement prediction (spatial and / or temporal). The UE may, e.g., be configured with one or more configuration for monitoring the outcome of prediction. Based on the outcome of prediction, the UE adjust (reduce of increase) the number of measurement instants. The network could indicate the UE the number or ratio of measurements that can be skipped.

[0251] Likewise, the UE could signal the current skipped / performed measurement to total measurements to the network, associated with a prediction or a set of predictions.

[0252] The UE could also report the difference between predicted and measured values for one or more measurements that are predicted.

[0253] In another example, the NW may indicate the UE the purpose for requesting a certain measurement and / or a reporting configuration. In some cases, the reporting configuration may, e.g., be used for logging the measurements and / or inference and / or additional information (e.g. UE location).

[0254] In some examples, the NW may provide a numeric value associated with the configurations prodded to the UE. When the value is not provided, the measurement are mandatory and need to be reported by the UE. For example, the measurement reporting according to legacy (e.g. Rel. 18 and earlier) mobility procedures, the measurements are mandatory and may not be skipped. There may be other values indicating high priority, medium priority, or best effort.

[0255] The UE may be configured with conditional reporting, wherein the network indicates the UE to perform and / or report certain measurement, subject to certain condition. Such conditions may be events detected at the UE or they may relate to certain state of the UE. For example, the UE may be configured or choose not to perform or report certain measurement if the remaining battery power is below the threshold. Or, logging data in a buffer for logged data at the UE may, e.g., be reduced or may, e.g., be deactivated.

[0256] In some examples, the UE may be configured to log the measurements and / or predictions (e.g. measurements, events) performed by the UE. The UE may run into low battery state and / or the buffer available for logging the measurement and / or predictions may become full or exceed a certain amount. A UE may send a message to a network entity indicating that the UE has data logged. In response to the message from the UE indicating the availability of logged data, the network may signal the UE to transmit logged data to the network.

[0257] In some examples, the UE may be configured by at least one network entity to log measurements and / or predictions (e.g. measurements, events) performed by the UE. The UE may further be configured to start or stop the measurement either upon reception configuration, or starting at x time units (e.g. next frame boundary, after x ms, etc) after reception of the configuration. The duration of measurement may be specified. Alternatively, the UE may receive the configuration from the network node and may wait for further signalling to start and / or stop the measurement. Finally, the UE may also initiate the logging and / or stop the logging in response to an event occurring (e.g. RLF, serving cell changing, serving cell becoming weaker / stronger than a neighbouring cell etc). Furthermore, the start and / stop condition may be conditional upon a first event occurring before the second event (trigger event) happens). For example, a logging may start when the serving cell becomes weaker than a threshold and stop when the cell-reselection or handover occurs.

[0258] The UE may optionally receive a configuration from the network, wherein the configuration indicates when the UE is expected to indicate the status of the logged data. Alternatively, the UE may indicate the status of the logged data based on events, such events could be low power of the UE (e.g. low battery remaining) or low buffer or high computation load at the UE or higher layer indication (e.g. high CPU processing at application layer).

[0259] The UE may indicate to the network, if one or more measurement reporting are skipped. The UE may further indicate to the network the cause (e.g. low battery power, high processing load, heating issues ... etc) why the measurement and / or reporting was skipped. Furthermore, the UE may request the network to not schedule measurements and / or reporting for a certain interval or a certain amount of time.

[0260] Although some aspects of the described concept have been described in the context of an apparatus, it is clear that these aspects also represent a description of the corresponding method, where a block or a device corresponds to a method step or a feature of a method step. Analogously, aspects described in the context of a method step also represent a description of a corresponding block or item or feature of a corresponding apparatus.

[0261] Various elements and features of the present invention may be implemented in hardware using analog and / or digital circuits, in software, through the execution of instructions by one or more general purpose or special-purpose processors, or as a combination of hardware and software. For example, embodiments of the present invention may be implemented in the environment of a computer system or another processing system. Fig. 10 illustrates an example of a computer system 600. The units or modules as well as the steps of the methods performed by these units may execute on one or more computer systems 600. The computer system 600 includes one or more processors 602, like a special purpose or a general-purpose digital signal processor. The processor 602 is connected to a communication infrastructure 604, like a bus or a network. The computer system 600 includes a main memory 606, e.g., a random-access memory, RAM, and a secondary memory 608, e.g., a hard disk drive and / or a removable storage drive. The secondary memory 608 may allow computer programs or other instructions to be loaded into the computer system 600. The computer system 600 may further include a communications interface 610 to allow software and data to be transferred between computer system 600 and external devices. The communication may be in the from electronic, electromagnetic, optical, or other signals capable of being handled by a communications interface. The communication may use a wire or a cable, fiber optics, a phone line, a cellular phone link, an RF link and other communications channels 612.

[0262] The terms “computer program medium” and “computer readable medium” are used to generally refer to tangible storage media such as removable storage units or a hard disk installed in a hard disk drive. These computer program products are means for providing software to the computer system 600. The computer programs, also referred to as computer control logic, are stored in main memory 606 and / or secondary memory 608. Computer programs may also be received via the communications interface 610. The computer program, when executed, enables the computer system 600 to implement the present invention. In particular, the computer program, when executed, enables processor 602 to implement the processes of the present invention, such as any of the methods described herein. Accordingly, such a computer program may represent a controller of the computer system 600. Where the disclosure is implemented using software, the software may be stored in a computer program product and loaded into computer system 600 using a removable storage drive, an interface, like communications interface 610.

