Methods and apparatus for Artificial Intelligence / Machine Learning (AI / ML)-based solutions for mobility enhancements

Abstract

A method for Artificial-Intelligence / Machine-Learning (AI / ML)-based ephemeris data enhancement in a wireless communication system comprising: receiving ephemeris data; identifying inaccurate or incomplete data within the received ephemeris data; generating, using an AI / ML model / function, enhanced ephemeris data; and distributing the enhanced data to network entities / functions within the wireless communication system. The ephemeris data can be for positioning functions, navigation functions, timing functions, and radio access network (RAN) procedures. The data may include information on the position and / or trajectory of Non-Terrestrial Network (NTN) nodes or GNSS nodes and may be received from user equipment (UE), NTN nodes, and GNSS nodes. The enhanced ephemeris data can be assigned time stamps, dates, and unique identifiers and may be distributed to UE, NTN nodes, gNB, and core network entities / functions of the wireless communication system via the NTN or the gNB. The core network entity / function of the wireless communication system may include location-management-functions (LMF), Layer1 / Layer / Lower layer triggered mobility (LTM), life-cycle-management (LCM), conditional-handover (CHO), network-data-analytics-functions (NWDAF). Training the ephemeris AI / ML model / function may be based on previously received ephemeris data, on previous uplink and / or downlink measurements at UEs and RAN nodes, or on core network data associated with the RAN.

Description

BACKGROUND Field

[0001] Certain examples of the present disclosure relate to methods, apparatus and / or systems for providing enhanced ephemeris data via the use of an AI / ML model / functionality. In particular, enhanced ephemeris data generated via the use of an AI / ML model may used to provide enhanced mobility functionality in a wireless communication system. Description of Related Art

[0002] The content of the following documents is referred to below and / or their content provides background information that the following disclosure should be considered in the context of: [1] "Guidelines for Extraterritorial 5G Systems, Stage 1, Release 18," 3GPP TR 22.926 V18.0.0 (2021-12), 2021. [2] X. Guo, L. Wang, W. Fu, Y. Suo, R. Chen and H. Sun, "An optimal design of the broadcast ephemeris for LEO navigation augmentation systems," Geo-Spatial Information Science, pp. 34--46, 2022. [3] "Solutions for NR to support NTN," 3GPP TR38.821 V16.2.0 (2023-03), 2023. [4] "NR; NR and NG-RAN Overall Description," TS 38.300 v17.5.0 (2023-06), 2023. [5] 3GPP, “Study on Artificial Intelligence (Al) / Machine Learning (ML) for mobility in NR”, RP-234055 Note: the indicated version numbers are provided for illustrative purposes, other (including future) versions of these documents are considered also.

[0003] Wireless or mobile (cellular) communications networks in which a mobile terminal (e.g., user equipment (UE), such as a mobile handset) communicates via a radio link with a network of base stations, or other wireless access points or nodes, have undergone rapid development through a number of generations. The 3rd Generation Partnership Project (3GPP) design, specify and standardise technologies for mobile wireless communication networks. Fourth (4th) Generation (4G) and Fifth Generation (5G) systems (5GS) are now widely deployed, while beyond 5G (B5G) and 6G systems are being considered.

[0004] 3GPP standards for 4G systems include an Evolved Packet Core (EPC) and an Enhanced-UTRAN (E-UTRAN: an Enhanced Universal Terrestrial Radio Access Network). The E-UTRAN uses Long Term Evolution (LTE) radio technology. LTE is commonly used to refer to the whole system including both the EPC and the E-UTRAN, and LTE is used in this sense in the remainder of this document. LTE should also be taken to include LTE enhancements such as LTE Advanced and LTE Pro, which offer enhanced data rates compared to LTE.

[0005] In 5G systems a new air interface has been developed, which may be referred to as 5G New Radio (5G NR) or simply NR. NR is designed to support the wide variety of services and use case scenarios envisaged for 5G networks, though builds upon established LTE technologies. B5G systems, such as 6G, are currently being considered and developed, and are expected to at least partly build on 5G systems.

[0006] New frameworks and architectures are being developed as part of 5G network (and beyond, such as 6G networks) in order to increase the range of functionality and use cases available through 5G networks.

[0007] One of the areas currently under development in 3GPP 5G wireless technology is support for Non-Terrestrial Networks (NTNs). An NTN is a network in which one or more nodes (e.g. a Next Generation (NG) Radio Access Network (RAN) node) are provided by a non-terrestrial infrastructure, for example a satellite or High Altitude Platform Station (HAPS). Advantages of using an NTN include (i) extending coverage to regions, such as remote areas, with limited or no coverage from more traditional terrestrial networks, (ii) providing continuous coverage in the event of inoperability of traditional terrestrial networks, such as during natural disasters, and (iii) enhancing overall reliability, resilience and capacity when used in conjunction with existing terrestrial networks.