[0263] The implementation in hardware or in software may be performed using a digital storage medium, for example cloud storage, a floppy disk, a DVD, a Blue-Ray, a CD, a ROM, a PROM, an EPROM, an EEPROM or a FLASH memory, having electronically readable control signals stored thereon, which cooperate or are capable of cooperating with a programmable computer system such that the respective method is performed. Therefore, the digital storage medium may be computer readable. Some embodiments according to the invention comprise a data carrier having electronically readable control signals, which are capable of cooperating with a programmable computer system, such that one of the methods described herein is performed.

[0264] Generally, embodiments of the present invention may be implemented as a computer program product with a program code, the program code being operative for performing one of the methods when the computer program product runs on a computer. The program code may for example be stored on a machine readable carrier.

[0265] Other embodiments comprise the computer program for performing one of the methods described herein, stored on a machine readable carrier. In other words, an embodiment of the inventive method is, therefore, a computer program having a program code for performing one of the methods described herein, when the computer program runs on a computer.

[0266] A further embodiment of the inventive methods is, therefore, a data carrier or a digital storage medium, or a computer-readable medium comprising, recorded thereon, the computer program for performing one of the methods described herein. A further embodiment of the inventive method is, therefore, a data stream or a sequence of signals representing the computer program for performing one of the methods described herein. The data stream or the sequence of signals may for example be configured to be transferred via a data communication connection, for example via the Internet. A further embodiment comprises a processing means, for example a computer, or a programmable logic device, configured to or adapted to perform one of the methods described herein. A further embodiment comprises a computer having installed thereon the computer program for performing one of the methods described herein.

[0267] In some embodiments, a programmable logic device, for example a field programmable gate array, may be used to perform some or all of the functionalities of the methods described herein. In some embodiments, a field programmable gate array may cooperate with a microprocessor in order to perform one of the methods described herein. Generally, the methods are preferably performed by any hardware apparatus.

[0268] The above described embodiments are merely illustrative for the principles of the present invention. It is understood that modifications and variations of the arrangements and the details described herein are apparent to others skilled in the art. It is the intent, therefore, to be limited only by the scope of the impending patent claims and not by the specific details presented by way of description and explanation of the embodiments herein.

[0269] ABBREVIATIONS

[0270]

Claims

1. CLAIMS1. An apparatus of a wireless communication network, wherein the apparatus is configured for: obtaining information on one or more measurements and / or one or more measurement estimates, wherein the one or more measurements and / or the one or more measurement estimates depend on a radio condition between a user equipment and a second entity of the wireless communication network, wherein the second entity is a network entity or is a further user equipment of the wireless communication network, making one or more predictions for one or more future time instants and / or one or more different frequency layers, wherein the one or more predictions are one or more measurement predictions and / or one or more event predictions and / or one or more predictions of network configurations for one or more future time instants and / or for one or more different frequency layers, wherein making the one or more measurement predictions or event predictions is conducted depending on the information on the one or more measurements and / or one or more measurement estimates, providing, depending on the one or more predictions, at least one command and / or a configuration or a set of configurations for the user equipment to maintain a connectivity with the network.

2. An apparatus according to claim 1 , wherein the information on the one or more measurements and / or the one or more measurement estimates comprises information on one or more measurements or measurement estimates of the user equipment and / or information on one or more measurements or measurement estimates of the apparatus or of another network entity of the wireless communication system, wherein said other network entity is different from the user equipment and is different from the apparatus and is different from or equal to the second entity.

3. An apparatus according to claim 1 or 2,wherein the apparatus is configured to use the information on the one or more measurements and / or the one or more measurement estimates to train an Artificial Intelligence / Machine Learning model, wherein the apparatus is configured to make the one or more predictions depending on the Artificial Intelligence / Machine Learning model.

4. An apparatus according to claim 3, wherein the apparatus is configured to provide input data to the Artificial Intelligence / Machine Learning model, and, wherein the input data comprises information on at least one of the one or more measurements or measurement estimates from the user equipment and / or from the apparatus and / or from a network node, wherein the apparatus is configured to receive output data from the Artificial Intelligence / Machine Learning model, wherein the output data comprises the one or more predictions or comprises information for conducting the one or more predictions.

5. An apparatus according to claim 3 or 4, wherein the apparatus comprises the Artificial Intelligence / Machine Learning model.

6. An apparatus according to one of claims 3 to 5, wherein the apparatus is configured to request a measurement or measurement estimate on a measurement object from the user equipment, wherein the apparatus is configured to receive the measurement or measurement estimate from the user equipment, wherein the apparatus is configured to validate and / or provide information to a network entity to validate the Artificial Intelligence / Machine Learning model using the measurement or the measurement estimate.

7. An apparatus according to claim 6, wherein the apparatus is configured to request the user equipment to provide the measurement on the measurement object instead of providing a measurement estimate.

8. An apparatus according to claim 6, wherein the apparatus is configured to receive the measurement estimate from the user equipment, wherein the apparatus is configured to validate the Artificial Intelligence / Machine Learning model using the measurement estimate.

9. An apparatus according to one of claims 3 to 8, wherein, depending on at least one of the one or more measurements or measurement estimates and depending on at least one of the one or more measurement predictions or event predictions, the apparatus is configured to indicate to the user equipment to temporarily disable to provide the one or more measurements or measurement predictions.

10. An apparatus according to claim 9, wherein the apparatus is configured to indicate to the user equipment to temporarily disable to provide the one or more measurements or measurement predictions, if a difference between at least one of the one or more measurements or measurement estimates and at least one of the one or more measurement predictions is within a predefined interval.

11. An apparatus according to one of claims 3 to 10, wherein the apparatus is configured to indicate to the user equipment to temporarily disable a measurement gap configuration depending on at least one of the one ormore measurements or measurement estimates and depending on at least one of the one or more measurement predictions or event predictions.

12. An apparatus according to claim 11 , wherein the measurement gap configuration is provided by network layer signalling (e.g., RRC) so that the measurement gap is aligned between one or more network entities of the wireless communication network and the user equipment, and wherein an activation or deactivation of the measurement gap configuration is conducted by MAC-CE signaling or physical layer signalling (such as DCI or SCI), (e.g., so as to enable fast skipping or activation of gaps configured).

13. An apparatus according to one of claims 3 to 12, wherein the apparatus is configured to provide input data to the Artificial Intelligence / Machine Learning model comprising additional information in addition to the information on said at least one of the one or more measurements or measurement estimates.

14. An apparatus according to claim 13, wherein the additional information comprises statistics provided by network data analytics.

15. An apparatus according to claim 13 or 14, wherein the additional information comprises information about a location of the user equipment and / or of another user equipment and / or of a network node of the wireless communication network.

16. An apparatus according to claim 15, wherein the location is a preconfigured location of the user equipment (e.g., a fixed user equipment) or of a fixed network node (e.g., BS), orwherein the location is a mobile location of a mobile user equipment, whose location is determined with GNSS and / or multi-RTT and / or DL-TDOA and / or DL-AoD and / or using multi-RTT with LEO satellites and / or UL-TDOA, or wherein the location is a location of a moving network node, such as a satellite (e.g., a LEO or a MEO or a GSO satellite) or, wherein the location is a location of a non-terrestrial network node or of a mobile IAB node.

17. An apparatus according to one of claims 3 to 16, wherein the output of the Artificial Intelligence / Machine Learning model comprises at least one of a RSRP, a RSRQ, a SINR, a network event (e.g., a radio link failure), a prediction of a configuration or a set of configuration of network nodes for handling connection to and / or from the user equipment.

18. An apparatus according to one of the preceding claims, wherein the apparatus is configured to provide the information on the one or more measurements and / or the one or more measurement estimates to a network entity of the wireless communication network (e.g., a NWDAF or, e.g., an O&M entity), wherein said network entity is different from the apparatus, and wherein the apparatus is configured to receive from said network entity one or more measurements and / or one or more predicted events.

19. An apparatus according to one of the preceding claims, wherein the apparatus is configured to receive statistics or analytics from a network entity of the wireless communication network (e.g., a NWDAF or, e.g., an O&M entity), wherein said network entity is different from the apparatus, wherein the apparatus is configured to transmit the statistics or the analytics to the user equipment, or wherein, depending on the statistics or the analytics, theapparatus is configured to generate and to transmit a configuration to the user equipment.

20. An apparatus according to one of the preceding claims, wherein the apparatus is configured to obtain information on the one or more measurement estimates from the user equipment, wherein the one or more measurement estimates are provided by an Artificial Intelligence / Machine Learning model of the user equipment.

21. An apparatus according to one of the preceding claims, wherein the one or more measurements or measurement estimates comprise one or more of the following: one or more measurements or measurement estimates on a radio condition between the user equipment and the network entity, one or more measurements or measurement estimates on a radio condition between the user equipment and another network entity, one or more measurements or measurement estimates on a radio condition between another user equipment and the network entity, one or more measurements or measurement estimates on a radio condition between another user equipment and another network entity, one or more measurements or measurement estimates on a radio condition between the user equipment and another user equipment, one or more measurements or measurement estimates on a radio condition between the network entity and another network entity.

22. An apparatus according to one of the preceding claims,wherein at least one of the one or more measurements or measurement estimates is a measurement or measurement estimate for a first frequency layer or for a first carrier frequency, and wherein at least one of the one or more measurement predictions or or more event predictions is a measurement prediction or an event prediction for said first frequency layer or for said first carrier frequency.

23. An apparatus according to one of the preceding claims, wherein at least one of the one or more measurements or measurement estimates is a measurement or measurement estimate for a first frequency layer or for a first carrier frequency, and wherein at least one of the one or more measurement predictions and / or of the one or more event predictions is a measurement prediction or an event prediction for a second frequency layer being different from the first frequency layer, or for a second carrier frequency being different from the first carrier frequency.

24. An apparatus according to claim 23, wherein the measurement or measurement estimate for the first frequency layer or for the first carrier frequency is a measurement made on a terrestrial TRP, and wherein the measurement prediction or the event prediction for the second frequency layer or for the second carrier frequency is a measurement prediction or an event prediction for a non-terrestrial TRP (e.g., for an NTN satellite).

25. An apparatus according to one of the preceding claims, wherein at least one of the one or more measurements or measurement estimates is a measurement or measurement estimate for a first signal, and wherein at least one of the one or more measurement predictions or event predictions is a measurement prediction or an event prediction for a second signal being collocated with the first signal.

26. An apparatus according to one of the preceding claims, wherein at least one of the one or more measurements or measurement estimates comprises a measurement or a measurement estimate on an uplink reference signal.

27. An apparatus according to claim 26, wherein the uplink reference signal is an SRS or a PRACH or a DMRS or an UL- PTRS.