[0008] A satellite network implementing a network node provides coverage through one or more radio beams forming a “footprint” on the surface of the Earth defining a coverage area or cell. An NTN cell may be Earth-moving (i.e. moving over the Earth’s surface according to the motion of the satellite, for example in the case of a Lower Earth Orbit (LEO) satellite), Earth-fixed (i.e. a fixed area of the Earth’s surface, for example in the case of a Geosynchronous Equatorial Orbit (GEO) satellite) or quasi-Earth-fixed (i.e. a fixed area of the Earth’s surface but is maintained for only a limited time as the satellite passes by).

[0009] Information on one or more NTN nodes (e.g. satellites) such as timing information, position information, trajectory information may be included in ephemeris (i.e. ephemeris data / information) that is broadcast by NTN nodes or provided via alternative communication paths so that a UE and or RAN entity can obtain such information. The ephemeris may be included in a system information broadcast by an NTN node for example. UEs and / or RAN entities may then utilise the ephemeris for purposes such as mobility (e.g. handover) or any other functionality requiring positioning, navigation or timing information for example.

[0010] 3GPP has also been standardizing mechanisms for mobility optimization e.g. handover (basic conditional and RACHIess) which work well in normal radio condition. However these mechanisms, being reactive by design, are not robust in certain environments e.g., in dense deployments and high mobility. For example, handover decisions are made based on historical measurements and the User Equipment (UE) location which are sometimes inaccurate and may lead to handover / radio link failure, causing an interruption in connectivity. In addition, there is high complexity, measurement effort and signalling overhead to react to fluctuating radio conditions. Thus, there is a need for mobility enhancements to improve handover performance, reduce signalling overhead, UE power consumption and connectivity interruption. These limitations can be addressed through the use of AI / ML to predict when and where fluctuations in the network will occur and preconfigure for example the target cells (cell reselection) and / or tune parameters to enable successful handovers and gain robustness in any radio environment.

[0011] This topic is identified as a study item for discussions under Rel-19 items in 3GPP RAN2 working group. RAN#102 (December 11-15, 2023) [RP-234055] Study on Al (Artificial lntelligence) / ML (Machine Learning) for mobility in NR In this study, RAN2 will consider mobility enhancement in ITRC G mode based on current mobility framework, i.e. the network decides the UE handover. The following are the objectives listed in [RP-234055]: Study and evaluate potential benefits and gains of AI / ML aided mobility for network triggered L3-based handover, considering the following aspects: • AI / ML based RRM measurement and event prediction, o Cell-level measurement prediction including intra and inter-frequency (UE sided and NW sided, model) [RAN2] ■ Inter-cell Beam-level measurement prediction for L3 Mobility (UE sided and NW sided model) [RAN2] o HO failure / RLF prediction (UE sided model) [RAN2] o Measurement events prediction (UE sided model) [RAN2] • Study the need / benefits of any other UE assistance information for the network side model [RAN2] • The evaluation of the AI / ML aided mobility benefits should consider HO performance 'KPIs (e.g., Ping-pong HO, HOF / RLF, Time of stay, Handover interruption, prediction accuracy, and measurement reduction) etc.) and complexity tradeoffs [RAN2] o NOTE: Simulation assumption and methodology can leverage TR 38.901, 38.843 and 36.839. And leave the detail discussion to RAN2 • Potential AI mobility specific enhancement should be based on the Rell9 AI / ML-air in terface WID general framework (e.g. LCM, performance monitoring etc) [RAN2] o NOTE: This would only be treated after sufficient progress is made in the Rel-19 AI / ML air interface WID • Potential specification impacts of AI / ML aided mobility [RAN2] • Evaluate testability, interoperability, and impacts on RRM requirements and performance [RAN4] • NOTE 1: RAN1 / 3 work can be triggered via LS • NOTE 2: RAN4 scope / work can be defined and confirmed by RAN#105 after some RAN2 discussions (within the RAN4 pre-allocated TUs) NOTE 3: To avoid duplicate study with "AI / MLfor NG-RAN" led by RAN3 NOTE 4: Two-sided model is not included

[0012] Ephemeris contains information about the satellites orbital trajectories that are important for both satellite navigation systems and communication systems including Terrestrial Networks (TN) / Non-Terrestrial Networks (NTN). However, the ephemeris data may be missing and / or inaccurate. This may impact performance of several RAN functions, procedures and any related UE measurements. Hence, without a solution to adjust to the inevitable changes in ephemeris (e.g., when a satellite arrives early / late), it would take additional resources to manage the trajectory of the satellite, handover and cell reselection in TN / NTN configurations.

[0013] However, in the ongoing 3GPP discussions on TN and NTN or NTN-NTN mobility, the ephemeris values are assumed to be fixed which present a limitation on the potential gains of NR-NTN networks. SUMMARY

[0014] It is an aim of certain examples of the present disclosure to address, solve and / or mitigate, at least partly, at least one of the problems and / or disadvantages associated with the related art, for example at least one of the problems and / or disadvantages described herein. It is an aim of certain examples of the present disclosure to provide at least one advantage over the related art, for example at least one of the advantages described herein.

[0015] In particular, this disclosure is related to AI / ML-based mobility enhancements in wireless networks. More specifically, AI / ML models / functions may be harnessed to enhance ephemeris. One example use case is the optimization of UE mobility in TN / NTN though adjustments (or correction) of inaccurate ephemeris information.