28. An apparatus according to one of the preceding claims, wherein the apparatus is configured to make a prediction of one or more channel parameters for a channel between the user equipment and the second entity as the one or more measurement predictions or event predictions for one or more future time instants.

29. An apparatus according to one of the preceding claims, wherein the one or more predictions comprise one or more of the following: a spatial prediction of a beam measurements, a temporal prediction of a beam measurement, a spatial and temporal prediction of a beam measurement, an inter-frequency prediction of a beam measurement, one or more cell-measurements beams of TRPs and / or group of TRPs, a dwell time in target cell,an anticipated RLF, an uplink synchronization, such as timing advance in the new cell, a carrier frequency offset, a transmit power, a pathloss reference, a UE-beam, a carrier frequency offset, a time difference between a propagation path between a user equipment and at least two network nodes (e.g., between a user equipment and two NTN nodes, or, e.g., between a user equipment and an NTN node and a terrestrial node, or, e.g., between two terrestrial nodes), a configuration of parameters to be applied by a user equipment, when handover occurs (e.g. TA values, CA parameters, such as primary cell and secondary cell configurations, etc), a configuration of parameters to be applied by a user equipment, when a conditional handover occurs (e.g., TA values, CA parameters, such as primary cell and secondary cell configurations, etc).

30. An apparatus according to one of the preceding claims, wherein the apparatus is configured to provide at least one of one or more measurement predictions to the user equipment, wherein the apparatus is configured to receive information on a difference between said at least one of the one or more measurement predictions and at least one actual measurement from the user equipment.

31. An apparatus according to one of the preceding claims, wherein the apparatus is configured to fine-tune or to calibrate or to switch an Artificial Intelligence / Machine Learning model depending on the one or more measurements or measurement estimates.

32. An apparatus according to one of the preceding claims, wherein the apparatus is configured to generate or update a configuration of an uplink reference signal and / or a sidelink reference signal as the configuration for the user equipment depending on the one or more measurement predictions or event predictions, and is configured to provide the configuration to the user equipment.

33. An apparatus according to one of the preceding claims, wherein the apparatus is configured to initiate a handover of the user equipment from one cell to another cell of the wireless communication network depending on the one or more measurement predictions or event predictions.

34. An apparatus according to one of the preceding claims, wherein, to obtain the one or more measurements, the apparatus is configured to request one or more measurements from a TRP of the wireless communication network, and wherein the apparatus is configured to receive the one or more measurements from the TRP.

35. An apparatus according to one of the preceding claims, wherein the appatus is a network entity of the wireless communication network being different from the user equipment.

36. An apparatus according to one of claims 1 to 34, wherein the apparatus is the user equipment, or is the further user equipment, or is another user equipment being different from the user equipment and being different from the further user equipment.

37. An apparatus according to one of the preceding claims, wherein the one or more measurements comprise one or more of the following: one or more measurements on signal power and / or signal quality and / or timing per SS / PBCH block, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least two SS / PBCH blocks; one or more measurements on signal power and / or signal quality and / or timing per cell based on SS / PBCH block(s), one or more measurements on signal power and / or signal quality and / or timing or timing diffrences between two cells based on SS / PBCH block(s), one or more measurements to detect SS / PBCH block(s) indexes and / or measured above a threshold, one or more measurements on signal power and / or signal quality and / or timing per CSI-RS resource, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least CSI-RS resource and a SS / PBCH block, at least two CSI-RS resources or a combination, one or more measurements on signal power and / or signal quality and / or timing per cell between at least CSI-RS resource and a SS / PBCH block, at least two CSI-RS resources or a combination, one or more measurements measuring CSI-RS resource measurement identifiers, one or more measurements on signal power and / or signal quality and / or timing, or timing differences above further consolidated using certain filtering or averaging,one or more measurements on signal power and / or signal quality and / or timing, or timing differences above further consolidated or predicted using certain AI / ML algorithms, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least DL-PRS resource and a SS / PBCH block, at least two DL-PRS resrouces or a combination, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least two LIL-SRS resources, one or more measurements on phase or phase differences between at least two signals.

38. An apparatus according to one of the preceding claims, wherein the one or more measurements comprise one or more measurements on a frequency layer or different frequency layers or different network layers (e.g. terrestrial and non-terrestrial).

39. An apparatus according to one of the preceding claims, wherein the apparatus is configured to make said one or more predictions of network configurations, which relate to the network settings to be used by the network and / or by the user equipment, wherein the one or more predictions of network configurations indicate a likely candidate where a handover may be carried out, so that packets from a user plane may be pre-buffered at a new network node in anticipation that the handover will happen and the data can be transferred with lower latency, since the new network node does not need to wait for the old network node to forward its buffer.

40. An apparatus according to one of the preceding claims, wherein the apparatus is configured to make said one or more predictions of network configurations to be used by the user equipment, wherein the one or more predictions of network configurations indicate a set of parameters to be used by theuser equipment, for example, TA, primary and secondary cells, multi-TRP configurations, TAG group, QCL information, initial BWP, BWPs, etc.

41. An apparatus according to one of the preceding claims, wherein the apparatus is configured to provide the at least one command for the user equipment, such that the at least one command comprises a handover command instructing the user equipment to initiate connection at a target cell, or a redirection command where the network instructs the UE to move to RRC DLE and initiate connection in target cell or frequency, or L1 / L2 initiated mobility, wherein the connection is changed based on preconfigured parameters based on MAC-CE or DCI trigger.