[0016] The present invention is defined in the independent claims. Advantageous features are defined in the dependent claims.

[0017] Other aspects, advantages, and salient features of the disclosure will become apparent to those skilled in the art from the following detailed description taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Embodiments / examples of the present disclosure are further described hereinafter with reference to the accompanying drawings, in which: Figure 1 provides an example wireless communication system including a terrestrial network (TN) and a non-terrestrial network (NTN) in accordance with the present disclosure, where an AI / ML model / function for ephemeris enhancement is located in the radio access network (RAN); Figure 2 provides an example scenario where a user equipment (UE) is in communication with NTNs and an AI / ML model / function located in the RAN provides enhanced ephemeris; Figure 3 provides an example scenario where a user equipment (UE) is in communication with a TN and a NTNs, and an AI / ML model / function located in the RAN provides enhanced ephemeris; and Figure 4 is a block diagram illustrating an example structure of a network entity in accordance with certain examples of the present disclosure. DETAILED DESCRIPTION

[0019] Ths following dsscription of sxamplss of ths prsssnt disclosure, with rsfsrsncs to ths accompanying drawings, is provided to assist in a comprehensive understanding of certain examples of the present disclosure. The description includes various specific details to assist in that understanding but these are to be regarded as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the examples described herein can be made without departing from the scope of the invention or disclosure.

[0020] The same or similar components may be designated by the same or similar reference numerals, although they may be illustrated in different drawings.

[0021] Detailed descriptions of techniques, structures, constructions, functions or processes known in the art may be omitted for clarity and conciseness, and to avoid obscuring the subject matter of the present disclosure.

[0022] The terms and words used herein are not limited to the bibliographical or standard meanings, but are merely used to enable a clear and consistent understanding of the disclosure.

[0023] Throughout the description of this specification, the words “comprise”, “include” and “contain” and variations of the words, for example “comprising” and “comprises”, means “including but not limited to”, and is not intended to (and does not) exclude other features, elements, components, integers, steps, processes, operations, functions, characteristics, properties and / or groups thereof.

[0024] Throughout the description of this specification, the singular form, for example “a”, “an” and “the”, encompasses the plural unless the context otherwise requires. For example, reference to “an object” includes reference to one or more of such objects.

[0025] Throughout the description, the expression “at least one of A, B and / or C” (or the like), the expression “and / or”, and the expression “one or more of A, B and / or C” (or the like) should be seen to separately include all possible combinations, for example: A, B, C, A and B, A and C, A and B and C.

[0026] Throughout the description of this specification, language in the general form of “X for Y” (where Y is some action, process, operation, function, activity or step and X is some means for carrying out that action, process, operation, function, activity or step) encompasses means X adapted, configured or arranged specifically, but not necessarily exclusively, to do Y.

[0027] Features, elements, components, integers, steps, processes, operations, functions, characteristics, properties and / or groups thereof described or disclosed in conjunction with a particular aspect, embodiment or example are to be understood to be applicable to any other aspect, embodiment or example described herein unless incompatible therewith.

[0028] The following examples are applicable to, and use terminology associated with, 3GPP 4G and 5G. However, the skilled person will appreciate that the techniques disclosed herein are not limited to these examples or to 3GPP 4G or 5G, and may be applied in any suitable system or standard, for example one or more existing and / or future generation wireless communication systems or standards. The skilled person will appreciate that the techniques disclosed herein may be applied in any existing or future releases of 3GPP 4G or 5G NR or any other relevant standard. For example, the functionality of the various network entities and other features disclosed herein may be applied to corresponding or equivalent entities or features in other communication systems or standards. Corresponding or equivalent entities or features may be regarded as entities or features that perform the same or similar role, function, operation or purpose within the network. In particular, the following disclosure should be considered at least in relation to 6G also, which is expected to use at least part of the 5G architecture, or equivalent, and to which the present disclosure also relates.

[0029] A particular network entity may be implemented as a network element on a dedicated hardware, as a software instance running on a dedicated hardware, and / or as a virtualised function instantiated on an appropriate platform, e.g. on a cloud infrastructure.

[0030] The skilled person will appreciate that the present disclosure is not limited to the specific examples disclosed herein. For example: • The techniques disclosed herein are not limited to 3GPP 4G, 5G, B5G or 6G. • One or more entities in the examples disclosed herein may be replaced with one or more alternative entities performing equivalent or corresponding functions, processes or operations. • One or more of the messages in the examples disclosed herein may be replaced with one or more alternative messages, signals or other type of information carriers that communicate equivalent or corresponding information. • One or more further elements, entities and / or messages may be added to the examples disclosed herein. • One or more non-essential elements, entities and / or messages may be omitted in certain examples. • The functions, processes or operations of a particular entity in one example may be divided between two or more separate entities in an alternative example. • The functions, processes or operations of two or more separate entities in one example may be performed by a single entity in an alternative example. • Information carried by a particular message in one example may be carried by two or more separate messages in an alternative example. • Information carried by two or more separate messages in one example may be carried by a single message in an alternative example. • The order in which operations are performed may be modified, if possible, in alternative examples. • The transmission of information between network entities is not limited to the specific form, type and / or order of messages described in relation to the examples disclosed herein.

[0031] Certain examples of the present disclosure may be provided in the form of an apparatus / device / network entity configured to perform one or more defined network functions and / or a method therefor. Such an apparatus / device / network entity may comprise one or more elements, for example one or more of receivers, transmitters, transceivers, processors, controllers, modules, units, and the like, each element configured to perform one or more corresponding processes, operations and / or method steps for implementing the techniques described herein. For example, an operation / function of X may be performed by a module configured to perform X (or an X-module). Certain examples of the present disclosure may be provided in the form of a system (e.g., a network) comprising one or more such apparatuses / devices / network entities, and / or a method therefor.

[0032] It will be appreciated that examples of the present disclosure may be realized in the form of hardware, software or a combination of hardware and software. Certain examples of the present disclosure may provide a computer program comprising instructions or code which, when executed, implement a method, system and / or apparatus in accordance with any aspect, example and / or embodiment disclosed herein. Certain embodiments of the present disclosure provide a machine-readable storage storing such a program.

[0033] The proposals of the present disclosure are centred around the use of AI / ML models to provide a solution for mobility enhancement in TN-NTN and / or NTN-NTN networks. More specifically, we present as an example the use case of mobility enhancement in NTN to solve the problem of ephemeris inaccuracies in TN and / or NTN networks.

[0034] The proposals are applicable in any radio environment utilizing AI / ML methods to: • Provide ephemeris accuracy improvements and enhancements to positioning, navigation (mobility) and timing • Provide the accurate and sufficient amount of imputation units when there are missing ephemeris data

[0035] The following are features, aspects and solutions that are introduced by the present disclosure. More detailed explanations of these and other features are provided below. • A set (one or more) of new network entity(-ies) and / or network function(s) to improve accuracy of satellite ephemeris (or manage, or handle, correct, propose, recommend, cancel, or control, reset, request, optimize, compensate, and / or other actions related to improvement of ephemeris). • The new network entity(-ies) and / or network function(s) may be included in (or part of, or co-located with) RAN (e.g. eNB, NG-RAN, gNB, etc.), CN (e.g. AMF, SMF, UPF, etc), dedicated internal / external entity (or function), a server, database, cloud, Application Function (AF), and / or a UE (e.g. loT UE, NTN UE, loT NTN UE, other UE category, or UE type, etc.) (or a set of UEs), etc. • The new network entity (or entities) and / or network function (or functions) is (are) involved in improvement of ephemeris for enhancement of positioning, mobility and timing. In one example, for the use case of UE mobility between TN and NTN and / or UE mobility between NTN and NTN networks. • The term AI / ML model may be replaced (or used interchangeably) with the term AI / ML functionality / use-case / configuration / scenario / site may be used interchangeably in this invention. • The solutions, methods, embodiments, and / or examples, presented in this invention, would apply to one or more type(s) of communication systems, such as 4G, 4G-Advanced, 5G, 5G-Advanced, and 6G. Moreover, the above may also apply (in full or part or modified) to systems of NonTerrestrial Networks (NR-NTN and / or loT-NTN), in addition to Terrestrial Networks (TN). • New signalling / messages (e.g. related to AI / ML mobility, improvement of accuracy of ephemeris, etc.) between the UE, the network, and the new set of network entity(-ies) (and / or network function(s)) introduced in this invention. For example, new RRC and / or NAS signalling / messages / IEs. In another example, new system information (and / or new SIBs). • In another example, the exchange of information (e.g. related to AI / ML mobility, improvement of accuracy of ephemeris, etc.) between the UE, network, and / or newly introduced set of network entity(-ies)(and / or function(s)) are carried on existing RRC and / or NAS signalling / messages / IEs, and / or system information e.g. SIBs). • This disclosed approaches also apply to non-3GPP entities.

[0036] Certain examples of the present disclosure provide a method for Artificial Intelligence / Machine Learning (AIZML)-based ephemeris data enhancement in a wireless communication system, the method comprising: receiving ephemeris data; identifying inaccurate or incomplete ephemeris data within the received ephemeris data; generating, using an ephemeris AI / ML model / function, enhanced ephemeris data; and distributing the enhanced ephemeris data to one or more network entities / functions within the wireless communication system.

[0037] In certain examples, the ephemeris data may be for one or more of a positioning function, a navigation function, a timing function, and a radio access network (RAN) procedure.

[0038] In certain examples, the ephemeris data may include information on the position and / or trajectory of one or more a Non-Terrestrial Network (NTN) node or a GNSS node.

[0039] In certain examples, the ephemeris data may be received from one or more of a user equipment, an NTN node, and a GNSS node.

[0040] In certain examples, the method may further comprise assigning one or more of a time stamp, a date, and a unique identifier to the enhanced ephemeris data.

[0041] In certain examples, the enhanced ephemeris data may be distributed to one or more of a user equipment (UE), an NTN node, a gNB, and a core network entity / function of the wireless communication system.

[0042] In certain examples, the enhanced ephemeris data may be distributed to the UE via the NTN or the gNB.