42. An apparatus according to one of the preceding claims, wherein the apparatus is configured to provide the at least one command for the user equipment, wherein the command is carried by an RRC signaling or an LPP signaling or a NAS signaling or a MAC-CE signaling or a DCI signaling.

43. An apparatus according to claim 42, wherein the command instructs the user equipment to conduct one or more of the following: modifying at least one measurement gap parameters, including gap-offset indicating the time location of the start of the measurement gap with respect to a certain frame, slot or symbol boundary and / or periodicity, instructing at least one measurement and / or measurement within at least one measurement gap to be either skipped or performed by the UE, based on measurement or measurement gap configured to the UE by earlier signalling (e.g. RRC), indicating the UE to adjust at least one parameter of the measurement configuration provided to the UE, in response to a status report or indication provided by the UE (e.g. battery power, buffer status report, power headroom report),indicating the UE to transmit at least one reference signal according to a configurationor a set of configurations provided to the UE (e.g. via preconfiguration, system information, RRC configuration), in response to a status report or indication provided by the UE (e.g. battery power, buffer status report, power headroom report) or capability or UE assistance information (UAI), sending information regarding the battery status of the UE, wherein the battery status may indicate the remaining battery power, the projected battery life, indication regarding remaining battery power remaining at a certain reference time (for example, the time when the battery would typically be connected to charging point) or reference times (last charge, next anticipated charge, etc), indication regarding change in remaining battery power, sending an indication to the network if the remaining battery power or projected battery power or remaining battery time or remaining projected battery power or remaining projected battery power subject to reduced or increased operation (e.g. measurements) falls below respective threshold value(s), performing at least one operation, such as adjusting measurement and / or measurement reporting parameters, indicating the NW its reduced capability to do certain operation (e.g. inter-frequency measurements / predictions) or start / stop transmission of certain reference signals (e.g. UL-SRS, positioning reference signals, scheduling request) in response to change in battery status (e.g. remaining battery power or projected battery power or remaining battery time or remaining projected battery power or remaining projected battery power), providing at least one information, describing the UE configuration or parameters, such as UE beams, UE orientation, Antenna orientation and / or location, UE dimensions etc, providing information pertaining to location (e.g. LCS or cell-ID) and / or motion of the UE (e.g. motion state, measurements from motion sensor), indicating the UE to transmit its measurement estimate, immediately, at a future time instant, on over an interval,indicating the UE to transmit its event prediction within a certain time interval (e.g. RLF within a certain window), wherein the interval may be configured to the UE by earlier configuration (e.g. RRC_configuration or indicated dynamically (e.g. using MAC-CE signalling or DCI signalling), indicating the configuration of the interval where the UE is expected to perform measurements (e.g., measurement window) and / or the interval where the UE is expected to perform predictions (e.g., prediction window), wherein the measurement window and prediction window may be adjacent to each other or may be separated by configured gap, alternatively the two windows may be signalled to the UE, wherein in some examples, the windows may be fixed and alternating and in other examples, the windows may be configured as sliding windows, filtering coefficient for averaging raw measurement or L1 predicted measurements and / or indication to AI / ML model (e.g. using identifier signalled to the NW by the UE or from the UE to the NW) to use for prediction, indication of QCL information to the UE informing the UE whether two signals are similar in terms of at least one of the following parameters: Doppler spread, average delay, delay spread, spatial Rx parameter, wherein the at least two signals may be SSB on FR1 and SSB on FR2, SSB on FR1 and CSI-RS on FR1 , DL-PRS on FR1 and SSB on FR2, SSB on FR2 and DL-PRS on FR1 , or any combination of DL signal on first band with any combination of DL signal on the second band.

44. An apparatus according to claim 43, wherein the measurement window is implementation-dependent and / or wherein only a prediction window is signalled to the user equipment.

45. An apparatus according to one of the preceding claims, wherein the apparatus is configured to provide the configuration or the set of configurations for the user equipment, such that the configuration or the set of configurations comprising a conditional handover, where the handover is performed where where the condition associated with the configuration are fulfilled, or comprising a configuration of a connection after performing the handover oradjustment of at least one connection parameter (such as a group of serving cells, timing adjustments, configuration for enabling swift connection restore, such as contention free-handover setting, etc), configuration for positioning of a user equipment, configuration of sidelink communication, configuration of IAB node, etc.

46. A user equipment of a wireless communication network, wherein the user equipment is configured for obtaining and processing at least one command and / or a configuration to maintain a connectivity with the network, wherein the at least one command and / or the at least one configuration depends on one or more measurement predictions or event predictions.

47. A user equipment according to claim 46, wherein the at least one command and / or the at least one configuration depends on the one or more measurement predictions or event predictions, which depend on information on the one or more measurements or on information on one or more measurement estimates, wherein the one or more measurements or the one or more measurement estimates depend on a radio condition between the user equipment and a network entity of the wireless communication network.

48. A user equipment according to claim 46 or 47, wherein the user equipment is configured to conduct one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network, wherein the one or more measurement predictions or event predictions depend on information on the one or more measurements.

49. A user equipment according to one of claims 46 to 48, wherein the user equipment is configured to receive information on one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network,wherein the one or more measurement predictions or event predictions depend on the information on the one or more measurements.

50. A user equipment according to claim 49, wherein the user equipment is configured to receive the information on the one or more measurements from said network entity; or wherein the user equipment is configured to receive the information on the one or more measurements from another network entity of the wireless communication system.