[0043] In certain examples, the core network entity / function of the wireless communication system may include one or more of a location management function (LMF), a Layerl / Layer / Lower layer triggered mobility (LTM), life cycle management (LCM), conditional handover (CHO), network data analytics function (NWDAF).

[0044] In certain examples, the method may be performed by one or more of a terrestrial RAN entity / function of the wireless communication system and a UE.

[0045] In certain examples, the method may further comprise training the ephemeris AI / ML model / function based on previously received ephemeris data.

[0046] In certain examples, the method may further comprise training the ephemeris AI / ML model based on previous uplink and / or downlink measurements at one or more a UE and a RAN node.

[0047] In certain examples, the method may further comprise training the ephemeris AI / ML model / function based on core network data associated with the RAN.

[0048] In certain examples, the enhanced ephemeris data may be for use in a UE mobility procedure.

[0049] In certain examples, the identifying inaccurate or incomplete ephemeris data within the received ephemeris data may be performed using the ephemeris AI / ML model / function.

[0050] Certain examples of the present disclosure provide a network entity for generating enhanced ephemeris information in wireless communication system using an ephemeris AI / ML model / function, wherein the network entity is configured to: receive ephemeris data; identify inaccurate or incomplete ephemeris data within the received ephemeris data; generate, using an ephemeris AI / ML model / function, enhanced ephemeris data; and distribute the enhanced ephemeris data to one or more network entities / functions within the wireless communication system.

[0051] In certain examples, the network entity is a radio access network (RAN) entity.

[0052] Certain examples of the present disclosure provide a network (or wireless communication system) comprising a network entity according to any example, aspect, embodiment and / or claim disclosed herein.

[0053] Certain examples of the present disclosure provide a computer program comprising instructions which, when the program is executed by a computer or processor, cause the computer or processor to carry out a method according to any example, aspect, embodiment and / or claim disclosed herein.

[0054] Certain examples of the present disclosure provide a computer or processor-readable data carrier having stored thereon a computer program according to any example, aspect, embodiment and / or claim disclosed herein. Ephemeris Enhancement

[0055] The present disclosure proposes the development and deployment of AI / ML models to improve ephemeris data for Positioning, Navigation and Timing (PNT) functionalities. This will be useful to implement in 3GPP because of the number of dependent RAN functions and procedures that are affected by inaccurate / missing ephemeris data. The AI / ML model can be trained on historical ephemeris information and the actions specified by the AI / ML model in the inference phase for estimation and correction of ephemeris data when there are missing / inaccurate data should be quickly broadcast to the UE, gNB and relevant network functions. Thus, improving the reliability of the aforementioned RAN procedures.

[0056] In accordance with an example of the present disclosure, the AI / ML model / function that is used to enhance ephemeris may be positioned within the RAN, either as part of an existing entity or a new entity.

[0057] Referring to the example of Figure 1, an AI / ML model is within the RAN such that enhanced ephemeris can be distributed from the RAN to other entities of the system such as UEs, core network entities, and NTN nodes / infrastructure, where example distribution paths are shown by the arrows other than those showing the ephemeris broadcast data. However, it should be noted that the location of the AI / ML model / function utilised to generate the enhanced ephemeris is not limited to being included in the RAN. For example, it may be included in a UE or a new or existing core network entity. Also, the location of the AI / ML model / function utilised to generate the enhanced ephemeris is not limited to being included in any particular RAN entity, but may be included in any suitable existing and / or future RAN entity.

[0058] The RAN-based AI / ML model may be used to analyse the broadcast ephemeris data, where the broadcast data may be received from UE and / or directly from NTN nodes. If the data is received with unacceptable errors, then the AI / ML model may then be used to improve the accuracy using previous information and regenerate the ephemeris data within a satisfactory level of accuracy for all the dependent NW elements and PNT functions. Any suitable technique may be used for the error detection and correction process. However, if the broadcasted ephemeris data is not received and missing for example, due to weather conditions, or signal jamming, the AI / ML model may also interpolate / make regression using past data to estimate the ephemeris data as inputs.

[0059] In order to generate the AI / ML model, a training phase will be required, where this training make that the form of localised training and / or federated training / learning.

[0060] In the training phase, the RAN-based AI / ML model may have one or more of the following as inputs: • Historical downlink and uplink location measurements and / or location estimates from the UE. • Historical downlink and uplink location measurements from the NG RAN. • Historical raw ephemeris data from GNSS (Global Navigation Satellite System) / Satcom and / or if real-time ephemeris data has been received. • Other 5G Core Network Functions (NF) assistance data related to the NG RAN (e.g., UE location estimation, gNB location on space). • Type of RAN procedure related to the ephemeris. For example, Figure 2 illustrates a technique in which a gNB can be provided and only the non-NTN infrastructure is used as a Gateway to connect with public data networks.

[0061] Using these inputs in the training phase provides the AI / ML model with hyper parameters, accuracy and validates its performance. For example, hyperparameter(s) may include one or more parameters, and / or one or more sets of parameters, used before the learning process begins. These parameters may be tunable and may go through optimization. Such parameters may directly affect how well a model trains. Some examples of Al models hyperparameters include: Learning Rate; Number of Epochs; Regularization constants.