51. A user equipment according to claim 49, wherein the user equipment is configured to receive the information on the one or more measurements from another user equipment of the wireless communication system.

52. A user equipment according to one of claims 48 to 51 , wherein the user equipment is configured to transmit the information on the one or more measurements to a network entity of the wireless communication network, wherein the user equipment is configured to receive the at least one command and / or the configuration, which depends on the information on the one or more measurements transmitted to the network entity.

53. A user equipment according to one of claims 48 to 52, wherein the user equipment is configured to determine one or more measurement estimates depending on the information on the one or more measurements, and wherein the user equipment is configured to transmit the information on the one or more measurement estimates to a network entity of the wireless communication network,wherein the user equipment is configured to receive the at least one command and / or the configuration, which depends on the information on the one or more measurement estimates.

54. A user equipment according to claim 53, wherein the user equipment comprises an Artificial Intelligence / Machine Learning model, wherein the user equipment is configured to conduct the one or more measurement estimates using the Artificial Intelligence / Machine Learning model, wherein the user equipment is configured to transmit information on the one or more measurement estimates to the network entity or to another network entity of the wireless communications network.

55. A user equipment of a wireless communication network, wherein the user equipment comprises an Artificial Intelligence / Machine Learning model, wherein the user equipment is configured to conduct one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network, wherein the Artificial Intelligence / Machine Learning model is configured to conduct one or more measurement estimates, which depend on the radio condition between the user equipment and said network entity of the wireless communication network, wherein the user equipment is configured to transmit information on the one or more measurement estimates to the network entity or to a second user equipment or to another network entity of the wireless communications network.

56. A user equipment according to claim 54 or 55, wherein the user equipment is configured to receive a request for a measurement or a measurement estimate on a measurement object from an entity of the wireless communication network,wherein the user equipment is configured to conduct a measurement estimate using the Artificial Intelligence / Machine Learning model using the measurement or the measurement estimate, and wherein the user equipment is configured to transmit information on the measurement estimate to said entity of the wireless communication network.

57. A user equipment according to claim 56, wherein the user equipment is configured to receive a request to provide a measurement on the measurement object instead of providing a measurement estimate, wherein, on receiving the request, the user equipment is configured to conduct the measurement on the measurement object.

58. A user equipment according to one of claims 54 to 57, wherein the user equipment is configured to receive an indication to temporarily disable to provide the one or more measurements or measurement predictions, wherein, in response to the indication, the user equipment is configured to not transmit any measurement or measurement prediction for a predetermined time period.

59. A user equipment according to claim 58, wherein the user equipment is configured to receive an indication to temporarily disable to provide the one or more measurements or measurement predictions, if a difference between at least one of the one or more measurements or measurement estimates and at least one of one or more measurement predictions of said network entity or of said other network entity is within a predefined interval.

60. A user equipment according to one of claims 54 to 59,wherein the user equipment is configured to receive an indication to temporarily disable a measurement gap configuration depending on at least one of the one or more measurements or measurement estimates and depending on at least one of one or more measurement predictions or event predictions of said network entity or of said other network entity, wherein the user equipment is configured to temporarily disable the measurement gap configuration in response to receiving the indication.

61. A user equipment according to one of claims 54 to 60, wherein the user equipment is configured to provide input data to the Artificial Intelligence / Machine Learning model comprising information on one or more measurements or measurement estimates, which depend on the radio condition between the user equipment and a network entity of the wireless communication network.

62. A user equipment according to claim 61 , wherein the user equipment is configured to provide the input data to the Artificial Intelligence / Machine Learning model, which further comprises additional information in addition to the information on said at least one of the one or more measurements or measurement estimates.

63. A user equipment according to claim 62, wherein the additional information comprises statistics provided by network data analytics.

64. A user equipment according to one of claims 54 to 63, wherein the one or more measurements or measurement estimates comprise one or more of the following: one or more measurements or measurement estimates on a radio condition between the user equipment and the network entity,one or more measurements or measurement estimates on a radio condition between the user equipment and another network entity, one or more measurements or measurement estimates on a radio condition between another user equipment and the network entity, one or more measurements or measurement estimates on a radio condition between another user equipment and another network entity, one or more measurements or measurement estimates on a radio condition between the user equipment and another user equipment, one or more measurements or measurement estimates on a radio condition between the network entity and another network entity.

65. A user equipment according to one of claims 54 to 64, wherein the user equipment is configured to conduct the one or more measurement estimates depending on the one or more measurements.

66. A user equipment according to claim 65, wherein the user equipment is configured to employ one or more of the one or more measurements to train the Artificial Intelligence / Machine Learning model.

67. A user equipment according to claim 66, wherein the user equipment is configured to feed at least one of the one or more measurements as input data into the Artificial Intelligence / Machine Learning model.

68. A user equipment according to claim 66 or 67, wherein the user equipment is configured to receive the Artificial Intelligence / Machine Learning model from a network entity or from an OTT server of the wireless communication network, andwherein the user equipment is configured to refine and / or update the Artificial Intelligence / Machine Learning model by training the Artificial Intelligence / Machine Learning model using the at least one of the one or more measurements.

69. A user equipment according to one of claims 66 to 68, wherein at least one of the one or more measurements is a measurement for a first frequency layer or for a first carrier frequency, and wherein at least one of the one or more measurement estimates is a measurement for said first frequency layer or for said first carrier frequency.