[0062] In the inference phase, the RAN-based AI / ML model provides the regenerated broadcasted data to improve the accuracy of the raw data with errors and / or provides the imputation data for unreceived / missing broadcasted ephemeris data.

[0063] The approaches disclosed by the present disclosure are applicable to any functions of the network which are dependent on ephemeris information. However, it is envisaged that the provision of enhanced ephemeris may play an important role in management of NTNs and the optimisation of mobility involving NTNs, such as between NTN (NTN-NTN) and between TN and NTN (TN-NTN).

[0064] Figures 2 and 3 provide example scenarios in which an AI / ML model for ephemeris enhancement is used. In particular, these figures provide an example procedure and life cycle for how to provide enhancements using the proposed RAN-based AI / ML model.

[0065] Referring to Figure 2, a scenario where UEs are in communication with NTNs (i.e. no direct communication with TNs) is considered, such that may occur as part of NTN-NTN mobility. In the figures (Figures 1 to 3), solid orange lines (e.g. those labelled “RF Link” and “RF Feeder Links”) indicate the targeted connection(s) (e.g. the preferred one(s)). Dashed orange lines (e.g. those labelled “Alternative in sight RF Link”) are the neighbour, or 2nd priority, connection(s) in case the targeted connection(s) fail(s), for example due to storm, obstruction, etc. The red crosses (Figures 2 and 3) indicate RF link failures, for example a failure to receive any data and / or messages, including the ephemeris data updates, general user data and / or voice communications, or even the RF Link failure itself. An example procedure is as follows: 1. Use one or more of up-to-date collected ephemeris data and historically saved ephemeris data, related to RAN procedures to train the Al ML model. Save / Register and / or acknowledge the RAN AI / ML model for PNT if existing / finetuned / created Al ML model has satisfactory accuracy. 2. If the PNT data for UE / gNB and / or other NW entity have missing / unacceptable ephemeris errors, then predict the enhanced ephemeris data to increase the NTN, Satcomm’s and / or the GNSS’s position accuracy using the AI / ML model. 3. The predicted output of the near real-time ephemeris data from the AI / ML model with corrections (i.e. enhanced ephemeris) will be reproduced to reduce the satellites positioning errors. 4. Time stamps, date and unique ID are created for the PNT regenerated ephemeris data ( e.g. in the case that ephemeris is missing due to the factors such as the weather and ionosphere conditions) 5. The RAN distributes the enhanced (regenerated) ephemeris data (optionally including the time stamps etc.) to the UEs and other NW entities and / or functions involving the NTN-NTN RAN existing procedures (e.g., the LMF and NWDAF.) 6. The RAN communicates with the related NW entities / functions (e.g., LMF, LTM, LCM, CHO and NWDAF) to exchange performance and evaluation of the AIML models if required. 7. Repeat the procedure starting from step (1). The procedure may be repeated using one or more of up-to-date collected ephemeris data and historically saved ephemeris data, related to RAN procedures to train the AIML model.

[0066] Note that other steps, sub-steps, and / or combined steps are also possible as part of the above example, but are not shown / described above for simplicity, however, can be easily added to this example (or a different example). Additionally, in another example, the steps maybe provided in a different order and / or one or more steps may be removed.

[0067] Referring to Figure 3, a scenario where UEs are in communication with NTNs and TNs is considered, such that may occur as part of TN-NTN mobility. As noted above, in the figures (Figures 1 to 3), solid orange lines (e.g. those labelled “RF Link” and “RF Feeder Links”) indicate the targeted connection(s) (e.g. the preferred one(s)). Dashed orange lines (e.g. those labelled “Alternative in sight RF Link”) are the neighbour, or 2nd priority, connection(s) in case the targeted connection(s) fail(s), for example due to storm, obstruction, etc. The red crosses (Figures 2 and 3) indicate RF link failures, for example a failure to receive any data and / or messages, including the ephemeris data updates, general user data and / or voice communications, or even the RF Link failure itself. 1. Use one or more of up-to-date collected ephemeris data and historically saved ephemeris data, related to RAN procedures to train the AI / ML model. Save / Register and / or acknowledge the RAN AI / ML model for PNT if existing / finetuned / created Al ML model have satisfactory accuracy 2. If the PNT data for UE / gNB and / or other NW have missing / unacceptable ephemeris errors , then predict the enhanced ephemeris data to increase the NTN Satcomm’s and GNSS’s position accuracy. 3. The predicted output of the near real time ephemeris data from the AI / ML-assisted model with corrections will be reproduced to reduce the satellites positioning errors. 4. Time stamps, date and unique ID are created for the PNT regenerated ephemeris data ( e.g. in the case that ephemeris is missing due to the factors such as the weather and ionosphere conditions) 5. The RAN distributes the enhanced (regenerated) ephemeris data (optionally including the time stamps etc.) back within the NTN-TN RAN, to the UEs and for other NW entities and / or functions involving in with the NTN-NTN RAN existing procedures (e.g., the LMF and NWDAF.) 6. The RAN communicates with the related NW entities functions (e.g., LMF, LTM, LCM, CHO and NWDAF) to exchange performance and evaluation of the AIML models if required. 7. Repeat the procedure starting from step (1). The procedure may be repeated using one or more of up-to-date collected ephemeris data and historically saved ephemeris data, related to RAN procedures to train the Al ML model.