70. A user equipment according to one of claims 66 to 69, wherein at least one of the one or more measurements is a measurement for a first frequency layer or for a first carrier frequency, and wherein at least one of the one or more measurement estimnates is a measurement estimate for a second frequency layer being different from the first frequency layer, or for a second carrier frequency being different from the first carrier frequency.

71. A user equipment according to one of claims 66 to 70, wherein at least one of the one or more measurements is a measurement for a first signal, and wherein at least one of the one or more measurement estimates is a measurement estimate for a second signal being collocated with the first signal.

72. A user equipment according to one of claims 46 to 71 , wherein at least one of the one or more measurements or measurement estimates comprises a measurement or a measurement estimate on an uplink reference signal.

73. A user equipment according to claim 72, wherein the uplink reference signal is an SRS or a PRACH or a DMRS or an UL- PTRS or a signal based on an orthogonal sequence (e.g., a Zadoff-Chu sequence or a Gold code sequence) transmitted by the user equipment or by another user equipment of the wireless communication network.

74. A user equipment according to one of claims 46 to 73, wherein the user equipment is configured to conduct one or more measurement estimates of channel parameters for a channel between the user equipment and the network entity.

75. A user equipment according to one of claims 46 to 74, wherein the one or more measurement estimates comprise one or more of the following: a spatial prediction of a beam measurements, a temporal prediction of a beam measurement, a spatial and temporal prediction of a beam measurement, an inter-frequency prediction of a beam measurement, one or more cell-measurements beams of TRPs and / or group of TRPs, a dwell time in target cell, an anticipated RLF, an uplink synchronization, such as timing advance in the new cell, a carrier frequency offset,a transmit power, a pathloss reference, a UE-beam, a carrier frequency offset.

76. A user equipment according to one of claims 46 to 75, wherein the user equipment is configured to receive a configuration or an updated configuration for an uplink reference signal and / or for a sidelink reference signal depending on the information on the one or more measurements or measurement estimates transmitted.

77. A user equipment according to one of claims 46 to 76, wherein the user equipment is configured to take part in a handover of the user equipment from one cell to another cell of the wireless communication network depending on the information on the one or more measurements or measurement estimates transmitted.

78. A user equipment according to one of claims 46 to 77, wherein the user equipment is configured to decide whether to conduct a measurement or whether to conduct a measurement estimate.

79. A user equipment according to one of claims 46 to 78, wherein the user equipment is configured to decide whether to conduct a measurement or whether to conduct a measurement estimate depending on a state of a battery power of a battery of the user equipment.

80. A user equipment according to one of claims 46 to 79,wherein the user equipment is configured to decide whether to conduct a measurement or whether to conduct a measurement estimate depending on a processing load and / or depending on a buffer state, (e.g. buffer size at the user equipment or network, or, e.g., a packet delay budget, or, e.g., an expiration deadline of packets in a buffer).

81. A user equipment according to one of claims 46 to 80, wherein the user equipment is configured to provide an indication to a network node of the wireless communication network that it has skipped a measurement and / or that it has skipped reporting a measurement.

82. A user equipment according to claim 81 , wherein the user equipment is configured to provide an indication to the network node indicating a cause why the user equipment skipped measurement and / or reporting (e.g., by providing a value).

83. A user equipment according to one of claims 46 to 82, wherein the one or more measurements comprise one or more of the following: one or more measurements on signal power and / or signal quality and / or timing per SS / PBCH block, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least two SS / PBCH blocks; one or more measurements on signal power and / or signal quality and / or timing per cell based on SS / PBCH block(s), one or more measurements on signal power and / or signal quality and / or timing or timing diffrences between two cells based on SS / PBCH block(s), one or more measurements to detect SS / PBCH block(s) indexes and / or measured above a threshold,one or more measurements on signal power and / or signal quality and / or timing per CSI-RS resource, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least CSI-RS resource and a SS / PBCH block, at least two CSI-RS resources or a combination, one or more measurements on signal power and / or signal quality and / or timing per cell between at least CSI-RS resource and a SS / PBCH block, at least two CSI-RS resources or a combination, one or more measurements measuring CSI-RS resource measurement identifiers, one or more measurements on signal power and / or signal quality and / or timing, or timing differences above further consolidated using certain filtering or averaging, one or more measurements on signal power and / or signal quality and / or timing, or timing differences above further consolidated or predicted using certain AI / ML algorithms, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least DL-PRS resource and a SS / PBCH block, at least two DL-PRS resrouces or a combination, one or more measurements on signal power and / or signal quality and / or timing or timing diffrence between at least two LIL-SRS resources, one or more measurements on phase or phase differences between at least two signals.

84. A user equipment according to one of claims 46 to 83, wherein the one or more measurements comprise one or more measurements on a frequency layer or different frequency layers or different network layers (e.g. terrestrial and non-terrestrial).

85. A user equipment according to one of claims 46 to 84, wherein the user equipment is configured to receive the at least one command for the user equipment, wherein the command is carried by an RRC signaling or an LPP signaling or a NAS signaling or a MAC-CE signaling or a DCI signaling.

86. A user equipment according to claim 85, wherein the MAC-CE received by the user equipment activates or deactivates a measurement prediction and / or reporting, if the user equipment has indicated that the user equipment has a model ready to perform measurement prediction using a RRC response to the network (e.g. UAI, RRC Reconfiguration Complete), and the user equipment has indicated the capability to perform AI / ML measurement prediction.