[0068] Note that other steps, sub-steps, and / or combined steps are also possible as part of the above example, but are not shown / described above for simplicity, however, can be easily added to this example (or a different example). Additionally, in another example, the steps maybe provided in a different order and / or one or more steps may be removed.

[0069] The procedures described with reference to Figure 2 and 3 illustrate that the provision of an AI / ML model / function for the generation of enhanced ephemeris is widely applicable to various scenarios with little change to the underlying methodology. For example, presuming adequate training of the AI / ML model has been performed for the relevant scenario, the paths by which the original ephemeris is received and the paths by which the enhanced ephemeris is distributed represent the main differences.

[0070] Although the AI / ML model / functionality as been shown to be provided within the RAN in relation to Figures 1, 2, and 3, it may also be provided at alternative a locations within the network.

[0071] Figure 4 is a block diagram of an exemplary apparatus, or network entity, that may be used in examples of the present disclosure, for example, an entity within the RAN responsible for the AI / ML model / function used to provide enhanced ephemeris. The skilled person will appreciate said entity may be implemented, for example, as a network element on a dedicated hardware, as a software instance running on a dedicated hardware, and / or as a virtualised function instantiated on an appropriate platform, e.g. on a cloud infrastructure.

[0072] The entity 400 comprises a processor (or controller) 401, a transmitter 403 and a receiver 405. The receiver 405 is configured for receiving one or more messages from one or more other network entities, for example as described above. The transmitter 403 is configured for transmitting one or more messages to one or more other network entities, for example as described above. The processor 401 is configured for performing one or more operations, for example according to the operations as described above.

[0073] It will be appreciated that, in each example / embodiment / aspect etc. described above, one or more features or operations may be omitted, modified or moved (e.g., to change the order of the features or the operations), if desired and appropriate. Additionally, one or more features or operations from any example / embodiment may be combined with features or operations from any other example / embodiment. In particular, regardless of whether or not a pointer towards a combination of features / examples is found herein, the present disclosure should be considered to include all combinations of two or more of the embodiments, examples etc. disclosed herein, and all combinations of two or more of the features disclosed herein.

[0074] The techniques described herein may be implemented using any suitably configured apparatus and / or system. Such an apparatus and / or system may be configured to perform a method according to any aspect, embodiment or example disclosed herein. Such an apparatus may comprise one or more elements, for example one or more of receivers, transmitters, transceivers, processors, controllers, modules, units, and the like, each element configured to perform one or more corresponding processes, operations and / or method steps for implementing the techniques described herein. For example, an operation / function of X may be performed by a module configured to perform X (or an X-module). The one or more elements may be implemented in the form of hardware, software, or any combination of hardware and software.

[0075] It will be appreciated that examples of the present disclosure may be implemented in the form of hardware, software or any combination of hardware and software. Any such software may be stored in the form of volatile or non-volatile storage, for example a storage device like a ROM, whether erasable or rewritable or not, or in the form of memory such as, for example, RAM, memory chips, device or integrated circuits or on an optically or magnetically readable medium such as, for example, a CD, DVD, magnetic disk or magnetic tape or the like.

[0076] It will be appreciated that the storage devices and storage media are embodiments of machine-readable storage that are suitable for storing a program or programs comprising instructions that, when executed, implement certain examples of the present disclosure. Accordingly, certain examples provide a program comprising code for implementing a method, apparatus or system according to any example, embodiment and / or aspect disclosed herein, and / or a machine-readable storage storing such a program. Still further, such programs may be conveyed electronically via any medium, for example a communication signal carried over a wired or wireless connection.

[0077] While the present disclosure has been shown, illustrated and described with reference to certain examples, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the disclosure.