87. A user equipment according to claim 85 or 86, wherein the command instructs the user equipment to conduct one or more of the following: modifying at least one measurement gap parameters, including gap-offset indicating the time location of the start of the measurement gap with respect to a certain frame, slot or symbol boundary and / or periodicity, instructing at least one measurement and / or measurement within at least one measurement gap to be either skipped or performed by the UE, based on measurement or measurement gap configured to the UE by earlier signalling (e.g. RRC), indicating the UE to adjust at least one parameter of the measurement configuration provided to the UE, in response to a status report or indication provided by the UE (e.g. battery power, buffer status report, power headroom report), indicating the UE to transmit at least one reference signal according to a configurationor a set of configurations provided to the UE (e.g. via preconfiguration, system information, RRC configuration), in response to astatus report or indication provided by the UE (e.g. battery power, buffer status report, power headroom report) or capability or UE assistance information (UAI), sending information regarding the battery status of the UE, wherein the battery status may indicate low power, the remaining battery power, the projected battery life, indication regarding remaining battery power remaining at a certain reference time (for example, the time when the battery would typically be connected to charging point) or reference times (last charge, next anticipated charge, etc), indication regarding change in remaining battery power, sending an indication to the network if the remaining battery power or projected battery power or remaining battery time or remaining projected battery power or remaining projected battery power subject to reduced or increased operation (e.g. measurements) falls below respective threshold value(s), performing at least one operation, such as adjusting measurement and / or measurement reporting parameters, indicating the NW its reduced capability to do certain operation (e.g. inter-frequency measurements / predictions) or start / stop transmission of certain reference signals (e.g. UL-SRS, positioning reference signals, scheduling request) in response to change in battery status (e.g. remaining battery power or projected battery power or remaining battery time or remaining projected battery power or remaining projected battery power), providing at least one information, describing the UE configuration or parameters, such as UE beams, UE orientation, Antenna orientation and / or location, UE dimensions etc, providing information pertaining to location (e.g. LCS or cell-ID) and / or motion of the UE (e.g. motion state, measurements from motion sensor), indicating the UE to transmit its measurement estimate, immediately, at a future time instant, on over an interval, indicating the UE to transmit its event prediction within a certain time interval (e.g. RLF within a certain window), wherein the interval may be configured to the UE by earlier configuration (e.g. RRC_configuration or indicated dynamically (e.g. using MAC-CE signalling or DCI signalling),indicating the configuration of the interval where the UE is expected to perform measurements (e.g., measurement window) and / or the interval where the UE is expected to perform predictions (e.g., prediction window), wherein the measurement window and prediction window may be adjacent to each other or may be separated by configured gap, alternatively the two windows may be signalled to the UE, wherein in some examples, the windows may be fixed and alternating and in other examples, the windows may be configured as sliding windows, filtering coefficient for averaging raw measurement or L1 predicted measurements and / or indication to AI / ML model (e.g. using identifier signalled to the NW by the UE or from the UE to the NW) to use for prediction, indication of QCL information to the UE informing the UE whether two signals are similar in terms of at least one of the following parameters: Doppler spread, average delay, delay spread, spatial Rx parameter, wherein the at least two signals may be SSB on FR1 and SSB on FR2, SSB on FR1 and CSI-RS on FR1 , DL-PRS on FR1 and SSB on FR2, SSB on FR2 and DL-PRS on FR1, or any combination of DL signal on first band with any combination of DL signal on the second band.

88. A user equipment according to claim 87, wherein the measurement window is implementation-dependent and / or wherein only a prediction window is signalled to the user equipment.

89. A system comprising, an apparatus according to one of claims 1 to 45, and a user equipment according to one of claims 46 to 88.

90. A method for a wireless communication network, wherein the method comprises: obtaining, by an apparatus of the wireless communication network, information on one or more measurements and / or one or more measurement estimates, wherein the one or more measurements and / or the one or more measurement estimatesdepend on a radio condition between a user equipment and a second entity of the wireless communication network, wherein the second entity is a network entity or is a further user equipment of the wireless communication network, making, by the apparatus, one or more predictions for one or more future time instants and / or one or more different frequency layers, wherein the one or more predictions are one or more measurement predictions and / or one or more event predictions and / or one or more predictions of network configurations for one or more future time instants and / or for one or more different frequency layers, wherein making the one or more measurement predictions or event predictions is conducted depending on the information on the one or more measurements and / or one or more measurement estimates, providing, by the apparatus, depending on the one or more predictions, at least one command and / or a configuration or a set of configurations for the user equipment to maintain a connectivity with the network.91 . A method for a wireless communication network, wherein the method comprises: obtaining and processing, by a user equipment of the wireless communication system, at least one command and / or a configuration to maintain a connectivity with the network, wherein the at least one command and / or the at least one configuration depends on one or more measurement predictions or event predictions.

92. A method for a wireless communication network, wherein the method comprises: conducting, by a user equipment of the wireless communication network, one or more measurements, which depend on a radio condition between the user equipment and a network entity of the wireless communication network, conducting, by an Artificial Intelligence / Machine Learning model of the user equipment, one or more measurement estimates, which depend on the radio condition between the user equipment and said network entity of the wireless communication network, andtransmitting, by the user equipment, information on the one or more measurement estimates to the network entity or to a second user equipment or to another network entity of the wireless communications network.

93. A computer program for implementing the method according to one of claims 90 to92, when the computer program is executed by a computer or signal processor.

Images