[0078] The reader's attention is directed to all papers and documents which are filed concurrently with or previous to this specification in connection with this application 5 and which are open to public inspection with this specification, and the contents of all such papers and documents are incorporated herein by reference. Acronyms and Definitions (as may be used herein) 3GPP 3rd Generation Partnership Project NTN Non-Terrestrial Network 5G 5th Generation NW Network 5GC 5G Core NWDAF Network Data Analytics Function 5QI 5G QoS Identifier OS Operating System 5GS 5G System OSAPP OS Application 5GSM 5G System Session Management PCF Policy Control Function 5GMM 5G System Mobility Management PCC Policy and Charging Control AF Application Function PCO Protocol Configuration Options Al Artificial Intelligence PDR Packet Detection Rule AIML Artificial Intelligence / Machine PDU Protocol Data Unit Learning PMF Performance Measurement Function AM Acknowledged Mode PNT Position, Navigation, Timing AMF Access and Mobility Management PSA PDU session anchor Function QFI QoS Flow Identifier (ID) AS Application Server QoE Quality of Experience ASP Application Service Provider QoS Quality of Service ATSSS Access Traffic Steering Switching RACH Random Access Channel & Splitting RAN Radio Access Network AUSF Authentication Server Function RAT Radio Access Technology CDRX Connected Mode Discontinuous RLC-AM Radio Link Control Acknowledge Reception Mode CE Control Element RLC-UM Radio Link Control Unacknowledge CSI Channel Status Information Mode DCAF Data Collection Application RRC Radio Resource Control Function RSD Route Selection Descriptor DNN Data Network Name SA Standalone DNS Domain Name Server SBA Service-Based Architecture DRB Data Radio Bearer SBI Service-Based Interface DRX Discontinuous Reception SCEF Service Capability Exposure Function eNB Evolved Node B SCP Service-Based Communication Proxy EPS Evolved Packet System SCTP Stream Control Transmission FQDN Fully Qualified Domain Name Protocol GBR Guaranteed Bit Rate SDAP Service Data Adaptation Protocol gNB Next generation Node B SDU Service Data Unit GNSS Global Navigation Satellite System SIM Subscriber Identity Module GPSI Generic Public Subscription SLA Service Level Agreement Identifier SM Session Management IAB Integrated Access and Backhaul SMF Session Management Function ID Identity / ldentifier SN Secondary Node loT Internet of Things S-NSSAI Single Network Slice Selection IMEI International Mobile Equipment Assistance Information Identities SSB Synchronization Signal Block IP Internet Protocol SSC Session and Service Continuity l-SMF Intermediate SMF SUPI Subscription Permanent Identifier LMF Location Management Function TAI Tracking Area Identity MA-PDU Multiple Access PDU TE Terminal Equipment MAC Medium Access Control TM Transparent Mode ML Machine Learning TS Technical Specification MME Mobility Management Entity UDM Unified Data Manager MN Master Node UDR Unified Data Repository MNO Mobile Network Operator UE User Equipment MPTCP MultiPath TCP UL Uplink MT Mobile Termination UM Unacknowledged Mode NAS Non-Access Stratum UP User Plane NB Narrowband UPF User Plane Function NRF Network Repository Function URLLC Ultra-Reliable and Low-Latency NG-RAN Next Generation Radio Access Communication Network URSP UE Route Selection Policy NG-eNB Next Generation eNB XRM Extended Reality and Media NSA Non-Standalone

Claims

1. A method for Artificial Intelligence / Machine Learning (AI / ML)-based ephemeris data enhancement in a wireless communication system, the method comprising:receiving ephemeris data;identifying inaccurate or incomplete ephemeris data within the received ephemeris data;generating, using an ephemeris AI / ML model / function, enhanced ephemeris data; anddistributing the enhanced ephemeris data to one or more network entities / functions within the wireless communication system.

2. The method of claim 1, wherein the ephemeris data is for one or more of a positioning function, a navigation function, a timing function, and a radio access network (RAN) procedure.

3. The method of claims 1 or 2, wherein the ephemeris data includes information on the position and / or trajectory of one or more a Non-Terrestrial Network (NTN) node or a GNSS node.

4. The method of claim 3, wherein the ephemeris data is received from one or more of a user equipment, an NTN node, and a GNSS node.

5. The method of any preceding claim, further comprising assigning one or more of a time stamp, a date, and a unique identifier to the enhanced ephemeris data.

6. The method of any preceding claim, wherein the enhanced ephemeris data is distributed to one or more of a user equipment (UE), an NTN node, a gNB, and a core network entity / function of the wireless communication system.

7. The method of claim 6, wherein the enhanced ephemeris data is distributed to the UE via the NTN or the gNB.

8. The method of claims 6 or 7, wherein the core network entity / function of the wireless communication system includes one or more of a location management function (LMF), a Layerl / Layer / Lower layer triggered mobility (LTM), life cycle management (LCM), conditional handover (CHO), network data analytics function (NWDAF).

9. The method of any preceding claim, wherein the method is performed by one or more of a terrestrial RAN entity / function of the wireless communication system and a UE.

10. The method of any preceding claim, further comprising training the ephemeris AI / ML model / function based on previously received ephemeris data.

11. The method of any preceding claim, further comprising training the ephemeris AI / ML model based on previous uplink and / or downlink measurements at one or more a UE and a RAN node.

12. The method of any preceding claim, further comprising training the ephemeris AI / ML model / function based on core network data associated with the RAN.

13. The method of any preceding claim, wherein the enhanced ephemeris data is for usein a UE mobility procedure.

14. The method of any preceding claim, wherein the identifying inaccurate or incomplete ephemeris data within the received ephemeris data is performed using the ephemeris AI / ML model / function.

15. A network entity for generating enhanced ephemeris information in wireless communication system using an ephemeris AI / ML model / function, wherein the network entity is configured to:receive ephemeris data;identify inaccurate or incomplete ephemeris data within the received ephemeris data;generate, using an ephemeris AI / ML model / function, enhanced ephemeris data; and distribute the enhanced ephemeris data to one or more network entities / functions within the wireless communication system.

16. The network entity of claim 15, wherein the network entity is a radio access network (RAN) entity.

Images